### What problem does this PR solve?

Add Zhipu GLM-4.5 model series. #9708.

### 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 ZhipuAI GLM-4.5 model series

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Refactor OpenAI to enable audio parsing.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

### What problem does this PR solve?

Fix Gemini parameters error.

### 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?

Add SMTP support for user invitation emails

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Allows set multiple types of default models in service config.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Supports GPT-5.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add Claude Opus 4.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring

### 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)

### What problem does this PR solve?

Support 302.AI provider.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### 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?

Added infinity rank_feature support

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### 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)

### 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)

### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### 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>

### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### 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?

Add voyage-multimodal-3.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Update gemini2.5

### Type of change

- [x] Refactoring

### What problem does this PR solve?

Add claude4 models.

### 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)

### 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

### 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)

### 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

### What problem does this PR solve?

#7608

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### 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)

### 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

### 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>

### 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>

### 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

### What problem does this PR solve?

Replace models of novita

### Type of change

- [x] Other (please describe): Replace models of novita

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?

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?

Update LLM models

### Type of change

- [x] Refactoring

### What problem does this PR solve?

#6733

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#6697

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

### Type of change

- [x] Refactoring
- [x] Performance Improvement

### 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?

#6577

### 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?

#6421

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)