### 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):
Fix: Enforce default embedding model in create_dataset / update_dataset (#8486)
### 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)
Refa: Implement centralized file name length limit using FILE_NAME_LEN_LIMIT constant (#8318)
### 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)
Fix: Move pagerank field from create to update dataset API (#8217)
### 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)
Refa: dataset operations to simplify error handling (#8132)
### What problem does this PR solve?
- Consolidate database operations within single try-except blocks in the
methods
### Type of change
- [x] Refactoring
Fix Bug: When performing the dify_retrieval, the metadata of the document was empty. (#7968)
### 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)
Refa: HTTP API list datasets / test cases / docs (#7720)
### 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)
Refa: HTTP API delete dataset / test cases / docs (#7657)
### 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
Fix(api): correct default value handling in dataset parser config (#7589)
### 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)
Feat: Add http api to create, update, or delete agents. (#7515)
### 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):
Refa: HTTP API update dataset / test cases / docs (#7564)
### 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 (#7500)
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>
Refa: http API create dataset and test cases (#7393)
### 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
Fix:Update chat assistant with an empty dataset (#7354)
### 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)
Refa: knowledge_graph chunk method is deprecated (#7220)
### 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
Fix: wrong “available” property when list chunk (#7093)
### 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?
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>
fix Conversation roles must alternate user/assistant/user/assistant/... bug (#6880)
### 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):
Feat: add primitive support for function calls (#6840)
### What problem does this PR solve?
This PR introduces **primitive support for function calls**,
enabling the system to handle basic function call capabilities.
However, this feature is currently experimental and **not yet enabled
for general use**, as it is only supported by a subset of models,
namely, Qwen and OpenAI models.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
add openai agent
_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)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: Handle the case of deleting empty blocks. Update the relevant message (#6643)
…gic to return the correct deletion message. Add handling for empty
arrays to ensure no errors occur during the deletion operation. Update
the test cases to verify the new logic.
### What problem does this PR solve?
fix this bug：https://github.com/infiniflow/ragflow/issues/6607
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Fix agent completion requiring calling twice with parameters in begin component (#6659)
### What problem does this PR solve?
Fix #5418
Actually, the fix #4329 also works for agent flows with parameters, so
this PR just relaxes the `else` branch of that. With this PR, it works
fine on my side, may need more testing to make sure this does not break
something.
I guess the real problem may be deeply hidden in the code which relates
to conversation and canvas execution. After a few hours of debugging, I
see the only difference between with and without parameters in `begin`
component, is the `history` field of canvas data. When the `begin`
component contains some parameters, the debug log shows:
```
025-03-29 19:50:38,521 DEBUG 356590 {
"component_name": "Begin",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [{"type": "fileUrls", "key": "fileUrls", "name": "files", "optional": true, "value": "问题.txt\n今天天气怎么样"}], "inputs": [], "debug_inputs": [], "prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？", "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
2025-03-29 19:50:38,523 DEBUG 356590 {
"component_name": "Answer",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "post_answers": [], "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
```
Then it does not go further along the flow.
When the `begin` component does not contain any parameter, the debug log
shows:
```
2025-03-29 19:41:13,518 DEBUG 353596 {
"component_name": "Begin",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？", "output": null},
"output": null,
"inputs": []
}, history: [], kwargs: {"stream": false}
2025-03-29 19:41:13,520 DEBUG 353596 {
"component_name": "Answer",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "post_answers": [], "output": null},
"output": null,
"inputs": []
}, history: [], kwargs: {"stream": false}
2025-03-29 19:41:13,556 INFO 353596 127.0.0.1 - - [29/Mar/2025 19:41:13] "POST /api/v1/agents/fee6886a0c6f11f09b48eb8798e9aa9b/sessions?user_id=123 HTTP/1.1" 200 -
2025-03-29 19:41:21,115 DEBUG 353596 Canvas.prepare2run: Retrieval:LateGuestsNotice
2025-03-29 19:41:21,116 DEBUG 353596 {
"component_name": "Retrieval",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "similarity_threshold": 0.2, "keywords_similarity_weight": 0.3, "top_n": 8, "top_k": 1024, "kb_ids": ["9aca3c700c5911f0811caf35658b9385"], "rerank_id": "", "empty_response": "", "tavily_api_key": "", "use_kg": false, "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
```
It correctly goes along the flow and generates correct answer.
You can see the difference: when the `begin` component has any
parameter, the `history` field is filled from the beginning, while it is
just `[]` if the `begin` component has no parameter.
### 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):
Feat: Add Duplicate ID Check and Update Deletion Logic (#6376)
- Introduce the `check_duplicate_ids` function in `dataset.py` and
`doc.py` to check for and handle duplicate IDs.
- Update the deletion operation to ensure that when deleting datasets
and documents, error messages regarding duplicate IDs can be returned.
- Implement the `check_duplicate_ids` function in `api_utils.py` to
return unique IDs and error messages for duplicate IDs.
### What problem does this PR solve?
Close https://github.com/infiniflow/ragflow/issues/6234
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
- Fix incorrect progress check condition that prevented re-parsing of
completed documents
- Allow parsing for documents with progress 0.0 (not started) or 1.0
(completed)
- Only block parsing for documents currently in progress (0.0 < progress
< 1.0)
Close #6312
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Stephen Hu
zhanglei
Liu An
dong
天海蒼灆
Yongteng Lei
Kevin Hu
Song Fuchang
duramisu
Qi
liwenju0
dylan
so95
hy89