Merge branch 'dev' into support-py-for-run-code

.env.example

@@ -11,7 +11,3 @@ OPENAI_API_KEY=''
 SCARF_NO_ANALYTICS=true
 DO_NOT_TRACK=true
 ANONYMIZED_TELEMETRY=false
-
-# Use locally bundled version of the LiteLLM cost map json
-# to avoid repetitive startup connections
-LITELLM_LOCAL_MODEL_COST_MAP="True"

.github/workflows/build-release.yml

@@ -11,7 +11,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     - name: Check for changes in package.json
       run: |
@@ -36,7 +36,7 @@ jobs:
         echo "::set-output name=content::$CHANGELOG_ESCAPED"
 
     - name: Create GitHub release
-      uses: actions/github-script@v5
+      uses: actions/github-script@v7
       with:
         github-token: ${{ secrets.GITHUB_TOKEN }}
         script: |
@@ -51,7 +51,7 @@ jobs:
           console.log(`Created release ${release.data.html_url}`)
 
     - name: Upload package to GitHub release
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: package
         path: .

.github/workflows/deploy-to-hf-spaces.yml

@@ -0,0 +1,59 @@
+name: Deploy to HuggingFace Spaces
+
+on:
+  push:
+    branches:
+      - dev
+      - main
+  workflow_dispatch:
+
+jobs:
+  check-secret:
+    runs-on: ubuntu-latest
+    outputs:
+      token-set: ${{ steps.check-key.outputs.defined }}
+    steps:
+      - id: check-key
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        if: "${{ env.HF_TOKEN != '' }}"
+        run: echo "defined=true" >> $GITHUB_OUTPUT
+
+  deploy:
+    runs-on: ubuntu-latest
+    needs: [check-secret]
+    if: needs.check-secret.outputs.token-set == 'true'
+    env:
+      HF_TOKEN: ${{ secrets.HF_TOKEN }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Remove git history
+        run: rm -rf .git
+
+      - name: Prepend YAML front matter to README.md
+        run: |
+          echo "---" > temp_readme.md
+          echo "title: Open WebUI" >> temp_readme.md
+          echo "emoji: 🐳" >> temp_readme.md
+          echo "colorFrom: purple" >> temp_readme.md
+          echo "colorTo: gray" >> temp_readme.md
+          echo "sdk: docker" >> temp_readme.md
+          echo "app_port: 8080" >> temp_readme.md
+          echo "---" >> temp_readme.md
+          cat README.md >> temp_readme.md
+          mv temp_readme.md README.md
+
+      - name: Configure git
+        run: |
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git config --global user.name "github-actions[bot]"
+      - name: Set up Git and push to Space
+        run: |
+          git init --initial-branch=main
+          git lfs track "*.ttf"
+          rm demo.gif
+          git add .
+          git commit -m "GitHub deploy: ${{ github.sha }}"
+          git push --force https://open-webui:${HF_TOKEN}@huggingface.co/spaces/open-webui/open-webui main

.github/workflows/docker-build.yaml

@@ -84,6 +84,8 @@ jobs:
           outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
           cache-from: type=registry,ref=${{ steps.cache-meta.outputs.tags }}
           cache-to: type=registry,ref=${{ steps.cache-meta.outputs.tags }},mode=max
+          build-args: |
+            BUILD_HASH=${{ github.sha }}
 
       - name: Export digest
         run: |
@@ -170,7 +172,9 @@ jobs:
           outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
           cache-from: type=registry,ref=${{ steps.cache-meta.outputs.tags }}
           cache-to: type=registry,ref=${{ steps.cache-meta.outputs.tags }},mode=max
-          build-args: USE_CUDA=true
+          build-args: |
+            BUILD_HASH=${{ github.sha }}
+            USE_CUDA=true
 
       - name: Export digest
         run: |
@@ -257,7 +261,9 @@ jobs:
           outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
           cache-from: type=registry,ref=${{ steps.cache-meta.outputs.tags }}
           cache-to: type=registry,ref=${{ steps.cache-meta.outputs.tags }},mode=max
-          build-args: USE_OLLAMA=true
+          build-args: |
+            BUILD_HASH=${{ github.sha }}
+            USE_OLLAMA=true
 
       - name: Export digest
         run: |

.github/workflows/format-backend.yaml

@@ -23,7 +23,7 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
 

.github/workflows/format-build-frontend.yaml

@@ -19,7 +19,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Setup Node.js
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: '20' # Or specify any other version you want to use
 

.github/workflows/integration-test.yml

@@ -20,7 +20,11 @@ jobs:
 
       - name: Build and run Compose Stack
         run: |
-          docker compose --file docker-compose.yaml --file docker-compose.api.yaml up --detach --build
+          docker compose \
+            --file docker-compose.yaml \
+            --file docker-compose.api.yaml \
+            --file docker-compose.a1111-test.yaml \
+            up --detach --build
           
       - name: Wait for Ollama to be up
         timeout-minutes: 5
@@ -95,7 +99,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 

.github/workflows/release-pypi.yml

@@ -0,0 +1,32 @@
+name: Release to PyPI
+
+on:
+  push:
+    branches:
+      - main # or whatever branch you want to use
+      - dev
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/open-webui
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+      - name: Build
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+          python -m build .
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

Dockerfile

@@ -11,12 +11,14 @@ ARG USE_CUDA_VER=cu121
 # IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
 ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 ARG USE_RERANKING_MODEL=""
+ARG BUILD_HASH=dev-build
 # Override at your own risk - non-root configurations are untested
 ARG UID=0
 ARG GID=0
 
 ######## WebUI frontend ########
 FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
+ARG BUILD_HASH
 
 WORKDIR /app
 
@@ -24,6 +26,7 @@ COPY package.json package-lock.json ./
 RUN npm ci
 
 COPY . .
+ENV APP_BUILD_HASH=${BUILD_HASH}
 RUN npm run build
 
 ######## WebUI backend ########
@@ -35,6 +38,7 @@ ARG USE_OLLAMA
 ARG USE_CUDA_VER
 ARG USE_EMBEDDING_MODEL
 ARG USE_RERANKING_MODEL
+ARG BUILD_HASH
 ARG UID
 ARG GID
 
@@ -59,11 +63,6 @@ ENV OPENAI_API_KEY="" \
     DO_NOT_TRACK=true \
     ANONYMIZED_TELEMETRY=false
 
-# Use locally bundled version of the LiteLLM cost map json
-# to avoid repetitive startup connections
-ENV LITELLM_LOCAL_MODEL_COST_MAP="True"
-
-
 #### Other models #########################################################
 ## whisper TTS model settings ##
 ENV WHISPER_MODEL="base" \
@@ -132,7 +131,8 @@ RUN pip3 install uv && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
-    fi
+    fi; \
+    chown -R $UID:$GID /app/backend/data/
 
 
 
@@ -154,4 +154,6 @@ HEALTHCHECK CMD curl --silent --fail http://localhost:8080/health | jq -e '.stat
 
 USER $UID:$GID
 
+ENV WEBUI_BUILD_VERSION=${BUILD_HASH}
+
 CMD [ "bash", "start.sh"]

backend/apps/litellm/main.py

@@ -1,379 +0,0 @@
-import sys
-from contextlib import asynccontextmanager
-
-from fastapi import FastAPI, Depends, HTTPException
-from fastapi.routing import APIRoute
-from fastapi.middleware.cors import CORSMiddleware
-
-import logging
-from fastapi import FastAPI, Request, Depends, status, Response
-from fastapi.responses import JSONResponse
-
-from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
-from starlette.responses import StreamingResponse
-import json
-import time
-import requests
-
-from pydantic import BaseModel, ConfigDict
-from typing import Optional, List
-
-from utils.utils import get_verified_user, get_current_user, get_admin_user
-from config import SRC_LOG_LEVELS, ENV
-from constants import MESSAGES
-
-import os
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["LITELLM"])
-
-
-from config import (
-    ENABLE_LITELLM,
-    ENABLE_MODEL_FILTER,
-    MODEL_FILTER_LIST,
-    DATA_DIR,
-    LITELLM_PROXY_PORT,
-    LITELLM_PROXY_HOST,
-)
-
-import warnings
-
-warnings.simplefilter("ignore")
-
-from litellm.utils import get_llm_provider
-
-import asyncio
-import subprocess
-import yaml
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    log.info("startup_event")
-    # TODO: Check config.yaml file and create one
-    asyncio.create_task(start_litellm_background())
-    yield
-
-
-app = FastAPI(lifespan=lifespan)
-
-origins = ["*"]
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-LITELLM_CONFIG_DIR = f"{DATA_DIR}/litellm/config.yaml"
-
-with open(LITELLM_CONFIG_DIR, "r") as file:
-    litellm_config = yaml.safe_load(file)
-
-
-app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER.value
-app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST.value
-
-
-app.state.ENABLE = ENABLE_LITELLM
-app.state.CONFIG = litellm_config
-
-# Global variable to store the subprocess reference
-background_process = None
-
-CONFLICT_ENV_VARS = [
-    # Uvicorn uses PORT, so LiteLLM might use it as well
-    "PORT",
-    # LiteLLM uses DATABASE_URL for Prisma connections
-    "DATABASE_URL",
-]
-
-
-async def run_background_process(command):
-    global background_process
-    log.info("run_background_process")
-
-    try:
-        # Log the command to be executed
-        log.info(f"Executing command: {command}")
-        # Filter environment variables known to conflict with litellm
-        env = {k: v for k, v in os.environ.items() if k not in CONFLICT_ENV_VARS}
-        # Execute the command and create a subprocess
-        process = await asyncio.create_subprocess_exec(
-            *command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env
-        )
-        background_process = process
-        log.info("Subprocess started successfully.")
-
-        # Capture STDERR for debugging purposes
-        stderr_output = await process.stderr.read()
-        stderr_text = stderr_output.decode().strip()
-        if stderr_text:
-            log.info(f"Subprocess STDERR: {stderr_text}")
-
-        # log.info output line by line
-        async for line in process.stdout:
-            log.info(line.decode().strip())
-
-        # Wait for the process to finish
-        returncode = await process.wait()
-        log.info(f"Subprocess exited with return code {returncode}")
-    except Exception as e:
-        log.error(f"Failed to start subprocess: {e}")
-        raise  # Optionally re-raise the exception if you want it to propagate
-
-
-async def start_litellm_background():
-    log.info("start_litellm_background")
-    # Command to run in the background
-    command = [
-        "litellm",
-        "--port",
-        str(LITELLM_PROXY_PORT),
-        "--host",
-        LITELLM_PROXY_HOST,
-        "--telemetry",
-        "False",
-        "--config",
-        LITELLM_CONFIG_DIR,
-    ]
-
-    await run_background_process(command)
-
-
-async def shutdown_litellm_background():
-    log.info("shutdown_litellm_background")
-    global background_process
-    if background_process:
-        background_process.terminate()
-        await background_process.wait()  # Ensure the process has terminated
-        log.info("Subprocess terminated")
-        background_process = None
-
-
-@app.get("/")
-async def get_status():
-    return {"status": True}
-
-
-async def restart_litellm():
-    """
-    Endpoint to restart the litellm background service.
-    """
-    log.info("Requested restart of litellm service.")
-    try:
-        # Shut down the existing process if it is running
-        await shutdown_litellm_background()
-        log.info("litellm service shutdown complete.")
-
-        # Restart the background service
-
-        asyncio.create_task(start_litellm_background())
-        log.info("litellm service restart complete.")
-
-        return {
-            "status": "success",
-            "message": "litellm service restarted successfully.",
-        }
-    except Exception as e:
-        log.info(f"Error restarting litellm service: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
-        )
-
-
-@app.get("/restart")
-async def restart_litellm_handler(user=Depends(get_admin_user)):
-    return await restart_litellm()
-
-
-@app.get("/config")
-async def get_config(user=Depends(get_admin_user)):
-    return app.state.CONFIG
-
-
-class LiteLLMConfigForm(BaseModel):
-    general_settings: Optional[dict] = None
-    litellm_settings: Optional[dict] = None
-    model_list: Optional[List[dict]] = None
-    router_settings: Optional[dict] = None
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@app.post("/config/update")
-async def update_config(form_data: LiteLLMConfigForm, user=Depends(get_admin_user)):
-    app.state.CONFIG = form_data.model_dump(exclude_none=True)
-
-    with open(LITELLM_CONFIG_DIR, "w") as file:
-        yaml.dump(app.state.CONFIG, file)
-
-    await restart_litellm()
-    return app.state.CONFIG
-
-
-@app.get("/models")
-@app.get("/v1/models")
-async def get_models(user=Depends(get_current_user)):
-
-    if app.state.ENABLE:
-        while not background_process:
-            await asyncio.sleep(0.1)
-
-        url = f"http://localhost:{LITELLM_PROXY_PORT}/v1"
-        r = None
-        try:
-            r = requests.request(method="GET", url=f"{url}/models")
-            r.raise_for_status()
-
-            data = r.json()
-
-            if app.state.ENABLE_MODEL_FILTER:
-                if user and user.role == "user":
-                    data["data"] = list(
-                        filter(
-                            lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
-                            data["data"],
-                        )
-                    )
-
-            return data
-        except Exception as e:
-
-            log.exception(e)
-            error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']}"
-                except:
-                    error_detail = f"External: {e}"
-
-            return {
-                "data": [
-                    {
-                        "id": model["model_name"],
-                        "object": "model",
-                        "created": int(time.time()),
-                        "owned_by": "openai",
-                    }
-                    for model in app.state.CONFIG["model_list"]
-                ],
-                "object": "list",
-            }
-    else:
-        return {
-            "data": [],
-            "object": "list",
-        }
-
-
-@app.get("/model/info")
-async def get_model_list(user=Depends(get_admin_user)):
-    return {"data": app.state.CONFIG["model_list"]}
-
-
-class AddLiteLLMModelForm(BaseModel):
-    model_name: str
-    litellm_params: dict
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@app.post("/model/new")
-async def add_model_to_config(
-    form_data: AddLiteLLMModelForm, user=Depends(get_admin_user)
-):
-    try:
-        get_llm_provider(model=form_data.model_name)
-        app.state.CONFIG["model_list"].append(form_data.model_dump())
-
-        with open(LITELLM_CONFIG_DIR, "w") as file:
-            yaml.dump(app.state.CONFIG, file)
-
-        await restart_litellm()
-
-        return {"message": MESSAGES.MODEL_ADDED(form_data.model_name)}
-    except Exception as e:
-        print(e)
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
-        )
-
-
-class DeleteLiteLLMModelForm(BaseModel):
-    id: str
-
-
-@app.post("/model/delete")
-async def delete_model_from_config(
-    form_data: DeleteLiteLLMModelForm, user=Depends(get_admin_user)
-):
-    app.state.CONFIG["model_list"] = [
-        model
-        for model in app.state.CONFIG["model_list"]
-        if model["model_name"] != form_data.id
-    ]
-
-    with open(LITELLM_CONFIG_DIR, "w") as file:
-        yaml.dump(app.state.CONFIG, file)
-
-    await restart_litellm()
-
-    return {"message": MESSAGES.MODEL_DELETED(form_data.id)}
-
-
-@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
-async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
-    body = await request.body()
-
-    url = f"http://localhost:{LITELLM_PROXY_PORT}"
-
-    target_url = f"{url}/{path}"
-
-    headers = {}
-    # headers["Authorization"] = f"Bearer {key}"
-    headers["Content-Type"] = "application/json"
-
-    r = None
-
-    try:
-        r = requests.request(
-            method=request.method,
-            url=target_url,
-            data=body,
-            headers=headers,
-            stream=True,
-        )
-
-        r.raise_for_status()
-
-        # Check if response is SSE
-        if "text/event-stream" in r.headers.get("Content-Type", ""):
-            return StreamingResponse(
-                r.iter_content(chunk_size=8192),
-                status_code=r.status_code,
-                headers=dict(r.headers),
-            )
-        else:
-            response_data = r.json()
-            return response_data
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
-            except:
-                error_detail = f"External: {e}"
-
-        raise HTTPException(
-            status_code=r.status_code if r else 500, detail=error_detail
-        )

backend/apps/ollama/main.py

@@ -29,8 +29,8 @@ import time
 from urllib.parse import urlparse
 from typing import Optional, List, Union
 
-
+from apps.webui.models.models import Models
-from apps.web.models.users import Users
+from apps.webui.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import (
     decode_token,
@@ -39,10 +39,13 @@ from utils.utils import (
     get_admin_user,
 )
 
+from utils.models import get_model_id_from_custom_model_id
+
 
 from config import (
     SRC_LOG_LEVELS,
     OLLAMA_BASE_URLS,
+    ENABLE_OLLAMA_API,
     ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
     UPLOAD_DIR,
@@ -67,6 +70,7 @@ app.state.config = AppConfig()
 app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
+app.state.config.ENABLE_OLLAMA_API = ENABLE_OLLAMA_API
 app.state.config.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS
 app.state.MODELS = {}
 
@@ -96,6 +100,21 @@ async def get_status():
     return {"status": True}
 
 
+@app.get("/config")
+async def get_config(user=Depends(get_admin_user)):
+    return {"ENABLE_OLLAMA_API": app.state.config.ENABLE_OLLAMA_API}
+
+
+class OllamaConfigForm(BaseModel):
+    enable_ollama_api: Optional[bool] = None
+
+
+@app.post("/config/update")
+async def update_config(form_data: OllamaConfigForm, user=Depends(get_admin_user)):
+    app.state.config.ENABLE_OLLAMA_API = form_data.enable_ollama_api
+    return {"ENABLE_OLLAMA_API": app.state.config.ENABLE_OLLAMA_API}
+
+
 @app.get("/urls")
 async def get_ollama_api_urls(user=Depends(get_admin_user)):
     return {"OLLAMA_BASE_URLS": app.state.config.OLLAMA_BASE_URLS}
@@ -156,15 +175,24 @@ def merge_models_lists(model_lists):
 
 async def get_all_models():
     log.info("get_all_models()")
-    tasks = [fetch_url(f"{url}/api/tags") for url in app.state.config.OLLAMA_BASE_URLS]
+
+    if app.state.config.ENABLE_OLLAMA_API:
+        tasks = [
+            fetch_url(f"{url}/api/tags") for url in app.state.config.OLLAMA_BASE_URLS
+        ]
         responses = await asyncio.gather(*tasks)
 
         models = {
             "models": merge_models_lists(
-            map(lambda response: response["models"] if response else None, responses)
+                map(
+                    lambda response: response["models"] if response else None, responses
+                )
             )
         }
 
+    else:
+        models = {"models": []}
+
     app.state.MODELS = {model["model"]: model for model in models["models"]}
 
     return models
@@ -278,6 +306,9 @@ async def pull_model(
 
     r = None
 
+    # Admin should be able to pull models from any source
+    payload = {**form_data.model_dump(exclude_none=True), "insecure": True}
+
     def get_request():
         nonlocal url
         nonlocal r
@@ -305,7 +336,7 @@ async def pull_model(
             r = requests.request(
                 method="POST",
                 url=f"{url}/api/pull",
-                data=form_data.model_dump_json(exclude_none=True).encode(),
+                data=json.dumps(payload),
                 stream=True,
             )
 
@@ -848,14 +879,93 @@ async def generate_chat_completion(
     user=Depends(get_verified_user),
 ):
 
+    log.debug(
+        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
+            form_data.model_dump_json(exclude_none=True).encode()
+        )
+    )
+
+    payload = {
+        **form_data.model_dump(exclude_none=True),
+    }
+
+    model_id = form_data.model
+    model_info = Models.get_model_by_id(model_id)
+
+    if model_info:
+        print(model_info)
+        if model_info.base_model_id:
+            payload["model"] = model_info.base_model_id
+
+        model_info.params = model_info.params.model_dump()
+
+        if model_info.params:
+            payload["options"] = {}
+
+            payload["options"]["mirostat"] = model_info.params.get("mirostat", None)
+            payload["options"]["mirostat_eta"] = model_info.params.get(
+                "mirostat_eta", None
+            )
+            payload["options"]["mirostat_tau"] = model_info.params.get(
+                "mirostat_tau", None
+            )
+            payload["options"]["num_ctx"] = model_info.params.get("num_ctx", None)
+
+            payload["options"]["repeat_last_n"] = model_info.params.get(
+                "repeat_last_n", None
+            )
+            payload["options"]["repeat_penalty"] = model_info.params.get(
+                "frequency_penalty", None
+            )
+
+            payload["options"]["temperature"] = model_info.params.get(
+                "temperature", None
+            )
+            payload["options"]["seed"] = model_info.params.get("seed", None)
+
+            payload["options"]["stop"] = (
+                [
+                    bytes(stop, "utf-8").decode("unicode_escape")
+                    for stop in model_info.params["stop"]
+                ]
+                if model_info.params.get("stop", None)
+                else None
+            )
+
+            payload["options"]["tfs_z"] = model_info.params.get("tfs_z", None)
+
+            payload["options"]["num_predict"] = model_info.params.get(
+                "max_tokens", None
+            )
+            payload["options"]["top_k"] = model_info.params.get("top_k", None)
+
+            payload["options"]["top_p"] = model_info.params.get("top_p", None)
+
+        if model_info.params.get("system", None):
+            # Check if the payload already has a system message
+            # If not, add a system message to the payload
+            if payload.get("messages"):
+                for message in payload["messages"]:
+                    if message.get("role") == "system":
+                        message["content"] = (
+                            model_info.params.get("system", None) + message["content"]
+                        )
+                        break
+                else:
+                    payload["messages"].insert(
+                        0,
+                        {
+                            "role": "system",
+                            "content": model_info.params.get("system", None),
+                        },
+                    )
+
     if url_idx == None:
-        model = form_data.model
+        if ":" not in payload["model"]:
+            payload["model"] = f"{payload['model']}:latest"
 
-        if ":" not in model:
+        if payload["model"] in app.state.MODELS:
-            model = f"{model}:latest"
+            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
@@ -865,16 +975,12 @@ async def generate_chat_completion(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    print(payload)
+
     r = None
 
-    log.debug(
-        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
-            form_data.model_dump_json(exclude_none=True).encode()
-        )
-    )
-
     def get_request():
-        nonlocal form_data
+        nonlocal payload
         nonlocal r
 
         request_id = str(uuid.uuid4())
@@ -883,7 +989,7 @@ async def generate_chat_completion(
 
             def stream_content():
                 try:
-                    if form_data.stream:
+                    if payload.get("stream", None):
                         yield json.dumps({"id": request_id, "done": False}) + "\n"
 
                     for chunk in r.iter_content(chunk_size=8192):
@@ -901,7 +1007,7 @@ async def generate_chat_completion(
             r = requests.request(
                 method="POST",
                 url=f"{url}/api/chat",
-                data=form_data.model_dump_json(exclude_none=True).encode(),
+                data=json.dumps(payload),
                 stream=True,
             )
 
@@ -957,14 +1063,62 @@ async def generate_openai_chat_completion(
     user=Depends(get_verified_user),
 ):
 
+    payload = {
+        **form_data.model_dump(exclude_none=True),
+    }
+
+    model_id = form_data.model
+    model_info = Models.get_model_by_id(model_id)
+
+    if model_info:
+        print(model_info)
+        if model_info.base_model_id:
+            payload["model"] = model_info.base_model_id
+
+        model_info.params = model_info.params.model_dump()
+
+        if model_info.params:
+            payload["temperature"] = model_info.params.get("temperature", None)
+            payload["top_p"] = model_info.params.get("top_p", None)
+            payload["max_tokens"] = model_info.params.get("max_tokens", None)
+            payload["frequency_penalty"] = model_info.params.get(
+                "frequency_penalty", None
+            )
+            payload["seed"] = model_info.params.get("seed", None)
+            payload["stop"] = (
+                [
+                    bytes(stop, "utf-8").decode("unicode_escape")
+                    for stop in model_info.params["stop"]
+                ]
+                if model_info.params.get("stop", None)
+                else None
+            )
+
+        if model_info.params.get("system", None):
+            # Check if the payload already has a system message
+            # If not, add a system message to the payload
+            if payload.get("messages"):
+                for message in payload["messages"]:
+                    if message.get("role") == "system":
+                        message["content"] = (
+                            model_info.params.get("system", None) + message["content"]
+                        )
+                        break
+                else:
+                    payload["messages"].insert(
+                        0,
+                        {
+                            "role": "system",
+                            "content": model_info.params.get("system", None),
+                        },
+                    )
+
     if url_idx == None:
-        model = form_data.model
+        if ":" not in payload["model"]:
+            payload["model"] = f"{payload['model']}:latest"
 
-        if ":" not in model:
+        if payload["model"] in app.state.MODELS:
-            model = f"{model}:latest"
+            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
         else:
             raise HTTPException(
                 status_code=400,
@@ -977,7 +1131,7 @@ async def generate_openai_chat_completion(
     r = None
 
     def get_request():
-        nonlocal form_data
+        nonlocal payload
         nonlocal r
 
         request_id = str(uuid.uuid4())
@@ -986,7 +1140,7 @@ async def generate_openai_chat_completion(
 
             def stream_content():
                 try:
-                    if form_data.stream:
+                    if payload.get("stream"):
                         yield json.dumps(
                             {"request_id": request_id, "done": False}
                         ) + "\n"
@@ -1006,7 +1160,7 @@ async def generate_openai_chat_completion(
             r = requests.request(
                 method="POST",
                 url=f"{url}/v1/chat/completions",
-                data=form_data.model_dump_json(exclude_none=True).encode(),
+                data=json.dumps(payload),
                 stream=True,
             )
 

backend/apps/openai/main.py

@@ -10,8 +10,8 @@ import logging
 
 from pydantic import BaseModel
 
-
+from apps.webui.models.models import Models
-from apps.web.models.users import Users
+from apps.webui.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import (
     decode_token,
@@ -53,7 +53,6 @@ app.state.config = AppConfig()
 app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
-
 app.state.config.ENABLE_OPENAI_API = ENABLE_OPENAI_API
 app.state.config.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
 app.state.config.OPENAI_API_KEYS = OPENAI_API_KEYS
@@ -199,14 +198,20 @@ async def fetch_url(url, key):
 
 
 def merge_models_lists(model_lists):
-    log.info(f"merge_models_lists {model_lists}")
+    log.debug(f"merge_models_lists {model_lists}")
     merged_list = []
 
     for idx, models in enumerate(model_lists):
         if models is not None and "error" not in models:
             merged_list.extend(
                 [
-                    {**model, "urlIdx": idx}
+                    {
+                        **model,
+                        "name": model.get("name", model["id"]),
+                        "owned_by": "openai",
+                        "openai": model,
+                        "urlIdx": idx,
+                    }
                     for model in models
                     if "api.openai.com"
                     not in app.state.config.OPENAI_API_BASE_URLS[idx]
@@ -232,7 +237,7 @@ async def get_all_models():
         ]
 
         responses = await asyncio.gather(*tasks)
-        log.info(f"get_all_models:responses() {responses}")
+        log.debug(f"get_all_models:responses() {responses}")
 
         models = {
             "data": merge_models_lists(
@@ -249,7 +254,7 @@ async def get_all_models():
             )
         }
 
-        log.info(f"models: {models}")
+        log.debug(f"models: {models}")
         app.state.MODELS = {model["id"]: model for model in models["data"]}
 
     return models
@@ -310,31 +315,93 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     body = await request.body()
     # TODO: Remove below after gpt-4-vision fix from Open AI
     # Try to decode the body of the request from bytes to a UTF-8 string (Require add max_token to fix gpt-4-vision)
+
+    payload = None
+
     try:
+        if "chat/completions" in path:
             body = body.decode("utf-8")
             body = json.loads(body)
 
-        idx = app.state.MODELS[body.get("model")]["urlIdx"]
+            payload = {**body}
+
+            model_id = body.get("model")
+            model_info = Models.get_model_by_id(model_id)
+
+            if model_info:
+                print(model_info)
+                if model_info.base_model_id:
+                    payload["model"] = model_info.base_model_id
+
+                model_info.params = model_info.params.model_dump()
+
+                if model_info.params:
+                    payload["temperature"] = model_info.params.get("temperature", None)
+                    payload["top_p"] = model_info.params.get("top_p", None)
+                    payload["max_tokens"] = model_info.params.get("max_tokens", None)
+                    payload["frequency_penalty"] = model_info.params.get(
+                        "frequency_penalty", None
+                    )
+                    payload["seed"] = model_info.params.get("seed", None)
+                    payload["stop"] = (
+                        [
+                            bytes(stop, "utf-8").decode("unicode_escape")
+                            for stop in model_info.params["stop"]
+                        ]
+                        if model_info.params.get("stop", None)
+                        else None
+                    )
+
+                if model_info.params.get("system", None):
+                    # Check if the payload already has a system message
+                    # If not, add a system message to the payload
+                    if payload.get("messages"):
+                        for message in payload["messages"]:
+                            if message.get("role") == "system":
+                                message["content"] = (
+                                    model_info.params.get("system", None)
+                                    + message["content"]
+                                )
+                                break
+                        else:
+                            payload["messages"].insert(
+                                0,
+                                {
+                                    "role": "system",
+                                    "content": model_info.params.get("system", None),
+                                },
+                            )
+            else:
+                pass
+
+            print(app.state.MODELS)
+            model = app.state.MODELS[payload.get("model")]
+
+            idx = model["urlIdx"]
+
+            if "pipeline" in model and model.get("pipeline"):
+                payload["user"] = {"name": user.name, "id": user.id}
+                payload["title"] = (
+                    True
+                    if payload["stream"] == False and payload["max_tokens"] == 50
+                    else False
+                )
 
             # Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000
             # This is a workaround until OpenAI fixes the issue with this model
-        if body.get("model") == "gpt-4-vision-preview":
+            if payload.get("model") == "gpt-4-vision-preview":
-            if "max_tokens" not in body:
+                if "max_tokens" not in payload:
-                body["max_tokens"] = 4000
+                    payload["max_tokens"] = 4000
-            log.debug("Modified body_dict:", body)
+                log.debug("Modified payload:", payload)
-
-        # Fix for ChatGPT calls failing because the num_ctx key is in body
-        if "num_ctx" in body:
-            # If 'num_ctx' is in the dictionary, delete it
-            # Leaving it there generates an error with the
-            # OpenAI API (Feb 2024)
-            del body["num_ctx"]
 
             # Convert the modified body back to JSON
-        body = json.dumps(body)
+            payload = json.dumps(payload)
+
     except json.JSONDecodeError as e:
         log.error("Error loading request body into a dictionary:", e)
 
+    print(payload)
+
     url = app.state.config.OPENAI_API_BASE_URLS[idx]
     key = app.state.config.OPENAI_API_KEYS[idx]
 
@@ -353,7 +420,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
         r = requests.request(
             method=request.method,
             url=target_url,
-            data=body,
+            data=payload if payload else body,
             headers=headers,
             stream=True,
         )

backend/apps/rag/main.py

@@ -46,7 +46,7 @@ import json
 
 import sentence_transformers
 
-from apps.web.models.documents import (
+from apps.webui.models.documents import (
     Documents,
     DocumentForm,
     DocumentResponse,

backend/apps/web/models/modelfiles.py

@@ -1,136 +0,0 @@
-from pydantic import BaseModel
-from peewee import *
-from playhouse.shortcuts import model_to_dict
-from typing import List, Union, Optional
-import time
-
-from utils.utils import decode_token
-from utils.misc import get_gravatar_url
-
-from apps.web.internal.db import DB
-
-import json
-
-####################
-# Modelfile DB Schema
-####################
-
-
-class Modelfile(Model):
-    tag_name = CharField(unique=True)
-    user_id = CharField()
-    modelfile = TextField()
-    timestamp = BigIntegerField()
-
-    class Meta:
-        database = DB
-
-
-class ModelfileModel(BaseModel):
-    tag_name: str
-    user_id: str
-    modelfile: str
-    timestamp: int  # timestamp in epoch
-
-
-####################
-# Forms
-####################
-
-
-class ModelfileForm(BaseModel):
-    modelfile: dict
-
-
-class ModelfileTagNameForm(BaseModel):
-    tag_name: str
-
-
-class ModelfileUpdateForm(ModelfileForm, ModelfileTagNameForm):
-    pass
-
-
-class ModelfileResponse(BaseModel):
-    tag_name: str
-    user_id: str
-    modelfile: dict
-    timestamp: int  # timestamp in epoch
-
-
-class ModelfilesTable:
-
-    def __init__(self, db):
-        self.db = db
-        self.db.create_tables([Modelfile])
-
-    def insert_new_modelfile(
-        self, user_id: str, form_data: ModelfileForm
-    ) -> Optional[ModelfileModel]:
-        if "tagName" in form_data.modelfile:
-            modelfile = ModelfileModel(
-                **{
-                    "user_id": user_id,
-                    "tag_name": form_data.modelfile["tagName"],
-                    "modelfile": json.dumps(form_data.modelfile),
-                    "timestamp": int(time.time()),
-                }
-            )
-
-            try:
-                result = Modelfile.create(**modelfile.model_dump())
-                if result:
-                    return modelfile
-                else:
-                    return None
-            except:
-                return None
-
-        else:
-            return None
-
-    def get_modelfile_by_tag_name(self, tag_name: str) -> Optional[ModelfileModel]:
-        try:
-            modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
-            return ModelfileModel(**model_to_dict(modelfile))
-        except:
-            return None
-
-    def get_modelfiles(self, skip: int = 0, limit: int = 50) -> List[ModelfileResponse]:
-        return [
-            ModelfileResponse(
-                **{
-                    **model_to_dict(modelfile),
-                    "modelfile": json.loads(modelfile.modelfile),
-                }
-            )
-            for modelfile in Modelfile.select()
-            # .limit(limit).offset(skip)
-        ]
-
-    def update_modelfile_by_tag_name(
-        self, tag_name: str, modelfile: dict
-    ) -> Optional[ModelfileModel]:
-        try:
-            query = Modelfile.update(
-                modelfile=json.dumps(modelfile),
-                timestamp=int(time.time()),
-            ).where(Modelfile.tag_name == tag_name)
-
-            query.execute()
-
-            modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
-            return ModelfileModel(**model_to_dict(modelfile))
-        except:
-            return None
-
-    def delete_modelfile_by_tag_name(self, tag_name: str) -> bool:
-        try:
-            query = Modelfile.delete().where((Modelfile.tag_name == tag_name))
-            query.execute()  # Remove the rows, return number of rows removed.
-
-            return True
-        except:
-            return False
-
-
-Modelfiles = ModelfilesTable(DB)

backend/apps/web/routers/modelfiles.py

@@ -1,124 +0,0 @@
-from fastapi import Depends, FastAPI, HTTPException, status
-from datetime import datetime, timedelta
-from typing import List, Union, Optional
-
-from fastapi import APIRouter
-from pydantic import BaseModel
-import json
-from apps.web.models.modelfiles import (
-    Modelfiles,
-    ModelfileForm,
-    ModelfileTagNameForm,
-    ModelfileUpdateForm,
-    ModelfileResponse,
-)
-
-from utils.utils import get_current_user, get_admin_user
-from constants import ERROR_MESSAGES
-
-router = APIRouter()
-
-############################
-# GetModelfiles
-############################
-
-
-@router.get("/", response_model=List[ModelfileResponse])
-async def get_modelfiles(
-    skip: int = 0, limit: int = 50, user=Depends(get_current_user)
-):
-    return Modelfiles.get_modelfiles(skip, limit)
-
-
-############################
-# CreateNewModelfile
-############################
-
-
-@router.post("/create", response_model=Optional[ModelfileResponse])
-async def create_new_modelfile(form_data: ModelfileForm, user=Depends(get_admin_user)):
-    modelfile = Modelfiles.insert_new_modelfile(user.id, form_data)
-
-    if modelfile:
-        return ModelfileResponse(
-            **{
-                **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.DEFAULT(),
-        )
-
-
-############################
-# GetModelfileByTagName
-############################
-
-
-@router.post("/", response_model=Optional[ModelfileResponse])
-async def get_modelfile_by_tag_name(
-    form_data: ModelfileTagNameForm, user=Depends(get_current_user)
-):
-    modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
-
-    if modelfile:
-        return ModelfileResponse(
-            **{
-                **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# UpdateModelfileByTagName
-############################
-
-
-@router.post("/update", response_model=Optional[ModelfileResponse])
-async def update_modelfile_by_tag_name(
-    form_data: ModelfileUpdateForm, user=Depends(get_admin_user)
-):
-    modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
-    if modelfile:
-        updated_modelfile = {
-            **json.loads(modelfile.modelfile),
-            **form_data.modelfile,
-        }
-
-        modelfile = Modelfiles.update_modelfile_by_tag_name(
-            form_data.tag_name, updated_modelfile
-        )
-
-        return ModelfileResponse(
-            **{
-                **modelfile.model_dump(),
-                "modelfile": json.loads(modelfile.modelfile),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-
-
-############################
-# DeleteModelfileByTagName
-############################
-
-
-@router.delete("/delete", response_model=bool)
-async def delete_modelfile_by_tag_name(
-    form_data: ModelfileTagNameForm, user=Depends(get_admin_user)
-):
-    result = Modelfiles.delete_modelfile_by_tag_name(form_data.tag_name)
-    return result

backend/apps/webui/internal/db.py

@@ -1,13 +1,25 @@
+import json
+
 from peewee import *
 from peewee_migrate import Router
 from playhouse.db_url import connect
-from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL
+from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL, BACKEND_DIR
 import os
 import logging
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["DB"])
 
+
+class JSONField(TextField):
+    def db_value(self, value):
+        return json.dumps(value)
+
+    def python_value(self, value):
+        if value is not None:
+            return json.loads(value)
+
+
 # Check if the file exists
 if os.path.exists(f"{DATA_DIR}/ollama.db"):
     # Rename the file
@@ -18,6 +30,10 @@ else:
 
 DB = connect(DATABASE_URL)
 log.info(f"Connected to a {DB.__class__.__name__} database.")
-router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
+router = Router(
+    DB,
+    migrate_dir=BACKEND_DIR / "apps" / "webui" / "internal" / "migrations",
+    logger=log,
+)
 router.run()
 DB.connect(reuse_if_open=True)

backend/apps/webui/internal/migrations/009_add_models.py

@@ -0,0 +1,61 @@
+"""Peewee migrations -- 009_add_models.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    @migrator.create_model
+    class Model(pw.Model):
+        id = pw.TextField(unique=True)
+        user_id = pw.TextField()
+        base_model_id = pw.TextField(null=True)
+
+        name = pw.TextField()
+
+        meta = pw.TextField()
+        params = pw.TextField()
+
+        created_at = pw.BigIntegerField(null=False)
+        updated_at = pw.BigIntegerField(null=False)
+
+        class Meta:
+            table_name = "model"
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_model("model")

backend/apps/webui/internal/migrations/010_migrate_modelfiles_to_models.py

@@ -0,0 +1,130 @@
+"""Peewee migrations -- 009_add_models.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+import json
+
+from utils.misc import parse_ollama_modelfile
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    # Fetch data from 'modelfile' table and insert into 'model' table
+    migrate_modelfile_to_model(migrator, database)
+    # Drop the 'modelfile' table
+    migrator.remove_model("modelfile")
+
+
+def migrate_modelfile_to_model(migrator: Migrator, database: pw.Database):
+    ModelFile = migrator.orm["modelfile"]
+    Model = migrator.orm["model"]
+
+    modelfiles = ModelFile.select()
+
+    for modelfile in modelfiles:
+        # Extract and transform data in Python
+
+        modelfile.modelfile = json.loads(modelfile.modelfile)
+        meta = json.dumps(
+            {
+                "description": modelfile.modelfile.get("desc"),
+                "profile_image_url": modelfile.modelfile.get("imageUrl"),
+                "ollama": {"modelfile": modelfile.modelfile.get("content")},
+                "suggestion_prompts": modelfile.modelfile.get("suggestionPrompts"),
+                "categories": modelfile.modelfile.get("categories"),
+                "user": {**modelfile.modelfile.get("user", {}), "community": True},
+            }
+        )
+
+        info = parse_ollama_modelfile(modelfile.modelfile.get("content"))
+
+        # Insert the processed data into the 'model' table
+        Model.create(
+            id=f"ollama-{modelfile.tag_name}",
+            user_id=modelfile.user_id,
+            base_model_id=info.get("base_model_id"),
+            name=modelfile.modelfile.get("title"),
+            meta=meta,
+            params=json.dumps(info.get("params", {})),
+            created_at=modelfile.timestamp,
+            updated_at=modelfile.timestamp,
+        )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    recreate_modelfile_table(migrator, database)
+    move_data_back_to_modelfile(migrator, database)
+    migrator.remove_model("model")
+
+
+def recreate_modelfile_table(migrator: Migrator, database: pw.Database):
+    query = """
+    CREATE TABLE IF NOT EXISTS modelfile (
+        user_id TEXT,
+        tag_name TEXT,
+        modelfile JSON,
+        timestamp BIGINT
+    )
+    """
+    migrator.sql(query)
+
+
+def move_data_back_to_modelfile(migrator: Migrator, database: pw.Database):
+    Model = migrator.orm["model"]
+    Modelfile = migrator.orm["modelfile"]
+
+    models = Model.select()
+
+    for model in models:
+        # Extract and transform data in Python
+        meta = json.loads(model.meta)
+
+        modelfile_data = {
+            "title": model.name,
+            "desc": meta.get("description"),
+            "imageUrl": meta.get("profile_image_url"),
+            "content": meta.get("ollama", {}).get("modelfile"),
+            "suggestionPrompts": meta.get("suggestion_prompts"),
+            "categories": meta.get("categories"),
+            "user": {k: v for k, v in meta.get("user", {}).items() if k != "community"},
+        }
+
+        # Insert the processed data back into the 'modelfile' table
+        Modelfile.create(
+            user_id=model.user_id,
+            tag_name=model.id,
+            modelfile=modelfile_data,
+            timestamp=model.created_at,
+        )

backend/apps/webui/internal/migrations/011_add_user_settings.py

@@ -0,0 +1,48 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    # Adding fields settings to the 'user' table
+    migrator.add_fields("user", settings=pw.TextField(null=True))
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    # Remove the settings field
+    migrator.remove_fields("user", "settings")

backend/apps/webui/internal/migrations/README.md

@@ -14,7 +14,7 @@ You will need to create a migration file to ensure that existing databases are u
 2. Make your changes to the models.
 3. From the `backend` directory, run the following command:
    ```bash
-   pw_migrate create --auto --auto-source apps.web.models --database sqlite:///${SQLITE_DB} --directory apps/web/internal/migrations ${MIGRATION_NAME}
+   pw_migrate create --auto --auto-source apps.webui.models --database sqlite:///${SQLITE_DB} --directory apps/web/internal/migrations ${MIGRATION_NAME}
    ```
    - `$SQLITE_DB` should be the path to the database file.
    - `$MIGRATION_NAME` should be a descriptive name for the migration.

backend/apps/webui/main.py

@@ -1,19 +1,19 @@
 from fastapi import FastAPI, Depends
 from fastapi.routing import APIRoute
 from fastapi.middleware.cors import CORSMiddleware
-from apps.web.routers import (
+from apps.webui.routers import (
     auths,
     users,
     chats,
     documents,
-    modelfiles,
+    models,
     prompts,
     configs,
     memories,
     utils,
 )
 from config import (
-    WEBUI_VERSION,
+    WEBUI_BUILD_HASH,
     WEBUI_AUTH,
     DEFAULT_MODELS,
     DEFAULT_PROMPT_SUGGESTIONS,
@@ -23,7 +23,9 @@ from config import (
     WEBHOOK_URL,
     WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
     JWT_EXPIRES_IN,
+    WEBUI_BANNERS,
     AppConfig,
+    ENABLE_COMMUNITY_SHARING,
 )
 
 app = FastAPI()
@@ -40,6 +42,11 @@ app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
+app.state.config.BANNERS = WEBUI_BANNERS
+
+app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
+
+app.state.MODELS = {}
 app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 
 
@@ -56,11 +63,10 @@ app.include_router(users.router, prefix="/users", tags=["users"])
 app.include_router(chats.router, prefix="/chats", tags=["chats"])
 
 app.include_router(documents.router, prefix="/documents", tags=["documents"])
-app.include_router(modelfiles.router, prefix="/modelfiles", tags=["modelfiles"])
+app.include_router(models.router, prefix="/models", tags=["models"])
 app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
 app.include_router(memories.router, prefix="/memories", tags=["memories"])
 
-
 app.include_router(configs.router, prefix="/configs", tags=["configs"])
 app.include_router(utils.router, prefix="/utils", tags=["utils"])
 

backend/apps/webui/models/auths.py

@@ -5,10 +5,10 @@ import uuid
 import logging
 from peewee import *
 
-from apps.web.models.users import UserModel, Users
+from apps.webui.models.users import UserModel, Users
 from utils.utils import verify_password
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 
 from config import SRC_LOG_LEVELS
 

backend/apps/webui/models/chats.py

@@ -7,7 +7,7 @@ import json
 import uuid
 import time
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 
 ####################
 # Chat DB Schema
@@ -191,6 +191,20 @@ class ChatTable:
         except:
             return None
 
+    def archive_all_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            chats = self.get_chats_by_user_id(user_id)
+            for chat in chats:
+                query = Chat.update(
+                    archived=True,
+                ).where(Chat.id == chat.id)
+
+                query.execute()
+
+            return True
+        except:
+            return False
+
     def get_archived_chat_list_by_user_id(
         self, user_id: str, skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
@@ -205,8 +219,22 @@ class ChatTable:
         ]
 
     def get_chat_list_by_user_id(
-        self, user_id: str, skip: int = 0, limit: int = 50
+        self,
+        user_id: str,
+        include_archived: bool = False,
+        skip: int = 0,
+        limit: int = 50,
     ) -> List[ChatModel]:
+        if include_archived:
+            return [
+                ChatModel(**model_to_dict(chat))
+                for chat in Chat.select()
+                .where(Chat.user_id == user_id)
+                .order_by(Chat.updated_at.desc())
+                # .limit(limit)
+                # .offset(skip)
+            ]
+        else:
             return [
                 ChatModel(**model_to_dict(chat))
                 for chat in Chat.select()

backend/apps/webui/models/documents.py

@@ -8,7 +8,7 @@ import logging
 from utils.utils import decode_token
 from utils.misc import get_gravatar_url
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 
 import json
 

backend/apps/webui/models/memories.py

@@ -3,8 +3,8 @@ from peewee import *
 from playhouse.shortcuts import model_to_dict
 from typing import List, Union, Optional
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
-from apps.web.models.chats import Chats
+from apps.webui.models.chats import Chats
 
 import time
 import uuid

backend/apps/webui/models/models.py

@@ -0,0 +1,179 @@
+import json
+import logging
+from typing import Optional
+
+import peewee as pw
+from peewee import *
+
+from playhouse.shortcuts import model_to_dict
+from pydantic import BaseModel, ConfigDict
+
+from apps.webui.internal.db import DB, JSONField
+
+from typing import List, Union, Optional
+from config import SRC_LOG_LEVELS
+
+import time
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+
+####################
+# Models DB Schema
+####################
+
+
+# ModelParams is a model for the data stored in the params field of the Model table
+class ModelParams(BaseModel):
+    model_config = ConfigDict(extra="allow")
+    pass
+
+
+# ModelMeta is a model for the data stored in the meta field of the Model table
+class ModelMeta(BaseModel):
+    profile_image_url: Optional[str] = "/favicon.png"
+
+    description: Optional[str] = None
+    """
+        User-facing description of the model.
+    """
+
+    capabilities: Optional[dict] = None
+
+    model_config = ConfigDict(extra="allow")
+
+    pass
+
+
+class Model(pw.Model):
+    id = pw.TextField(unique=True)
+    """
+        The model's id as used in the API. If set to an existing model, it will override the model.
+    """
+    user_id = pw.TextField()
+
+    base_model_id = pw.TextField(null=True)
+    """
+        An optional pointer to the actual model that should be used when proxying requests.
+    """
+
+    name = pw.TextField()
+    """
+        The human-readable display name of the model.
+    """
+
+    params = JSONField()
+    """
+        Holds a JSON encoded blob of parameters, see `ModelParams`.
+    """
+
+    meta = JSONField()
+    """
+        Holds a JSON encoded blob of metadata, see `ModelMeta`.
+    """
+
+    updated_at = BigIntegerField()
+    created_at = BigIntegerField()
+
+    class Meta:
+        database = DB
+
+
+class ModelModel(BaseModel):
+    id: str
+    user_id: str
+    base_model_id: Optional[str] = None
+
+    name: str
+    params: ModelParams
+    meta: ModelMeta
+
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class ModelResponse(BaseModel):
+    id: str
+    name: str
+    meta: ModelMeta
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+
+
+class ModelForm(BaseModel):
+    id: str
+    base_model_id: Optional[str] = None
+    name: str
+    meta: ModelMeta
+    params: ModelParams
+
+
+class ModelsTable:
+    def __init__(
+        self,
+        db: pw.SqliteDatabase | pw.PostgresqlDatabase,
+    ):
+        self.db = db
+        self.db.create_tables([Model])
+
+    def insert_new_model(
+        self, form_data: ModelForm, user_id: str
+    ) -> Optional[ModelModel]:
+        model = ModelModel(
+            **{
+                **form_data.model_dump(),
+                "user_id": user_id,
+                "created_at": int(time.time()),
+                "updated_at": int(time.time()),
+            }
+        )
+        try:
+            result = Model.create(**model.model_dump())
+
+            if result:
+                return model
+            else:
+                return None
+        except Exception as e:
+            print(e)
+            return None
+
+    def get_all_models(self) -> List[ModelModel]:
+        return [ModelModel(**model_to_dict(model)) for model in Model.select()]
+
+    def get_model_by_id(self, id: str) -> Optional[ModelModel]:
+        try:
+            model = Model.get(Model.id == id)
+            return ModelModel(**model_to_dict(model))
+        except:
+            return None
+
+    def update_model_by_id(self, id: str, model: ModelForm) -> Optional[ModelModel]:
+        try:
+            # update only the fields that are present in the model
+            query = Model.update(**model.model_dump()).where(Model.id == id)
+            query.execute()
+
+            model = Model.get(Model.id == id)
+            return ModelModel(**model_to_dict(model))
+        except Exception as e:
+            print(e)
+
+            return None
+
+    def delete_model_by_id(self, id: str) -> bool:
+        try:
+            query = Model.delete().where(Model.id == id)
+            query.execute()
+            return True
+        except:
+            return False
+
+
+Models = ModelsTable(DB)

backend/apps/webui/models/prompts.py

@@ -7,7 +7,7 @@ import time
 from utils.utils import decode_token
 from utils.misc import get_gravatar_url
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 
 import json
 

backend/apps/webui/models/tags.py

@@ -8,7 +8,7 @@ import uuid
 import time
 import logging
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 
 from config import SRC_LOG_LEVELS
 

backend/apps/webui/models/users.py

@@ -1,12 +1,12 @@
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 from peewee import *
 from playhouse.shortcuts import model_to_dict
 from typing import List, Union, Optional
 import time
 from utils.misc import get_gravatar_url
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB, JSONField
-from apps.web.models.chats import Chats
+from apps.webui.models.chats import Chats
 
 ####################
 # User DB Schema
@@ -25,11 +25,18 @@ class User(Model):
     created_at = BigIntegerField()
 
     api_key = CharField(null=True, unique=True)
+    settings = JSONField(null=True)
 
     class Meta:
         database = DB
 
 
+class UserSettings(BaseModel):
+    ui: Optional[dict] = {}
+    model_config = ConfigDict(extra="allow")
+    pass
+
+
 class UserModel(BaseModel):
     id: str
     name: str
@@ -42,6 +49,7 @@ class UserModel(BaseModel):
     created_at: int  # timestamp in epoch
 
     api_key: Optional[str] = None
+    settings: Optional[UserSettings] = None
 
 
 ####################

backend/apps/webui/routers/auths.py

@@ -10,7 +10,7 @@ import uuid
 import csv
 
 
-from apps.web.models.auths import (
+from apps.webui.models.auths import (
     SigninForm,
     SignupForm,
     AddUserForm,
@@ -21,7 +21,7 @@ from apps.web.models.auths import (
     Auths,
     ApiKey,
 )
-from apps.web.models.users import Users
+from apps.webui.models.users import Users
 
 from utils.utils import (
     get_password_hash,

backend/apps/webui/routers/chats.py

@@ -7,8 +7,8 @@ from pydantic import BaseModel
 import json
 import logging
 
-from apps.web.models.users import Users
+from apps.webui.models.users import Users
-from apps.web.models.chats import (
+from apps.webui.models.chats import (
     ChatModel,
     ChatResponse,
     ChatTitleForm,
@@ -18,7 +18,7 @@ from apps.web.models.chats import (
 )
 
 
-from apps.web.models.tags import (
+from apps.webui.models.tags import (
     TagModel,
     ChatIdTagModel,
     ChatIdTagForm,
@@ -78,43 +78,25 @@ async def delete_all_user_chats(request: Request, user=Depends(get_current_user)
 async def get_user_chat_list_by_user_id(
     user_id: str, user=Depends(get_admin_user), skip: int = 0, limit: int = 50
 ):
-    return Chats.get_chat_list_by_user_id(user_id, skip, limit)
+    return Chats.get_chat_list_by_user_id(
-
+        user_id, include_archived=True, skip=skip, limit=limit
-
-############################
-# GetArchivedChats
-############################
-
-
-@router.get("/archived", response_model=List[ChatTitleIdResponse])
-async def get_archived_session_user_chat_list(
-    user=Depends(get_current_user), skip: int = 0, limit: int = 50
-):
-    return Chats.get_archived_chat_list_by_user_id(user.id, skip, limit)
-
-
-############################
-# GetSharedChatById
-############################
-
-
-@router.get("/share/{share_id}", response_model=Optional[ChatResponse])
-async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
-    if user.role == "pending":
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
     )
 
-    if user.role == "user":
-        chat = Chats.get_chat_by_share_id(share_id)
-    elif user.role == "admin":
-        chat = Chats.get_chat_by_id(share_id)
 
-    if chat:
+############################
+# CreateNewChat
+############################
+
+
+@router.post("/new", response_model=Optional[ChatResponse])
+async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
+    try:
+        chat = Chats.insert_new_chat(user.id, form_data)
         return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-    else:
+    except Exception as e:
+        log.exception(e)
         raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
         )
 
 
@@ -150,19 +132,49 @@ async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
 
 
 ############################
-# CreateNewChat
+# GetArchivedChats
 ############################
 
 
-@router.post("/new", response_model=Optional[ChatResponse])
+@router.get("/archived", response_model=List[ChatTitleIdResponse])
-async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
+async def get_archived_session_user_chat_list(
-    try:
+    user=Depends(get_current_user), skip: int = 0, limit: int = 50
-        chat = Chats.insert_new_chat(user.id, form_data)
+):
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+    return Chats.get_archived_chat_list_by_user_id(user.id, skip, limit)
-    except Exception as e:
+
-        log.exception(e)
+
+############################
+# ArchiveAllChats
+############################
+
+
+@router.post("/archive/all", response_model=List[ChatTitleIdResponse])
+async def archive_all_chats(user=Depends(get_current_user)):
+    return Chats.archive_all_chats_by_user_id(user.id)
+
+
+############################
+# GetSharedChatById
+############################
+
+
+@router.get("/share/{share_id}", response_model=Optional[ChatResponse])
+async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
+    if user.role == "pending":
         raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    if user.role == "user":
+        chat = Chats.get_chat_by_share_id(share_id)
+    elif user.role == "admin":
+        chat = Chats.get_chat_by_id(share_id)
+
+    if chat:
+        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
         )
 
