Skip to content

arch: Implement PostgreSQL + pgvector Storage Adapter for Sub-Millisecond Semantic Search #145

Description

@kavix

🎯 Goal

Implement a production-grade PostgreSQL 16 + pgvector storage adapter (internal/db/pgvector.go) for indexing code ASTs, diffs, and repository memory embeddings.

🛠️ Implementation Steps

  1. Add pgvector-go or standard SQL driver with vector(1536) HNSW index support.
  2. Add semantic similarity search query for eko ai ask and eko ai bisect.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

      Milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions