⚡ Bolt: Optimize retrieval pipelines with concurrent tool execution#113
⚡ Bolt: Optimize retrieval pipelines with concurrent tool execution#113ishaanxgupta wants to merge 1 commit intomainfrom
Conversation
Parallelized the sequential tool execution loops inside `CodeRetrievalPipeline.run`, `CodeRetrievalPipeline.run_stream`, and `RetrievalPipeline.run` using `asyncio.gather`. This avoids I/O blocking bottlenecks during querying when the LLM outputs multiple tool calls.
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
💡 What: Refactored LLM tool execution to run concurrently rather than sequentially.
🎯 Why: Previously, if the LLM outputted multiple tool calls in a single turn, the pipeline executed them sequentially. For
get_file_contextorsearch_symbols, the waiting times accumulated linearly, unnecessarily blocking the final query resolution.📊 Impact: Expecting significantly reduced response latency when multiple tool calls are used in an iteration.
🔬 Measurement: Verify query response time (or overall LLM ms tracking logs) when invoking queries that trigger complex, multi-tool analysis (e.g.
impact_analysisfollowed byget_file_context).PR created automatically by Jules for task 2313201174069911635 started by @ishaanxgupta