 

backend/apps/webui/routers/configs.py

@@ -8,7 +8,9 @@ from pydantic import BaseModel
 import time
 import uuid
 
-from apps.web.models.users import Users
+from config import BannerModel
+
+from apps.webui.models.users import Users
 
 from utils.utils import (
     get_password_hash,
@@ -57,3 +59,31 @@ async def set_global_default_suggestions(
     data = form_data.model_dump()
     request.app.state.config.DEFAULT_PROMPT_SUGGESTIONS = data["suggestions"]
     return request.app.state.config.DEFAULT_PROMPT_SUGGESTIONS
+
+
+############################
+# SetBanners
+############################
+
+
+class SetBannersForm(BaseModel):
+    banners: List[BannerModel]
+
+
+@router.post("/banners", response_model=List[BannerModel])
+async def set_banners(
+    request: Request,
+    form_data: SetBannersForm,
+    user=Depends(get_admin_user),
+):
+    data = form_data.model_dump()
+    request.app.state.config.BANNERS = data["banners"]
+    return request.app.state.config.BANNERS
+
+
+@router.get("/banners", response_model=List[BannerModel])
+async def get_banners(
+    request: Request,
+    user=Depends(get_current_user),
+):
+    return request.app.state.config.BANNERS

backend/apps/webui/routers/documents.py

@@ -6,7 +6,7 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import json
 
-from apps.web.models.documents import (
+from apps.webui.models.documents import (
     Documents,
     DocumentForm,
     DocumentUpdateForm,

backend/apps/webui/routers/memories.py

@@ -7,7 +7,7 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import logging
 
-from apps.web.models.memories import Memories, MemoryModel
+from apps.webui.models.memories import Memories, MemoryModel
 
 from utils.utils import get_verified_user
 from constants import ERROR_MESSAGES

backend/apps/webui/routers/models.py

@@ -0,0 +1,108 @@
+from fastapi import Depends, FastAPI, HTTPException, status, Request
+from datetime import datetime, timedelta
+from typing import List, Union, Optional
+
+from fastapi import APIRouter
+from pydantic import BaseModel
+import json
+from apps.webui.models.models import Models, ModelModel, ModelForm, ModelResponse
+
+from utils.utils import get_verified_user, get_admin_user
+from constants import ERROR_MESSAGES
+
+router = APIRouter()
+
+###########################
+# getModels
+###########################
+
+
+@router.get("/", response_model=List[ModelResponse])
+async def get_models(user=Depends(get_verified_user)):
+    return Models.get_all_models()
+
+
+############################
+# AddNewModel
+############################
+
+
+@router.post("/add", response_model=Optional[ModelModel])
+async def add_new_model(
+    request: Request, form_data: ModelForm, user=Depends(get_admin_user)
+):
+    if form_data.id in request.app.state.MODELS:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.MODEL_ID_TAKEN,
+        )
+    else:
+        model = Models.insert_new_model(form_data, user.id)
+
+        if model:
+            return model
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail=ERROR_MESSAGES.DEFAULT(),
+            )
+
+
+############################
+# GetModelById
+############################
+
+
+@router.get("/", response_model=Optional[ModelModel])
+async def get_model_by_id(id: str, user=Depends(get_verified_user)):
+    model = Models.get_model_by_id(id)
+
+    if model:
+        return model
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# UpdateModelById
+############################
+
+
+@router.post("/update", response_model=Optional[ModelModel])
+async def update_model_by_id(
+    request: Request, id: str, form_data: ModelForm, user=Depends(get_admin_user)
+):
+    model = Models.get_model_by_id(id)
+    if model:
+        model = Models.update_model_by_id(id, form_data)
+        return model
+    else:
+        if form_data.id in request.app.state.MODELS:
+            model = Models.insert_new_model(form_data, user.id)
+            print(model)
+            if model:
+                return model
+            else:
+                raise HTTPException(
+                    status_code=status.HTTP_401_UNAUTHORIZED,
+                    detail=ERROR_MESSAGES.DEFAULT(),
+                )
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail=ERROR_MESSAGES.DEFAULT(),
+            )
+
+
+############################
+# DeleteModelById
+############################
+
+
+@router.delete("/delete", response_model=bool)
+async def delete_model_by_id(id: str, user=Depends(get_admin_user)):
+    result = Models.delete_model_by_id(id)
+    return result

backend/apps/webui/routers/prompts.py

@@ -6,7 +6,7 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import json
 
-from apps.web.models.prompts import Prompts, PromptForm, PromptModel
+from apps.webui.models.prompts import Prompts, PromptForm, PromptModel
 
 from utils.utils import get_current_user, get_admin_user
 from constants import ERROR_MESSAGES

backend/apps/webui/routers/users.py

@@ -9,9 +9,15 @@ import time
 import uuid
 import logging
 
-from apps.web.models.users import UserModel, UserUpdateForm, UserRoleUpdateForm, Users
+from apps.webui.models.users import (
-from apps.web.models.auths import Auths
+    UserModel,
-from apps.web.models.chats import Chats
+    UserUpdateForm,
+    UserRoleUpdateForm,
+    UserSettings,
+    Users,
+)
+from apps.webui.models.auths import Auths
+from apps.webui.models.chats import Chats
 
 from utils.utils import get_verified_user, get_password_hash, get_admin_user
 from constants import ERROR_MESSAGES
@@ -68,6 +74,42 @@ async def update_user_role(form_data: UserRoleUpdateForm, user=Depends(get_admin
     )
 
 
+############################
+# GetUserSettingsBySessionUser
+############################
+
+
+@router.get("/user/settings", response_model=Optional[UserSettings])
+async def get_user_settings_by_session_user(user=Depends(get_verified_user)):
+    user = Users.get_user_by_id(user.id)
+    if user:
+        return user.settings
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.USER_NOT_FOUND,
+        )
+
+
+############################
+# UpdateUserSettingsBySessionUser
+############################
+
+
+@router.post("/user/settings/update", response_model=UserSettings)
+async def update_user_settings_by_session_user(
+    form_data: UserSettings, user=Depends(get_verified_user)
+):
+    user = Users.update_user_by_id(user.id, {"settings": form_data.model_dump()})
+    if user:
+        return user.settings
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.USER_NOT_FOUND,
+        )
+
+
 ############################
 # GetUserById
 ############################
@@ -81,6 +123,8 @@ class UserResponse(BaseModel):
 @router.get("/{user_id}", response_model=UserResponse)
 async def get_user_by_id(user_id: str, user=Depends(get_verified_user)):
 
+    # Check if user_id is a shared chat
+    # If it is, get the user_id from the chat
     if user_id.startswith("shared-"):
         chat_id = user_id.replace("shared-", "")
         chat = Chats.get_chat_by_id(chat_id)

backend/apps/webui/routers/utils.py

@@ -8,7 +8,7 @@ from pydantic import BaseModel
 from fpdf import FPDF
 import markdown
 
-from apps.web.internal.db import DB
+from apps.webui.internal.db import DB
 from utils.utils import get_admin_user
 from utils.misc import calculate_sha256, get_gravatar_url
 

backend/config.py

@@ -1,11 +1,15 @@
 import os
 import sys
 import logging
+import importlib.metadata
+import pkgutil
 import chromadb
 from chromadb import Settings
 from base64 import b64encode
 from bs4 import BeautifulSoup
 from typing import TypeVar, Generic, Union
+from pydantic import BaseModel
+from typing import Optional
 
 from pathlib import Path
 import json
@@ -22,10 +26,15 @@ from constants import ERROR_MESSAGES
 # Load .env file
 ####################################
 
+BACKEND_DIR = Path(__file__).parent  # the path containing this file
+BASE_DIR = BACKEND_DIR.parent  # the path containing the backend/
+
+print(BASE_DIR)
+
 try:
     from dotenv import load_dotenv, find_dotenv
 
-    load_dotenv(find_dotenv("../.env"))
+    load_dotenv(find_dotenv(str(BASE_DIR / ".env")))
 except ImportError:
     print("dotenv not installed, skipping...")
 
@@ -51,7 +60,6 @@ log_sources = [
     "CONFIG",
     "DB",
     "IMAGES",
-    "LITELLM",
     "MAIN",
     "MODELS",
     "OLLAMA",
@@ -87,9 +95,11 @@ WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 ENV = os.environ.get("ENV", "dev")
 
 try:
-    with open(f"../package.json", "r") as f:
+    PACKAGE_DATA = json.loads((BASE_DIR / "package.json").read_text())
-        PACKAGE_DATA = json.load(f)
 except:
+    try:
+        PACKAGE_DATA = {"version": importlib.metadata.version("open-webui")}
+    except importlib.metadata.PackageNotFoundError:
         PACKAGE_DATA = {"version": "0.0.0"}
 
 VERSION = PACKAGE_DATA["version"]
@@ -115,10 +125,13 @@ def parse_section(section):
 
 
 try:
-    with open("../CHANGELOG.md", "r") as file:
+    changelog_path = BASE_DIR / "CHANGELOG.md"
+    with open(str(changelog_path.absolute()), "r", encoding="utf8") as file:
         changelog_content = file.read()
+
 except:
-    changelog_content = ""
+    changelog_content = (pkgutil.get_data("open_webui", "CHANGELOG.md") or b"").decode()
+
 
 # Convert markdown content to HTML
 html_content = markdown.markdown(changelog_content)
@@ -155,21 +168,20 @@ CHANGELOG = changelog_json
 
 
 ####################################
-# WEBUI_VERSION
+# WEBUI_BUILD_HASH
 ####################################
 
-WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
+WEBUI_BUILD_HASH = os.environ.get("WEBUI_BUILD_HASH", "dev-build")
 
 ####################################
 # DATA/FRONTEND BUILD DIR
 ####################################
 
-DATA_DIR = str(Path(os.getenv("DATA_DIR", "./data")).resolve())
+DATA_DIR = Path(os.getenv("DATA_DIR", BACKEND_DIR / "data")).resolve()
-FRONTEND_BUILD_DIR = str(Path(os.getenv("FRONTEND_BUILD_DIR", "../build")))
+FRONTEND_BUILD_DIR = Path(os.getenv("FRONTEND_BUILD_DIR", BASE_DIR / "build")).resolve()
 
 try:
-    with open(f"{DATA_DIR}/config.json", "r") as f:
+    CONFIG_DATA = json.loads((DATA_DIR / "config.json").read_text())
-        CONFIG_DATA = json.load(f)
 except:
     CONFIG_DATA = {}
 
@@ -279,11 +291,11 @@ JWT_EXPIRES_IN = PersistentConfig(
 # Static DIR
 ####################################
 
-STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
+STATIC_DIR = Path(os.getenv("STATIC_DIR", BACKEND_DIR / "static")).resolve()
 
-frontend_favicon = f"{FRONTEND_BUILD_DIR}/favicon.png"
+frontend_favicon = FRONTEND_BUILD_DIR / "favicon.png"
-if os.path.exists(frontend_favicon):
+if frontend_favicon.exists():
-    shutil.copyfile(frontend_favicon, f"{STATIC_DIR}/favicon.png")
+    shutil.copyfile(frontend_favicon, STATIC_DIR / "favicon.png")
 else:
     logging.warning(f"Frontend favicon not found at {frontend_favicon}")
 
@@ -368,16 +380,23 @@ def create_config_file(file_path):
 
 LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"
 
-if not os.path.exists(LITELLM_CONFIG_PATH):
+# if not os.path.exists(LITELLM_CONFIG_PATH):
-    log.info("Config file doesn't exist. Creating...")
+#     log.info("Config file doesn't exist. Creating...")
-    create_config_file(LITELLM_CONFIG_PATH)
+#     create_config_file(LITELLM_CONFIG_PATH)
-    log.info("Config file created successfully.")
+#     log.info("Config file created successfully.")
 
 
 ####################################
 # OLLAMA_BASE_URL
 ####################################
 
+
+ENABLE_OLLAMA_API = PersistentConfig(
+    "ENABLE_OLLAMA_API",
+    "ollama.enable",
+    os.environ.get("ENABLE_OLLAMA_API", "True").lower() == "true",
+)
+
 OLLAMA_API_BASE_URL = os.environ.get(
     "OLLAMA_API_BASE_URL", "http://localhost:11434/api"
 )
@@ -549,6 +568,27 @@ WEBHOOK_URL = PersistentConfig(
 
 ENABLE_ADMIN_EXPORT = os.environ.get("ENABLE_ADMIN_EXPORT", "True").lower() == "true"
 
+ENABLE_COMMUNITY_SHARING = PersistentConfig(
+    "ENABLE_COMMUNITY_SHARING",
+    "ui.enable_community_sharing",
+    os.environ.get("ENABLE_COMMUNITY_SHARING", "True").lower() == "true",
+)
+
+class BannerModel(BaseModel):
+    id: str
+    type: str
+    title: Optional[str] = None
+    content: str
+    dismissible: bool
+    timestamp: int
+
+
+WEBUI_BANNERS = PersistentConfig(
+    "WEBUI_BANNERS",
+    "ui.banners",
+    [BannerModel(**banner) for banner in json.loads("[]")],
+)
+
 ####################################
 # WEBUI_SECRET_KEY
 ####################################
@@ -813,18 +853,6 @@ AUDIO_OPENAI_API_VOICE = PersistentConfig(
     os.getenv("AUDIO_OPENAI_API_VOICE", "alloy"),
 )
 
-####################################
-# LiteLLM
-####################################
-
-
-ENABLE_LITELLM = os.environ.get("ENABLE_LITELLM", "True").lower() == "true"
-
-LITELLM_PROXY_PORT = int(os.getenv("LITELLM_PROXY_PORT", "14365"))
-if LITELLM_PROXY_PORT < 0 or LITELLM_PROXY_PORT > 65535:
-    raise ValueError("Invalid port number for LITELLM_PROXY_PORT")
-LITELLM_PROXY_HOST = os.getenv("LITELLM_PROXY_HOST", "127.0.0.1")
-
 
 ####################################
 # Database

backend/constants.py

@@ -32,6 +32,8 @@ class ERROR_MESSAGES(str, Enum):
     COMMAND_TAKEN = "Uh-oh! This command is already registered. Please choose another command string."
     FILE_EXISTS = "Uh-oh! This file is already registered. Please choose another file."
 
+    MODEL_ID_TAKEN = "Uh-oh! This model id is already registered. Please choose another model id string."
+
     NAME_TAG_TAKEN = "Uh-oh! This name tag is already registered. Please choose another name tag string."
     INVALID_TOKEN = (
         "Your session has expired or the token is invalid. Please sign in again."

backend/main.py

@@ -8,6 +8,7 @@ import sys
 import logging
 import aiohttp
 import requests
+import mimetypes
 
 from fastapi import FastAPI, Request, Depends, status
 from fastapi.staticfiles import StaticFiles
@@ -18,27 +19,20 @@ from starlette.exceptions import HTTPException as StarletteHTTPException
 from starlette.middleware.base import BaseHTTPMiddleware
 from starlette.responses import StreamingResponse, Response
 
-from apps.ollama.main import app as ollama_app
+from apps.ollama.main import app as ollama_app, get_all_models as get_ollama_models
-from apps.openai.main import app as openai_app
+from apps.openai.main import app as openai_app, get_all_models as get_openai_models
-
-from apps.litellm.main import (
-    app as litellm_app,
-    start_litellm_background,
-    shutdown_litellm_background,
-)
-
 
 from apps.audio.main import app as audio_app
 from apps.images.main import app as images_app
 from apps.rag.main import app as rag_app
-from apps.web.main import app as webui_app
+from apps.webui.main import app as webui_app
 
 import asyncio
 from pydantic import BaseModel
-from typing import List
+from typing import List, Optional
 
-
+from apps.webui.models.models import Models, ModelModel
-from utils.utils import get_admin_user
+from utils.utils import get_admin_user, get_verified_user
 from apps.rag.utils import rag_messages
 
 from config import (
@@ -52,7 +46,8 @@ from config import (
     FRONTEND_BUILD_DIR,
     CACHE_DIR,
     STATIC_DIR,
-    ENABLE_LITELLM,
+    ENABLE_OPENAI_API,
+    ENABLE_OLLAMA_API,
     ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
     GLOBAL_LOG_LEVEL,
@@ -60,6 +55,7 @@ from config import (
     WEBHOOK_URL,
     ENABLE_ADMIN_EXPORT,
     AppConfig,
+    WEBUI_BUILD_HASH,
 )
 from constants import ERROR_MESSAGES
 
@@ -90,6 +86,7 @@ print(
 
       
 v{VERSION} - building the best open-source AI user interface.
+{f"Commit: {WEBUI_BUILD_HASH}" if WEBUI_BUILD_HASH != "dev-build" else ""}
 https://github.com/open-webui/open-webui
 """
 )
@@ -97,11 +94,7 @@ https://github.com/open-webui/open-webui
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    if ENABLE_LITELLM:
-        asyncio.create_task(start_litellm_background())
     yield
-    if ENABLE_LITELLM:
-        await shutdown_litellm_background()
 
 
 app = FastAPI(
@@ -109,11 +102,19 @@ app = FastAPI(
 )
 
 app.state.config = AppConfig()
+
+app.state.config.ENABLE_OPENAI_API = ENABLE_OPENAI_API
+app.state.config.ENABLE_OLLAMA_API = ENABLE_OLLAMA_API
+
 app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
+
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 
+
+app.state.MODELS = {}
+
 origins = ["*"]
 
 
@@ -230,6 +231,11 @@ app.add_middleware(
 
 @app.middleware("http")
 async def check_url(request: Request, call_next):
+    if len(app.state.MODELS) == 0:
+        await get_all_models()
+    else:
+        pass
+
     start_time = int(time.time())
     response = await call_next(request)
     process_time = int(time.time()) - start_time
@@ -246,9 +252,8 @@ async def update_embedding_function(request: Request, call_next):
     return response
 
 
-app.mount("/litellm/api", litellm_app)
 app.mount("/ollama", ollama_app)
-app.mount("/openai/api", openai_app)
+app.mount("/openai", openai_app)
 
 app.mount("/images/api/v1", images_app)
 app.mount("/audio/api/v1", audio_app)
@@ -259,6 +264,87 @@ app.mount("/api/v1", webui_app)
 webui_app.state.EMBEDDING_FUNCTION = rag_app.state.EMBEDDING_FUNCTION
 
 
+async def get_all_models():
+    openai_models = []
+    ollama_models = []
+
+    if app.state.config.ENABLE_OPENAI_API:
+        openai_models = await get_openai_models()
+
+        openai_models = openai_models["data"]
+
+    if app.state.config.ENABLE_OLLAMA_API:
+        ollama_models = await get_ollama_models()
+
+        ollama_models = [
+            {
+                "id": model["model"],
+                "name": model["name"],
+                "object": "model",
+                "created": int(time.time()),
+                "owned_by": "ollama",
+                "ollama": model,
+            }
+            for model in ollama_models["models"]
+        ]
+
+    models = openai_models + ollama_models
+    custom_models = Models.get_all_models()
+
+    for custom_model in custom_models:
+        if custom_model.base_model_id == None:
+            for model in models:
+                if (
+                    custom_model.id == model["id"]
+                    or custom_model.id == model["id"].split(":")[0]
+                ):
+                    model["name"] = custom_model.name
+                    model["info"] = custom_model.model_dump()
+        else:
+            owned_by = "openai"
+            for model in models:
+                if (
+                    custom_model.base_model_id == model["id"]
+                    or custom_model.base_model_id == model["id"].split(":")[0]
+                ):
+                    owned_by = model["owned_by"]
+                    break
+
+            models.append(
+                {
+                    "id": custom_model.id,
+                    "name": custom_model.name,
+                    "object": "model",
+                    "created": custom_model.created_at,
+                    "owned_by": owned_by,
+                    "info": custom_model.model_dump(),
+                    "preset": True,
+                }
+            )
+
+    app.state.MODELS = {model["id"]: model for model in models}
+
+    webui_app.state.MODELS = app.state.MODELS
+
+    return models
+
+
+@app.get("/api/models")
+async def get_models(user=Depends(get_verified_user)):
+    models = await get_all_models()
+    if app.state.config.ENABLE_MODEL_FILTER:
+        if user.role == "user":
+            models = list(
+                filter(
+                    lambda model: model["id"] in app.state.config.MODEL_FILTER_LIST,
+                    models,
+                )
+            )
+            return {"data": models}
+
+    return {"data": models}
+
+
 @app.get("/api/config")
 async def get_app_config():
     # Checking and Handling the Absence of 'ui' in CONFIG_DATA
@@ -272,13 +358,17 @@ async def get_app_config():
         "status": True,
         "name": WEBUI_NAME,
         "version": VERSION,
-        "auth": WEBUI_AUTH,
         "default_locale": default_locale,
-        "images": images_app.state.config.ENABLED,
         "default_models": webui_app.state.config.DEFAULT_MODELS,
         "default_prompt_suggestions": webui_app.state.config.DEFAULT_PROMPT_SUGGESTIONS,
-        "trusted_header_auth": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
+        "features": {
-        "admin_export_enabled": ENABLE_ADMIN_EXPORT,
+            "auth": WEBUI_AUTH,
+            "auth_trusted_header": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
+            "enable_signup": webui_app.state.config.ENABLE_SIGNUP,
+            "enable_image_generation": images_app.state.config.ENABLED,
+            "enable_admin_export": ENABLE_ADMIN_EXPORT,
+            "enable_community_sharing": webui_app.state.config.ENABLE_COMMUNITY_SHARING,
+        },
     }
 
 
@@ -302,15 +392,6 @@ async def update_model_filter_config(
     app.state.config.ENABLE_MODEL_FILTER = form_data.enabled
     app.state.config.MODEL_FILTER_LIST = form_data.models
 
-    ollama_app.state.config.ENABLE_MODEL_FILTER = app.state.config.ENABLE_MODEL_FILTER
-    ollama_app.state.config.MODEL_FILTER_LIST = app.state.config.MODEL_FILTER_LIST
-
-    openai_app.state.config.ENABLE_MODEL_FILTER = app.state.config.ENABLE_MODEL_FILTER
-    openai_app.state.config.MODEL_FILTER_LIST = app.state.config.MODEL_FILTER_LIST
-
-    litellm_app.state.ENABLE_MODEL_FILTER = app.state.config.ENABLE_MODEL_FILTER
-    litellm_app.state.MODEL_FILTER_LIST = app.state.config.MODEL_FILTER_LIST
-
     return {
         "enabled": app.state.config.ENABLE_MODEL_FILTER,
         "models": app.state.config.MODEL_FILTER_LIST,
@@ -331,7 +412,6 @@ class UrlForm(BaseModel):
 @app.post("/api/webhook")
 async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
     app.state.config.WEBHOOK_URL = form_data.url
-
     webui_app.state.WEBHOOK_URL = app.state.config.WEBHOOK_URL
 
     return {
@@ -339,6 +419,19 @@ async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
     }
 
 
+@app.get("/api/community_sharing", response_model=bool)
+async def get_community_sharing_status(request: Request, user=Depends(get_admin_user)):
+    return webui_app.state.config.ENABLE_COMMUNITY_SHARING
+
+
+@app.get("/api/community_sharing/toggle", response_model=bool)
+async def toggle_community_sharing(request: Request, user=Depends(get_admin_user)):
+    webui_app.state.config.ENABLE_COMMUNITY_SHARING = (
+        not webui_app.state.config.ENABLE_COMMUNITY_SHARING
+    )
+    return webui_app.state.config.ENABLE_COMMUNITY_SHARING
+
+
 @app.get("/api/version")
 async def get_app_config():
     return {
@@ -408,6 +501,7 @@ app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
 app.mount("/cache", StaticFiles(directory=CACHE_DIR), name="cache")
 
 if os.path.exists(FRONTEND_BUILD_DIR):
+    mimetypes.add_type("text/javascript", ".js")
     app.mount(
         "/",
         SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),

backend/open_webui/__init__.py

@@ -0,0 +1,60 @@
+import base64
+import os
+import random
+from pathlib import Path
+
+import typer
+import uvicorn
+
+app = typer.Typer()
+
+KEY_FILE = Path.cwd() / ".webui_secret_key"
+if (frontend_build_dir := Path(__file__).parent / "frontend").exists():
+    os.environ["FRONTEND_BUILD_DIR"] = str(frontend_build_dir)
+
+
+@app.command()
+def serve(
+    host: str = "0.0.0.0",
+    port: int = 8080,
+):
+    if os.getenv("WEBUI_SECRET_KEY") is None:
+        typer.echo(
+            "Loading WEBUI_SECRET_KEY from file, not provided as an environment variable."
+        )
+        if not KEY_FILE.exists():
+            typer.echo(f"Generating a new secret key and saving it to {KEY_FILE}")
+            KEY_FILE.write_bytes(base64.b64encode(random.randbytes(12)))
+        typer.echo(f"Loading WEBUI_SECRET_KEY from {KEY_FILE}")
+        os.environ["WEBUI_SECRET_KEY"] = KEY_FILE.read_text()
+
+    if os.getenv("USE_CUDA_DOCKER", "false") == "true":
+        typer.echo(
+            "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
+        )
+        LD_LIBRARY_PATH = os.getenv("LD_LIBRARY_PATH", "").split(":")
+        os.environ["LD_LIBRARY_PATH"] = ":".join(
+            LD_LIBRARY_PATH
+            + [
+                "/usr/local/lib/python3.11/site-packages/torch/lib",
+                "/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib",
+            ]
+        )
+    import main  # we need set environment variables before importing main
+
+    uvicorn.run(main.app, host=host, port=port, forwarded_allow_ips="*")
+
+
+@app.command()
+def dev(
+    host: str = "0.0.0.0",
+    port: int = 8080,
+    reload: bool = True,
+):
+    uvicorn.run(
+        "main:app", host=host, port=port, reload=reload, forwarded_allow_ips="*"
+    )
+
+
+if __name__ == "__main__":
+    app()

backend/requirements.txt

@@ -1,42 +1,40 @@
-fastapi==0.109.2
+fastapi==0.111.0
 uvicorn[standard]==0.22.0
 pydantic==2.7.1
 python-multipart==0.0.9
 
 Flask==3.0.3
-Flask-Cors==4.0.0
+Flask-Cors==4.0.1
 
 python-socketio==5.11.2
 python-jose==3.3.0
 passlib[bcrypt]==1.7.4
 
-requests==2.31.0
+requests==2.32.2
 aiohttp==3.9.5
-peewee==3.17.3
+peewee==3.17.5
 peewee-migrate==1.12.2
 psycopg2-binary==2.9.9
-PyMySQL==1.1.0
+PyMySQL==1.1.1
-bcrypt==4.1.2
+bcrypt==4.1.3
 
-litellm[proxy]==1.35.28
+boto3==1.34.110
-
-boto3==1.34.95
 
 argon2-cffi==23.1.0
 APScheduler==3.10.4
-google-generativeai==0.5.2
+google-generativeai==0.5.4
 
-langchain==0.1.16
+langchain==0.2.0
-langchain-community==0.0.34
+langchain-community==0.2.0
-langchain-chroma==0.1.0
+langchain-chroma==0.1.1
 
 fake-useragent==1.5.1
-chromadb==0.4.24
+chromadb==0.5.0
 sentence-transformers==2.7.0
 pypdf==4.2.0
 docx2txt==0.8
 python-pptx==0.6.23
-unstructured==0.11.8
+unstructured==0.14.0
 Markdown==3.6
 pypandoc==1.13
 pandas==2.2.2
@@ -46,16 +44,16 @@ xlrd==2.0.1
 validators==0.28.1
 
 opencv-python-headless==4.9.0.80
-rapidocr-onnxruntime==1.2.3
+rapidocr-onnxruntime==1.3.22
 
-fpdf2==2.7.8
+fpdf2==2.7.9
 rank-bm25==0.2.2
 
-faster-whisper==1.0.1
+faster-whisper==1.0.2
 
 PyJWT[crypto]==2.8.0
 
 black==24.4.2
-langfuse==2.27.3
+langfuse==2.33.0
 youtube-transcript-api==0.6.2
-pytube
+pytube==15.0.0

backend/start.sh

@@ -30,4 +30,29 @@ if [ "$USE_CUDA_DOCKER" = "true" ]; then
   export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
 fi
 
+
+# Check if SPACE_ID is set, if so, configure for space
+if [ -n "$SPACE_ID" ]; then
+  echo "Configuring for HuggingFace Space deployment"
+  if [ -n "$ADMIN_USER_EMAIL" ] && [ -n "$ADMIN_USER_PASSWORD" ]; then
+    echo "Admin user configured, creating"
+    WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" uvicorn main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*' &
+    webui_pid=$!
+    echo "Waiting for webui to start..."
+    while ! curl -s http://localhost:8080/health > /dev/null; do
+      sleep 1
+    done
+    echo "Creating admin user..."
+    curl \
+      -X POST "http://localhost:8080/api/v1/auths/signup" \
+      -H "accept: application/json" \
+      -H "Content-Type: application/json" \
+      -d "{ \"email\": \"${ADMIN_USER_EMAIL}\", \"password\": \"${ADMIN_USER_PASSWORD}\", \"name\": \"Admin\" }"
+    echo "Shutting down webui..."
+    kill $webui_pid
+  fi
+
+  export WEBUI_URL=${SPACE_HOST}
+fi
+
 WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*'

backend/utils/misc.py

@@ -1,5 +1,6 @@
 from pathlib import Path
 import hashlib
+import json
 import re
 from datetime import timedelta
 from typing import Optional
@@ -110,3 +111,76 @@ def parse_duration(duration: str) -> Optional[timedelta]:
             total_duration += timedelta(weeks=number)
 
     return total_duration
+
+
+def parse_ollama_modelfile(model_text):
+    parameters_meta = {
+        "mirostat": int,
+        "mirostat_eta": float,
+        "mirostat_tau": float,
+        "num_ctx": int,
+        "repeat_last_n": int,
+        "repeat_penalty": float,
+        "temperature": float,
+        "seed": int,
+        "stop": str,
+        "tfs_z": float,
+        "num_predict": int,
+        "top_k": int,
+        "top_p": float,
+    }
+
+    data = {"base_model_id": None, "params": {}}
+
+    # Parse base model
+    base_model_match = re.search(
+        r"^FROM\s+(\w+)", model_text, re.MULTILINE | re.IGNORECASE
+    )
+    if base_model_match:
+        data["base_model_id"] = base_model_match.group(1)
+
+    # Parse template
+    template_match = re.search(
+        r'TEMPLATE\s+"""(.+?)"""', model_text, re.DOTALL | re.IGNORECASE
+    )
+    if template_match:
+        data["params"] = {"template": template_match.group(1).strip()}
+
+    # Parse stops
+    stops = re.findall(r'PARAMETER stop "(.*?)"', model_text, re.IGNORECASE)
+    if stops:
+        data["params"]["stop"] = stops
+
+    # Parse other parameters from the provided list
+    for param, param_type in parameters_meta.items():
+        param_match = re.search(rf"PARAMETER {param} (.+)", model_text, re.IGNORECASE)
+        if param_match:
+            value = param_match.group(1)
+            if param_type == int:
+                value = int(value)
+            elif param_type == float:
+                value = float(value)
+            data["params"][param] = value
+
+    # Parse adapter
+    adapter_match = re.search(r"ADAPTER (.+)", model_text, re.IGNORECASE)
+    if adapter_match:
+        data["params"]["adapter"] = adapter_match.group(1)
+
+    # Parse system description
+    system_desc_match = re.search(
+        r'SYSTEM\s+"""(.+?)"""', model_text, re.DOTALL | re.IGNORECASE
+    )
+    if system_desc_match:
+        data["params"]["system"] = system_desc_match.group(1).strip()
+
+    # Parse messages
+    messages = []
+    message_matches = re.findall(r"MESSAGE (\w+) (.+)", model_text, re.IGNORECASE)
+    for role, content in message_matches:
+        messages.append({"role": role, "content": content})
+
+    if messages:
+        data["params"]["messages"] = messages
+
+    return data

backend/utils/models.py

@@ -0,0 +1,10 @@
+from apps.webui.models.models import Models, ModelModel, ModelForm, ModelResponse
+
+
+def get_model_id_from_custom_model_id(id: str):
+    model = Models.get_model_by_id(id)
+
+    if model:
+        return model.id
+    else:
+        return id

backend/utils/utils.py

@@ -1,7 +1,7 @@
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi import HTTPException, status, Depends
 
