From 23dcbc94ef1fc7a31250f36ac8d06cbe3cc06c9e Mon Sep 17 00:00:00 2001 From: Neal Davis Date: Mon, 28 Apr 2025 13:35:09 +0800 Subject: [PATCH] feat: replace models of novita (#7360) ### What problem does this PR solve? Replace models of novita ### Type of change - [x] Other (please describe): Replace models of novita --- conf/llm_factories.json | 232 ++++++++------------------- docs/references/supported_models.mdx | 2 +- docs/release_notes.md | 2 +- rag/llm/__init__.py | 2 +- web/src/constants/llm.ts | 2 +- 5 files changed, 74 insertions(+), 166 deletions(-) diff --git a/conf/llm_factories.json b/conf/llm_factories.json index 4ec74af92..3ea0feb3a 100644 --- a/conf/llm_factories.json +++ b/conf/llm_factories.json @@ -2203,58 +2203,21 @@ ] }, { - "name": "novita.ai", + "name": "NovitaAI", "logo": "", - "tags": "LLM,IMAGE2TEXT", + "tags": "LLM,TEXT EMBEDDING", "status": "1", "llm": [ { - "llm_name": "deepseek/deepseek-r1", - "tags": "LLM,CHAT,64k", - "max_tokens": 64000, - "model_type": "chat" - }, - { - "llm_name": "deepseek/deepseek_v3", - "tags": "LLM,CHAT,64k", - "max_tokens": 64000, - "model_type": "chat" - }, - { - "llm_name": "deepseek/deepseek-r1-distill-llama-70b", - "tags": "LLM,CHAT,64k", - "max_tokens": 64000, - "model_type": "chat" - }, - { - "llm_name": "deepseek/deepseek-r1-distill-qwen-32b", - "tags": "LLM,CHAT,64k", - "max_tokens": 64000, - "model_type": "chat" - }, - { - "llm_name": "deepseek/deepseek-r1-distill-qwen-14b", - "tags": "LLM,CHAT,64k", - "max_tokens": 64000, - "model_type": "chat" - }, - { - "llm_name": "deepseek/deepseek-r1-distill-llama-8b", + "llm_name": "qwen/qwen2.5-7b-instruct", "tags": "LLM,CHAT,32k", "max_tokens": 32000, "model_type": "chat" }, { - "llm_name": "meta-llama/llama-3.3-70b-instruct", - "tags": "LLM,CHAT,128k", - "max_tokens": 131072, - "model_type": "chat", - "is_tools": true - }, - { - "llm_name": "meta-llama/llama-3.2-11b-vision-instruct", - "tags": "LLM,CHAT,32k", - "max_tokens": 32768, + "llm_name": "meta-llama/llama-3.2-1b-instruct", + "tags": "LLM,CHAT,131k", + "max_tokens": 131000, "model_type": "chat" }, { @@ -2264,15 +2227,21 @@ "model_type": "chat" }, { - "llm_name": "meta-llama/llama-3.2-1b-instruct", + "llm_name": "thudm/glm-4-9b-0414", "tags": "LLM,CHAT,32k", - "max_tokens": 32768, + "max_tokens": 32000, "model_type": "chat" }, { - "llm_name": "meta-llama/llama-3.1-70b-instruct", + "llm_name": "thudm/glm-z1-9b-0414", "tags": "LLM,CHAT,32k", - "max_tokens": 32768, + "max_tokens": 32000, + "model_type": "chat" + }, + { + "llm_name": "meta-llama/llama-3.1-8b-instruct-bf16", + "tags": "LLM,CHAT,8k", + "max_tokens": 8192, "model_type": "chat", "is_tools": true }, @@ -2284,55 +2253,15 @@ "is_tools": true }, { - "llm_name": "meta-llama/llama-3.1-8b-instruct-bf16", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat", - "is_tools": true - }, - { - "llm_name": "meta-llama/llama-3-70b-instruct", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat", - "is_tools": true - }, - { - "llm_name": "meta-llama/llama-3-8b-instruct", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat", - "is_tools": true - }, - { - "llm_name": "qwen/qwen-2.5-72b-instruct", - "tags": "LLM,CHAT,32k", - "max_tokens": 32000, - "model_type": "chat", - "is_tools": true - }, - { - "llm_name": "qwen/qwen-2-vl-72b-instruct", - "tags": "LLM,IMAGE2TEXT,32k", - "max_tokens": 32768, - "model_type": "image2text" - }, - { - "llm_name": "qwen/qwen-2-7b-instruct", - "tags": "LLM,CHAT,32k", - "max_tokens": 32768, - "model_type": "chat" - }, - { - "llm_name": "mistralai/mistral-nemo", + "llm_name": "deepseek/deepseek-v3-0324", "tags": "LLM,CHAT,128k", - "max_tokens": 131072, + "max_tokens": 128000, "model_type": "chat" }, { - "llm_name": "mistralai/mistral-7b-instruct", - "tags": "LLM,CHAT,32k", - "max_tokens": 32768, + "llm_name": "deepseek/deepseek-r1-turbo", + "tags": "LLM,CHAT,64k", + "max_tokens": 64000, "model_type": "chat" }, { @@ -2342,82 +2271,61 @@ "model_type": "chat" }, { - "llm_name": "sao10k/l3-70b-euryale-v2.1", + "llm_name": "meta-llama/llama-3.3-70b-instruct", + "tags": "LLM,CHAT,128k", + "max_tokens": 131072, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "deepseek/deepseek-r1-distill-llama-8b", + "tags": "LLM,CHAT,32k", + "max_tokens": 32000, + "model_type": "chat" + }, + { + "llm_name": "mistralai/mistral-nemo", + "tags": "LLM,CHAT,128k", + "max_tokens": 131072, + "model_type": "chat" + }, + { + "llm_name": "meta-llama/llama-3-8b-instruct", "tags": "LLM,CHAT,8k", "max_tokens": 