Perf Impr: Decouple reasoning and extraction for faster, more precise logic (#9191)
### What problem does this PR solve?
This commit refactors the core prompts to decouple the high-level
reasoning from the low-level information extraction. By making
REASON_PROMPT a dedicated strategist that only generates search queries
and re-tasking RELEVANT_EXTRACTION_PROMPT to be a specialized tool for
single-fact extraction, we eliminate redundant information
summarization. This clear separation of concerns makes the overall
reasoning process significantly faster and more precise, as each
component now has a single, well-defined responsibility.
### Type of change
- [x] Performance Improvement
### 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
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Some models force thinking, resulting in the absence of the think tag in
the returned content
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Refactoring: Optimization of the Deep Research Module Code Structure (#5959)
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>
謝富祥
LUO huan huan
WhiteBear
liwenju0
Kevin Hu