### What problem does this PR solve?

SpringAI can only add session_id in metadata。so add new way to get
session_id from "id" or "metadata.id"

![image](https://github.com/user-attachments/assets/0c698ebb-2228-46d8-94c5-2a291b6f70bf)

### Type of change

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

### What problem does this PR solve?

Change citation mark as [ID:n], it's easier for LLMs to follow the
instruction :) #7904

### Type of change

- [x] Refactoring

### What problem does this PR solve?

Fix early return when update doc. #7886

### Type of change

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

…sing the SDK chat API

### What problem does this PR solve?

When using the SDK for chat, you can include the IDs of additional
knowledge bases you want to use in the request. This way, you don’t need
to repeatedly create new assistants to support various combinations of
knowledge bases. This is especially useful when there are many knowledge
bases with different content. If users clearly know which knowledge base
contains the information they need and select accordingly, the recall
accuracy will be greatly improved.

Users only need to add an extra field, a kb_ids array, in the HTTP
request. The content of this field can be determined by the client
fetching the list of knowledge bases and letting the user select from
it.

### Type of change

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

Co-authored-by: Li Ye <liye@unittec.com>

### What problem does this PR solve?

**Issue Description:**

When using the `/api/retrieval` endpoint with a POST request and setting
the `keyword` parameter to `true`, the system invokes the
`model_instance` method from `TenantLLMService` to create a `chat_mdl`
instance. Subsequently, it calls the `keyword_extraction` method to
extract keywords.

However, within the `keyword_extraction` method, the `chat` function of
the LLM attempts to access the `chat_mdl.max_length` attribute to
validate input length. This results in the following error:

```
AttributeError: 'SILICONFLOWChat' object has no attribute 'max_length'
```

**Proposed Solution:**

Upon reviewing other parts of the codebase where `chat_mdl` instances
are created, it appears that utilizing `LLMBundle` for instantiation is
more appropriate. `LLMBundle` includes the `max_length` attribute, which
should resolve the encountered error.



### 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?

[Regular Expression Injection leading to Denial of Service
(ReDoS)](https://github.com/infiniflow/ragflow/security/advisories/GHSA-wqq6-x8g9-f7mh)

### Type of change

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

### What problem does this PR solve?

Close #7837
### Type of change

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

### What problem does this PR solve?

Delete Corresponding Minio Bucket When Deleting a Knowledge Base
[issue #4113 ](https://github.com/infiniflow/ragflow/issues/4113)

### 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?

Add more robust fallbacks for citations

### 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?

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?

Wrong hint type. #7729.

### Type of change

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

### What problem does this PR solve?

This PR introduces Pydantic-based validation for the list datasets HTTP
API, improving code clarity and robustness. Key changes include:

Pydantic Validation
Error Handling
Test Updates
Documentation Updates

### Type of change

- [x] Documentation Update
- [x] Refactoring

### What problem does this PR solve?

Add OAuth `state` parameter for CSRF protection:
- Updated `get_authorization_url()` to accept an optional state
parameter
- Generated a unique state value during OAuth login and stored in
session
- Verified state parameter in callback to ensure request legitimacy

This PR follows OAuth 2.0 security best practices by ensuring that the
authorization request originates from the same user who initiated the
flow.

### Type of change

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

### What problem does this PR solve?

Fix:When you create a new API module named xxxa_api, the access route
will become xxx instead of xxxa. For example, when I create a new API
module named 'data_api', the access route will become 'dat' instead of
'data'
Fix:Fixed the issue where the new knowledge base would not be renamed
when there was a knowledge base with the same name

### Type of change

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

---------

Co-authored-by: tangyu <1@1.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

More fallbacks for bad citation format

### Type of change

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

### What problem does this PR solve?

Try the best to repair corrupted PDF files on upload automatically.

### Type of change

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

### What problem does this PR solve?

- Updated the dialog settings function to add a default prompt
configuration for no dataset.
- The prompt configuration will be determined based on the presence of
`kb_ids` in the request.


### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (Non-breaking change, adding functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

---------

Co-authored-by: wenju.li <wenju.li@deepctr.cn>

### What problem does this PR solve?

Hello, when I input a very long line in the chat input box, it will fail
with following error:

```
2025-05-17 16:11:26,004 ERROR    182558 value too long for type character varying(255)
Traceback (most recent call last):
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3291, in execute_sql
    cursor.execute(sql, params or ())
psycopg2.errors.StringDataRightTruncation: value too long for type character varying(255)


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/var/home/sfc/Projects/ragflow/api/apps/conversation_app.py", line 68, in set_conversation
    ConversationService.save(**conv)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3128, in inner
    return fn(*args, **kwargs)
  File "/var/home/sfc/Projects/ragflow/api/db/services/common_service.py", line 145, in save
    return cls.save_n(**kwargs)
  File "/var/home/sfc/Projects/ragflow/api/db/services/common_service.py", line 139, in save_n
    sample_obj = cls.model(**kwargs).save(force_insert=True)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 6923, in save
    pk = self.insert(**field_dict).execute()
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 2011, in inner
    return method(self, database, *args, **kwargs)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 2082, in execute
    return self._execute(database)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 2887, in _execute
    return super(Insert, self)._execute(database)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 2598, in _execute
    cursor = self.execute_returning(database)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 2605, in execute_returning
    cursor = database.execute(self)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3299, in execute
    return self.execute_sql(sql, params)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3289, in execute_sql
    with __exception_wrapper__:
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3059, in __exit__
    reraise(new_type, new_type(exc_value, *exc_args), traceback)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 192, in reraise
    raise value.with_traceback(tb)
  File "/var/home/sfc/Projects/ragflow/.venv/lib/python3.10/site-packages/peewee.py", line 3291, in execute_sql
    cursor.execute(sql, params or ())
peewee.DataError: value too long for type character varying(255)
```

This PR fix it by truncate the `name` field in the `set_conversation`
method in the `conversation_app.py`.

