Feat: Add tool call caching#53
Open
Mir47-47 wants to merge 6 commits intothisisthepy:developfrom
Open
Conversation
# Conflicts: # api/src/main/models/base.py # api/src/main/models/llama3/model.py # api/src/main/utils/__init__.py # api/src/main/utils/cache.py
Updated the tool call rules to emphasize a cache-first principle, detailing a step-by-step process for checking and utilizing cached data before invoking new tool calls. This change aims to improve efficiency and ensure cached results are prioritized when relevant.
Deleted the api.zip binary file
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Server consolidation:
I modified server.py to retrieve the session's 'tool_call_cache' for both standard chat requests and streaming chat requests and forward it to the model.
Update Tool Features and Schema:
To retrieve cached tool call results, we added a new function 'get_cache_data' to 'cache.py ' and registered it in the tool function schema and implementation
I updated the system prompt at 'qwen3/model.py ' and instructed the model to follow the cache priority principle when handling tool calls.