-from apps.web.models.users import Users
+from apps.webui.models.users import Users
 
 from pydantic import BaseModel
 from typing import Union, Optional

cypress/e2e/chat.cy.ts

@@ -74,5 +74,28 @@ describe('Settings', () => {
 				expect(spy).to.be.callCount(2);
 			});
 		});
+
+		it('user can generate image', () => {
+			// Click on the model selector
+			cy.get('button[aria-label="Select a model"]').click();
+			// Select the first model
+			cy.get('button[aria-label="model-item"]').first().click();
+			// Type a message
+			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
+				force: true
+			});
+			// Send the message
+			cy.get('button[type="submit"]').click();
+			// User's message should be visible
+			cy.get('.chat-user').should('exist');
+			// Wait for the response
+			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
+				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
+				.should('exist');
+			// Click on the generate image button
+			cy.get('[aria-label="Generate Image"]').click();
+			// Wait for image to be visible
+			cy.get('img[data-cy="image"]', { timeout: 60_000 }).should('be.visible');
+		});
 	});
 });

docker-compose.a1111-test.yaml

@@ -0,0 +1,31 @@
+# This is an overlay that spins up stable-diffusion-webui for integration testing
+# This is not designed to be used in production
+services:
+  stable-diffusion-webui:
+    # Not built for ARM64
+    platform: linux/amd64
+    image: ghcr.io/neggles/sd-webui-docker:latest
+    restart: unless-stopped
+    environment:
+      CLI_ARGS: "--api --use-cpu all --precision full --no-half --skip-torch-cuda-test --ckpt /empty.pt --do-not-download-clip --disable-nan-check --disable-opt-split-attention"
+      PYTHONUNBUFFERED: "1"
+      TERM: "vt100"
+      SD_WEBUI_VARIANT: "default"
+    # Hack to get container working on Apple Silicon
+    # Rosetta creates a conflict ${HOME}/.cache folder
+    entrypoint: /bin/bash
+    command:
+      - -c
+      - |
+        export HOME=/root-home
+        rm -rf $${HOME}/.cache
+        /docker/entrypoint.sh python -u webui.py --listen --port $${WEBUI_PORT} --skip-version-check $${CLI_ARGS}
+    volumes:
+      - ./test/test_files/image_gen/sd-empty.pt:/empty.pt
+
+  open-webui:
+    environment:
+      ENABLE_IMAGE_GENERATION: "true"
+      AUTOMATIC1111_BASE_URL: http://stable-diffusion-webui:7860
+      IMAGE_SIZE: "64x64"
+      IMAGE_STEPS: "3"

hatch_build.py

@@ -0,0 +1,23 @@
+# noqa: INP001
+import os
+import shutil
+import subprocess
+from sys import stderr
+
+from hatchling.builders.hooks.plugin.interface import BuildHookInterface
+
+
+class CustomBuildHook(BuildHookInterface):
+    def initialize(self, version, build_data):
+        super().initialize(version, build_data)
+        stderr.write(">>> Building Open Webui frontend\n")
+        npm = shutil.which("npm")
+        if npm is None:
+            raise RuntimeError(
+                "NodeJS `npm` is required for building Open Webui but it was not found"
+            )
+        stderr.write("### npm install\n")
+        subprocess.run([npm, "install"], check=True)  # noqa: S603
+        stderr.write("\n### npm run build\n")
+        os.environ["APP_BUILD_HASH"] = version
+        subprocess.run([npm, "run", "build"], check=True)  # noqa: S603

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.1.125",
+	"version": "0.2.0.dev2",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.1.125",
+			"version": "0.2.0.dev2",
 			"dependencies": {
 				"@pyscript/core": "^0.4.32",
 				"@sveltejs/adapter-node": "^1.3.1",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.125",
+	"version": "0.2.0.dev2",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -13,7 +13,7 @@
 		"lint:types": "npm run check",
 		"lint:backend": "pylint backend/",
 		"format": "prettier --plugin-search-dir --write \"**/*.{js,ts,svelte,css,md,html,json}\"",
-		"format:backend": "black . --exclude \"/venv/\"",
+		"format:backend": "black . --exclude \".venv/|/venv/\"",
 		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write \"src/lib/i18n/**/*.{js,json}\"",
 		"cy:open": "cypress open",
 		"test:frontend": "vitest",

pyproject.toml

@@ -0,0 +1,115 @@
+[project]
+name = "open-webui"
+description = "Open WebUI (Formerly Ollama WebUI)"
+authors = [
+    { name = "Timothy Jaeryang Baek", email = "tim@openwebui.com" }
+]
+license = { file = "LICENSE" }
+dependencies = [
+    "fastapi==0.111.0",
+    "uvicorn[standard]==0.22.0",
+    "pydantic==2.7.1",
+    "python-multipart==0.0.9",
+
+    "Flask==3.0.3",
+    "Flask-Cors==4.0.1",
+
+    "python-socketio==5.11.2",
+    "python-jose==3.3.0",
+    "passlib[bcrypt]==1.7.4",
+
+    "requests==2.32.2",
+    "aiohttp==3.9.5",
+    "peewee==3.17.5",
+    "peewee-migrate==1.12.2",
+    "psycopg2-binary==2.9.9",
+    "PyMySQL==1.1.0",
+    "bcrypt==4.1.3",
+
+    "litellm[proxy]==1.37.20",
+
+    "boto3==1.34.110",
+
+    "argon2-cffi==23.1.0",
+    "APScheduler==3.10.4",
+    "google-generativeai==0.5.4",
+
+    "langchain==0.2.0",
+    "langchain-community==0.2.0",
+    "langchain-chroma==0.1.1",
+
+    "fake-useragent==1.5.1",
+    "chromadb==0.5.0",
+    "sentence-transformers==2.7.0",
+    "pypdf==4.2.0",
+    "docx2txt==0.8",
+    "unstructured==0.14.0",
+    "Markdown==3.6",
+    "pypandoc==1.13",
+    "pandas==2.2.2",
+    "openpyxl==3.1.2",
+    "pyxlsb==1.0.10",
+    "xlrd==2.0.1",
+    "validators==0.28.1",
+
+    "opencv-python-headless==4.9.0.80",
+    "rapidocr-onnxruntime==1.3.22",
+
+    "fpdf2==2.7.9",
+    "rank-bm25==0.2.2",
+
+    "faster-whisper==1.0.2",
+
+    "PyJWT[crypto]==2.8.0",
+
+    "black==24.4.2",
+    "langfuse==2.33.0",
+    "youtube-transcript-api==0.6.2",
+    "pytube==15.0.0",
+]
+readme = "README.md"
+requires-python = ">= 3.11, < 3.12.0a1"
+dynamic = ["version"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Communications :: Chat",
+    "Topic :: Multimedia",
+]
+
+[project.scripts]
+open-webui = "open_webui:app"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = []
+
+[tool.hatch.metadata]
+allow-direct-references = true
+
+[tool.hatch.version]
+path = "package.json"
+pattern = '"version":\s*"(?P<version>[^"]+)"'
+
+[tool.hatch.build.hooks.custom]  # keep this for reading hooks from `hatch_build.py`
+
+[tool.hatch.build.targets.wheel]
+sources = ["backend"]
+exclude = [
+    ".dockerignore",
+    ".gitignore",
+    ".webui_secret_key",
+    "dev.sh",
+    "requirements.txt",
+    "start.sh",
+    "start_windows.bat",
+    "webui.db",
+    "chroma.sqlite3",
+]
+force-include = { "CHANGELOG.md" = "open_webui/CHANGELOG.md", build = "open_webui/frontend" }

requirements-dev.lock

@@ -0,0 +1,688 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+
+-e file:.
+aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
+    # via litellm
+    # via open-webui
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.6.0
+    # via pydantic
+anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+apscheduler==3.10.4
+    # via litellm
+    # via open-webui
+argon2-cffi==23.1.0
+    # via open-webui
+argon2-cffi-bindings==21.2.0
+    # via argon2-cffi
+asgiref==3.8.1
+    # via opentelemetry-instrumentation-asgi
+attrs==23.2.0
+    # via aiohttp
+av==11.0.0
+    # via faster-whisper
+backoff==2.2.1
+    # via langfuse
+    # via litellm
+    # via posthog
+    # via unstructured
+bcrypt==4.1.3
+    # via chromadb
+    # via open-webui
+    # via passlib
+beautifulsoup4==4.12.3
+    # via unstructured
+bidict==0.23.1
+    # via python-socketio
+black==24.4.2
+    # via open-webui
+blinker==1.8.2
+    # via flask
+boto3==1.34.110
+    # via open-webui
+botocore==1.34.110
+    # via boto3
+    # via s3transfer
+build==1.2.1
+    # via chromadb
+cachetools==5.3.3
+    # via google-auth
+certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+cffi==1.16.0
+    # via argon2-cffi-bindings
+    # via cryptography
+chardet==5.2.0
+    # via unstructured
+charset-normalizer==3.3.2
+    # via requests
+    # via unstructured-client
+chroma-hnswlib==0.7.3
+    # via chromadb
+chromadb==0.5.0
+    # via langchain-chroma
+    # via open-webui
+click==8.1.7
+    # via black
+    # via flask
+    # via litellm
+    # via nltk
+    # via peewee-migrate
+    # via rq
+    # via typer
+    # via uvicorn
+coloredlogs==15.0.1
+    # via onnxruntime
+cryptography==42.0.7
+    # via litellm
+    # via pyjwt
+ctranslate2==4.2.1
+    # via faster-whisper
+dataclasses-json==0.6.6
+    # via langchain
+    # via langchain-community
+    # via unstructured
+    # via unstructured-client
+deepdiff==7.0.1
+    # via unstructured-client
+defusedxml==0.7.1
+    # via fpdf2
+deprecated==1.2.14
+    # via opentelemetry-api
+    # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via openai
+dnspython==2.6.1
+    # via email-validator
+docx2txt==0.8
+    # via open-webui
+ecdsa==0.19.0
+    # via python-jose
+email-validator==2.1.1
+    # via fastapi
+    # via pydantic
+emoji==2.11.1
+    # via unstructured
+et-xmlfile==1.1.0
+    # via openpyxl
+fake-useragent==1.5.1
+    # via open-webui
+fastapi==0.111.0
+    # via chromadb
+    # via fastapi-sso
+    # via langchain-chroma
+    # via litellm
+    # via open-webui
+fastapi-cli==0.0.4
+    # via fastapi
+fastapi-sso==0.10.0
+    # via litellm
+faster-whisper==1.0.2
+    # via open-webui
+filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+filetype==1.2.0
+    # via unstructured
+flask==3.0.3
+    # via flask-cors
+    # via open-webui
+flask-cors==4.0.1
+    # via open-webui
+flatbuffers==24.3.25
+    # via onnxruntime
+fonttools==4.51.0
+    # via fpdf2
+fpdf2==2.7.9
+    # via open-webui
+frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
+fsspec==2024.3.1
+    # via huggingface-hub
+    # via torch
+google-ai-generativelanguage==0.6.4
+    # via google-generativeai
+google-api-core==2.19.0
+    # via google-ai-generativelanguage
+    # via google-api-python-client
+    # via google-generativeai
+google-api-python-client==2.129.0
+    # via google-generativeai
+google-auth==2.29.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-api-python-client
+    # via google-auth-httplib2
+    # via google-generativeai
+    # via kubernetes
+google-auth-httplib2==0.2.0
+    # via google-api-python-client
+google-generativeai==0.5.4
+    # via open-webui
+googleapis-common-protos==1.63.0
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio==1.63.0
+    # via chromadb
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio-status==1.62.2
+    # via google-api-core
+gunicorn==22.0.0
+    # via litellm
+h11==0.14.0
+    # via httpcore
+    # via uvicorn
+    # via wsproto
+httpcore==1.0.5
+    # via httpx
+httplib2==0.22.0
+    # via google-api-python-client
+    # via google-auth-httplib2
+httptools==0.6.1
+    # via uvicorn
+httpx==0.27.0
+    # via fastapi
+    # via fastapi-sso
+    # via langfuse
+    # via openai
+huggingface-hub==0.23.0
+    # via faster-whisper
+    # via sentence-transformers
+    # via tokenizers
+    # via transformers
+humanfriendly==10.0
+    # via coloredlogs
+idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via langfuse
+    # via requests
+    # via unstructured-client
+    # via yarl
+importlib-metadata==7.0.0
+    # via litellm
+    # via opentelemetry-api
+importlib-resources==6.4.0
+    # via chromadb
+itsdangerous==2.2.0
+    # via flask
+jinja2==3.1.4
+    # via fastapi
+    # via flask
+    # via litellm
+    # via torch
+jmespath==1.0.1
+    # via boto3
+    # via botocore
+joblib==1.4.2
+    # via nltk
+    # via scikit-learn
+jsonpatch==1.33
+    # via langchain-core
+jsonpath-python==1.0.6
+    # via unstructured-client
+jsonpointer==2.4
+    # via jsonpatch
+kubernetes==29.0.0
+    # via chromadb
+langchain==0.2.0
+    # via langchain-community
+    # via open-webui
+langchain-chroma==0.1.1
+    # via open-webui
+langchain-community==0.2.0
+    # via open-webui
+langchain-core==0.2.1
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via langchain-text-splitters
+langchain-text-splitters==0.2.0
+    # via langchain
+langdetect==1.0.9
+    # via unstructured
+langfuse==2.33.0
+    # via open-webui
+langsmith==0.1.57
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+litellm==1.37.20
+    # via open-webui
+lxml==5.2.2
+    # via unstructured
+markdown==3.6
+    # via open-webui
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via jinja2
+    # via werkzeug
+marshmallow==3.21.2
+    # via dataclasses-json
+    # via unstructured-client
+mdurl==0.1.2
+    # via markdown-it-py
+mmh3==4.1.0
+    # via chromadb
+monotonic==1.6
+    # via posthog
+mpmath==1.3.0
+    # via sympy
+multidict==6.0.5
+    # via aiohttp
+    # via yarl
+mypy-extensions==1.0.0
+    # via black
+    # via typing-inspect
+    # via unstructured-client
+networkx==3.3
+    # via torch
+nltk==3.8.1
+    # via unstructured
+numpy==1.26.4
+    # via chroma-hnswlib
+    # via chromadb
+    # via ctranslate2
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via onnxruntime
+    # via opencv-python
+    # via opencv-python-headless
+    # via pandas
+    # via rank-bm25
+    # via rapidocr-onnxruntime
+    # via scikit-learn
+    # via scipy
+    # via sentence-transformers
+    # via shapely
+    # via transformers
+    # via unstructured
+oauthlib==3.2.2
+    # via fastapi-sso
+    # via kubernetes
+    # via requests-oauthlib
+onnxruntime==1.17.3
+    # via chromadb
+    # via faster-whisper
+    # via rapidocr-onnxruntime
+openai==1.28.1
+    # via litellm
+opencv-python==4.9.0.80
+    # via rapidocr-onnxruntime
+opencv-python-headless==4.9.0.80
+    # via open-webui
+openpyxl==3.1.2
+    # via open-webui
+opentelemetry-api==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+    # via opentelemetry-instrumentation
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-exporter-otlp-proto-common==1.24.0
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+    # via chromadb
+opentelemetry-instrumentation==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-asgi==0.45b0
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-fastapi==0.45b0
+    # via chromadb
+opentelemetry-proto==1.24.0
+    # via opentelemetry-exporter-otlp-proto-common
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-sdk==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-semantic-conventions==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-util-http==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+ordered-set==4.1.0
+    # via deepdiff
+orjson==3.10.3
+    # via chromadb
+    # via fastapi
+    # via langsmith
+    # via litellm
+overrides==7.7.0
+    # via chromadb
+packaging==23.2
+    # via black
+    # via build
+    # via gunicorn
+    # via huggingface-hub
+    # via langchain-core
+    # via langfuse
+    # via marshmallow
+    # via onnxruntime
+    # via transformers
+    # via unstructured-client
+pandas==2.2.2
+    # via open-webui
+passlib==1.7.4
+    # via open-webui
+pathspec==0.12.1
+    # via black
+peewee==3.17.5
+    # via open-webui
+    # via peewee-migrate
+peewee-migrate==1.12.2
+    # via open-webui
+pillow==10.3.0
+    # via fpdf2
+    # via rapidocr-onnxruntime
+    # via sentence-transformers
+platformdirs==4.2.1
+    # via black
+posthog==3.5.0
+    # via chromadb
+proto-plus==1.23.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+protobuf==4.25.3
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-generativeai
+    # via googleapis-common-protos
+    # via grpcio-status
+    # via onnxruntime
+    # via opentelemetry-proto
+    # via proto-plus
+psycopg2-binary==2.9.9
+    # via open-webui
+pyasn1==0.6.0
+    # via pyasn1-modules
+    # via python-jose
+    # via rsa
+pyasn1-modules==0.4.0
+    # via google-auth
+pyclipper==1.3.0.post5
+    # via rapidocr-onnxruntime
+pycparser==2.22
+    # via cffi
+pydantic==2.7.1
+    # via chromadb
+    # via fastapi
+    # via fastapi-sso
+    # via google-generativeai
+    # via langchain
+    # via langchain-core
+    # via langfuse
+    # via langsmith
+    # via open-webui
+    # via openai
+pydantic-core==2.18.2
+    # via pydantic
+pygments==2.18.0
+    # via rich
+pyjwt==2.8.0
+    # via litellm
+    # via open-webui
+pymysql==1.1.0
+    # via open-webui
+pypandoc==1.13
+    # via open-webui
+pyparsing==3.1.2
+    # via httplib2
+pypdf==4.2.0
+    # via open-webui
+    # via unstructured-client
+pypika==0.48.9
+    # via chromadb
+pyproject-hooks==1.1.0
+    # via build
+python-dateutil==2.9.0.post0
+    # via botocore
+    # via kubernetes
+    # via pandas
+    # via posthog
+    # via unstructured-client
+python-dotenv==1.0.1
+    # via litellm
+    # via uvicorn
+python-engineio==4.9.0
+    # via python-socketio
+python-iso639==2024.4.27
+    # via unstructured
+python-jose==3.3.0
+    # via open-webui
+python-magic==0.4.27
+    # via unstructured
+python-multipart==0.0.9
+    # via fastapi
+    # via litellm
+    # via open-webui
+python-socketio==5.11.2
+    # via open-webui
+pytube==15.0.0
+    # via open-webui
+pytz==2024.1
+    # via apscheduler
+    # via pandas
+pyxlsb==1.0.10
+    # via open-webui
+pyyaml==6.0.1
+    # via chromadb
+    # via ctranslate2
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via litellm
+    # via rapidocr-onnxruntime
+    # via transformers
+    # via uvicorn
+rank-bm25==0.2.2
+    # via open-webui
+rapidfuzz==3.9.0
+    # via unstructured
+rapidocr-onnxruntime==1.3.22
+    # via open-webui
+redis==5.0.4
+    # via rq
+regex==2024.5.10
+    # via nltk
+    # via tiktoken
+    # via transformers
+requests==2.32.2
+    # via chromadb
+    # via google-api-core
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via litellm
+    # via open-webui
+    # via posthog
+    # via requests-oauthlib
+    # via tiktoken
+    # via transformers
+    # via unstructured
+    # via unstructured-client
+    # via youtube-transcript-api
+requests-oauthlib==2.0.0
+    # via kubernetes
+rich==13.7.1
+    # via typer
+rq==1.16.2
+    # via litellm
+rsa==4.9
+    # via google-auth
+    # via python-jose
+s3transfer==0.10.1
+    # via boto3
+safetensors==0.4.3
+    # via transformers
+scikit-learn==1.4.2
+    # via sentence-transformers
+scipy==1.13.0
+    # via scikit-learn
+    # via sentence-transformers
+sentence-transformers==2.7.0
+    # via open-webui
+setuptools==69.5.1
+    # via ctranslate2
+    # via opentelemetry-instrumentation
+shapely==2.0.4
+    # via rapidocr-onnxruntime
+shellingham==1.5.4
+    # via typer
+simple-websocket==1.0.0
+    # via python-engineio
+six==1.16.0
+    # via apscheduler
+    # via ecdsa
+    # via kubernetes
+    # via langdetect
+    # via posthog
+    # via python-dateutil
+    # via rapidocr-onnxruntime
+    # via unstructured-client
+sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
+soupsieve==2.5
+    # via beautifulsoup4
+sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
+starlette==0.37.2
+    # via fastapi
+sympy==1.12
+    # via onnxruntime
+    # via torch
+tabulate==0.9.0
+    # via unstructured
+tenacity==8.3.0
+    # via chromadb
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.6.0
+    # via litellm
+tokenizers==0.15.2
+    # via chromadb
+    # via faster-whisper
+    # via litellm
+    # via transformers
+torch==2.3.0
+    # via sentence-transformers
+tqdm==4.66.4
+    # via chromadb
+    # via google-generativeai
+    # via huggingface-hub
+    # via nltk
+    # via openai
+    # via sentence-transformers
+    # via transformers
+transformers==4.39.3
+    # via sentence-transformers
+typer==0.12.3
+    # via chromadb
+    # via fastapi-cli
+typing-extensions==4.11.0
+    # via chromadb
+    # via fastapi
+    # via google-generativeai
+    # via huggingface-hub
+    # via openai
+    # via opentelemetry-sdk
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via unstructured
+    # via unstructured-client
+typing-inspect==0.9.0
+    # via dataclasses-json
+    # via unstructured-client
+tzdata==2024.1
+    # via pandas
+tzlocal==5.2
+    # via apscheduler
+ujson==5.10.0
+    # via fastapi
+unstructured==0.14.0
+    # via open-webui
+unstructured-client==0.22.0
+    # via unstructured
+uritemplate==4.1.1
+    # via google-api-python-client
+urllib3==2.2.1
+    # via botocore
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+uvicorn==0.22.0
+    # via chromadb
+    # via fastapi
+    # via litellm
+    # via open-webui
+uvloop==0.19.0
+    # via uvicorn
+validators==0.28.1
+    # via open-webui
+watchfiles==0.21.0
+    # via uvicorn
+websocket-client==1.8.0
+    # via kubernetes
+websockets==12.0
+    # via uvicorn
+werkzeug==3.0.3
+    # via flask
+wrapt==1.16.0
+    # via deprecated
+    # via langfuse
+    # via opentelemetry-instrumentation
+    # via unstructured
+wsproto==1.2.0
+    # via simple-websocket
+xlrd==2.0.1
+    # via open-webui
+yarl==1.9.4
+    # via aiohttp
+youtube-transcript-api==0.6.2
+    # via open-webui
+zipp==3.18.1
+    # via importlib-metadata