8192, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "deepseek/deepseek-v3-turbo", + "tags": "LLM,CHAT,64k", + "max_tokens": 64000, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "mistralai/mistral-7b-instruct", + "tags": "LLM,CHAT,32k", + "max_tokens": 32768, "model_type": "chat" }, { - "llm_name": "sao10k/l3-8b-lunaris", - "tags": "LLM,CHAT,8k", + "llm_name": "deepseek/deepseek-r1", + "tags": "LLM,CHAT,64k", + "max_tokens": 64000, + "model_type": "chat" + }, + { + "llm_name": "deepseek/deepseek-r1-distill-qwen-14b", + "tags": "LLM,CHAT,64k", + "max_tokens": 64000, + "model_type": "chat" + }, + { + "llm_name": "baai/bge-m3", + "tags": "TEXT EMBEDDING,8K", "max_tokens": 8192, - "model_type": "chat" - }, - { - "llm_name": "sao10k/l31-70b-euryale-v2.2", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat" - }, - { - "llm_name": "nousresearch/hermes-2-pro-llama-3-8b", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat" - }, - { - "llm_name": "nousresearch/nous-hermes-llama2-13b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" - }, - { - "llm_name": "openchat/openchat-7b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" - }, - { - "llm_name": "gryphe/mythomax-l2-13b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" - }, - { - "llm_name": "microsoft/wizardlm-2-8x22b", - "tags": "LLM,CHAT,65k", - "max_tokens": 65535, - "model_type": "chat" - }, - { - "llm_name": "google/gemma-2-9b-it", - "tags": "LLM,CHAT,8k", - "max_tokens": 8192, - "model_type": "chat" - }, - { - "llm_name": "cognitivecomputations/dolphin-mixtral-8x22b", - "tags": "LLM,CHAT,16k", - "max_tokens": 16000, - "model_type": "chat" - }, - { - "llm_name": "jondurbin/airoboros-l2-70b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" - }, - { - "llm_name": "teknium/openhermes-2.5-mistral-7b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" - }, - { - "llm_name": "sophosympatheia/midnight-rose-70b", - "tags": "LLM,CHAT,4k", - "max_tokens": 4096, - "model_type": "chat" + "model_type": "embedding" } ] }, diff --git a/docs/references/supported_models.mdx b/docs/references/supported_models.mdx index 202db8392..04aa6ce04 100644 --- a/docs/references/supported_models.mdx +++ b/docs/references/supported_models.mdx @@ -37,7 +37,7 @@ A complete list of models supported by RAGFlow, which will continue to expand. | Mistral | :heavy_check_mark: | :heavy_check_mark: | | | | | | ModelScope | :heavy_check_mark: | | | | | | | Moonshot | :heavy_check_mark: | | | :heavy_check_mark: | | | -| novita.ai | :heavy_check_mark: | | | | | | +| Novita AI | :heavy_check_mark: | :heavy_check_mark: | | | | | | NVIDIA | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | | | Ollama | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | | | OpenAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | diff --git a/docs/release_notes.md b/docs/release_notes.md index ff0140438..f3790f9f0 100644 --- a/docs/release_notes.md +++ b/docs/release_notes.md @@ -412,7 +412,7 @@ Released on August 26, 2024. - Incorporates monitoring for the task executor. - Introduces Agent tools **GitHub**, **DeepL**, **BaiduFanyi**, **QWeather**, and **GoogleScholar**. - Supports chunking of EML files. -- Supports more LLMs or model services: **GPT-4o-mini**, **PerfXCloud**, **TogetherAI**, **Upstage**, **Novita.AI**, **01.AI**, **SiliconFlow**, **PPIO**, **XunFei Spark**, **Baidu Yiyan**, and **Tencent Hunyuan**. +- Supports more LLMs or model services: **GPT-4o-mini**, **PerfXCloud**, **TogetherAI**, **Upstage**, **Novita AI**, **01.AI**, **SiliconFlow**, **PPIO**, **XunFei Spark**, **Baidu Yiyan**, and **Tencent Hunyuan**. ## v0.9.0 diff --git a/rag/llm/__init__.py b/rag/llm/__init__.py index 9e7945d04..ce78e2914 100644 --- a/rag/llm/__init__.py +++ b/rag/llm/__init__.py @@ -234,7 +234,7 @@ ChatModel = { "TogetherAI": TogetherAIChat, "PerfXCloud": PerfXCloudChat, "Upstage": UpstageChat, - "novita.ai": NovitaAIChat, + "NovitaAI": NovitaAIChat, "SILICONFLOW": SILICONFLOWChat, "PPIO": PPIOChat, "01.AI": YiChat, diff --git a/web/src/constants/llm.ts b/web/src/constants/llm.ts index dcb37b514..26f092731 100644 --- a/web/src/constants/llm.ts +++ b/web/src/constants/llm.ts @@ -28,7 +28,7 @@ export enum LLMFactory { TogetherAI = 'TogetherAI', PerfXCloud = 'PerfXCloud', Upstage = 'Upstage', - NovitaAI = 'novita.ai', + NovitaAI = 'NovitaAI', SILICONFLOW = 'SILICONFLOW', PPIO = 'PPIO', ZeroOneAI = '01.AI',