o19s/quepid

Improve your OpenSearch, Elasticsearch, Solr, Vectara, Algolia and Custom Search search quality.

What it solves

Quepid transforms the process of improving application search results into a reliable engineering workflow. It addresses the lack of cross-functional collaboration, the difficulty of testing search changes without causing regressions, and the slow pace of iteration typically associated with search relevance tuning.

How it works

Quepid provides a centralized platform for teams to collaborate on search requirements and test relevance changes. It allows teams to move away from spreadsheets and emails, creating a repeatable process to ensure that search improvements are tracked and verified without sliding backwards in quality.

Who it’s for

It is designed for product teams and engineers who need to improve the search experience of their applications through a structured, collaborative approach to relevance tuning.

Highlights

  • Facilitates cross-functional collaboration on search requirements.
  • Provides a framework for testing search changes to prevent regressions.
  • Enables a repeatable engineering process for search relevance iteration.

Related

  • Project
    tobi/qmd

    An on-device hybrid search engine that indexes local markdown notes and documentation using BM25, vector search, and LLM reranking for high-precision retrieval.

  • Project
    marcoaapfortes/Mantic.sh

    A context-aware code search engine that prioritizes relevance over raw speed to provide AI agents and developers with precise, intent-based file retrieval.

  • Project
    embeddings-benchmark/mteb

    A multimodal toolbox for evaluating embeddings and retrieval systems, providing a standardized benchmark and leaderboard for comparing model performance.

  • Project
    galilai-group/stable-worldmodel

    A platform for reproducible world model research and evaluation that provides a unified interface for data collection, training, and model-predictive control evaluation.

  • Project
    chAng-L19/codex-redteam-mode

    A durable red-team runtime for Codex App and CLI that automates security workflows using goal contracts and evidence-based verification to prevent session interruptions and false completions.