requirements.lock

@@ -0,0 +1,688 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+
+-e file:.
+aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
+    # via litellm
+    # via open-webui
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.6.0
+    # via pydantic
+anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+apscheduler==3.10.4
+    # via litellm
+    # via open-webui
+argon2-cffi==23.1.0
+    # via open-webui
+argon2-cffi-bindings==21.2.0
+    # via argon2-cffi
+asgiref==3.8.1
+    # via opentelemetry-instrumentation-asgi
+attrs==23.2.0
+    # via aiohttp
+av==11.0.0
+    # via faster-whisper
+backoff==2.2.1
+    # via langfuse
+    # via litellm
+    # via posthog
+    # via unstructured
+bcrypt==4.1.3
+    # via chromadb
+    # via open-webui
+    # via passlib
+beautifulsoup4==4.12.3
+    # via unstructured
+bidict==0.23.1
+    # via python-socketio
+black==24.4.2
+    # via open-webui
+blinker==1.8.2
+    # via flask
+boto3==1.34.110
+    # via open-webui
+botocore==1.34.110
+    # via boto3
+    # via s3transfer
+build==1.2.1
+    # via chromadb
+cachetools==5.3.3
+    # via google-auth
+certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+cffi==1.16.0
+    # via argon2-cffi-bindings
+    # via cryptography
+chardet==5.2.0
+    # via unstructured
+charset-normalizer==3.3.2
+    # via requests
+    # via unstructured-client
+chroma-hnswlib==0.7.3
+    # via chromadb
+chromadb==0.5.0
+    # via langchain-chroma
+    # via open-webui
+click==8.1.7
+    # via black
+    # via flask
+    # via litellm
+    # via nltk
+    # via peewee-migrate
+    # via rq
+    # via typer
+    # via uvicorn
+coloredlogs==15.0.1
+    # via onnxruntime
+cryptography==42.0.7
+    # via litellm
+    # via pyjwt
+ctranslate2==4.2.1
+    # via faster-whisper
+dataclasses-json==0.6.6
+    # via langchain
+    # via langchain-community
+    # via unstructured
+    # via unstructured-client
+deepdiff==7.0.1
+    # via unstructured-client
+defusedxml==0.7.1
+    # via fpdf2
+deprecated==1.2.14
+    # via opentelemetry-api
+    # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via openai
+dnspython==2.6.1
+    # via email-validator
+docx2txt==0.8
+    # via open-webui
+ecdsa==0.19.0
+    # via python-jose
+email-validator==2.1.1
+    # via fastapi
+    # via pydantic
+emoji==2.11.1
+    # via unstructured
+et-xmlfile==1.1.0
+    # via openpyxl
+fake-useragent==1.5.1
+    # via open-webui
+fastapi==0.111.0
+    # via chromadb
+    # via fastapi-sso
+    # via langchain-chroma
+    # via litellm
+    # via open-webui
+fastapi-cli==0.0.4
+    # via fastapi
+fastapi-sso==0.10.0
+    # via litellm
+faster-whisper==1.0.2
+    # via open-webui
+filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+filetype==1.2.0
+    # via unstructured
+flask==3.0.3
+    # via flask-cors
+    # via open-webui
+flask-cors==4.0.1
+    # via open-webui
+flatbuffers==24.3.25
+    # via onnxruntime
+fonttools==4.51.0
+    # via fpdf2
+fpdf2==2.7.9
+    # via open-webui
+frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
+fsspec==2024.3.1
+    # via huggingface-hub
+    # via torch
+google-ai-generativelanguage==0.6.4
+    # via google-generativeai
+google-api-core==2.19.0
+    # via google-ai-generativelanguage
+    # via google-api-python-client
+    # via google-generativeai
+google-api-python-client==2.129.0
+    # via google-generativeai
+google-auth==2.29.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-api-python-client
+    # via google-auth-httplib2
+    # via google-generativeai
+    # via kubernetes
+google-auth-httplib2==0.2.0
+    # via google-api-python-client
+google-generativeai==0.5.4
+    # via open-webui
+googleapis-common-protos==1.63.0
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio==1.63.0
+    # via chromadb
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio-status==1.62.2
+    # via google-api-core
+gunicorn==22.0.0
+    # via litellm
+h11==0.14.0
+    # via httpcore
+    # via uvicorn
+    # via wsproto
+httpcore==1.0.5
+    # via httpx
+httplib2==0.22.0
+    # via google-api-python-client
+    # via google-auth-httplib2
+httptools==0.6.1
+    # via uvicorn
+httpx==0.27.0
+    # via fastapi
+    # via fastapi-sso
+    # via langfuse
+    # via openai
+huggingface-hub==0.23.0
+    # via faster-whisper
+    # via sentence-transformers
+    # via tokenizers
+    # via transformers
+humanfriendly==10.0
+    # via coloredlogs
+idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via langfuse
+    # via requests
+    # via unstructured-client
+    # via yarl
+importlib-metadata==7.0.0
+    # via litellm
+    # via opentelemetry-api
+importlib-resources==6.4.0
+    # via chromadb
+itsdangerous==2.2.0
+    # via flask
+jinja2==3.1.4
+    # via fastapi
+    # via flask
+    # via litellm
+    # via torch
+jmespath==1.0.1
+    # via boto3
+    # via botocore
+joblib==1.4.2
+    # via nltk
+    # via scikit-learn
+jsonpatch==1.33
+    # via langchain-core
+jsonpath-python==1.0.6
+    # via unstructured-client
+jsonpointer==2.4
+    # via jsonpatch
+kubernetes==29.0.0
+    # via chromadb
+langchain==0.2.0
+    # via langchain-community
+    # via open-webui
+langchain-chroma==0.1.1
+    # via open-webui
+langchain-community==0.2.0
+    # via open-webui
+langchain-core==0.2.1
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via langchain-text-splitters
+langchain-text-splitters==0.2.0
+    # via langchain
+langdetect==1.0.9
+    # via unstructured
+langfuse==2.33.0
+    # via open-webui
+langsmith==0.1.57
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+litellm==1.37.20
+    # via open-webui
+lxml==5.2.2
+    # via unstructured
+markdown==3.6
+    # via open-webui
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via jinja2
+    # via werkzeug
+marshmallow==3.21.2
+    # via dataclasses-json
+    # via unstructured-client
+mdurl==0.1.2
+    # via markdown-it-py
+mmh3==4.1.0
+    # via chromadb
+monotonic==1.6
+    # via posthog
+mpmath==1.3.0
+    # via sympy
+multidict==6.0.5
+    # via aiohttp
+    # via yarl
+mypy-extensions==1.0.0
+    # via black
+    # via typing-inspect
+    # via unstructured-client
+networkx==3.3
+    # via torch
+nltk==3.8.1
+    # via unstructured
+numpy==1.26.4
+    # via chroma-hnswlib
+    # via chromadb
+    # via ctranslate2
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via onnxruntime
+    # via opencv-python
+    # via opencv-python-headless
+    # via pandas
+    # via rank-bm25
+    # via rapidocr-onnxruntime
+    # via scikit-learn
+    # via scipy
+    # via sentence-transformers
+    # via shapely
+    # via transformers
+    # via unstructured
+oauthlib==3.2.2
+    # via fastapi-sso
+    # via kubernetes
+    # via requests-oauthlib
+onnxruntime==1.17.3
+    # via chromadb
+    # via faster-whisper
+    # via rapidocr-onnxruntime
+openai==1.28.1
+    # via litellm
+opencv-python==4.9.0.80
+    # via rapidocr-onnxruntime
+opencv-python-headless==4.9.0.80
+    # via open-webui
+openpyxl==3.1.2
+    # via open-webui
+opentelemetry-api==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+    # via opentelemetry-instrumentation
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-exporter-otlp-proto-common==1.24.0
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+    # via chromadb
+opentelemetry-instrumentation==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-asgi==0.45b0
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-fastapi==0.45b0
+    # via chromadb
+opentelemetry-proto==1.24.0
+    # via opentelemetry-exporter-otlp-proto-common
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-sdk==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-semantic-conventions==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-util-http==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+ordered-set==4.1.0
+    # via deepdiff
+orjson==3.10.3
+    # via chromadb
+    # via fastapi
+    # via langsmith
+    # via litellm
+overrides==7.7.0
+    # via chromadb
+packaging==23.2
+    # via black
+    # via build
+    # via gunicorn
+    # via huggingface-hub
+    # via langchain-core
+    # via langfuse
+    # via marshmallow
+    # via onnxruntime
+    # via transformers
+    # via unstructured-client
+pandas==2.2.2
+    # via open-webui
+passlib==1.7.4
+    # via open-webui
+pathspec==0.12.1
+    # via black
+peewee==3.17.5
+    # via open-webui
+    # via peewee-migrate
+peewee-migrate==1.12.2
+    # via open-webui
+pillow==10.3.0
+    # via fpdf2
+    # via rapidocr-onnxruntime
+    # via sentence-transformers
+platformdirs==4.2.1
+    # via black
+posthog==3.5.0
+    # via chromadb
+proto-plus==1.23.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+protobuf==4.25.3
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-generativeai
+    # via googleapis-common-protos
+    # via grpcio-status
+    # via onnxruntime
+    # via opentelemetry-proto
+    # via proto-plus
+psycopg2-binary==2.9.9
+    # via open-webui
+pyasn1==0.6.0
+    # via pyasn1-modules
+    # via python-jose
+    # via rsa
+pyasn1-modules==0.4.0
+    # via google-auth
+pyclipper==1.3.0.post5
+    # via rapidocr-onnxruntime
+pycparser==2.22
+    # via cffi
+pydantic==2.7.1
+    # via chromadb
+    # via fastapi
+    # via fastapi-sso
+    # via google-generativeai
+    # via langchain
+    # via langchain-core
+    # via langfuse
+    # via langsmith
+    # via open-webui
+    # via openai
+pydantic-core==2.18.2
+    # via pydantic
+pygments==2.18.0
+    # via rich
+pyjwt==2.8.0
+    # via litellm
+    # via open-webui
+pymysql==1.1.0
+    # via open-webui
+pypandoc==1.13
+    # via open-webui
+pyparsing==3.1.2
+    # via httplib2
+pypdf==4.2.0
+    # via open-webui
+    # via unstructured-client
+pypika==0.48.9
+    # via chromadb
+pyproject-hooks==1.1.0
+    # via build
+python-dateutil==2.9.0.post0
+    # via botocore
+    # via kubernetes
+    # via pandas
+    # via posthog
+    # via unstructured-client
+python-dotenv==1.0.1
+    # via litellm
+    # via uvicorn
+python-engineio==4.9.0
+    # via python-socketio
+python-iso639==2024.4.27
+    # via unstructured
+python-jose==3.3.0
+    # via open-webui
+python-magic==0.4.27
+    # via unstructured
+python-multipart==0.0.9
+    # via fastapi
+    # via litellm
+    # via open-webui
+python-socketio==5.11.2
+    # via open-webui
+pytube==15.0.0
+    # via open-webui
+pytz==2024.1
+    # via apscheduler
+    # via pandas
+pyxlsb==1.0.10
+    # via open-webui
+pyyaml==6.0.1
+    # via chromadb
+    # via ctranslate2
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via litellm
+    # via rapidocr-onnxruntime
+    # via transformers
+    # via uvicorn
+rank-bm25==0.2.2
+    # via open-webui
+rapidfuzz==3.9.0
+    # via unstructured
+rapidocr-onnxruntime==1.3.22
+    # via open-webui
+redis==5.0.4
+    # via rq
+regex==2024.5.10
+    # via nltk
+    # via tiktoken
+    # via transformers
+requests==2.32.2
+    # via chromadb
+    # via google-api-core
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via litellm
+    # via open-webui
+    # via posthog
+    # via requests-oauthlib
+    # via tiktoken
+    # via transformers
+    # via unstructured
+    # via unstructured-client
+    # via youtube-transcript-api
+requests-oauthlib==2.0.0
+    # via kubernetes
+rich==13.7.1
+    # via typer
+rq==1.16.2
+    # via litellm
+rsa==4.9
+    # via google-auth
+    # via python-jose
+s3transfer==0.10.1
+    # via boto3
+safetensors==0.4.3
+    # via transformers
+scikit-learn==1.4.2
+    # via sentence-transformers
+scipy==1.13.0
+    # via scikit-learn
+    # via sentence-transformers
+sentence-transformers==2.7.0
+    # via open-webui
+setuptools==69.5.1
+    # via ctranslate2
+    # via opentelemetry-instrumentation
+shapely==2.0.4
+    # via rapidocr-onnxruntime
+shellingham==1.5.4
+    # via typer
+simple-websocket==1.0.0
+    # via python-engineio
+six==1.16.0
+    # via apscheduler
+    # via ecdsa
+    # via kubernetes
+    # via langdetect
+    # via posthog
+    # via python-dateutil
+    # via rapidocr-onnxruntime
+    # via unstructured-client
+sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
+soupsieve==2.5
+    # via beautifulsoup4
+sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
+starlette==0.37.2
+    # via fastapi
+sympy==1.12
+    # via onnxruntime
+    # via torch
+tabulate==0.9.0
+    # via unstructured
+tenacity==8.3.0
+    # via chromadb
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.6.0
+    # via litellm
+tokenizers==0.15.2
+    # via chromadb
+    # via faster-whisper
+    # via litellm
+    # via transformers
+torch==2.3.0
+    # via sentence-transformers
+tqdm==4.66.4
+    # via chromadb
+    # via google-generativeai
+    # via huggingface-hub
+    # via nltk
+    # via openai
+    # via sentence-transformers
+    # via transformers
+transformers==4.39.3
+    # via sentence-transformers
+typer==0.12.3
+    # via chromadb
+    # via fastapi-cli
+typing-extensions==4.11.0
+    # via chromadb
+    # via fastapi
+    # via google-generativeai
+    # via huggingface-hub
+    # via openai
+    # via opentelemetry-sdk
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via unstructured
+    # via unstructured-client
+typing-inspect==0.9.0
+    # via dataclasses-json
+    # via unstructured-client
+tzdata==2024.1
+    # via pandas
+tzlocal==5.2
+    # via apscheduler
+ujson==5.10.0
+    # via fastapi
+unstructured==0.14.0
+    # via open-webui
+unstructured-client==0.22.0
+    # via unstructured
+uritemplate==4.1.1
+    # via google-api-python-client
+urllib3==2.2.1
+    # via botocore
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+uvicorn==0.22.0
+    # via chromadb
+    # via fastapi
+    # via litellm
+    # via open-webui
+uvloop==0.19.0
+    # via uvicorn
+validators==0.28.1
+    # via open-webui
+watchfiles==0.21.0
+    # via uvicorn
+websocket-client==1.8.0
+    # via kubernetes
+websockets==12.0
+    # via uvicorn
+werkzeug==3.0.3
+    # via flask
+wrapt==1.16.0
+    # via deprecated
+    # via langfuse
+    # via opentelemetry-instrumentation
+    # via unstructured
+wsproto==1.2.0
+    # via simple-websocket
+xlrd==2.0.1
+    # via open-webui
+yarl==1.9.4
+    # via aiohttp
+youtube-transcript-api==0.6.2
+    # via open-webui
+zipp==3.18.1
+    # via importlib-metadata

src/lib/apis/chats/index.ts

@@ -654,3 +654,35 @@ export const deleteAllChats = async (token: string) => {
 
 	return res;
 };
+
+export const archiveAllChats = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/archive/all`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err.detail;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/apis/configs/index.ts

@@ -1,4 +1,5 @@
 import { WEBUI_API_BASE_URL } from '$lib/constants';
+import type { Banner } from '$lib/types';
 
 export const setDefaultModels = async (token: string, models: string) => {
 	let error = null;
@@ -59,3 +60,60 @@ export const setDefaultPromptSuggestions = async (token: string, promptSuggestio
 
 	return res;
 };
+
+export const getBanners = async (token: string): Promise<Banner[]> => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/banners`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const setBanners = async (token: string, banners: Banner[]) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/banners`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			banners: banners
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/apis/index.ts

@@ -1,4 +1,53 @@
-import { WEBUI_BASE_URL } from '$lib/constants';
+import { WEBUI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
+
+export const getModels = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/models`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	let models = res?.data ?? [];
+
+	models = models
+		.filter((models) => models)
+		.sort((a, b) => {
+			// Compare case-insensitively
+			const lowerA = a.name.toLowerCase();
+			const lowerB = b.name.toLowerCase();
+
+			if (lowerA < lowerB) return -1;
+			if (lowerA > lowerB) return 1;
+
+			// If same case-insensitively, sort by original strings,
+			// lowercase will come before uppercase due to ASCII values
+			if (a < b) return -1;
+			if (a > b) return 1;
+
+			return 0; // They are equal
+		});
+
+	console.log(models);
+	return models;
+};
 
 export const getBackendConfig = async () => {
 	let error = null;
@@ -196,3 +245,131 @@ export const updateWebhookUrl = async (token: string, url: string) => {
 
 	return res.url;
 };
+
+export const getCommunitySharingEnabledStatus = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/community_sharing`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const toggleCommunitySharingEnabledStatus = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/community_sharing/toggle`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getModelConfig = async (token: string): Promise<GlobalModelConfig> => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/models`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.models;
+};
+
+export interface ModelConfig {
+	id: string;
+	name: string;
+	meta: ModelMeta;
+	base_model_id?: string;
+	params: ModelParams;
+}
+
+export interface ModelMeta {
+	description?: string;
+	capabilities?: object;
+}
+
+export interface ModelParams {}
+
+export type GlobalModelConfig = ModelConfig[];
+
+export const updateModelConfig = async (token: string, config: GlobalModelConfig) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/models`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			models: config
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/apis/litellm/index.ts

@@ -1,150 +0,0 @@
-import { LITELLM_API_BASE_URL } from '$lib/constants';
-
-export const getLiteLLMModels = async (token: string = '') => {
-	let error = null;
-
-	const res = await fetch(`${LITELLM_API_BASE_URL}/v1/models`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
-			return [];
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	const models = Array.isArray(res) ? res : res?.data ?? null;
-
-	return models
-		? models
-				.map((model) => ({
-					id: model.id,
-					name: model.name ?? model.id,
-					external: true,
-					source: 'LiteLLM'
-				}))
-				.sort((a, b) => {
-					return a.name.localeCompare(b.name);
-				})
-		: models;
-};
-
-export const getLiteLLMModelInfo = async (token: string = '') => {
-	let error = null;
-
-	const res = await fetch(`${LITELLM_API_BASE_URL}/model/info`, {
-		method: 'GET',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		}
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
-			return [];
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	const models = Array.isArray(res) ? res : res?.data ?? null;
-
-	return models;
-};
-
-type AddLiteLLMModelForm = {
-	name: string;
-	model: string;
-	api_base: string;
-	api_key: string;
-	rpm: string;
-	max_tokens: string;
-};
-
-export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMModelForm) => {
-	let error = null;
-
-	const res = await fetch(`${LITELLM_API_BASE_URL}/model/new`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		},
-		body: JSON.stringify({
-			model_name: payload.name,
-			litellm_params: {
-				model: payload.model,
-				...(payload.api_base === '' ? {} : { api_base: payload.api_base }),
-				...(payload.api_key === '' ? {} : { api_key: payload.api_key }),
-				...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) }),
-				...(payload.max_tokens === '' ? {} : { max_tokens: payload.max_tokens })
-			}
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
-			return [];
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const deleteLiteLLMModel = async (token: string = '', id: string) => {
-	let error = null;
-
-	const res = await fetch(`${LITELLM_API_BASE_URL}/model/delete`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			...(token && { authorization: `Bearer ${token}` })
-		},
-		body: JSON.stringify({
-			id: id
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
-			return [];
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};

src/lib/apis/models/index.ts

@@ -1,18 +1,16 @@
 import { WEBUI_API_BASE_URL } from '$lib/constants';
 
-export const createNewModelfile = async (token: string, modelfile: object) => {
+export const addNewModel = async (token: string, model: object) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/modelfiles/create`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/add`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
 			authorization: `Bearer ${token}`
 		},
-		body: JSON.stringify({
+		body: JSON.stringify(model)
-			modelfile: modelfile
-		})
 	})
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();
@@ -31,10 +29,10 @@ export const createNewModelfile = async (token: string, modelfile: object) => {
 	return res;
 };
 
-export const getModelfiles = async (token: string = '') => {
+export const getModelInfos = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/modelfiles/`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -59,62 +57,22 @@ export const getModelfiles = async (token: string = '') => {
 		throw error;
 	}
 
-	return res.map((modelfile) => modelfile.modelfile);
+	return res;
 };
 
-export const getModelfileByTagName = async (token: string, tagName: string) => {
+export const getModelById = async (token: string, id: string) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/modelfiles/`, {
+	const searchParams = new URLSearchParams();
-		method: 'POST',
+	searchParams.append('id', id);
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models?${searchParams.toString()}`, {
+		method: 'GET',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
 			authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			tag_name: tagName
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.then((json) => {
-			return json;
-		})
-		.catch((err) => {
-			error = err;
-
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
 		}
-
-	return res.modelfile;
-};
-
-export const updateModelfileByTagName = async (
-	token: string,
-	tagName: string,
-	modelfile: object
-) => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/modelfiles/update`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			tag_name: tagName,
-			modelfile: modelfile
-		})
 	})
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();
@@ -137,19 +95,55 @@ export const updateModelfileByTagName = async (
 	return res;
 };
 
-export const deleteModelfileByTagName = async (token: string, tagName: string) => {
+export const updateModelById = async (token: string, id: string, model: object) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/modelfiles/delete`, {
+	const searchParams = new URLSearchParams();
+	searchParams.append('id', id);
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/update?${searchParams.toString()}`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify(model)
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const deleteModelById = async (token: string, id: string) => {
+	let error = null;
+
+	const searchParams = new URLSearchParams();
+	searchParams.append('id', id);
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/delete?${searchParams.toString()}`, {
 		method: 'DELETE',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
 			authorization: `Bearer ${token}`
-		},
+		}
-		body: JSON.stringify({
-			tag_name: tagName
-		})
 	})
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();

src/lib/apis/ollama/index.ts

@@ -1,6 +1,73 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
 import { promptTemplate } from '$lib/utils';
 
+export const getOllamaConfig = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/config`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateOllamaConfig = async (token: string = '', enable_ollama_api: boolean) => {
+	let error = null;
+
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/config/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			enable_ollama_api: enable_ollama_api
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getOllamaUrls = async (token: string = '') => {
 	let error = null;
 
@@ -97,7 +164,7 @@ export const getOllamaVersion = async (token: string = '') => {
 		throw error;
 	}
 
-	return res?.version ?? '';
+	return res?.version ?? false;
 };
 
 export const getOllamaModels = async (token: string = '') => {

src/lib/apis/openai/index.ts

@@ -230,7 +230,12 @@ export const getOpenAIModels = async (token: string = '') => {
 
 	return models
 		? models
-				.map((model) => ({ id: model.id, name: model.name ?? model.id, external: true }))
+				.map((model) => ({
+					id: model.id,
+					name: model.name ?? model.id,
+					external: true,
+					custom_info: model.custom_info
+				}))
 				.sort((a, b) => {
 					return a.name.localeCompare(b.name);
 				})

src/lib/apis/users/index.ts

@@ -115,6 +115,62 @@ export const getUsers = async (token: string) => {
 	return res ? res : [];
 };
 
+export const getUserSettings = async (token: string) => {
+	let error = null;
+	const res = await fetch(`${WEBUI_API_BASE_URL}/users/user/settings`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateUserSettings = async (token: string, settings: object) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/users/user/settings/update`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...settings
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getUserById = async (token: string, userId: string) => {
 	let error = null;
 

src/lib/components/admin/Settings/Banners.svelte

@@ -0,0 +1,137 @@
+<script lang="ts">
+	import { v4 as uuidv4 } from 'uuid';
+
+	import { getContext, onMount } from 'svelte';
+	import { banners as _banners } from '$lib/stores';
+	import type { Banner } from '$lib/types';
+
+	import { getBanners, setBanners } from '$lib/apis/configs';
+
+	import type { Writable } from 'svelte/store';
+	import type { i18n as i18nType } from 'i18next';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import Switch from '$lib/components/common/Switch.svelte';
+	const i18n: Writable<i18nType> = getContext('i18n');
+
+	export let saveHandler: Function;
+
+	let banners: Banner[] = [];
+
+	onMount(async () => {
+		banners = await getBanners(localStorage.token);
+	});
+
+	const updateBanners = async () => {
+		_banners.set(await setBanners(localStorage.token, banners));
+	};
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={async () => {
+		updateBanners();
+		saveHandler();
+	}}
+>
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80 h-full">
+		<div class=" space-y-3 pr-1.5">
+			<div class="flex w-full justify-between mb-2">
+				<div class=" self-center text-sm font-semibold">
+					{$i18n.t('Banners')}
+				</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						if (banners.length === 0 || banners.at(-1).content !== '') {
+							banners = [
+								...banners,
+								{
+									id: uuidv4(),
+									type: '',
+									title: '',
+									content: '',
+									dismissible: true,
+									timestamp: Math.floor(Date.now() / 1000)
+								}
+							];
+						}
+					}}
+				>
+					<svg
+						xmlns="http://www.w3.org/2000/svg"
+						viewBox="0 0 20 20"
+						fill="currentColor"
+						class="w-4 h-4"
+					>
+						<path
+							d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
+						/>
+					</svg>
+				</button>
+			</div>
+			<div class="flex flex-col space-y-1">
+				{#each banners as banner, bannerIdx}
+					<div class=" flex justify-between">
+						<div class="flex flex-row flex-1 border rounded-xl dark:border-gray-800">
+							<select
+								class="w-fit capitalize rounded-xl py-2 px-4 text-xs bg-transparent outline-none"
+								bind:value={banner.type}
+							>
+								{#if banner.type == ''}
+									<option value="" selected disabled class="text-gray-900">{$i18n.t('Type')}</option
+									>
+								{/if}
+								<option value="info" class="text-gray-900">{$i18n.t('Info')}</option>
+								<option value="warning" class="text-gray-900">{$i18n.t('Warning')}</option>
+								<option value="error" class="text-gray-900">{$i18n.t('Error')}</option>
+								<option value="success" class="text-gray-900">{$i18n.t('Success')}</option>
+							</select>
+
+							<input
+								class="pr-5 py-1.5 text-xs w-full bg-transparent outline-none"
+								placeholder={$i18n.t('Content')}
+								bind:value={banner.content}
+							/>
+
+							<div class="relative top-1.5 -left-2">
+								<Tooltip content="Dismissible" className="flex h-fit items-center">
+									<Switch bind:state={banner.dismissible} />
+								</Tooltip>
+							</div>
+						</div>
+
+						<button
+							class="px-2"
+							type="button"
+							on:click={() => {
+								banners.splice(bannerIdx, 1);
+								banners = banners;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				{/each}
+			</div>
+		</div>
+	</div>
+	<div class="flex justify-end pt-3 text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
+			type="submit"
+		>
+			Save
+		</button>
+	</div>
+</form>

src/lib/components/admin/Settings/Database.svelte

@@ -1,13 +1,24 @@
 <script lang="ts">
+	import fileSaver from 'file-saver';
+	const { saveAs } = fileSaver;
+
 	import { downloadDatabase } from '$lib/apis/utils';
 	import { onMount, getContext } from 'svelte';
-	import { config } from '$lib/stores';
+	import { config, user } from '$lib/stores';
 	import { toast } from 'svelte-sonner';
+	import { getAllUserChats } from '$lib/apis/chats';
 
 	const i18n = getContext('i18n');
 
 	export let saveHandler: Function;
 
+	const exportAllUserChats = async () => {
+		let blob = new Blob([JSON.stringify(await getAllUserChats(localStorage.token))], {
+			type: 'application/json'
+		});
+		saveAs(blob, `all-chats-export-${Date.now()}.json`);
+	};
+
 	onMount(async () => {
 		// permissions = await getUserPermissions(localStorage.token);
 	});
@@ -23,10 +34,10 @@
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('Database')}</div>
 
+			{#if $config?.features.enable_admin_export ?? true}
 				<div class="  flex w-full justify-between">
 					<!-- <div class=" self-center text-xs font-medium">{$i18n.t('Allow Chat Deletion')}</div> -->
 
-				{#if $config?.admin_export_enabled ?? true}
 					<button
 						class=" flex rounded-md py-1.5 px-3 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
 						type="button"
@@ -55,8 +66,36 @@
 						</div>
 						<div class=" self-center text-sm font-medium">{$i18n.t('Download Database')}</div>
 					</button>
-				{/if}
 				</div>
+
+				<hr class=" dark:border-gray-700 my-1" />
+
+				<button
+					class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					on:click={() => {
+						exportAllUserChats();
+					}}
+				>
+					<div class=" self-center mr-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
+							<path
+								fill-rule="evenodd"
+								d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM8.75 7.75a.75.75 0 0 0-1.5 0v2.69L6.03 9.22a.75.75 0 0 0-1.06 1.06l2.5 2.5a.75.75 0 0 0 1.06 0l2.5-2.5a.75.75 0 1 0-1.06-1.06l-1.22 1.22V7.75Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center text-sm font-medium">
+						{$i18n.t('Export All Chats (All Users)')}
+					</div>
+				</button>
+			{/if}
 		</div>
 	</div>
 

src/lib/components/admin/Settings/General.svelte

@@ -1,5 +1,10 @@
 <script lang="ts">
-	import { getWebhookUrl, updateWebhookUrl } from '$lib/apis';
+	import {
+		getCommunitySharingEnabledStatus,
+		getWebhookUrl,
+		toggleCommunitySharingEnabledStatus,
+		updateWebhookUrl
+	} from '$lib/apis';
 	import {
 		getDefaultUserRole,
 		getJWTExpiresDuration,
@@ -18,6 +23,7 @@
 	let JWTExpiresIn = '';
 
 	let webhookUrl = '';
+	let communitySharingEnabled = true;
 
 	const toggleSignUpEnabled = async () => {
 		signUpEnabled = await toggleSignUpEnabledStatus(localStorage.token);
@@ -35,11 +41,28 @@
 		webhookUrl = await updateWebhookUrl(localStorage.token, webhookUrl);
 	};
 
+	const toggleCommunitySharingEnabled = async () => {
+		communitySharingEnabled = await toggleCommunitySharingEnabledStatus(localStorage.token);
+	};
+
 	onMount(async () => {
+		await Promise.all([
+			(async () => {
 				signUpEnabled = await getSignUpEnabledStatus(localStorage.token);
+			})(),
+			(async () => {
 				defaultUserRole = await getDefaultUserRole(localStorage.token);
+			})(),
+			(async () => {
 				JWTExpiresIn = await getJWTExpiresDuration(localStorage.token);
+			})(),
+			(async () => {
 				webhookUrl = await getWebhookUrl(localStorage.token);
+			})(),
+			(async () => {
+				communitySharingEnabled = await getCommunitySharingEnabledStatus(localStorage.token);
+			})()
+		]);
 	});
 </script>
 
@@ -114,6 +137,47 @@
 				</div>
 			</div>
 
+			<div class="  flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('Enable Community Sharing')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					on:click={() => {
+						toggleCommunitySharingEnabled();
+					}}
+					type="button"
+				>
+					{#if communitySharingEnabled}
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path
+								d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
+							/>
+						</svg>
+						<span class="ml-2 self-center">{$i18n.t('Enabled')}</span>
+					{:else}
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M8 1a3.5 3.5 0 0 0-3.5 3.5V7A1.5 1.5 0 0 0 3 8.5v5A1.5 1.5 0 0 0 4.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 11.5 7V4.5A3.5 3.5 0 0 0 8 1Zm2 6V4.5a2 2 0 1 0-4 0V7h4Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+
+						<span class="ml-2 self-center">{$i18n.t('Disabled')}</span>
+					{/if}
+				</button>
+			</div>
+
 			<hr class=" dark:border-gray-700 my-3" />
 
 			<div class=" w-full justify-between">

src/lib/components/admin/Settings/Users.svelte

@@ -1,15 +1,19 @@
 <script lang="ts">
-	import { getModelFilterConfig, updateModelFilterConfig } from '$lib/apis';
+	import { getBackendConfig, getModelFilterConfig, updateModelFilterConfig } from '$lib/apis';
 	import { getSignUpEnabledStatus, toggleSignUpEnabledStatus } from '$lib/apis/auths';
 	import { getUserPermissions, updateUserPermissions } from '$lib/apis/users';
 
 	import { onMount, getContext } from 'svelte';
-	import { models } from '$lib/stores';
+	import { models, config } from '$lib/stores';
+	import Switch from '$lib/components/common/Switch.svelte';
+	import { setDefaultModels } from '$lib/apis/configs';
 
 	const i18n = getContext('i18n');
 
 	export let saveHandler: Function;
 
+	let defaultModelId = '';
+
 	let whitelistEnabled = false;
 	let whitelistModels = [''];
 	let permissions = {
@@ -24,9 +28,10 @@
 		const res = await getModelFilterConfig(localStorage.token);
 		if (res) {
 			whitelistEnabled = res.enabled;
-
 			whitelistModels = res.models.length > 0 ? res.models : [''];
 		}
+
+		defaultModelId = $config.default_models ? $config?.default_models.split(',')[0] : '';
 	});
 </script>
 
