### What problem does this PR solve?
Add embedded search functionality.
### 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?
Update broken create agent session due to v0.20.0 changes. #9383
**NOTE: A session ID is no longer required to interact with the agent.**
See: #9241, #9309.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- Add type and boundary checks for conv["reference"] access
- Prevent KeyError: 0 when reference list is empty or malformed
- Ensure reference is list type before indexing
- Handle cases where reference items are None or missing chunks
- Maintains backward compatibility with existing data structures
This resolves crashes in /api/v1/agents/<agent_id>/sessions endpoint
when conversation reference data is not properly structured.
### What problem does this PR solve?
This PR fixes a critical `KeyError: 0` that occurs in the
`/api/v1/agents/<agent_id>/sessions` endpoint when the system attempts
to access conversation reference data that is not properly structured.
**Background Context:**
The `list_agent_session` method in `api/apps/sdk/session.py` assumes
that `conv["reference"]` is always a properly indexed list with valid
dictionary structures. However, in real-world scenarios, this data can
be:
- Not a list type (could be None, string, or other types)
- An empty list when `chunk_num` tries to access index 0
- Contains None values or malformed dictionary structures
- Missing expected "chunks" keys in reference items
**Impact Before Fix:**
When malformed reference data is encountered, the API crashes with:
```json
{
"code": 100,
"data": null,
"message": "KeyError(0)"
}
```
**Solution:**
Added comprehensive safety checks including type validation, boundary
checking, null safety, and structure validation to ensure the API
gracefully handles all reference data formats while maintaining backward
compatibility.
### 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):
- Root cause: accessing req.get("dataset_ids") returns None when the key
is absent, causing KeyError.
- Fix: use req.get("dataset_ids", []) to default to empty list.
### 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?
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?
#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?
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?
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?
OpenAI-compatible-API supports references.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### 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?
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
```
### 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?
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?
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?
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?
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):
