This commit refactors the deep research module (deep_research.py), with
the following major improvements: The complex thinking and retrieval
logic has been broken down into multiple independent private methods,
enhancing code readability and maintainability. Static methods and class
methods have been introduced to simplify the logic for tag processing.
The search and reasoning processes have been optimized, increasing the
modularity of the code. The flexibility of information retrieval and
processing has been improved. The refactored code structure is now
clearer, making it easier to understand and extend the functionality of
the deep research module.
### What problem does this PR solve?
increase the modularity of the code
### Type of change
- [x] Refactoring
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
### What problem does this PR solve?
Fixes#5923
Fixes the readonly variables from payload at
/datasets/<dataset_id>
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
Now if user tries to modify readonly values then it will show " The
input parameters are invalid. "
invalid_keys = {"id", "embd_id", "chunk_num", "doc_num", "parser_id",
"create_date", "create_time", "created_by",
"status","token_num","update_date","update_time"}
if any(key in req for key in invalid_keys):
return get_error_data_result(message="The input parameters are
invalid.")
i have include those readonly keys in invalid_keys
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Raghav <2020csb1115@iitrpr.ac.in>
### What problem does this PR solve?
Fix:signal.SIGUSR1 and signal.SIGUSR2 can't use in window. so don't bind
signal.SIGUSR1 and signal.SIGUSR2 in the windows env
### 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):
Co-authored-by: tangyu <1@1.com>
### What problem does this PR solve?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: renqi <renqi08266@fxomail.com>
### What problem does this PR solve?
Feat: Add Breadcrumb component #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add Support for german language
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fixed #5839
This PR fix error code 102, stating dataset_ids is required.
curl --request POST \
--url http://{address}/api/v1/chats \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <YOUR_API_KEY>' \
--data '{
"name": "test_chat"
}'
this is not getting datasetids , fix for it.
file location : sdk\python\ragflow_sdk\ragflow.py
added : "dataset_ids": dataset_list if dataset_list else [],
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Raghav <2020csb1115@iitrpr.ac.in>
### What problem does this PR solve?
Feat: Add AvatarGroup component. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
**generate.py 更新：**
问题：部分模型提供商对输入对话内容的格式有严格校验，要求第一条内容的 role 不能为 assistant，否则会报错。
解决：删除了系统设置的 agent 开场白，确保传递给模型的对话内容中，第一条内容的 role 不为 assistant。
**retrieval.py 更新：**
问题：当前知识库检索使用全部对话内容作为输入，可能导致检索结果不准确。
解决：改为仅使用用户最后提出的一个问题进行知识库检索，提高检索的准确性。
**Update generate.py:**
Issue: Some model providers have strict validation rules for the format
of input conversation content, requiring that the role of the first
content must not be assistant. Otherwise, an error will occur.
Solution: Removed the system-set agent opening statement to ensure that
the role of the first content in the conversation passed to the model is
not assistant.
**Update retrieval.py:**
Issue: The current knowledge base retrieval uses the entire conversation
content as input, which may lead to inaccurate retrieval results.
Solution: Changed the retrieval logic to use only the last question
asked by the user for knowledge base retrieval, improving retrieval
accuracy.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
When accessing the /api/v1/agents/{agent_id}/completions API, sessions
created before agent modifications retain the old DSL data. To use the
latest agent configuration (like new prompts) in historical sessions, I
added the sync_dsl parameter. It defaults to False to maintain existing
behavior and only synchronizes when set to True. If needed, a manual
synchronization API can be created to trigger the sync explicitly.
### What problem does this PR solve?
Fix: keyword compont display issue #5794
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: When selecting a reordering model, give a prompt that it takes too
long. #5834
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add TransferList component. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The `/api/v1/chats` API endpoint was broken, any GET request got the
following response:
```
{"code":100,"data":null,"message":"TypeError(\"'int' object is not callable\")"}
```
With this log ragflow-server side:
```
2025-03-07 14:36:26,297 ERROR 20 'int' object is not callable
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 303, in decorated_function
return func(*args, **kwargs)
File "/ragflow/api/apps/sdk/chat.py", line 323, in list_chat
logging.WARN(f"Don't exist the kb {kb_id}")
TypeError: 'int' object is not callable
2025-03-07 14:36:26,298 INFO 20 172.18.0.6 - - [07/Mar/2025 14:36:26] "GET /api/v1/chats HTTP/1.1" 200 -
```
This was caused by the incorrect use of `logging.WARN` as a method (it's
a loglevel object), instead of the correct `logging.warning()` method.
This PR fixes that, and also rewrites the message to be grammaticaly
correct.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
vLLM provider with a reranking model does not work : as vLLM uses under
the hood the [CoHereRerank
provider](https://github.com/infiniflow/ragflow/blob/v0.17.0/rag/llm/__init__.py#L250)
with a `base_url`, if this URL [is not passed to the Cohere
client](https://github.com/infiniflow/ragflow/blob/v0.17.0/rag/llm/rerank_model.py#L379-L382)
any attempt will endup on the Cohere SaaS (sending your private api key
in the process) instead of your vLLM instance.
### 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?
fix:when start with source code not in docker env report
"UnicodeDecodeError: 'gbk' codec can't decode byte 0xad in position 5:
illegal multibyte sequence" in windows
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: tangyu <1@1.com>
### What problem does this PR solve?
Fixed the issue of "stop deleting when encountering invalid dataset ID"
#5760
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Enhance the recognition of both borderless and bordered Markdown tables.
Add support for extracting HTML tables, including various scenarios with
nested HTML tags. Improve performance by using conditional checks to
reduce unnecessary regular expression matching.
### What problem does this PR solve?
Optimize the table extraction logic in the Markdown parser:
Enhance the recognition of both borderless and bordered Markdown tables.
Add support for extracting HTML tables, including various scenarios with
nested HTML tags.
Improve performance by using conditional checks to reduce unnecessary
regular expression matching.
### Type of change
- [x] Performance Improvement
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
1. **Issue**: When calling `list_agent_session` via the HTTP API, users
may only need to display conversation messages, and do not want to see
the associated dsl, which can be very large. Therefore, consider adding
a control option to determine whether the DSL should be returned, with
the default being to return it.
2. **Documentation Discrepancy**: In the HTTP API documentation, under
"List agent sessions," the "Response" section states that the "data"
field is a dictionary when "success" is returned. However, the actual
returned data is a list. This discrepancy has been corrected.