@@ -34,10 +39,13 @@
 	class="flex flex-col h-full justify-between space-y-3 text-sm"
 	on:submit|preventDefault={async () => {
 		// console.log('submit');
-		await updateUserPermissions(localStorage.token, permissions);
 
+		await setDefaultModels(localStorage.token, defaultModelId);
+		await updateUserPermissions(localStorage.token, permissions);
 		await updateModelFilterConfig(localStorage.token, whitelistEnabled, whitelistModels);
 		saveHandler();
+
+		await config.set(await getBackendConfig());
 	}}
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
@@ -88,26 +96,40 @@
 
 		<hr class=" dark:border-gray-700 my-2" />
 
-		<div class="mt-2 space-y-3 pr-1.5">
+		<div class="mt-2 space-y-3">
 			<div>
 				<div class="mb-2">
 					<div class="flex justify-between items-center text-xs">
 						<div class=" text-sm font-medium">{$i18n.t('Manage Models')}</div>
 					</div>
 				</div>
+				<div class=" space-y-1 mb-3">
+					<div class="mb-2">
+						<div class="flex justify-between items-center text-xs">
+							<div class=" text-xs font-medium">{$i18n.t('Default Model')}</div>
+						</div>
+					</div>
 
-				<div class=" space-y-3">
+					<div class="flex-1 mr-2">
-					<div>
+						<select
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							bind:value={defaultModelId}
+							placeholder="Select a model"
+						>
+							<option value="" disabled selected>{$i18n.t('Select a model')}</option>
+							{#each $models.filter((model) => model.id) as model}
+								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">{model.name}</option>
+							{/each}
+						</select>
+					</div>
+				</div>
+
+				<div class=" space-y-1">
+					<div class="mb-2">
 						<div class="flex justify-between items-center text-xs">
 							<div class=" text-xs font-medium">{$i18n.t('Model Whitelisting')}</div>
 
-							<button
+							<Switch bind:state={whitelistEnabled} />
-								class=" text-xs font-medium text-gray-500"
-								type="button"
-								on:click={() => {
-									whitelistEnabled = !whitelistEnabled;
-								}}>{whitelistEnabled ? $i18n.t('On') : $i18n.t('Off')}</button
-							>
 						</div>
 					</div>
 

src/lib/components/admin/SettingsModal.svelte

@@ -6,6 +6,9 @@
 	import General from './Settings/General.svelte';
 	import Users from './Settings/Users.svelte';
 
+	import Banners from '$lib/components/admin/Settings/Banners.svelte';
+	import { toast } from 'svelte-sonner';
+
 	const i18n = getContext('i18n');
 
 	export let show = false;
@@ -117,24 +120,63 @@
 					</div>
 					<div class=" self-center">{$i18n.t('Database')}</div>
 				</button>
+
+				<button
+					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+					'banners'
+						? 'bg-gray-200 dark:bg-gray-700'
+						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+					on:click={() => {
+						selectedTab = 'banners';
+					}}
+				>
+					<div class=" self-center mr-2">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								d="M5.85 3.5a.75.75 0 0 0-1.117-1 9.719 9.719 0 0 0-2.348 4.876.75.75 0 0 0 1.479.248A8.219 8.219 0 0 1 5.85 3.5ZM19.267 2.5a.75.75 0 1 0-1.118 1 8.22 8.22 0 0 1 1.987 4.124.75.75 0 0 0 1.48-.248A9.72 9.72 0 0 0 19.266 2.5Z"
+							/>
+							<path
+								fill-rule="evenodd"
+								d="M12 2.25A6.75 6.75 0 0 0 5.25 9v.75a8.217 8.217 0 0 1-2.119 5.52.75.75 0 0 0 .298 1.206c1.544.57 3.16.99 4.831 1.243a3.75 3.75 0 1 0 7.48 0 24.583 24.583 0 0 0 4.83-1.244.75.75 0 0 0 .298-1.205 8.217 8.217 0 0 1-2.118-5.52V9A6.75 6.75 0 0 0 12 2.25ZM9.75 18c0-.034 0-.067.002-.1a25.05 25.05 0 0 0 4.496 0l.002.1a2.25 2.25 0 1 1-4.5 0Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center">{$i18n.t('Banners')}</div>
+				</button>
 			</div>
 			<div class="flex-1 md:min-h-[380px]">
 				{#if selectedTab === 'general'}
 					<General
 						saveHandler={() => {
 							show = false;
+							toast.success($i18n.t('Settings saved successfully!'));
 						}}
 					/>
 				{:else if selectedTab === 'users'}
 					<Users
 						saveHandler={() => {
 							show = false;
+							toast.success($i18n.t('Settings saved successfully!'));
 						}}
 					/>
 				{:else if selectedTab === 'db'}
 					<Database
 						saveHandler={() => {
 							show = false;
+							toast.success($i18n.t('Settings saved successfully!'));
+						}}
+					/>
+				{:else if selectedTab === 'banners'}
+					<Banners
+						saveHandler={() => {
+							show = false;
+							toast.success($i18n.t('Settings saved successfully!'));
 						}}
 					/>
 				{/if}

src/lib/components/chat/MessageInput.svelte

@@ -1,7 +1,7 @@
 <script lang="ts">
 	import { toast } from 'svelte-sonner';
 	import { onMount, tick, getContext } from 'svelte';
-	import { mobile, modelfiles, settings, showSidebar } from '$lib/stores';
+	import { type Model, mobile, settings, showSidebar, models } from '$lib/stores';
 	import { blobToFile, calculateSHA256, findWordIndices } from '$lib/utils';
 
 	import {
@@ -27,7 +27,9 @@
 	export let stopResponse: Function;
 
 	export let autoScroll = true;
-	export let selectedModel = '';
+
+	export let atSelectedModel: Model | undefined;
+	export let selectedModels: [''];
 
 	let chatTextAreaElement: HTMLTextAreaElement;
 	let filesInputElement;
@@ -52,6 +54,11 @@
 
 	let speechRecognition;
 
+	let visionCapableModels = [];
+	$: visionCapableModels = [...(atSelectedModel ? [atSelectedModel] : selectedModels)].filter(
+		(model) => $models.find((m) => m.id === model)?.info?.meta?.capabilities?.vision ?? true
+	);
+
 	$: if (prompt) {
 		if (chatTextAreaElement) {
 			chatTextAreaElement.style.height = '';
@@ -358,6 +365,10 @@
 					inputFiles.forEach((file) => {
 						console.log(file, file.name.split('.').at(-1));
 						if (['image/gif', 'image/webp', 'image/jpeg', 'image/png'].includes(file['type'])) {
+							if (visionCapableModels.length === 0) {
+								toast.error($i18n.t('Selected model(s) do not support image inputs'));
+								return;
+							}
 							let reader = new FileReader();
 							reader.onload = (event) => {
 								files = [
@@ -429,8 +440,8 @@
 
 <div class="fixed bottom-0 {$showSidebar ? 'left-0 md:left-[260px]' : 'left-0'} right-0">
 	<div class="w-full">
-		<div class="px-2.5 md:px-16 -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
+		<div class=" -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
-			<div class="flex flex-col max-w-5xl w-full">
+			<div class="flex flex-col max-w-6xl px-2.5 md:px-6 w-full">
 				<div class="relative">
 					{#if autoScroll === false && messages.length > 0}
 						<div class=" absolute -top-12 left-0 right-0 flex justify-center z-30">
@@ -494,12 +505,12 @@
 						bind:chatInputPlaceholder
 						{messages}
 						on:select={(e) => {
-							selectedModel = e.detail;
+							atSelectedModel = e.detail;
 							chatTextAreaElement?.focus();
 						}}
 					/>
 
-					{#if selectedModel !== ''}
+					{#if atSelectedModel !== undefined}
 						<div
 							class="px-3 py-2.5 text-left w-full flex justify-between items-center absolute bottom-0 left-0 right-0 bg-gradient-to-t from-50% from-white dark:from-gray-900"
 						>
@@ -508,21 +519,21 @@
 									crossorigin="anonymous"
 									alt="model profile"
 									class="size-5 max-w-[28px] object-cover rounded-full"
-									src={$modelfiles.find((modelfile) => modelfile.tagName === selectedModel.id)
+									src={$models.find((model) => model.id === atSelectedModel.id)?.info?.meta
-										?.imageUrl ??
+										?.profile_image_url ??
 										($i18n.language === 'dg-DG'
 											? `/doge.png`
 											: `${WEBUI_BASE_URL}/static/favicon.png`)}
 								/>
 								<div>
-									Talking to <span class=" font-medium">{selectedModel.name} </span>
+									Talking to <span class=" font-medium">{atSelectedModel.name}</span>
 								</div>
 							</div>
 							<div>
 								<button
 									class="flex items-center"
 									on:click={() => {
-										selectedModel = '';
+										atSelectedModel = undefined;
 									}}
 								>
 									<XMark />
@@ -535,7 +546,7 @@
 		</div>
 
 		<div class="bg-white dark:bg-gray-900">
-			<div class="max-w-6xl px-2.5 md:px-16 mx-auto inset-x-0">
+			<div class="max-w-6xl px-2.5 md:px-6 mx-auto inset-x-0">
 				<div class=" pb-2">
 					<input
 						bind:this={filesInputElement}
@@ -550,6 +561,12 @@
 									if (
 										['image/gif', 'image/webp', 'image/jpeg', 'image/png'].includes(file['type'])
 									) {
+										if (visionCapableModels.length === 0) {
+											toast.error($i18n.t('Selected model(s) do not support image inputs'));
+											inputFiles = null;
+											filesInputElement.value = '';
+											return;
+										}
 										let reader = new FileReader();
 										reader.onload = (event) => {
 											files = [
@@ -589,6 +606,7 @@
 						dir={$settings?.chatDirection ?? 'LTR'}
 						class=" flex flex-col relative w-full rounded-3xl px-1.5 bg-gray-50 dark:bg-gray-850 dark:text-gray-100"
 						on:submit|preventDefault={() => {
+							// check if selectedModels support image input
 							submitPrompt(prompt, user);
 						}}
 					>
@@ -597,7 +615,36 @@
 								{#each files as file, fileIdx}
 									<div class=" relative group">
 										{#if file.type === 'image'}
-											<img src={file.url} alt="input" class=" h-16 w-16 rounded-xl object-cover" />
+											<div class="relative">
+												<img
+													src={file.url}
+													alt="input"
+													class=" h-16 w-16 rounded-xl object-cover"
+												/>
+												{#if atSelectedModel ? visionCapableModels.length === 0 : selectedModels.length !== visionCapableModels.length}
+													<Tooltip
+														className=" absolute top-1 left-1"
+														content={$i18n.t('{{ models }}', {
+															models: [...(atSelectedModel ? [atSelectedModel] : selectedModels)]
+																.filter((id) => !visionCapableModels.includes(id))
+																.join(', ')
+														})}
+													>
+														<svg
+															xmlns="http://www.w3.org/2000/svg"
+															viewBox="0 0 24 24"
+															fill="currentColor"
+															class="size-4 fill-yellow-300"
+														>
+															<path
+																fill-rule="evenodd"
+																d="M9.401 3.003c1.155-2 4.043-2 5.197 0l7.355 12.748c1.154 2-.29 4.5-2.599 4.5H4.645c-2.309 0-3.752-2.5-2.598-4.5L9.4 3.003ZM12 8.25a.75.75 0 0 1 .75.75v3.75a.75.75 0 0 1-1.5 0V9a.75.75 0 0 1 .75-.75Zm0 8.25a.75.75 0 1 0 0-1.5.75.75 0 0 0 0 1.5Z"
+																clip-rule="evenodd"
+															/>
+														</svg>
+													</Tooltip>
+												{/if}
+											</div>
 										{:else if file.type === 'doc'}
 											<div
 												class="h-16 w-[15rem] flex items-center space-x-3 px-2.5 dark:bg-gray-600 rounded-xl border border-gray-200 dark:border-none"
@@ -883,7 +930,7 @@
 
 									if (e.key === 'Escape') {
 										console.log('Escape');
-										selectedModel = '';
+										atSelectedModel = undefined;
 									}
 								}}
 								rows="1"

src/lib/components/chat/Messages.svelte

@@ -1,7 +1,7 @@
 <script lang="ts">
 	import { v4 as uuidv4 } from 'uuid';
 
-	import { chats, config, modelfiles, settings, user as _user, mobile } from '$lib/stores';
+	import { chats, config, settings, user as _user, mobile } from '$lib/stores';
 	import { tick, getContext } from 'svelte';
 
 	import { toast } from 'svelte-sonner';
@@ -26,7 +26,6 @@
 
 	export let user = $_user;
 	export let prompt;
-	export let suggestionPrompts = [];
 	export let processing = '';
 	export let bottomPadding = false;
 	export let autoScroll;
@@ -34,7 +33,6 @@
 	export let messages = [];
 
 	export let selectedModels;
-	export let selectedModelfiles = [];
 
 	$: if (autoScroll && bottomPadding) {
 		(async () => {
@@ -247,9 +245,7 @@
 <div class="h-full flex mb-16">
 	{#if messages.length == 0}
 		<Placeholder
-			models={selectedModels}
+			modelIds={selectedModels}
-			modelfiles={selectedModelfiles}
-			{suggestionPrompts}
 			submitPrompt={async (p) => {
 				let text = p;
 
@@ -316,7 +312,6 @@
 								{#key message.id}
 									<ResponseMessage
 										{message}
-										modelfiles={selectedModelfiles}
 										siblings={history.messages[message.parentId]?.childrenIds ?? []}
 										isLastMessage={messageIdx + 1 === messages.length}
 										{readOnly}
@@ -348,7 +343,6 @@
 										{chatId}
 										parentMessage={history.messages[message.parentId]}
 										{messageIdx}
-										{selectedModelfiles}
 										{updateChatMessages}
 										{confirmEditResponseMessage}
 										{rateMessage}

src/lib/components/chat/Messages/CodeBlock.svelte

@@ -4,7 +4,7 @@
 	import hljs from 'highlight.js';
 	import 'highlight.js/styles/github-dark.min.css';
 	import { loadPyodide } from 'pyodide';
-	import { tick } from 'svelte';
+	import { onMount, tick } from 'svelte';
 	import PyodideWorker from '$lib/workers/pyodide.worker?worker';
 
 	export let id = '';
@@ -12,6 +12,7 @@
 	export let lang = '';
 	export let code = '';
 
+	let highlightedCode = null;
 	let executing = false;
 
 	let stdout = null;
@@ -202,10 +203,11 @@ __builtins__.input = input`);
 		};
 	};
 
-	$: highlightedCode = code ? hljs.highlightAuto(code, hljs.getLanguage(lang)?.aliases).value : '';
+	$: if (code) {
+		highlightedCode = hljs.highlightAuto(code, hljs.getLanguage(lang)?.aliases).value || code;
+	}
 </script>
 
-{#if code}
 <div class="mb-4" dir="ltr">
 	<div
 		class="flex justify-between bg-[#202123] text-white text-xs px-4 pt-1 pb-0.5 rounded-t-lg overflow-x-auto"
@@ -258,4 +260,3 @@ __builtins__.input = input`);
 		</div>
 	{/if}
 </div>
-{/if}

src/lib/components/chat/Messages/CompareMessages.svelte

@@ -13,8 +13,6 @@
 
 	export let parentMessage;
 
-	export let selectedModelfiles;
-
 	export let updateChatMessages: Function;
 	export let confirmEditResponseMessage: Function;
 	export let rateMessage: Function;
@@ -130,7 +128,6 @@
 				>
 					<ResponseMessage
 						message={groupedMessages[model].messages[groupedMessagesIdx[model]]}
-						modelfiles={selectedModelfiles}
 						siblings={groupedMessages[model].messages.map((m) => m.id)}
 						isLastMessage={true}
 						{updateChatMessages}

src/lib/components/chat/Messages/Placeholder.svelte

@@ -1,6 +1,6 @@
 <script lang="ts">
 	import { WEBUI_BASE_URL } from '$lib/constants';
-	import { user } from '$lib/stores';
+	import { config, user, models as _models } from '$lib/stores';
 	import { onMount, getContext } from 'svelte';
 
 	import { blur, fade } from 'svelte/transition';
@@ -9,23 +9,20 @@
 
 	const i18n = getContext('i18n');
 
+	export let modelIds = [];
 	export let models = [];
-	export let modelfiles = [];
 
 	export let submitPrompt;
-	export let suggestionPrompts;
 
 	let mounted = false;
-	let modelfile = null;
 	let selectedModelIdx = 0;
 
-	$: modelfile =
+	$: if (modelIds.length > 0) {
-		models[selectedModelIdx] in modelfiles ? modelfiles[models[selectedModelIdx]] : null;
-
-	$: if (models.length > 0) {
 		selectedModelIdx = models.length - 1;
 	}
 
+	$: models = modelIds.map((id) => $_models.find((m) => m.id === id));
+
 	onMount(() => {
 		mounted = true;
 	});
@@ -41,25 +38,14 @@
 							selectedModelIdx = modelIdx;
 						}}
 					>
-						{#if model in modelfiles}
 						<img
 							crossorigin="anonymous"
-								src={modelfiles[model]?.imageUrl ?? `${WEBUI_BASE_URL}/static/favicon.png`}
+							src={model?.info?.meta?.profile_image_url ??
-								alt="modelfile"
+								($i18n.language === 'dg-DG' ? `/doge.png` : `${WEBUI_BASE_URL}/static/favicon.png`)}
-								class=" size-[2.7rem] rounded-full border-[1px] border-gray-200 dark:border-none"
-								draggable="false"
-							/>
-						{:else}
-							<img
-								crossorigin="anonymous"
-								src={$i18n.language === 'dg-DG'
-									? `/doge.png`
-									: `${WEBUI_BASE_URL}/static/favicon.png`}
 							class=" size-[2.7rem] rounded-full border-[1px] border-gray-200 dark:border-none"
 							alt="logo"
 							draggable="false"
 						/>
-						{/if}
 					</button>
 				{/each}
 			</div>
@@ -70,23 +56,32 @@
 		>
 			<div>
 				<div class=" capitalize line-clamp-1" in:fade={{ duration: 200 }}>
-					{#if modelfile}
+					{#if models[selectedModelIdx]?.info}
-						{modelfile.title}
+						{models[selectedModelIdx]?.info?.name}
 					{:else}
 						{$i18n.t('Hello, {{name}}', { name: $user.name })}
 					{/if}
 				</div>
 
 				<div in:fade={{ duration: 200, delay: 200 }}>
-					{#if modelfile}
+					{#if models[selectedModelIdx]?.info}
-						<div class="mt-0.5 text-base font-normal text-gray-500 dark:text-gray-400">
+						<div class="mt-0.5 text-base font-normal text-gray-500 dark:text-gray-400 line-clamp-3">
-							{modelfile.desc}
+							{models[selectedModelIdx]?.info?.meta?.description}
 						</div>
-						{#if modelfile.user}
+						{#if models[selectedModelIdx]?.info?.meta?.user}
 							<div class="mt-0.5 text-sm font-normal text-gray-400 dark:text-gray-500">
-								By <a href="https://openwebui.com/m/{modelfile.user.username}"
+								By
-									>{modelfile.user.name ? modelfile.user.name : `@${modelfile.user.username}`}</a
+								{#if models[selectedModelIdx]?.info?.meta?.user.community}
+									<a
+										href="https://openwebui.com/m/{models[selectedModelIdx]?.info?.meta?.user
+											.username}"
+										>{models[selectedModelIdx]?.info?.meta?.user.name
+											? models[selectedModelIdx]?.info?.meta?.user.name
+											: `@${models[selectedModelIdx]?.info?.meta?.user.username}`}</a
 									>
+								{:else}
+									{models[selectedModelIdx]?.info?.meta?.user.name}
+								{/if}
 							</div>
 						{/if}
 					{:else}
@@ -99,7 +94,11 @@
 		</div>
 
 		<div class=" w-full" in:fade={{ duration: 200, delay: 300 }}>
-			<Suggestions {suggestionPrompts} {submitPrompt} />
+			<Suggestions
+				suggestionPrompts={models[selectedModelIdx]?.info?.meta?.suggestion_prompts ??
+					$config.default_prompt_suggestions}
+				{submitPrompt}
+			/>
 		</div>
 	</div>
 {/key}

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -14,7 +14,7 @@
 
 	const dispatch = createEventDispatcher();
 
-	import { config, settings } from '$lib/stores';
+	import { config, models, settings } from '$lib/stores';
 	import { synthesizeOpenAISpeech } from '$lib/apis/audio';
 	import { imageGenerations } from '$lib/apis/images';
 	import {
@@ -34,7 +34,6 @@
 	import RateComment from './RateComment.svelte';
 	import CitationsModal from '$lib/components/chat/Messages/CitationsModal.svelte';
 
-	export let modelfiles = [];
 	export let message;
 	export let siblings;
 
@@ -52,6 +51,9 @@
 	export let continueGeneration: Function;
 	export let regenerateResponse: Function;
 
+	let model = null;
+	$: model = $models.find((m) => m.id === message.model);
+
 	let edit = false;
 	let editedContent = '';
 	let editTextAreaElement: HTMLTextAreaElement;
@@ -78,6 +80,13 @@
 		return `<code>${code.replaceAll('&amp;', '&')}</code>`;
 	};
 
+	// Open all links in a new tab/window (from https://github.com/markedjs/marked/issues/655#issuecomment-383226346)
+	const origLinkRenderer = renderer.link;
+	renderer.link = (href, title, text) => {
+		const html = origLinkRenderer.call(renderer, href, title, text);
+		return html.replace(/^<a /, '<a target="_blank" rel="nofollow" ');
+	};
+
 	const { extensions, ...defaults } = marked.getDefaults() as marked.MarkedOptions & {
 		// eslint-disable-next-line @typescript-eslint/no-explicit-any
 		extensions: any;
@@ -338,17 +347,13 @@
 		dir={$settings.chatDirection}
 	>
 		<ProfileImage
-			src={modelfiles[message.model]?.imageUrl ??
+			src={model?.info?.meta?.profile_image_url ??
 				($i18n.language === 'dg-DG' ? `/doge.png` : `${WEBUI_BASE_URL}/static/favicon.png`)}
 		/>
 
 		<div class="w-full overflow-hidden pl-1">
 			<Name>
-				{#if message.model in modelfiles}
+				{model?.name ?? message.model}
-					{modelfiles[message.model]?.title}
-				{:else}
-					{message.model ? ` ${message.model}` : ''}
-				{/if}
 
 				{#if message.timestamp}
 					<span
@@ -391,7 +396,7 @@
 							<div class=" mt-2 mb-1 flex justify-end space-x-1.5 text-sm font-medium">
 								<button
 									id="close-edit-message-button"
-									class=" px-4 py-2 bg-gray-900 hover:bg-gray-850 text-gray-100 transition rounded-3xl"
+									class="px-4 py-2 bg-white hover:bg-gray-100 text-gray-800 transition rounded-3xl"
 									on:click={() => {
 										cancelEditMessage();
 									}}
@@ -401,7 +406,7 @@
 
 								<button
 									id="save-edit-message-button"
-									class="px-4 py-2 bg-white hover:bg-gray-100 text-gray-800 transition rounded-3xl"
+									class=" px-4 py-2 bg-gray-900 hover:bg-gray-850 text-gray-100 transition rounded-3xl"
 									on:click={() => {
 										editMessageConfirmHandler();
 									}}
@@ -442,8 +447,8 @@
 									{#if token.type === 'code'}
 										<CodeBlock
 											id={`${message.id}-${tokenIdx}`}
-											lang={token.lang}
+											lang={token?.lang ?? ''}
-											code={revertSanitizedResponseContent(token.text)}
+											code={revertSanitizedResponseContent(token?.text ?? '')}
 										/>
 									{:else}
 										{@html marked.parse(token.raw, {
@@ -688,7 +693,7 @@
 											</button>
 										</Tooltip>
 
-										{#if $config.images && !readOnly}
+										{#if $config?.features.enable_image_generation && !readOnly}
 											<Tooltip content="Generate Image" placement="bottom">
 												<button
 													class="{isLastMessage

src/lib/components/chat/Messages/UserMessage.svelte

@@ -4,7 +4,7 @@
 	import { tick, createEventDispatcher, getContext } from 'svelte';
 	import Name from './Name.svelte';
 	import ProfileImage from './ProfileImage.svelte';
-	import { modelfiles, settings } from '$lib/stores';
+	import { models, settings } from '$lib/stores';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 
 	import { user as _user } from '$lib/stores';
@@ -60,8 +60,7 @@
 	{#if !($settings?.chatBubble ?? true)}
 		<ProfileImage
 			src={message.user
-				? $modelfiles.find((modelfile) => modelfile.tagName === message.user)?.imageUrl ??
+				? $models.find((m) => m.id === message.user)?.info?.meta?.profile_image_url ?? '/user.png'
-				  '/user.png'
 				: user?.profile_image_url ?? '/user.png'}
 		/>
 	{/if}
@@ -70,12 +69,8 @@
 			<div>
 				<Name>
 					{#if message.user}
-						{#if $modelfiles.map((modelfile) => modelfile.tagName).includes(message.user)}
-							{$modelfiles.find((modelfile) => modelfile.tagName === message.user)?.title}
-						{:else}
 						{$i18n.t('You')}
 						<span class=" text-gray-500 text-sm font-medium">{message?.user ?? ''}</span>
-						{/if}
 					{:else if $settings.showUsername || $_user.name !== user.name}
 						{user.name}
 					{:else}
@@ -201,7 +196,7 @@
 					<div class=" mt-2 mb-1 flex justify-end space-x-1.5 text-sm font-medium">
 						<button
 							id="close-edit-message-button"
-							class=" px-4 py-2 bg-gray-900 hover:bg-gray-850 text-gray-100 transition rounded-3xl"
+							class="px-4 py-2 bg-white hover:bg-gray-100 text-gray-800 transition rounded-3xl"
 							on:click={() => {
 								cancelEditMessage();
 							}}
@@ -211,7 +206,7 @@
 
 						<button
 							id="save-edit-message-button"
-							class="px-4 py-2 bg-white hover:bg-gray-100 text-gray-800 transition rounded-3xl"
+							class=" px-4 py-2 bg-gray-900 hover:bg-gray-850 text-gray-100 transition rounded-3xl"
 							on:click={() => {
 								editMessageConfirmHandler();
 							}}

src/lib/components/chat/ModelSelector.svelte

@@ -1,13 +1,13 @@
 <script lang="ts">
-	import { Collapsible } from 'bits-ui';
-
-	import { setDefaultModels } from '$lib/apis/configs';
 	import { models, showSettings, settings, user, mobile } from '$lib/stores';
 	import { onMount, tick, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
 	import Selector from './ModelSelector/Selector.svelte';
 	import Tooltip from '../common/Tooltip.svelte';
 
+	import { setDefaultModels } from '$lib/apis/configs';
+	import { updateUserSettings } from '$lib/apis/users';
+
 	const i18n = getContext('i18n');
 
 	export let selectedModels = [''];
@@ -22,12 +22,8 @@
 			return;
 		}
 		settings.set({ ...$settings, models: selectedModels });
-		localStorage.setItem('settings', JSON.stringify($settings));
+		await updateUserSettings(localStorage.token, { ui: $settings });
 
-		if ($user.role === 'admin') {
-			console.log('setting default models globally');
-			await setDefaultModels(localStorage.token, selectedModels.join(','));
-		}
 		toast.success($i18n.t('Default model updated'));
 	};
 
@@ -45,12 +41,10 @@
 				<div class="mr-1 max-w-full">
 					<Selector
 						placeholder={$i18n.t('Select a model')}
-						items={$models
+						items={$models.map((model) => ({
-							.filter((model) => model.name !== 'hr')
-							.map((model) => ({
 							value: model.id,
 							label: model.name,
-								info: model
+							model: model
 						}))}
 						bind:value={selectedModel}
 					/>

src/lib/components/chat/ModelSelector/Selector.svelte

@@ -12,7 +12,9 @@
 
 	import { user, MODEL_DOWNLOAD_POOL, models, mobile } from '$lib/stores';
 	import { toast } from 'svelte-sonner';
-	import { capitalizeFirstLetter, getModels, splitStream } from '$lib/utils';
+	import { capitalizeFirstLetter, sanitizeResponseContent, splitStream } from '$lib/utils';
+	import { getModels } from '$lib/apis';
+
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 
 	const i18n = getContext('i18n');
@@ -23,7 +25,12 @@
 	export let searchEnabled = true;
 	export let searchPlaceholder = $i18n.t('Search a model');
 
-	export let items = [{ value: 'mango', label: 'Mango' }];
+	export let items: {
+		label: string;
+		value: string;
+		// eslint-disable-next-line @typescript-eslint/no-explicit-any
+		[key: string]: any;
+	} = [];
 
 	export let className = 'w-[30rem]';
 
