### What problem does this PR solve?
Add a series of qwen3 latest SOTA models:
qwen3-coder-480b-a35b-instruct, qwen3-30b-a3b-instruct-2507,
qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-instruct-2507,
qwen3-235b-a22b-thinking-2507
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix kimi-latest is not authorized.
Add kimi-thinking-preview.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
add Kimi-K2-Instruct from Tongyi-Qianwen API (#9125)
### What problem does this PR solve?
add Kimi-K2-Instruct from Tongyi-Qianwen API
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add model provider DeepInfra. This model list comes from our community.
NOTE: most endpoints haven't been tested, but they should work as OpenAI
does.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix: Adds newest Gemini models to fit google's standard API rate limits (#8970)
### What problem does this PR solve?
Adds configurations for gemini-2.5-flash and Gemini 2.5-pro models,
including tags, maximum token limits, and model types.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add Kimi model series support.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR enhances the application's capabilities by adding support for
four new Voyage embedding models (voyage-3-large, voyage-3.5,
voyage-3.5-lite, and voyage-code-3) to the `llm_factories.json`
configuration file. These models expand the available options for text
embedding tasks, enabling improved processing of text data with a
maximum token limit of 32,000. This addition addresses the need for more
diverse and specialized embedding models to support various use cases
without altering existing functionality.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add xAI provider (experimental feature, requires user feedback).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
fix opendal config 'oss_table' and 'max_allowed_packet' (#8611)
### What problem does this PR solve?
Fix the config option name of the opendal table name and setting of
'max_allowed_packet'.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: He Wang <wanghechn@qq.com>
Fix: unify opendal config key from `schema` to `scheme` (#8232)
### What problem does this PR solve?
This PR resolves the inconsistency in the opendal configuration where
both `schema` and `scheme` were used as keys. The code and
configuration file now consistently use `scheme`, which helps prevent
configuration errors and runtime issues. This change improves code
clarity and maintainability.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Additional context
- Updated both `conf/service_conf.yaml` and
`rag/utils/opendal_conn.py` to use `scheme` instead of `schema`
- No breaking changes to other configuration fields
### What problem does this PR solve?
#8074
Oss support opendal(including mysql)
### 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?
Add Qwen3-Embedding text-embedding-v4.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
change default models to buildin models
https://github.com/infiniflow/ragflow/issues/7774
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Docs: Improve oauth configuration documentation and examples (#7675)
### What problem does this PR solve?
Improve oauth configuration documentation and examples.
- Related pull requests:
- #7379
- #7553
- #7587
- Related issues:
- #3495
### Type of change
- [x] Documentation Update
Refa: Deprecate `/github_callback` in favor of `/oauth/callback/<channel>` for GitHub OAuth integration (#7587)
### What problem does this PR solve?
Deprecate `/github_callback` route in favor of
`/oauth/callback/<channel>` for GitHub OAuth integration:
- Added GitHub OAuth support in the authentication module
- Introduced `GithubOAuthClient` with methods to fetch and normalize
user info
- Updated `CLIENT_TYPES` to include GitHub OAuth client
- Deprecated `/github_callback` route and suggested using the generic
`/oauth/callback/<channel>` route
---
- Related pull requests:
- #7379
- #7553
### Usage
- [Create a GitHub OAuth
App](https://github.com/settings/applications/new) to obtain the
`client_id` and `client_secret`, configure the authorization callback
url: `https://your-app.com/v1/user/oauth/callback/github`
- Edit `service_conf.yaml.template`:
```yaml
# ...
oauth:
github:
type: "github"
icon: "github"
display_name: "Github"
client_id: "your_client_id"
client_secret: "your_client_secret"
redirect_uri: "https://your-app.com/v1/user/oauth/callback/github"
# ...
```
### Type of change
- [x] Documentation Update
- [x] Refactoring (non-breaking change)
Feat: update llm factories for SILICONFLOW (#7620)
### 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] Other (please describe): llm factories update
Feat: add support for OpenAi gpt 4.1 series (#7540)
### What problem does this PR solve?
Adds support for the GPT-4.1 series from OpenAI.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
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>
TeslaZY
Yongteng Lei
JI4JUN
Zhichang Yu
謝富祥
Tuan Le
Kevin Hu
He Wang
cutiechi
africa-worker
liu an
Chaoxi Weng
Debug Doctor
Andrea
QuintinTao
Neal Davis
Jason Li
pyyuhao
Chenzy
crypticGøøse
kuro5989
汪威
yihong