weaviate / weaviate/query-agent-benchmarking

Rethink how to add a `SearchAgent`, Function Calling Loop with Search Tool

Open
#72 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
17
Forks
3
PR merge metrics
No merged PRs in 30d

Description

This needs to inherit either Search Mode or Hybrid Search / BM25 / Vector Search. And then ablate which LLM you are using.

Maybe inherit from retrieve-dspy to decouple implementations of alternate search agents from query-agent-evals.

Used for BrowseComp-Plus testing.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by mapping the proposed SearchAgent against Search Mode, Hybrid Search, BM25, Vector Search, and retrieve-dspy, while checking how query-agent-evals is structured. Done means selecting an implementation boundary and inheritance approach, then defining the LLM ablation needed for BrowseComp-Plus testing.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
ai, search, testing
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.