@@ -239,19 +246,37 @@
 						}}
 					>
 						<div class="flex items-center gap-2">
+							<div class="flex items-center">
 								<div class="line-clamp-1">
 									{item.label}
-
+								</div>
-								<span class=" text-xs font-medium text-gray-600 dark:text-gray-400"
+								{#if item.model.owned_by === 'ollama' && (item.model.ollama?.details?.parameter_size ?? '') !== ''}
-									>{item.info?.details?.parameter_size ?? ''}</span
+									<div class="flex ml-1 items-center">
+										<Tooltip
+											content={`${
+												item.model.ollama?.details?.quantization_level
+													? item.model.ollama?.details?.quantization_level + ' '
+													: ''
+											}${
+												item.model.ollama?.size
+													? `(${(item.model.ollama?.size / 1024 ** 3).toFixed(1)}GB)`
+													: ''
+											}`}
+											className="self-end"
 										>
+											<span class=" text-xs font-medium text-gray-600 dark:text-gray-400"
+												>{item.model.ollama?.details?.parameter_size ?? ''}</span
+											>
+										</Tooltip>
+									</div>
+								{/if}
 							</div>
 
 							<!-- {JSON.stringify(item.info)} -->
 
-							{#if item.info.external}
+							{#if item.model.owned_by === 'openai'}
-								<Tooltip content={item.info?.source ?? 'External'}>
+								<Tooltip content={`${'External'}`}>
-									<div class=" mr-2">
+									<div class="">
 										<svg
 											xmlns="http://www.w3.org/2000/svg"
 											viewBox="0 0 16 16"
@@ -271,15 +296,15 @@
 										</svg>
 									</div>
 								</Tooltip>
-							{:else}
+							{/if}
+
+							{#if item.model?.info?.meta?.description}
 								<Tooltip
-									content={`${
+									content={`${sanitizeResponseContent(
-										item.info?.details?.quantization_level
+										item.model?.info?.meta?.description
-											? item.info?.details?.quantization_level + ' '
+									).replaceAll('\n', '<br>')}`}
-											: ''
-									}${item.info.size ? `(${(item.info.size / 1024 ** 3).toFixed(1)}GB)` : ''}`}
 								>
-									<div class=" mr-2">
+									<div class="">
 										<svg
 											xmlns="http://www.w3.org/2000/svg"
 											fill="none"

src/lib/components/chat/Settings/About.svelte

@@ -1,7 +1,7 @@
 <script lang="ts">
 	import { getVersionUpdates } from '$lib/apis';
 	import { getOllamaVersion } from '$lib/apis/ollama';
-	import { WEBUI_VERSION } from '$lib/constants';
+	import { WEBUI_BUILD_HASH, WEBUI_VERSION } from '$lib/constants';
 	import { WEBUI_NAME, config, showChangelog } from '$lib/stores';
 	import { compareVersion } from '$lib/utils';
 	import { onMount, getContext } from 'svelte';
@@ -54,7 +54,7 @@
 			<div class="flex w-full justify-between items-center">
 				<div class="flex flex-col text-xs text-gray-700 dark:text-gray-200">
 					<div class="flex gap-1">
-						<Tooltip content={WEBUI_VERSION === '0.1.117' ? "🪖 We're just getting started." : ''}>
+						<Tooltip content={WEBUI_BUILD_HASH}>
 							v{WEBUI_VERSION}
 						</Tooltip>
 

src/lib/components/chat/Settings/Advanced.svelte

@@ -1,155 +0,0 @@
-<script lang="ts">
-	import { createEventDispatcher, onMount, getContext } from 'svelte';
-	import AdvancedParams from './Advanced/AdvancedParams.svelte';
-
-	const i18n = getContext('i18n');
-	const dispatch = createEventDispatcher();
-
-	export let saveSettings: Function;
-
-	// Advanced
-	let requestFormat = '';
-	let keepAlive = null;
-
-	let options = {
-		// Advanced
-		seed: 0,
-		temperature: '',
-		repeat_penalty: '',
-		repeat_last_n: '',
-		mirostat: '',
-		mirostat_eta: '',
-		mirostat_tau: '',
-		top_k: '',
-		top_p: '',
-		stop: '',
-		tfs_z: '',
-		num_ctx: '',
-		num_predict: ''
-	};
-
-	const toggleRequestFormat = async () => {
-		if (requestFormat === '') {
-			requestFormat = 'json';
-		} else {
-			requestFormat = '';
-		}
-
-		saveSettings({ requestFormat: requestFormat !== '' ? requestFormat : undefined });
-	};
-
-	onMount(() => {
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
-
-		requestFormat = settings.requestFormat ?? '';
-		keepAlive = settings.keepAlive ?? null;
-
-		options.seed = settings.seed ?? 0;
-		options.temperature = settings.temperature ?? '';
-		options.repeat_penalty = settings.repeat_penalty ?? '';
-		options.top_k = settings.top_k ?? '';
-		options.top_p = settings.top_p ?? '';
-		options.num_ctx = settings.num_ctx ?? '';
-		options = { ...options, ...settings.options };
-		options.stop = (settings?.options?.stop ?? []).join(',');
-	});
-</script>
-
-<div class="flex flex-col h-full justify-between text-sm">
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
-		<div class=" text-sm font-medium">{$i18n.t('Parameters')}</div>
-
-		<AdvancedParams bind:options />
-		<hr class=" dark:border-gray-700" />
-
-		<div class=" py-1 w-full justify-between">
-			<div class="flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Keep Alive')}</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition"
-					type="button"
-					on:click={() => {
-						keepAlive = keepAlive === null ? '5m' : null;
-					}}
-				>
-					{#if keepAlive === null}
-						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-					{:else}
-						<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
-					{/if}
-				</button>
-			</div>
-
-			{#if keepAlive !== null}
-				<div class="flex mt-1 space-x-2">
-					<input
-						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-						type="text"
-						placeholder={$i18n.t("e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.")}
-						bind:value={keepAlive}
-					/>
-				</div>
-			{/if}
-		</div>
-
-		<div>
-			<div class=" py-1 flex w-full justify-between">
-				<div class=" self-center text-sm font-medium">{$i18n.t('Request Mode')}</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition"
-					on:click={() => {
-						toggleRequestFormat();
-					}}
-				>
-					{#if requestFormat === ''}
-						<span class="ml-2 self-center"> {$i18n.t('Default')} </span>
-					{:else if requestFormat === 'json'}
-						<!-- <svg
-                            xmlns="http://www.w3.org/2000/svg"
-                            viewBox="0 0 20 20"
-                            fill="currentColor"
-                            class="w-4 h-4 self-center"
-                        >
-                            <path
-                                d="M10 2a.75.75 0 01.75.75v1.5a.75.75 0 01-1.5 0v-1.5A.75.75 0 0110 2zM10 15a.75.75 0 01.75.75v1.5a.75.75 0 01-1.5 0v-1.5A.75.75 0 0110 15zM10 7a3 3 0 100 6 3 3 0 000-6zM15.657 5.404a.75.75 0 10-1.06-1.06l-1.061 1.06a.75.75 0 001.06 1.06l1.06-1.06zM6.464 14.596a.75.75 0 10-1.06-1.06l-1.06 1.06a.75.75 0 001.06 1.06l1.06-1.06zM18 10a.75.75 0 01-.75.75h-1.5a.75.75 0 010-1.5h1.5A.75.75 0 0118 10zM5 10a.75.75 0 01-.75.75h-1.5a.75.75 0 010-1.5h1.5A.75.75 0 015 10zM14.596 15.657a.75.75 0 001.06-1.06l-1.06-1.061a.75.75 0 10-1.06 1.06l1.06 1.06zM5.404 6.464a.75.75 0 001.06-1.06l-1.06-1.06a.75.75 0 10-1.061 1.06l1.06 1.06z"
-                            />
-                        </svg> -->
-						<span class="ml-2 self-center">{$i18n.t('JSON')}</span>
-					{/if}
-				</button>
-			</div>
-		</div>
-	</div>
-
-	<div class="flex justify-end pt-3 text-sm font-medium">
-		<button
-			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
-			on:click={() => {
-				saveSettings({
-					options: {
-						seed: (options.seed !== 0 ? options.seed : undefined) ?? undefined,
-						stop: options.stop !== '' ? options.stop.split(',').filter((e) => e) : undefined,
-						temperature: options.temperature !== '' ? options.temperature : undefined,
-						repeat_penalty: options.repeat_penalty !== '' ? options.repeat_penalty : undefined,
-						repeat_last_n: options.repeat_last_n !== '' ? options.repeat_last_n : undefined,
-						mirostat: options.mirostat !== '' ? options.mirostat : undefined,
-						mirostat_eta: options.mirostat_eta !== '' ? options.mirostat_eta : undefined,
-						mirostat_tau: options.mirostat_tau !== '' ? options.mirostat_tau : undefined,
-						top_k: options.top_k !== '' ? options.top_k : undefined,
-						top_p: options.top_p !== '' ? options.top_p : undefined,
-						tfs_z: options.tfs_z !== '' ? options.tfs_z : undefined,
-						num_ctx: options.num_ctx !== '' ? options.num_ctx : undefined,
-						num_predict: options.num_predict !== '' ? options.num_predict : undefined
-					},
-					keepAlive: keepAlive ? (isNaN(keepAlive) ? keepAlive : parseInt(keepAlive)) : undefined
-				});
-
-				dispatch('save');
-			}}
-		>
-			{$i18n.t('Save')}
-		</button>
-	</div>
-</div>

src/lib/components/chat/Settings/Advanced/AdvancedParams.svelte

@@ -1,14 +1,16 @@
 <script lang="ts">
-	import { getContext } from 'svelte';
+	import { getContext, createEventDispatcher } from 'svelte';
+
+	const dispatch = createEventDispatcher();
 
 	const i18n = getContext('i18n');
 
-	export let options = {
+	export let params = {
 		// Advanced
 		seed: 0,
-		stop: '',
+		stop: null,
 		temperature: '',
-		repeat_penalty: '',
+		frequency_penalty: '',
 		repeat_last_n: '',
 		mirostat: '',
 		mirostat_eta: '',
@@ -17,40 +19,86 @@
 		top_p: '',
 		tfs_z: '',
 		num_ctx: '',
-		num_predict: ''
+		max_tokens: '',
+		template: null
 	};
+
+	let customFieldName = '';
+	let customFieldValue = '';
+
+	$: if (params) {
+		dispatch('change', params);
+	}
 </script>
 
-<div class=" space-y-3 text-xs">
+<div class=" space-y-1 text-xs">
-	<div>
+	<div class=" py-0.5 w-full justify-between">
-		<div class=" py-0.5 flex w-full justify-between">
+		<div class="flex w-full justify-between">
-			<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Seed')}</div>
+			<div class=" self-center text-xs font-medium">{$i18n.t('Seed')}</div>
-			<div class=" flex-1 self-center">
+
+			<button
+				class="p-1 px-3 text-xs flex rounded transition"
+				type="button"
+				on:click={() => {
+					params.seed = (params?.seed ?? null) === null ? 0 : null;
+				}}
+			>
+				{#if (params?.seed ?? null) === null}
+					<span class="ml-2 self-center"> {$i18n.t('Default')} </span>
+				{:else}
+					<span class="ml-2 self-center"> {$i18n.t('Custom')} </span>
+				{/if}
+			</button>
+		</div>
+
+		{#if (params?.seed ?? null) !== null}
+			<div class="flex mt-0.5 space-x-2">
+				<div class=" flex-1">
 					<input
 						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 						type="number"
 						placeholder="Enter Seed"
-					bind:value={options.seed}
+						bind:value={params.seed}
 						autocomplete="off"
 						min="0"
 					/>
 				</div>
 			</div>
+		{/if}
 	</div>
 
-	<div>
+	<div class=" py-0.5 w-full justify-between">
-		<div class=" py-0.5 flex w-full justify-between">
+		<div class="flex w-full justify-between">
-			<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Stop Sequence')}</div>
+			<div class=" self-center text-xs font-medium">{$i18n.t('Stop Sequence')}</div>
-			<div class=" flex-1 self-center">
+
+			<button
+				class="p-1 px-3 text-xs flex rounded transition"
+				type="button"
+				on:click={() => {
+					params.stop = (params?.stop ?? null) === null ? '' : null;
+				}}
+			>
+				{#if (params?.stop ?? null) === null}
+					<span class="ml-2 self-center"> {$i18n.t('Default')} </span>
+				{:else}
+					<span class="ml-2 self-center"> {$i18n.t('Custom')} </span>
+				{/if}
+			</button>
+		</div>
+
+		{#if (params?.stop ?? null) !== null}
+			<div class="flex mt-0.5 space-x-2">
+				<div class=" flex-1">
 					<input
 						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
 						type="text"
 						placeholder={$i18n.t('Enter stop sequence')}
-					bind:value={options.stop}
+						bind:value={params.stop}
 						autocomplete="off"
 					/>
 				</div>
 			</div>
+		{/if}
 	</div>
 
 	<div class=" py-0.5 w-full justify-between">
@@ -61,10 +109,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.temperature = options.temperature === '' ? 0.8 : '';
+					params.temperature = (params?.temperature ?? '') === '' ? 0.8 : '';
 				}}
 			>
-				{#if options.temperature === ''}
+				{#if (params?.temperature ?? '') === ''}
 					<span class="ml-2 self-center"> {$i18n.t('Default')} </span>
 				{:else}
 					<span class="ml-2 self-center"> {$i18n.t('Custom')} </span>
@@ -72,7 +120,7 @@
 			</button>
 		</div>
 
-		{#if options.temperature !== ''}
+		{#if (params?.temperature ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -81,13 +129,13 @@
 						min="0"
 						max="1"
 						step="0.05"
-						bind:value={options.temperature}
+						bind:value={params.temperature}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.temperature}
+						bind:value={params.temperature}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -107,18 +155,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.mirostat = options.mirostat === '' ? 0 : '';
+					params.mirostat = (params?.mirostat ?? '') === '' ? 0 : '';
 				}}
 			>
-				{#if options.mirostat === ''}
+				{#if (params?.mirostat ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.mirostat !== ''}
+		{#if (params?.mirostat ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -127,13 +175,13 @@
 						min="0"
 						max="2"
 						step="1"
-						bind:value={options.mirostat}
+						bind:value={params.mirostat}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.mirostat}
+						bind:value={params.mirostat}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -153,18 +201,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.mirostat_eta = options.mirostat_eta === '' ? 0.1 : '';
+					params.mirostat_eta = (params?.mirostat_eta ?? '') === '' ? 0.1 : '';
 				}}
 			>
-				{#if options.mirostat_eta === ''}
+				{#if (params?.mirostat_eta ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.mirostat_eta !== ''}
+		{#if (params?.mirostat_eta ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -173,13 +221,13 @@
 						min="0"
 						max="1"
 						step="0.05"
-						bind:value={options.mirostat_eta}
+						bind:value={params.mirostat_eta}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.mirostat_eta}
+						bind:value={params.mirostat_eta}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -199,10 +247,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.mirostat_tau = options.mirostat_tau === '' ? 5.0 : '';
+					params.mirostat_tau = (params?.mirostat_tau ?? '') === '' ? 5.0 : '';
 				}}
 			>
-				{#if options.mirostat_tau === ''}
+				{#if (params?.mirostat_tau ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -210,7 +258,7 @@
 			</button>
 		</div>
 
-		{#if options.mirostat_tau !== ''}
+		{#if (params?.mirostat_tau ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -219,13 +267,13 @@
 						min="0"
 						max="10"
 						step="0.5"
-						bind:value={options.mirostat_tau}
+						bind:value={params.mirostat_tau}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.mirostat_tau}
+						bind:value={params.mirostat_tau}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -245,18 +293,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.top_k = options.top_k === '' ? 40 : '';
+					params.top_k = (params?.top_k ?? '') === '' ? 40 : '';
 				}}
 			>
-				{#if options.top_k === ''}
+				{#if (params?.top_k ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.top_k !== ''}
+		{#if (params?.top_k ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -265,13 +313,13 @@
 						min="0"
 						max="100"
 						step="0.5"
-						bind:value={options.top_k}
+						bind:value={params.top_k}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.top_k}
+						bind:value={params.top_k}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -291,18 +339,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.top_p = options.top_p === '' ? 0.9 : '';
+					params.top_p = (params?.top_p ?? '') === '' ? 0.9 : '';
 				}}
 			>
-				{#if options.top_p === ''}
+				{#if (params?.top_p ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.top_p !== ''}
+		{#if (params?.top_p ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -311,13 +359,13 @@
 						min="0"
 						max="1"
 						step="0.05"
-						bind:value={options.top_p}
+						bind:value={params.top_p}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.top_p}
+						bind:value={params.top_p}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -331,24 +379,24 @@
 
 	<div class=" py-0.5 w-full justify-between">
 		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('Repeat Penalty')}</div>
+			<div class=" self-center text-xs font-medium">{$i18n.t('Frequencey Penalty')}</div>
 
 			<button
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.repeat_penalty = options.repeat_penalty === '' ? 1.1 : '';
+					params.frequency_penalty = (params?.frequency_penalty ?? '') === '' ? 1.1 : '';
 				}}
 			>
-				{#if options.repeat_penalty === ''}
+				{#if (params?.frequency_penalty ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.repeat_penalty !== ''}
+		{#if (params?.frequency_penalty ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -357,13 +405,13 @@
 						min="0"
 						max="2"
 						step="0.05"
-						bind:value={options.repeat_penalty}
+						bind:value={params.frequency_penalty}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.repeat_penalty}
+						bind:value={params.frequency_penalty}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -383,18 +431,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.repeat_last_n = options.repeat_last_n === '' ? 64 : '';
+					params.repeat_last_n = (params?.repeat_last_n ?? '') === '' ? 64 : '';
 				}}
 			>
-				{#if options.repeat_last_n === ''}
+				{#if (params?.repeat_last_n ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.repeat_last_n !== ''}
+		{#if (params?.repeat_last_n ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -403,13 +451,13 @@
 						min="-1"
 						max="128"
 						step="1"
-						bind:value={options.repeat_last_n}
+						bind:value={params.repeat_last_n}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.repeat_last_n}
+						bind:value={params.repeat_last_n}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="-1"
@@ -429,18 +477,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.tfs_z = options.tfs_z === '' ? 1 : '';
+					params.tfs_z = (params?.tfs_z ?? '') === '' ? 1 : '';
 				}}
 			>
-				{#if options.tfs_z === ''}
+				{#if (params?.tfs_z ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.tfs_z !== ''}
+		{#if (params?.tfs_z ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -449,13 +497,13 @@
 						min="0"
 						max="2"
 						step="0.05"
-						bind:value={options.tfs_z}
+						bind:value={params.tfs_z}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div>
 					<input
-						bind:value={options.tfs_z}
+						bind:value={params.tfs_z}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="0"
@@ -475,18 +523,18 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.num_ctx = options.num_ctx === '' ? 2048 : '';
+					params.num_ctx = (params?.num_ctx ?? '') === '' ? 2048 : '';
 				}}
 			>
-				{#if options.num_ctx === ''}
+				{#if (params?.num_ctx ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.num_ctx !== ''}
+		{#if (params?.num_ctx ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -495,13 +543,13 @@
 						min="-1"
 						max="10240000"
 						step="1"
-						bind:value={options.num_ctx}
+						bind:value={params.num_ctx}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div class="">
 					<input
-						bind:value={options.num_ctx}
+						bind:value={params.num_ctx}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="-1"
@@ -513,24 +561,24 @@
 	</div>
 	<div class=" py-0.5 w-full justify-between">
 		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('Max Tokens')}</div>
+			<div class=" self-center text-xs font-medium">{$i18n.t('Max Tokens (num_predict)')}</div>
 
 			<button
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					options.num_predict = options.num_predict === '' ? 128 : '';
+					params.max_tokens = (params?.max_tokens ?? '') === '' ? 128 : '';
 				}}
 			>
-				{#if options.num_predict === ''}
+				{#if (params?.max_tokens ?? '') === ''}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
 				{/if}
 			</button>
 		</div>
 
-		{#if options.num_predict !== ''}
+		{#if (params?.max_tokens ?? '') !== ''}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -539,13 +587,13 @@
 						min="-2"
 						max="16000"
 						step="1"
-						bind:value={options.num_predict}
+						bind:value={params.max_tokens}
 						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
 					/>
 				</div>
 				<div class="">
 					<input
-						bind:value={options.num_predict}
+						bind:value={params.max_tokens}
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="-2"
@@ -556,4 +604,36 @@
 			</div>
 		{/if}
 	</div>
+	<div class=" py-0.5 w-full justify-between">
+		<div class="flex w-full justify-between">
+			<div class=" self-center text-xs font-medium">{$i18n.t('Template')}</div>
+
+			<button
+				class="p-1 px-3 text-xs flex rounded transition"
+				type="button"
+				on:click={() => {
+					params.template = (params?.template ?? null) === null ? '' : null;
+				}}
+			>
+				{#if (params?.template ?? null) === null}
+					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+				{:else}
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
+				{/if}
+			</button>
+		</div>
+
+		{#if (params?.template ?? null) !== null}
+			<div class="flex mt-0.5 space-x-2">
+				<div class=" flex-1">
+					<textarea
+						class="px-3 py-1.5 text-sm w-full bg-transparent border dark:border-gray-600 outline-none rounded-lg -mb-1"
+						placeholder="Write your model template content here"
+						rows="4"
+						bind:value={params.template}
+					/>
+				</div>
+			</div>
+		{/if}
+	</div>
 </div>

src/lib/components/chat/Settings/Audio.svelte

@@ -1,6 +1,6 @@
 <script lang="ts">
 	import { getAudioConfig, updateAudioConfig } from '$lib/apis/audio';
-	import { user } from '$lib/stores';
+	import { user, settings } from '$lib/stores';
 	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
 	const dispatch = createEventDispatcher();
@@ -99,16 +99,14 @@
 	};
 
 	onMount(async () => {
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
+		conversationMode = $settings.conversationMode ?? false;
+		speechAutoSend = $settings.speechAutoSend ?? false;
+		responseAutoPlayback = $settings.responseAutoPlayback ?? false;
 
-		conversationMode = settings.conversationMode ?? false;
+		STTEngine = $settings?.audio?.STTEngine ?? '';
-		speechAutoSend = settings.speechAutoSend ?? false;
+		TTSEngine = $settings?.audio?.TTSEngine ?? '';
-		responseAutoPlayback = settings.responseAutoPlayback ?? false;
+		speaker = $settings?.audio?.speaker ?? '';
-
+		model = $settings?.audio?.model ?? '';
-		STTEngine = settings?.audio?.STTEngine ?? '';
-		TTSEngine = settings?.audio?.TTSEngine ?? '';
-		speaker = settings?.audio?.speaker ?? '';
-		model = settings?.audio?.model ?? '';
 
 		if (TTSEngine === 'openai') {
 			getOpenAIVoices();

src/lib/components/chat/Settings/Chats.svelte

@@ -2,9 +2,10 @@
 	import fileSaver from 'file-saver';
 	const { saveAs } = fileSaver;
 
-	import { chats, user, config } from '$lib/stores';
+	import { chats, user, settings } from '$lib/stores';
 
 	import {
+		archiveAllChats,
 		createNewChat,
 		deleteAllChats,
 		getAllChats,
@@ -22,7 +23,10 @@
 	// Chats
 	let saveChatHistory = true;
 	let importFiles;
+
+	let showArchiveConfirm = false;
 	let showDeleteConfirm = false;
+
 	let chatImportInputElement: HTMLInputElement;
 
 	$: if (importFiles) {
@@ -68,14 +72,15 @@
 		saveAs(blob, `chat-export-${Date.now()}.json`);
 	};
 
-	const exportAllUserChats = async () => {
+	const archiveAllChatsHandler = async () => {
-		let blob = new Blob([JSON.stringify(await getAllUserChats(localStorage.token))], {
+		await goto('/');
-			type: 'application/json'
+		await archiveAllChats(localStorage.token).catch((error) => {
+			toast.error(error);
 		});
-		saveAs(blob, `all-chats-export-${Date.now()}.json`);
+		await chats.set(await getChatList(localStorage.token));
 	};
 
-	const deleteChats = async () => {
+	const deleteAllChatsHandler = async () => {
 		await goto('/');
 		await deleteAllChats(localStorage.token).catch((error) => {
 			toast.error(error);
@@ -94,9 +99,7 @@
 	};
 
 	onMount(async () => {
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
+		saveChatHistory = $settings.saveChatHistory ?? true;
-
-		saveChatHistory = settings.saveChatHistory ?? true;
 	});
 </script>
 
@@ -217,6 +220,94 @@
 
 		<hr class=" dark:border-gray-700" />
 
+		<div class="flex flex-col">
+			{#if showArchiveConfirm}
+				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
+					<div class="flex items-center space-x-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
+							<path
+								fill-rule="evenodd"
+								d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM5.72 7.47a.75.75 0 0 1 1.06 0L8 8.69l1.22-1.22a.75.75 0 1 1 1.06 1.06L9.06 9.75l1.22 1.22a.75.75 0 1 1-1.06 1.06L8 10.81l-1.22 1.22a.75.75 0 0 1-1.06-1.06l1.22-1.22-1.22-1.22a.75.75 0 0 1 0-1.06Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+						<span>{$i18n.t('Are you sure?')}</span>
+					</div>
+
+					<div class="flex space-x-1.5 items-center">
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								archiveAllChatsHandler();
+								showArchiveConfirm = false;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									fill-rule="evenodd"
+									d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
+									clip-rule="evenodd"
+								/>
+							</svg>
+						</button>
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								showArchiveConfirm = false;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				</div>
+			{:else}
+				<button
+					class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					on:click={() => {
+						showArchiveConfirm = true;
+					}}
+				>
+					<div class=" self-center mr-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								d="M3.375 3C2.339 3 1.5 3.84 1.5 4.875v.75c0 1.036.84 1.875 1.875 1.875h17.25c1.035 0 1.875-.84 1.875-1.875v-.75C22.5 3.839 21.66 3 20.625 3H3.375Z"
+							/>
+							<path
+								fill-rule="evenodd"
+								d="m3.087 9 .54 9.176A3 3 0 0 0 6.62 21h10.757a3 3 0 0 0 2.995-2.824L20.913 9H3.087Zm6.163 3.75A.75.75 0 0 1 10 12h4a.75.75 0 0 1 0 1.5h-4a.75.75 0 0 1-.75-.75Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Archive All Chats')}</div>
+				</button>
+			{/if}
+
 			{#if showDeleteConfirm}
 				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
 					<div class="flex items-center space-x-3">
@@ -240,7 +331,7 @@
 						<button
 							class="hover:text-white transition"
 							on:click={() => {
-							deleteChats();
+								deleteAllChatsHandler();
 								showDeleteConfirm = false;
 							}}
 						>
@@ -297,38 +388,9 @@
 							/>
 						</svg>
 					</div>
-				<div class=" self-center text-sm font-medium">{$i18n.t('Delete Chats')}</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Delete All Chats')}</div>
-			</button>
-		{/if}
-
-		{#if $user?.role === 'admin' && ($config?.admin_export_enabled ?? true)}
-			<hr class=" dark:border-gray-700" />
-
-			<button
-				class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
-				on:click={() => {
-					exportAllUserChats();
-				}}
-			>
-				<div class=" self-center mr-3">
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 16 16"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
-						<path
-							fill-rule="evenodd"
-							d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM8.75 7.75a.75.75 0 0 0-1.5 0v2.69L6.03 9.22a.75.75 0 0 0-1.06 1.06l2.5 2.5a.75.75 0 0 0 1.06 0l2.5-2.5a.75.75 0 1 0-1.06-1.06l-1.22 1.22V7.75Z"
-							clip-rule="evenodd"
-						/>
-					</svg>
-				</div>
-				<div class=" self-center text-sm font-medium">
-					{$i18n.t('Export All Chats (All Users)')}
-				</div>
 				</button>
 			{/if}
 		</div>
 	</div>
+</div>

src/lib/components/chat/Settings/Connections.svelte

@@ -3,7 +3,13 @@
 	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	const dispatch = createEventDispatcher();
 
-	import { getOllamaUrls, getOllamaVersion, updateOllamaUrls } from '$lib/apis/ollama';
+	import {
+		getOllamaConfig,
+		getOllamaUrls,
+		getOllamaVersion,
+		updateOllamaConfig,
+		updateOllamaUrls
+	} from '$lib/apis/ollama';
 	import {
 		getOpenAIConfig,
 		getOpenAIKeys,
@@ -14,6 +20,7 @@
 	} from '$lib/apis/openai';
 	import { toast } from 'svelte-sonner';
 	import Switch from '$lib/components/common/Switch.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -25,7 +32,8 @@
 	let OPENAI_API_KEYS = [''];
 	let OPENAI_API_BASE_URLS = [''];
 
