### 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>
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140)
### 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?
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?
Add mcp self-host mode, a complement of #7084.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add MCP support with a client example.
Issue link: #4344
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: extend S3 storage compatibility and add knowledge base ID prefix (#6355)
### What problem does this PR solve?
- Added support for S3-compatible protocols.
- Enabled the use of knowledge base ID as a file prefix when storing
files in S3.
- Updated docker/README.md to include detailed S3 and OSS configuration
instructions.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Consolidate entrypoint to support broader deployment scenarios (#6566)
### What problem does this PR solve?
This PR gives better control over how we distribute which service will
be loaded. With this approach, we can create containers to run only the
web server and others to run the task executor. It also introduces the
unique ID per task executor host, this will be important when scaling
task executors horizontally, considering unique task executor ids will
be required.
This new `entrypoint.sh` maintains the default behavior of starting the
web server and task executor in the same host.
### 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):
This PR updates the MySQL container configuration by setting the
parameter --binlog_expire_logs_seconds to 604800 seconds (7 days). This
change ensures that MySQL automatically purges binary logs older than 7
days, helping to conserve disk space and maintain precise log
management.
### 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] 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?
Removed set_entity and set_relation to avoid accessing doc engine during
graph computation.
Introduced GraphChange to avoid writing unchanged chunks.
### Type of change
- [x] Performance Improvement
Feat: Add user registration toggle feature (#6327)
### What problem does this PR solve?
Feat: Add user registration toggle feature. Added a user registration
toggle REGISTER_ENABLED in the settings and .env config file. The user
creation interface now checks the state of this toggle to control the
enabling and disabling of the user registration feature.
the front-end implementation is done, the registration button does not
appear if registration is not allowed. I did the actual tests on my
local server and it worked smoothly.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Feat: Add the functionality to load environment variables from a .env file (#6331)
### Change Content
- A new function `load_env_file` has been added to load environment
variables from a .env file in the current script directory.
- If the .env file exists, the variables within it will be loaded; if it
does not exist, a warning message will be output.
I found this issue while testing this pr:
https://github.com/infiniflow/ragflow/pull/6327. The locally started
server did not read the REGISTER_ENABLED variables in the .env. The
result has always been the default True
### What problem does this PR solve?
Follow the tutorial in the README.md to start from source code. base's
container that is es、redis，etc will load .env. Therefore,
`launch_backend_service.sh` should also load .env to be consistent with
the configuration of the docker container when it was started
### 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?
Add history version save
- Allows users to view and download agent files by version revision
history
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### 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):
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Refactored DocumentService.update_progress
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: better start experience PYTHONPATH in shell (#5593)
### What problem does this PR solve?
As title export PYTHONPATH in the shell
### Type of change
- [x] Refactoring
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
### What problem does this PR solve?
Introduced jemalloc.
Python uses pymalloc (which is an reimplementation of gblibc malloc) to
manage RES. It has pools for small objects to avoid returning memory to
OS aggressively. My experience is: Replacing pymalloc with
[jemalloc](https://github.com/jemalloc/jemalloc) can reduce RES and
speedup task_executor.py.
### Type of change
- [x] Performance Improvement
Fix: enhance aliyun oss access with adding prefix path (#5475)
### What problem does this PR solve?
Enhance aliyun oss access with adding prefix path.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Add configuration to choose default llm models (#5245)
### What problem does this PR solve?
This pull request includes changes to the `api/settings.py` and
`docker/service_conf.yaml.template` files to add support for default
models in the LLM configuration (specially for LIGHTEN builds). The most
important changes include adding default model configurations and
updating the initialization settings to use these defaults.
For example:
With this configuration Bedrock will be enable by default with claude
and titan embeddings.
```
user_default_llm:
factory: 'Bedrock'
api_key: '{}'
base_url: ''
default_models:
chat_model: 'anthropic.claude-3-5-sonnet-20240620-v1:0'
embedding_model: 'amazon.titan-embed-text-v2:0'
rerank_model: ''
asr_model: ''
image2text_model: ''
```
### 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?
https://github.com/infiniflow/ragflow/issues/4319
This pull request includes several changes to improve the Docker setup
and documentation for the project. The most important changes include
updating the Dockerfile to support modern versions of Rust, adding a new
Docker Compose configuration for macOS, and updating the build
instructions in the documentation.
Improvements to Docker setup:
*
[`Dockerfile`](diffhunk://#diff-dd2c0eb6ea5cfc6c4bd4eac30934e2d5746747af48fef6da689e85b752f39557L80-R107):
Added installation steps for a modern version of Rust and updated the
logic for installing the correct ODBC driver based on the architecture.
*
[`docker/docker-compose-macos.yml`](diffhunk://#diff-8e8587143bb2442c02f6dff4caa217ebbe3ba4ec8e7c23b2e568886a67b00eafR1-R56):
Added a new Docker Compose configuration file specifically for macOS,
including service dependencies, environment variables, and volume
mappings.
Updates to documentation:
*
[`docs/guides/develop/build_docker_image.mdx`](diffhunk://#diff-d6136bb897f7245aae33b0accbcf7c508ceaef005c545f9f09cad3cada840a19L44-R44):
Updated the build instructions to use the new Docker Compose
configuration for macOS instead of the previous Docker build command.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
---------
Signed-off-by: Samuel Giffard <samuel.giffard@mytomorrows.com>
### What problem does this PR solve?
Bump infinity to v0.6.0-dev2. Close #4477
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Bring `STORAGE_IMPL` back in `rag/svr/cache_file_svr.py`
- Simplify storage connection when working with AWS S3
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Update version info to 0.15.1
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Elasticsearch disk-based shard allocator use absolute byte values instead of ratio (#4069)
### What problem does this PR solve?
Elasticsearch disk-based shard allocator use absolute byte values
instead of ratio. Close #4018
### Type of change
- [ ] Documentation Update
- [x] Refactoring
yiminghub2024
writinwaters
pyyuhao
Pierre Lafievre
yxkong
liu an
Yongteng Lei
Kevin Hu
RedBookOfMemory
Wanderson Pinto dos Santos
AdySec
Zhichang Yu
liwenju0
so95
yihong
The Wind
hy89
Omar Leonardo Sanchez Granados
Samuel GIFFARD
Kenny Dizi
Jin Hai