Skip to content
Gittensory
Self-hosting

RAG indexing

RAG adds relevant existing code and docs to the AI reviewer prompt. It is additive and fail-safe.

Prerequisites

Repo activation
GITTENSORY_REVIEW_RAG=true and the repo in GITTENSORY_REVIEW_REPOS, or a private per-repo feature toggle.
Vector backend
SQLite vectors by default, Qdrant with the qdrant profile, or Postgres/pgvector where configured.
Embedding provider
An OpenAI-compatible embeddings endpoint with a model whose dimension matches the vector collection.

Choosing a vector backend

SQLite vectors are the default and need no extra service — fine for a small instance or getting started. Qdrant (QDRANT_URL, --profile qdrant) is the preferred dedicated vector store for review context at scale. A third option, PGVECTOR_ENABLED=true, uses the Postgres pgvector table instead — only relevant if you're already running the postgres profile and want to avoid standing up a separate Qdrant service. Leave it false (the default) when QDRANT_URL is set; Qdrant remains preferred for RAG at scale.

Qdrant and Ollama example

.env
GITTENSORY_REVIEW_RAG=true
GITTENSORY_REVIEW_REPOS=owner/repo
QDRANT_URL=http://qdrant:6333
QDRANT_DIM=768
AI_EMBED_BASE_URL=http://ollama:11434/v1
AI_EMBED_MODEL=nomic-embed-text:latest
docker compose --profile qdrant --profile ollama up -d
docker compose exec ollama ollama pull nomic-embed-text:latest
bash

Use QDRANT_DIM=1024 for 1024-dimensional models such as bge-m3 or mxbai-embed-large. If a Qdrant collection already exists, recreate it before changing dimensions.

AI_EMBED_API_KEY is the bearer credential for AI_EMBED_BASE_URL, if that endpoint requires one — a local Ollama typically doesn't, but a hosted OpenAI-compatible embeddings endpoint usually does. Setting AI_EMBED_MODEL alone does nothing without AI_EMBED_BASE_URL also set; unset, embeddings use the same provider as the rest of the review chain.

Indexing

RAG needs an index before it can retrieve useful context. A cold or missing index degrades to no context; the review still runs.

curl -X POST http://localhost:8787/v1/internal/jobs/rag-index \
  -H "authorization: Bearer $INTERNAL_JOB_TOKEN" \
  -H "content-type: application/json" \
  -d '{"repoFullName":"owner/repo"}'
bash

Operational checks

  • Boot logs should include selfhost_embed_provider when an embedding provider is configured.
  • Qdrant mode should log selfhost_vectorize with backend qdrant.
  • Empty RAG context usually means the repo is not indexed, the embed model is unavailable, or dimensions do not match.
RAG is context, not authority. The AI reviewer still has to verify every claim against the diff, grounding, and review rules.

Pair RAG with AI providers and optionally REES.

← PreviousREES analyzersNext →Operations