togotogo
Marketplace

RAG · Postgres

Other

pgvector + pg_search hybrid retrieval store for ai-rag.

togo-framework
bash
togo install togo-framework/rag-postgres

Install

bash
togo install togo-framework/rag-postgres

rag-postgres — PostgreSQL vector store for togo ai-rag

A rag.Store driver backed by PostgreSQL: pgvector for similarity + pg_search (ParadeDB BM25) for keyword ranking → hybrid retrieval. Pairs with togo-postgres (ships pgvector + ParadeDB).

bash
togo install togo-framework/rag-postgres

Set RAG_STORE=postgres + DATABASE_URL (optionally RAG_PG_DIM, default 1536). On boot it ensures CREATE EXTENSION vector, the rag_chunks table, an HNSW cosine index, and — if pg_search is present — a BM25 index for hybrid search.

  • Search(vector, topK) — pgvector cosine (the standard ai-rag path).
  • HybridSearch(vector, query, topK) — vector + BM25 via reciprocal-rank fusion (call it directly via a type assertion; falls back to vector-only without pg_search).

MIT

<div align="center"> <h3>Premium sponsors</h3> <p> <a href="https://id8media.com"><strong>ID8 Media</strong></a> &nbsp;·&nbsp; <a href="https://one-studio.co"><strong>One Studio</strong></a> </p> <p><sub>Support togo — <a href="https://github.com/sponsors/fadymondy">become a sponsor</a>.</sub></p> </div>