### 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?

Hello, our use case requires LLM agent to invoke some tools, so I made a
simple implementation here.

This PR does two things:

1. A simple plugin mechanism based on `pluginlib`:

This mechanism lives in the `plugin` directory. It will only load
plugins from `plugin/embedded_plugins` for now.

A sample plugin `bad_calculator.py` is placed in
`plugin/embedded_plugins/llm_tools`, it accepts two numbers `a` and `b`,
then give a wrong result `a + b + 100`.

In the future, it can load plugins from external location with little
code change.

Plugins are divided into different types. The only plugin type supported
in this PR is `llm_tools`, which must implement the `LLMToolPlugin`
class in the `plugin/llm_tool_plugin.py`.
More plugin types can be added in the future.

2. A tool selector in the `Generate` component:

Added a tool selector to select one or more tools for LLM:


![image](https://github.com/user-attachments/assets/74a21fdf-9333-4175-991b-43df6524c5dc)

And with the `bad_calculator` tool, it results this with the `qwen-max`
model:


![image](https://github.com/user-attachments/assets/93aff9c4-8550-414a-90a2-1a15a5249d94)


### 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: Yingfeng <yingfeng.zhang@gmail.com>

### 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?

Launch sandbox from docker-compose.
#4977
### Type of change

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

---------

Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>

### What problem does this PR solve?

Close #7655

Based on the codes atthe api_app, I think the reference is one-to-one
with the message
`
    def fillin_conv(ans):
        nonlocal conv, message_id
        if not conv.reference:
            conv.reference.append(ans["reference"])
        else:
            conv.reference[-1] = ans["reference"]
conv.message[-1] = {"role": "assistant", "content": ans["answer"], "id":
message_id}
        ans["id"] = message_id
`



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

### What problem does this PR solve?

This PR introduces Pydantic-based validation for the delete dataset HTTP
API, improving code clarity and robustness. Key changes include:

1. Pydantic Validation
2. Error Handling
3. Test Updates
4. Documentation Updates

### Type of change

- [x] Documentation Update
- [x] Refactoring

### 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?

When Delete Chunk Will Also Delete Chunk Related Image

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

### What problem does this PR solve?

#7623

### Type of change

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

### What problem does this PR solve?

Close #7612

### Type of change

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

### What problem does this PR solve?

Close #7597

### Type of change

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

### What problem does this PR solve?

#7623

### Type of change

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

### What problem does this PR solve?

Close #7592

### Type of change

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

### What problem does this PR solve?

Fix  HTTP API Create/Update dataset parser config default value error

### Type of change

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

### What problem does this PR solve?

Hello, we are using ragflow as a backend service, so we need to manage
agents from our own frontend. So adding these http APIs to manage
agents.

The code logic is copied and modified from the `rm` and `save` methods
in `api/apps/canvas_app.py`.

btw, I found that the `save` method in `canvas_app.py` actually allows
to modify an agent to an existing title, so I kept the behavior in the
http api. I'm not sure if this is intentional.

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

### What problem does this PR solve?

add show debug
![Recording2025-04-28142829-ezgif
com-video-to-gif-converter](https://github.com/user-attachments/assets/0c67da34-c2b6-428f-ae9b-b5b21464885c)

### Type of change

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

### What problem does this PR solve?


Close #7567

### Type of change

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

### What problem does this PR solve?

This PR introduces Pydantic-based validation for the update dataset HTTP
API, improving code clarity and robustness. Key changes include:
1. Pydantic Validation
2. ​​Error Handling
3. Test Updates
4. Documentation Updates
5. fix bug: #5915

### Type of change

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

### 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?

#7376
#4503
#5710 
#7470

### Type of change

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

### 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

- [ ] 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?

Kb detail supports return document total size now.

### Type of change

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

### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7519
### 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 `/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?

#7484

### Type of change

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

Fix:When sharing the knowledge base of multiple tenants with one person,
when this person queries the knowledge base of both tenants, they will
only query the question of the first person's knowledge base

Co-authored-by: 杜有强 <duyq@internal.ths.com.cn>

### What problem does this PR solve?

1.  Add delete_by_ids method
2. Add get_doc_ids_by_doc_names
3. Improve user_canvan_version's logic (avoid O(n) db IO)
4. Improve document delete logic (avoid O(n) db IO)

### Type of change

- [x] Performance Improvement

### What problem does this PR solve?

Fix: After deleting the file from the file management menu, it was not
removed from the MinIO bucket.

### 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: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>

### 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?

Optimize dataset validation and add function docs

### Type of change

- [x] Refactoring

### What problem does this PR solve?

Fix `filed_map` was incorrectly persisted. #7412 

### Type of change

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

### What problem does this PR solve?

change create dataset delimiter default value to r'\n'

### Type of change

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

### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/7407

Based on this context, I think there should be some reasons that let
some LLMs have a mismatch (add the wrong "@xxx"),
So I think when use fid can not fetch llm then tried to just use name
should can fetch it.

### Type of change

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