Perf: Increase database connection pool size (#7559)
### What problem does this PR solve?
1. The MySQL instance is configured with max_connections=1000,
but our connection pool was limited to max_connections: 100.
This mismatch caused connection pool exhaustion during performance
testing.
2. Increase stale_timeout to resolve #6548
### Type of change
- [x] Performance Improvement
fix bug #7309 deepseek-ai/deepseek-vl2 model can not be select as a VL model to parse pdf image (#7312)
### What problem does this PR solve?
fix deepseek-ai/deepseek-vl2 model can not be select as a VL model to
parse pdf image . And add other vl models config from siliconflow
_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):
---------
Co-authored-by: unknown <taoshi.ln@chinatelecom.cn>
Feat: Add `/login/channels` route and improve auth logic for frontend third-party login integration (#7521)
### What problem does this PR solve?
Add `/login/channels` route and improve auth logic to support frontend
integration with third-party login providers:
- Add `/login/channels` route to provide authentication channel list
with `display_name` and `icon`
- Optimize user info parsing logic by prioritizing `avatar_url` and
falling back to `picture`
- Simplify OIDC token validation by removing unnecessary `kid` checks
- Ensure `client_id` is safely cast to string during `audience`
validation
- Fix typo
---
- Related pull request: #7379
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Qwen3 and more LLMs.
Close #7296
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Feat: Add support for OAuth2 and OpenID Connect (OIDC) authentication (#7379)
### What problem does this PR solve?
Add support for OAuth2 and OpenID Connect (OIDC) authentication,
allowing OAuth/OIDC authentication using the specified routes:
- `/login/<channel>`: Initiates the OAuth flow for the specified channel
- `/oauth/callback/<channel>`: Handles the OAuth callback after
successful authentication
The callback URL should be configured in your OAuth provider as:
```
https://your-app.com/oauth/callback/<channel>
```
For detailed instructions on configuring **service_conf.yaml.template**,
see: `./api/apps/auth/README.md#usage`.
- Related issues
#3495
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
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)
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>
Fix knowledge_graph_kwd on infinity. Close #6476 and #6624 (#6651)
### What problem does this PR solve?
Fix knowledge_graph_kwd on infinity. Close #6476 and #6624
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Chenzy <chenzy901@gmail.com>
### 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
### What problem does this PR solve?
AWS Bedrock has made deepseek-r1 available on its serverless inference.
This adds the R1 serverless model for use via the bedrock model
abilities.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
use to_df replace to_pl when get infinity Result (#5604)
### 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] Performance Improvement
---------
Co-authored-by: wangwei <dwxiayi@163.com>
### What problem does this PR solve?
This patch fix most of the issues like #4853#5038 and so on
the root reason is that we need to add the hostname to the `/etc/hosts`
which is not wrote in main README
and the code side read `conf/service_conf.yaml` as settings
and its hard for developers to debug, this patch fix it, or maybe can
discuss better solution here
### Type of change
- [x] Refactoring
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Support downloading models from ModelScope Community. (#5073)
This PR supports downloading models from ModelScope. The main
modifications are as follows:
-New Feature (non-breaking change which adds functionality)
-Documentation Update
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
The current design is not well-suited for multimodal models, as each
model can only be configured for a single purpose—either chat or
Img2txt. To work around this limitation, we use model aliases such as
gpt-4o-mini and gpt-4o-mini-2024-07-18.
To fix this, this PR allows specifying the Img2txt model by tag instead
of model_type.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Add a LLM provider: PPIO
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Add GPUStack as a new model provider.
[GPUStack](https://github.com/gpustack/gpustack) is an open-source GPU
cluster manager for running LLMs. Currently, locally deployed models in
GPUStack cannot integrate well with RAGFlow. GPUStack provides both
OpenAI compatible APIs (Models / Chat Completions / Embeddings /
Speech2Text / TTS) and other APIs like Rerank. We would like to use
GPUStack as a model provider in ragflow.
[GPUStack Docs](https://docs.gpustack.ai/latest/quickstart/)
Related issue: https://github.com/infiniflow/ragflow/issues/4064.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Testing Instructions
1. Install GPUStack and deploy the `llama-3.2-1b-instruct` llm, `bge-m3`
text embedding model, `bge-reranker-v2-m3` rerank model,
`faster-whisper-medium` Speech-to-Text model, `cosyvoice-300m-sft` in
GPUStack.
2. Add provider in ragflow settings.
3. Testing in ragflow.
### 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
Support OpenAI gpt-4o and gpt-4o-mini for img2text (#4300)
### What problem does this PR solve?
OpenAI has deprecated the gpt-4-vision-preview model. This PR adds
support for the newer gpt-4o and gpt-4o-mini models in the img2text
feature.
This PR add addtional 4o/4o-mini entry for img2text besides original
ones. Utilized [alias](https://platform.openai.com/docs/models#gpt-4o)
model names (e.g., gpt-4o-2024-08-06) because the database schema uses
the model name as the primary key.
- [x] Other (please describe): model update
liu an
QuintinTao
Chaoxi Weng
Yongteng Lei
Neal Davis
Jason Li
pyyuhao
Kevin Hu
Zhichang Yu
Chenzy
crypticGøøse
kuro5989
汪威
Debug Doctor
yihong
hy89
yrk111222
petertc
saikidev
so95
DiamondPoirier
Alex Chen
Kenny Dizi