-	let ENABLE_OPENAI_API = false;
+	let ENABLE_OPENAI_API = null;
+	let ENABLE_OLLAMA_API = null;
 
 	const updateOpenAIHandler = async () => {
 		OPENAI_API_BASE_URLS = await updateOpenAIUrls(localStorage.token, OPENAI_API_BASE_URLS);
@@ -50,13 +58,23 @@
 
 	onMount(async () => {
 		if ($user.role === 'admin') {
+			await Promise.all([
+				(async () => {
 					OLLAMA_BASE_URLS = await getOllamaUrls(localStorage.token);
-
+				})(),
-			const config = await getOpenAIConfig(localStorage.token);
+				(async () => {
-			ENABLE_OPENAI_API = config.ENABLE_OPENAI_API;
-
 					OPENAI_API_BASE_URLS = await getOpenAIUrls(localStorage.token);
+				})(),
+				(async () => {
 					OPENAI_API_KEYS = await getOpenAIKeys(localStorage.token);
+				})()
+			]);
+
+			const ollamaConfig = await getOllamaConfig(localStorage.token);
+			const openaiConfig = await getOpenAIConfig(localStorage.token);
+
+			ENABLE_OPENAI_API = openaiConfig.ENABLE_OPENAI_API;
+			ENABLE_OLLAMA_API = ollamaConfig.ENABLE_OLLAMA_API;
 		}
 	});
 </script>
@@ -68,7 +86,8 @@
 		dispatch('save');
 	}}
 >
-	<div class="  pr-1.5 overflow-y-scroll max-h-[25rem] space-y-3">
+	<div class="space-y-3 pr-1.5 overflow-y-scroll h-[24rem] max-h-[25rem]">
+		{#if ENABLE_OPENAI_API !== null && ENABLE_OLLAMA_API !== null}
 			<div class=" space-y-3">
 				<div class="mt-2 space-y-2 pr-1.5">
 					<div class="flex justify-between items-center text-sm">
@@ -161,8 +180,20 @@
 
 			<hr class=" dark:border-gray-700" />
 
-		<div>
+			<div class="pr-1.5 space-y-2">
-			<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Ollama Base URL')}</div>
+				<div class="flex justify-between items-center text-sm">
+					<div class="  font-medium">{$i18n.t('Ollama API')}</div>
+
+					<div class="mt-1">
+						<Switch
+							bind:state={ENABLE_OLLAMA_API}
+							on:change={async () => {
+								updateOllamaConfig(localStorage.token, ENABLE_OLLAMA_API);
+							}}
+						/>
+					</div>
+				</div>
+				{#if ENABLE_OLLAMA_API}
 					<div class="flex w-full gap-1.5">
 						<div class="flex-1 flex flex-col gap-2">
 							{#each OLLAMA_BASE_URLS as url, idx}
@@ -197,7 +228,9 @@
 											<button
 												class="px-1"
 												on:click={() => {
-											OLLAMA_BASE_URLS = OLLAMA_BASE_URLS.filter((url, urlIdx) => idx !== urlIdx);
+													OLLAMA_BASE_URLS = OLLAMA_BASE_URLS.filter(
+														(url, urlIdx) => idx !== urlIdx
+													);
 												}}
 												type="button"
 											>
@@ -216,9 +249,9 @@
 							{/each}
 						</div>
 
-				<div class="">
+						<div class="flex">
 							<button
-						class="p-2.5 bg-gray-200 hover:bg-gray-300 dark:bg-gray-850 dark:hover:bg-gray-800 rounded-lg transition"
+								class="self-center p-2 bg-gray-200 hover:bg-gray-300 dark:bg-gray-900 dark:hover:bg-gray-850 rounded-lg transition"
 								on:click={() => {
 									updateOllamaUrlsHandler();
 								}}
@@ -250,7 +283,15 @@
 							{$i18n.t('Click here for help.')}
 						</a>
 					</div>
+				{/if}
 			</div>
+		{:else}
+			<div class="flex h-full justify-center">
+				<div class="my-auto">
+					<Spinner className="size-6" />
+				</div>
+			</div>
+		{/if}
 	</div>
 
 	<div class="flex justify-end pt-3 text-sm font-medium">

src/lib/components/chat/Settings/General.svelte

@@ -4,7 +4,7 @@
 	import { getLanguages } from '$lib/i18n';
 	const dispatch = createEventDispatcher();
 
-	import { models, user, theme } from '$lib/stores';
+	import { models, settings, theme } from '$lib/stores';
 
 	const i18n = getContext('i18n');
 
@@ -41,21 +41,21 @@
 	let requestFormat = '';
 	let keepAlive = null;
 
-	let options = {
+	let params = {
 		// Advanced
 		seed: 0,
 		temperature: '',
-		repeat_penalty: '',
+		frequency_penalty: '',
 		repeat_last_n: '',
 		mirostat: '',
 		mirostat_eta: '',
 		mirostat_tau: '',
 		top_k: '',
 		top_p: '',
-		stop: '',
+		stop: null,
 		tfs_z: '',
 		num_ctx: '',
-		num_predict: ''
+		max_tokens: ''
 	};
 
 	const toggleRequestFormat = async () => {
@@ -71,23 +71,22 @@
 	onMount(async () => {
 		selectedTheme = localStorage.theme ?? 'system';
 
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
 		languages = await getLanguages();
 
-		notificationEnabled = settings.notificationEnabled ?? false;
+		notificationEnabled = $settings.notificationEnabled ?? false;
-		system = settings.system ?? '';
+		system = $settings.system ?? '';
 
-		requestFormat = settings.requestFormat ?? '';
+		requestFormat = $settings.requestFormat ?? '';
-		keepAlive = settings.keepAlive ?? null;
+		keepAlive = $settings.keepAlive ?? null;
 
-		options.seed = settings.seed ?? 0;
+		params.seed = $settings.seed ?? 0;
-		options.temperature = settings.temperature ?? '';
+		params.temperature = $settings.temperature ?? '';
-		options.repeat_penalty = settings.repeat_penalty ?? '';
+		params.frequency_penalty = $settings.frequency_penalty ?? '';
-		options.top_k = settings.top_k ?? '';
+		params.top_k = $settings.top_k ?? '';
-		options.top_p = settings.top_p ?? '';
+		params.top_p = $settings.top_p ?? '';
-		options.num_ctx = settings.num_ctx ?? '';
+		params.num_ctx = $settings.num_ctx ?? '';
-		options = { ...options, ...settings.options };
+		params = { ...params, ...$settings.params };
-		options.stop = (settings?.options?.stop ?? []).join(',');
+		params.stop = $settings?.params?.stop ? ($settings?.params?.stop ?? []).join(',') : null;
 	});
 
 	const applyTheme = (_theme: string) => {
@@ -228,7 +227,7 @@
 			</div>
 
 			{#if showAdvanced}
-				<AdvancedParams bind:options />
+				<AdvancedParams bind:params />
 				<hr class=" dark:border-gray-700" />
 
 				<div class=" py-1 w-full justify-between">
@@ -300,20 +299,21 @@
 			on:click={() => {
 				saveSettings({
 					system: system !== '' ? system : undefined,
-					options: {
+					params: {
-						seed: (options.seed !== 0 ? options.seed : undefined) ?? undefined,
+						seed: (params.seed !== 0 ? params.seed : undefined) ?? undefined,
-						stop: options.stop !== '' ? options.stop.split(',').filter((e) => e) : undefined,
+						stop: params.stop ? params.stop.split(',').filter((e) => e) : undefined,
-						temperature: options.temperature !== '' ? options.temperature : undefined,
+						temperature: params.temperature !== '' ? params.temperature : undefined,
-						repeat_penalty: options.repeat_penalty !== '' ? options.repeat_penalty : undefined,
+						frequency_penalty:
-						repeat_last_n: options.repeat_last_n !== '' ? options.repeat_last_n : undefined,
+							params.frequency_penalty !== '' ? params.frequency_penalty : undefined,
-						mirostat: options.mirostat !== '' ? options.mirostat : undefined,
+						repeat_last_n: params.repeat_last_n !== '' ? params.repeat_last_n : undefined,
-						mirostat_eta: options.mirostat_eta !== '' ? options.mirostat_eta : undefined,
+						mirostat: params.mirostat !== '' ? params.mirostat : undefined,
-						mirostat_tau: options.mirostat_tau !== '' ? options.mirostat_tau : undefined,
+						mirostat_eta: params.mirostat_eta !== '' ? params.mirostat_eta : undefined,
-						top_k: options.top_k !== '' ? options.top_k : undefined,
+						mirostat_tau: params.mirostat_tau !== '' ? params.mirostat_tau : undefined,
-						top_p: options.top_p !== '' ? options.top_p : undefined,
+						top_k: params.top_k !== '' ? params.top_k : undefined,
-						tfs_z: options.tfs_z !== '' ? options.tfs_z : undefined,
+						top_p: params.top_p !== '' ? params.top_p : undefined,
-						num_ctx: options.num_ctx !== '' ? options.num_ctx : undefined,
+						tfs_z: params.tfs_z !== '' ? params.tfs_z : undefined,
-						num_predict: options.num_predict !== '' ? options.num_predict : undefined
+						num_ctx: params.num_ctx !== '' ? params.num_ctx : undefined,
+						max_tokens: params.max_tokens !== '' ? params.max_tokens : undefined
 					},
 					keepAlive: keepAlive ? (isNaN(keepAlive) ? keepAlive : parseInt(keepAlive)) : undefined
 				});

src/lib/components/chat/Settings/Interface.svelte

@@ -104,23 +104,18 @@
 			promptSuggestions = $config?.default_prompt_suggestions;
 		}
 
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
+		titleAutoGenerate = $settings?.title?.auto ?? true;
-
+		titleAutoGenerateModel = $settings?.title?.model ?? '';
-		titleAutoGenerate = settings?.title?.auto ?? true;
+		titleAutoGenerateModelExternal = $settings?.title?.modelExternal ?? '';
-		titleAutoGenerateModel = settings?.title?.model ?? '';
-		titleAutoGenerateModelExternal = settings?.title?.modelExternal ?? '';
 		titleGenerationPrompt =
-			settings?.title?.prompt ??
+			$settings?.title?.prompt ??
-			$i18n.t(
+			`Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title': {{prompt}}`;
-				"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':"
+		responseAutoCopy = $settings.responseAutoCopy ?? false;
-			) + ' {{prompt}}';
+		showUsername = $settings.showUsername ?? false;
-
+		chatBubble = $settings.chatBubble ?? true;
-		responseAutoCopy = settings.responseAutoCopy ?? false;
+		fullScreenMode = $settings.fullScreenMode ?? false;
-		showUsername = settings.showUsername ?? false;
+		splitLargeChunks = $settings.splitLargeChunks ?? false;
-		chatBubble = settings.chatBubble ?? true;
+		chatDirection = $settings.chatDirection ?? 'LTR';
-		fullScreenMode = settings.fullScreenMode ?? false;
-		splitLargeChunks = settings.splitLargeChunks ?? false;
-		chatDirection = settings.chatDirection ?? 'LTR';
 	});
 </script>
 

src/lib/components/chat/Settings/Models.svelte

@@ -1,5 +1,4 @@
 <script lang="ts">
-	import queue from 'async/queue';
 	import { toast } from 'svelte-sonner';
 
 	import {
@@ -12,32 +11,20 @@
 		cancelOllamaRequest,
 		uploadModel
 	} from '$lib/apis/ollama';
+
 	import { WEBUI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
-	import { WEBUI_NAME, models, MODEL_DOWNLOAD_POOL, user } from '$lib/stores';
+	import { WEBUI_NAME, models, MODEL_DOWNLOAD_POOL, user, config } from '$lib/stores';
 	import { splitStream } from '$lib/utils';
 	import { onMount, getContext } from 'svelte';
-	import { addLiteLLMModel, deleteLiteLLMModel, getLiteLLMModelInfo } from '$lib/apis/litellm';
+
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
 
 	const i18n = getContext('i18n');
 
 	export let getModels: Function;
 
-	let showLiteLLM = false;
-	let showLiteLLMParams = false;
 	let modelUploadInputElement: HTMLInputElement;
-	let liteLLMModelInfo = [];
-
-	let liteLLMModel = '';
-	let liteLLMModelName = '';
-	let liteLLMAPIBase = '';
-	let liteLLMAPIKey = '';
-	let liteLLMRPM = '';
-	let liteLLMMaxTokens = '';
-
-	let deleteLiteLLMModelName = '';
-
-	$: liteLLMModelName = liteLLMModel;
 
 	// Models
 
@@ -48,7 +35,8 @@
 	let updateProgress = null;
 
 	let showExperimentalOllama = false;
-	let ollamaVersion = '';
+
+	let ollamaVersion = null;
 	const MAX_PARALLEL_DOWNLOADS = 3;
 
 	let modelTransferring = false;
@@ -70,8 +58,11 @@
 	const updateModelsHandler = async () => {
 		for (const model of $models.filter(
 			(m) =>
-				m.size != null &&
+				!(m?.preset ?? false) &&
-				(selectedOllamaUrlIdx === null ? true : (m?.urls ?? []).includes(selectedOllamaUrlIdx))
+				m.owned_by === 'ollama' &&
+				(selectedOllamaUrlIdx === null
+					? true
+					: (m?.ollama?.urls ?? []).includes(selectedOllamaUrlIdx))
 		)) {
 			console.log(model);
 
@@ -439,60 +430,9 @@
 		}
 	};
 
-	const addLiteLLMModelHandler = async () => {
-		if (!liteLLMModelInfo.find((info) => info.model_name === liteLLMModelName)) {
-			const res = await addLiteLLMModel(localStorage.token, {
-				name: liteLLMModelName,
-				model: liteLLMModel,
-				api_base: liteLLMAPIBase,
-				api_key: liteLLMAPIKey,
-				rpm: liteLLMRPM,
-				max_tokens: liteLLMMaxTokens
-			}).catch((error) => {
-				toast.error(error);
-				return null;
-			});
-
-			if (res) {
-				if (res.message) {
-					toast.success(res.message);
-				}
-			}
-		} else {
-			toast.error($i18n.t(`Model {{modelName}} already exists.`, { modelName: liteLLMModelName }));
-		}
-
-		liteLLMModelName = '';
-		liteLLMModel = '';
-		liteLLMAPIBase = '';
-		liteLLMAPIKey = '';
-		liteLLMRPM = '';
-		liteLLMMaxTokens = '';
-
-		liteLLMModelInfo = await getLiteLLMModelInfo(localStorage.token);
-		models.set(await getModels());
-	};
-
-	const deleteLiteLLMModelHandler = async () => {
-		const res = await deleteLiteLLMModel(localStorage.token, deleteLiteLLMModelName).catch(
-			(error) => {
-				toast.error(error);
-				return null;
-			}
-		);
-
-		if (res) {
-			if (res.message) {
-				toast.success(res.message);
-			}
-		}
-
-		deleteLiteLLMModelName = '';
-		liteLLMModelInfo = await getLiteLLMModelInfo(localStorage.token);
-		models.set(await getModels());
-	};
-
 	onMount(async () => {
+		await Promise.all([
+			(async () => {
 				OLLAMA_URLS = await getOllamaUrls(localStorage.token).catch((error) => {
 					toast.error(error);
 					return [];
@@ -501,15 +441,17 @@
 				if (OLLAMA_URLS.length > 0) {
 					selectedOllamaUrlIdx = 0;
 				}
-
+			})(),
+			(async () => {
 				ollamaVersion = await getOllamaVersion(localStorage.token).catch((error) => false);
-		liteLLMModelInfo = await getLiteLLMModelInfo(localStorage.token);
+			})()
+		]);
 	});
 </script>
 
 <div class="flex flex-col h-full justify-between text-sm">
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll h-[24rem]">
-		{#if ollamaVersion}
+		{#if ollamaVersion !== null}
 			<div class="space-y-2 pr-1.5">
 				<div class="text-sm font-medium">{$i18n.t('Manage Ollama Models')}</div>
 
@@ -587,24 +529,28 @@
 											viewBox="0 0 24 24"
 											fill="currentColor"
 											xmlns="http://www.w3.org/2000/svg"
-											><style>
+										>
+											<style>
 												.spinner_ajPY {
 													transform-origin: center;
 													animation: spinner_AtaB 0.75s infinite linear;
 												}
+
 												@keyframes spinner_AtaB {
 													100% {
 														transform: rotate(360deg);
 													}
 												}
-											</style><path
+											</style>
+											<path
 												d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
 												opacity=".25"
-											/><path
+											/>
+											<path
 												d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
 												class="spinner_ajPY"
-											/></svg
+											/>
-										>
+										</svg>
 									</div>
 								{:else}
 									<svg
@@ -703,9 +649,12 @@
 									{#if !deleteModelTag}
 										<option value="" disabled selected>{$i18n.t('Select a model')}</option>
 									{/if}
-									{#each $models.filter((m) => m.size != null && (selectedOllamaUrlIdx === null ? true : (m?.urls ?? []).includes(selectedOllamaUrlIdx))) as model}
+									{#each $models.filter((m) => !(m?.preset ?? false) && m.owned_by === 'ollama' && (selectedOllamaUrlIdx === null ? true : (m?.ollama?.urls ?? []).includes(selectedOllamaUrlIdx))) as model}
 										<option value={model.name} class="bg-gray-100 dark:bg-gray-700"
-											>{model.name + ' (' + (model.size / 1024 ** 3).toFixed(1) + ' GB)'}</option
+											>{model.name +
+												' (' +
+												(model.ollama.size / 1024 ** 3).toFixed(1) +
+												' GB)'}</option
 										>
 									{/each}
 								</select>
@@ -833,24 +782,28 @@
 													viewBox="0 0 24 24"
 													fill="currentColor"
 													xmlns="http://www.w3.org/2000/svg"
-													><style>
+												>
+													<style>
 														.spinner_ajPY {
 															transform-origin: center;
 															animation: spinner_AtaB 0.75s infinite linear;
 														}
+
 														@keyframes spinner_AtaB {
 															100% {
 																transform: rotate(360deg);
 															}
 														}
-													</style><path
+													</style>
+													<path
 														d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
 														opacity=".25"
-													/><path
+													/>
+													<path
 														d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
 														class="spinner_ajPY"
-													/></svg
+													/>
-												>
+												</svg>
 											</div>
 										{:else}
 											<svg
@@ -929,203 +882,14 @@
 					{/if}
 				</div>
 			</div>
-			<hr class=" dark:border-gray-700 my-2" />
+		{:else if ollamaVersion === false}
-		{/if}
+			<div>Ollama Not Detected</div>
-
+		{:else}
-		<div class=" space-y-3">
+			<div class="flex h-full justify-center">
-			<div class="mt-2 space-y-3 pr-1.5">
+				<div class="my-auto">
-				<div>
+					<Spinner className="size-6" />
-					<div class="mb-2">
-						<div class="flex justify-between items-center text-xs">
-							<div class=" text-sm font-medium">{$i18n.t('Manage LiteLLM Models')}</div>
-							<button
-								class=" text-xs font-medium text-gray-500"
-								type="button"
-								on:click={() => {
-									showLiteLLM = !showLiteLLM;
-								}}>{showLiteLLM ? $i18n.t('Hide') : $i18n.t('Show')}</button
-							>
-						</div>
-					</div>
-
-					{#if showLiteLLM}
-						<div>
-							<div class="flex justify-between items-center text-xs">
-								<div class=" text-sm font-medium">{$i18n.t('Add a model')}</div>
-								<button
-									class=" text-xs font-medium text-gray-500"
-									type="button"
-									on:click={() => {
-										showLiteLLMParams = !showLiteLLMParams;
-									}}
-									>{showLiteLLMParams
-										? $i18n.t('Hide Additional Params')
-										: $i18n.t('Show Additional Params')}</button
-								>
-							</div>
-						</div>
-
-						<div class="my-2 space-y-2">
-							<div class="flex w-full mb-1.5">
-								<div class="flex-1 mr-2">
-									<input
-										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-										placeholder={$i18n.t('Enter LiteLLM Model (litellm_params.model)')}
-										bind:value={liteLLMModel}
-										autocomplete="off"
-									/>
-								</div>
-
-								<button
-									class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
-									on:click={() => {
-										addLiteLLMModelHandler();
-									}}
-								>
-									<svg
-										xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 16 16"
-										fill="currentColor"
-										class="w-4 h-4"
-									>
-										<path
-											d="M8.75 3.75a.75.75 0 0 0-1.5 0v3.5h-3.5a.75.75 0 0 0 0 1.5h3.5v3.5a.75.75 0 0 0 1.5 0v-3.5h3.5a.75.75 0 0 0 0-1.5h-3.5v-3.5Z"
-										/>
-									</svg>
-								</button>
-							</div>
-
-							{#if showLiteLLMParams}
-								<div>
-									<div class=" mb-1.5 text-sm font-medium">{$i18n.t('Model Name')}</div>
-									<div class="flex w-full">
-										<div class="flex-1">
-											<input
-												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-												placeholder="Enter Model Name (model_name)"
-												bind:value={liteLLMModelName}
-												autocomplete="off"
-											/>
-										</div>
-									</div>
-								</div>
-
-								<div>
-									<div class=" mb-1.5 text-sm font-medium">{$i18n.t('API Base URL')}</div>
-									<div class="flex w-full">
-										<div class="flex-1">
-											<input
-												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-												placeholder={$i18n.t(
-													'Enter LiteLLM API Base URL (litellm_params.api_base)'
-												)}
-												bind:value={liteLLMAPIBase}
-												autocomplete="off"
-											/>
-										</div>
-									</div>
-								</div>
-
-								<div>
-									<div class=" mb-1.5 text-sm font-medium">{$i18n.t('API Key')}</div>
-									<div class="flex w-full">
-										<div class="flex-1">
-											<input
-												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-												placeholder={$i18n.t('Enter LiteLLM API Key (litellm_params.api_key)')}
-												bind:value={liteLLMAPIKey}
-												autocomplete="off"
-											/>
-										</div>
-									</div>
-								</div>
-
-								<div>
-									<div class="mb-1.5 text-sm font-medium">{$i18n.t('API RPM')}</div>
-									<div class="flex w-full">
-										<div class="flex-1">
-											<input
-												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-												placeholder={$i18n.t('Enter LiteLLM API RPM (litellm_params.rpm)')}
-												bind:value={liteLLMRPM}
-												autocomplete="off"
-											/>
-										</div>
-									</div>
-								</div>
-
-								<div>
-									<div class="mb-1.5 text-sm font-medium">{$i18n.t('Max Tokens')}</div>
-									<div class="flex w-full">
-										<div class="flex-1">
-											<input
-												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-												placeholder={$i18n.t('Enter Max Tokens (litellm_params.max_tokens)')}
-												bind:value={liteLLMMaxTokens}
-												type="number"
-												min="1"
-												autocomplete="off"
-											/>
-										</div>
-									</div>
-								</div>
-							{/if}
-						</div>
-
-						<div class="mb-2 text-xs text-gray-400 dark:text-gray-500">
-							{$i18n.t('Not sure what to add?')}
-							<a
-								class=" text-gray-300 font-medium underline"
-								href="https://litellm.vercel.app/docs/proxy/configs#quick-start"
-								target="_blank"
-							>
-								{$i18n.t('Click here for help.')}
-							</a>
-						</div>
-
-						<div>
-							<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Delete a model')}</div>
-							<div class="flex w-full">
-								<div class="flex-1 mr-2">
-									<select
-										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-										bind:value={deleteLiteLLMModelName}
-										placeholder={$i18n.t('Select a model')}
-									>
-										{#if !deleteLiteLLMModelName}
-											<option value="" disabled selected>{$i18n.t('Select a model')}</option>
-										{/if}
-										{#each liteLLMModelInfo as model}
-											<option value={model.model_name} class="bg-gray-100 dark:bg-gray-700"
-												>{model.model_name}</option
-											>
-										{/each}
-									</select>
-								</div>
-								<button
-									class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
-									on:click={() => {
-										deleteLiteLLMModelHandler();
-									}}
-								>
-									<svg
-										xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 16 16"
-										fill="currentColor"
-										class="w-4 h-4"
-									>
-										<path
-											fill-rule="evenodd"
-											d="M5 3.25V4H2.75a.75.75 0 0 0 0 1.5h.3l.815 8.15A1.5 1.5 0 0 0 5.357 15h5.285a1.5 1.5 0 0 0 1.493-1.35l.815-8.15h.3a.75.75 0 0 0 0-1.5H11v-.75A2.25 2.25 0 0 0 8.75 1h-1.5A2.25 2.25 0 0 0 5 3.25Zm2.25-.75a.75.75 0 0 0-.75.75V4h3v-.75a.75.75 0 0 0-.75-.75h-1.5ZM6.05 6a.75.75 0 0 1 .787.713l.275 5.5a.75.75 0 0 1-1.498.075l-.275-5.5A.75.75 0 0 1 6.05 6Zm3.9 0a.75.75 0 0 1 .712.787l-.275 5.5a.75.75 0 0 1-1.498-.075l.275-5.5a.75.75 0 0 1 .786-.711Z"
-											clip-rule="evenodd"
-										/>
-									</svg>
-								</button>
 				</div>
 			</div>
 		{/if}
 	</div>
 </div>
-		</div>
-	</div>
-</div>

src/lib/components/chat/Settings/Personalization.svelte

@@ -19,8 +19,7 @@
 	let enableMemory = false;
 
 	onMount(async () => {
-		let settings = JSON.parse(localStorage.getItem('settings') ?? '{}');
+		enableMemory = $settings?.memory ?? false;
-		enableMemory = settings?.memory ?? false;
 	});
 </script>
 

src/lib/components/chat/Settings/Personalization/ManageModal.svelte

@@ -54,7 +54,7 @@
 				class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6 h-[28rem] max-h-screen outline outline-1 rounded-xl outline-gray-100 dark:outline-gray-800 mb-4 mt-1"
 			>
 				{#if memories.length > 0}
-					<div class="text-left text-sm w-full mb-4 max-h-[22rem] overflow-y-scroll">
+					<div class="text-left text-sm w-full mb-4 overflow-y-scroll">
 						<div class="relative overflow-x-auto">
 							<table class="w-full text-sm text-left text-gray-600 dark:text-gray-400 table-auto">
 								<thead

src/lib/components/chat/SettingsModal.svelte

@@ -3,7 +3,7 @@
 	import { toast } from 'svelte-sonner';
 	import { models, settings, user } from '$lib/stores';
 
-	import { getModels as _getModels } from '$lib/utils';
+	import { getModels as _getModels } from '$lib/apis';
 
 	import Modal from '../common/Modal.svelte';
 	import Account from './Settings/Account.svelte';
@@ -17,6 +17,7 @@
 	import Images from './Settings/Images.svelte';
 	import User from '../icons/User.svelte';
 	import Personalization from './Settings/Personalization.svelte';
+	import { updateUserSettings } from '$lib/apis/users';
 
 	const i18n = getContext('i18n');
 
@@ -26,7 +27,7 @@
 		console.log(updated);
 		await settings.set({ ...$settings, ...updated });
 		await models.set(await getModels());
-		localStorage.setItem('settings', JSON.stringify($settings));
+		await updateUserSettings(localStorage.token, { ui: $settings });
 	};
 
 	const getModels = async () => {

src/lib/components/chat/ShareChatModal.svelte

@@ -1,9 +1,9 @@
 <script lang="ts">
 	import { getContext, onMount } from 'svelte';
+	import { models, config } from '$lib/stores';
 
 	import { toast } from 'svelte-sonner';
 	import { deleteSharedChatById, getChatById, shareChatById } from '$lib/apis/chats';
-	import { modelfiles } from '$lib/stores';
 	import { copyToClipboard } from '$lib/utils';
 
 	import Modal from '../common/Modal.svelte';
@@ -43,9 +43,7 @@
 					tab.postMessage(
 						JSON.stringify({
 							chat: _chat,
-							modelfiles: $modelfiles.filter((modelfile) =>
+							models: $models.filter((m) => _chat.models.includes(m.id))
-								_chat.models.includes(modelfile.tagName)
-							)
 						}),
 						'*'
 					);
@@ -136,6 +134,7 @@
 				<div class="flex justify-end">
 					<div class="flex flex-col items-end space-x-1 mt-1.5">
 						<div class="flex gap-1">
+							{#if $config?.features.enable_community_sharing}
 								<button
 									class=" self-center px-3.5 py-2 rounded-xl text-sm font-medium bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-white"
 									type="button"
@@ -146,6 +145,7 @@
 								>
 									{$i18n.t('Share to OpenWebUI Community')}
 								</button>
+							{/if}
 
 							<button
 								class=" self-center flex items-center gap-1 px-3.5 py-2 rounded-xl text-sm font-medium bg-emerald-600 hover:bg-emerald-500 text-white"