### What problem does this PR solve?
当前graphrag的LOOP_PROMPT，会导致模型输出Y之后，继续补充了实体和关系，比较浪费时间。参照[graph
rag](https://github.com/microsoft/graphrag/blob/main/graphrag/prompts/index/extract_graph.py)最新的代码，修改了LOOP_PROMPT，经过验证，修改后可以稳定的输出Y停止。
Currently, GraphRAG’s LOOP_PROMPT causes the model to keep appending
entities and relationships even after outputting “Y,” which wastes time.
Referring to the latest code in
[graphRAG](https://github.com/microsoft/graphrag/blob/main/graphrag/prompts/index/extract_graph.py),
I modified the LOOP_PROMPT, and after verification the updated prompt
reliably outputs “Y” and stops.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
### What problem does this PR solve?
0.18.0 mcp server can not start with upgrade from 0.17.2 or new install
except rebuild all docker
Close#7321
mcp server can not start auto from docker :
2025-04-25 17:30:44,512 INFO 25 task_executor_2a9f3e2de99a_0 reported
heartbeat: {"name": "task_executor_2a9f3e2de99a_0", "now":
"2025-04-25T17:30:44.509+08:00", "boot_at":
"2025-04-25T16:43:33.038+08:00", "pending": 0, "lag": 0, "done": 0,
"failed": 0, "current": {}}
usage: server.py [-h] [--base_url BASE_URL] [--host HOST] [--port PORT]
[--mode MODE] [--api_key API_KEY]
server.py: error: unrecognized arguments:
problem:
server.py in docker start arguments not correct , so mcp server start
fail
reason:
```
1. docker-copose.yaml
example - --mcp-host-api-key="ragflow-12345678" is wrong. do not add "" to key or it says:"api-key wrong"
2.docker file entrypoint.sh can not translate config to exec command , we need mapping file from host to docker
- ./entrypoint.sh:/ragflow/entrypoint.sh
3.just add one code raw fix all probelm
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
- [x] Performance Improvement
---------
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
In the generate_confirmation_token method, a spelling error was found
with 'tenent_id'. The correct spelling should be 'tenant_id'.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: shengliang xiao <shengliangxiao2024@gmail.com>
With current config will get error "Fail to access model(gemma-7b-it)
using this api key"
Since the model has been removed, according to Groq official document:
https://console.groq.com/docs/models
### Type of change
- [ x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Batch operations on documents in a dataset #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Enhance capability of `list_docs`.
Breaking change: change method from `GET` to `POST`.
### Type of change
- [x] Refactoring
- [x] Enhancement with breaking change
### What problem does this PR solve?
Feat: Create empty document. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Filter document by running status and file type. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Save document metadata #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6984
1. Markdown parser supports get pictures
2. For Native, when handling Markdown, it will handle images
3. improve merge and
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Feat: Save the configuration information of the knowledge base document
#3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display the document configuration dialog with shadcn #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR adds the support for latest OpenSearch2.19.1 as the store engine
& search engine option for RAGFlow.
### Main Benefit
1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is
much better than Elasticsearch
2. For search, OpenSearch2.19.1 supports full-text
search、vector_search、hybrid_search those are similar with Elasticsearch
on schema
3. For store, OpenSearch2.19.1 stores text、vector those are quite
simliar with Elasticsearch on schema
### Changes
- Support opensearch_python_connetor. I make a lot of adaptions since
the schema and api/method between ES and Opensearch differs in many
ways(especially the knn_search has a significant gap) :
rag/utils/opensearch_coon.py
- Support static config adaptions by changing:
conf/service_conf.yaml、api/settings.py、rag/settings.py
- Supprt some store&search schema changes between OpenSearch and ES:
conf/os_mapping.json
- Support OpenSearch python sdk : pyproject.toml
- Support docker config for OpenSearch2.19.1 :
docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template
### How to use
- I didn't change the priority that ES as the default doc/search engine.
Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it
will work.
### Others
Our team tested a lot of docs in our environment by using OpenSearch as
the vector database ,it works very well.
All the conifg for OpenSearch is necessary.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Feat: Delete and rename files in the knowledge base #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display document parsing status #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The lock is not released correctly when task_exectuor is abnormal
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Some models force thinking, resulting in the absence of the think tag in
the returned content
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Sometimes after we commit the code and open the PR the CI pipeline fails
in Ruff checks. Including a pre-commit we can identify this problem
early and avoid time loss.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [X] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix the entrypoint file from the docker container to solve #7249
Here is the important part from the logs:
```
docker logs -f ragflow-server
...
usage: server.py [-h] [--base_url BASE_URL] [--host HOST] [--port PORT]
[--mode MODE] [--api_key API_KEY]
server.py: error: unrecognized arguments:
...
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
This PR fixes an issue with the MCP server configuration in RAGFlow's
Docker deployment where:
1. Incorrect parameter naming (`--mcp--host-api-key` with double
hyphens) caused server startup failures
2. Port binding conflicts occurred due to unexposed MCP ports in Docker
3. Inconsistent host addressing between `0.0.0.0` and `127.0.0.1` led to
connectivity issues
The changes ensure proper MCP server initialization and reliable
inter-service communication.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### Key Changes
1. **Parameter Correction**:
- Fixed `--mcp--host-api-key` → `--mcp-host-api-key`
### What problem does this PR solve?
Feat: Deleting files in batches. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The knowledge_graph chunk method is deprecated and should no longer be
used. #7184.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
Enhance capability of `list_kbs`.
Breaking change: change method from `GET` to `POST`.
### Type of change
- [x] Refactoring
- [x] Enhancement with breaking change
### What problem does this PR solve?
Feat: Show the owner of this knowledge base on the list card. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Even if the knowledge base has slices, the chunk method can be
changed #7115
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: Knowledge Graph Extraction Conflict Between Dataset-Level and
File-Specific Configurations #7198
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix retrieval testing wrong pagination. #7171
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Put the knowledge base list related hooks into use-knowledge-request.ts
#3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Move langfuse configuration to api page #6155
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Filter the knowledge base list using owner #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR changes Redis to be a statefulset. In some situation when we
Redis pod gets rescheduled to another Node, it gets stuck in pending
state due to the PVC attached to another Kubernetes node.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [X] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
When parsing pptx files, some shapes do not contain the `shape_type`
attribute, which causes the original code to throw an exception during
extraction, leading to failure in content extraction. This optimization
introduces handling logic for such anomalous shapes, providing a safer
and more robust processing mechanism.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
