### What problem does this PR solve?

Revert token_required decorator of agent_bot completions and inputs.

### Type of change

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

### 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?

Update broken agent completion due to v0.20.0 changes. #9199

### Type of change

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

### What problem does this PR solve?

Update broken agent OpenAI-Compatible completion due to v0.20.0. #9199 

Usage example:

**Referring the input is important, otherwise, will result in empty
output.**

<img width="1273" height="711" alt="Image"
src="https://github.com/user-attachments/assets/30740be8-f4d6-400d-9fda-d2616f89063f"
/>

<img width="622" height="247" alt="Image"
src="https://github.com/user-attachments/assets/0a2ca57a-9600-4cec-9362-0cafd0ab3aee"
/>

### Type of change

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

### What problem does this PR solve?

#9232

### Type of change

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

1. When creating a new session, initialize an empty reference that
includes both the app api and sdk API.
2. Fix the logic when retrieving references for historical messages: the
number of dialogue messages and reference messages may differ, but it
should match the number of assistant messages.

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

### What problem does this PR solve?

Close #9197
Close #9145

### Type of change

- [x] Refactoring
- [x] Bug fixing.

### What problem does this PR solve?

list_document supports range filtering.

### Type of change

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

### What problem does this PR solve?

fix #8424 NPE in dify_retrieval.py, add log exception

### Type of change

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

### What problem does this PR solve?


### Type of change

- [x] Refactoring

### What problem does this PR solve?
Add industry-related search keyword generation function
- When generating search keywords, support for specific industries has
been added
- If the "industry" parameter is provided, industry-specific
restrictions will be added to the prompt
- This change can help users generate more precise search keywords
within specific industries

### Type of change

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

### What problem does this PR solve?

#9082 #6365

<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>

### Type of change

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

### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/8995

### 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?
https://github.com/infiniflow/ragflow/issues/9034

### Type of change

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

### What problem does this PR solve?

OpenAI-compatible-API supports references.

### Type of change

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

### What problem does this PR solve?

Close #8943

### Type of change

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

### What problem does this PR solve?

Add knowledge graph http api

### Type of change

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

### What problem does this PR solve?

Fix typo process_duration.

### Type of change

- [x] Documentation Update
- [x] Refactoring

### What problem does this PR solve?

Add file management HTTP_API for operating files

### Type of change

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

### What problem does this PR solve?

Remove useless logic in a loop for list_doc

### Type of change

- [x] Refactoring
- [x] Performance Improvement

### What problem does this PR solve?

stack：

```
2025-06-26 17:22:24,739 ERROR    1609 list index out of range
Traceback (most recent call last):
  File "/ragflow/.venv/lib/python3.10/site-packages/flask/app.py", line 880, in full_dispatch_request
    rv = self.dispatch_request()
  File "/ragflow/.venv/lib/python3.10/site-packages/flask/app.py", line 865, in dispatch_request
    return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)  # type: ignore[no-any-return]
  File "/ragflow/api/utils/api_utils.py", line 298, in decorated_function
    return func(*args, **kwargs)
  File "/ragflow/api/apps/sdk/session.py", line 472, in list_session
    print(conv["reference"][message_num])
IndexError: list index out of range

```


![图片](https://github.com/user-attachments/assets/93fe90a8-0434-4842-ba9f-bb5a995b498a)


### 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?

Previous:
- Defaulted to hardcoded model 'BAAI/bge-large-zh-v1.5@BAAI'
- Did not respect user-configured default embedding_model

Now:
- Correctly prioritizes user-configured default embedding_model

Other:
- Make embedding_model optional in CreateDatasetReq with proper None
handling
- Add default embedding model fallback in dataset update when empty
- Enhance validation utils to handle None values and string
normalization
- Update SDK default embedding model to None to match API changes
- Adjust related test cases to reflect new validation rules

### Type of change

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

### What problem does this PR solve?

- Replace hardcoded 255-byte file name length checks with
FILE_NAME_LEN_LIMIT constant
- Update error messages to show the actual limit value
- #8290

### Type of change

- [x] Refactoring

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

### What problem does this PR solve?

- Add filename length validation (<=255 bytes) for document
upload/rename in both HTTP and SDK APIs
- Update error messages for consistency
- Fix comparison operator in SDK from '>=' to '>' for filename length
check

### Type of change

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

### What problem does this PR solve?

- Remove pagerank from CreateDatasetReq and add to UpdateDatasetReq
- Add pagerank update logic in dataset update endpoint
- Update API documentation to reflect changes
- Modify related test cases and SDK references

#8208

This change makes pagerank a mutable property that can only be set after
dataset creation, and only when using elasticsearch as the doc engine.

### Type of change

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

### What problem does this PR solve?

- Consolidate database operations within single try-except blocks in the
methods

### Type of change

- [x] Refactoring

### What problem does this PR solve?

#8067 

### Type of change

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

### What problem does this PR solve?

#8057 

### Type of change

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

### What problem does this PR solve?

#7791

### Type of change

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

### What problem does this PR solve?
When performing the dify_retrieval, the metadata of the document was
empty.


### Type of change

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

### 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?

Fix early return when update doc. #7886

### 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?

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?

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?

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?

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?


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?

_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):

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?

Optimize dataset validation and add function docs

### Type of change

- [x] Refactoring

### What problem does this PR solve?

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

### Type of change

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

### What problem does this PR solve?

When updating a chat assistant using API,if the dataset attached by the
current chat assistant is not empty，setting dataset to
null("dataset_ids":[]) will cause update failure：'dataset_ids' can't be
empty

### Type of change

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

### What problem does this PR solve?

The knowledge_graph chunk method is deprecated and should no longer be
used. #7184.

### Type of change

- [x] Refactoring

### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/7083

Internal due to when returning from ES, fields changed to str, so the
bool conversion does not work as expected.

### Type of change

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

### What problem does this PR solve?

#6875

### Type of change

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

### What problem does this PR solve?

resolve this issue：https://github.com/infiniflow/ragflow/issues/6876

### Type of change

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

---------

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

### What problem does this PR solve?

The old logic filters out all assistant messages from messages, which,
in multi-turn conversations, results in only user messages being
retained. This leads to an error in locally deployed models:
Conversation roles must alternate user/assistant/user/assistant/...

### 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):