example.env

# CodeRAG configuration. Copy to .env and adjust. All values are optional —
# CodeRAG runs out of the box with a local model and no API key.

# --- Embedding backend ---
# Provider: fastembed (local, default) | openai | fake
CODERAG_PROVIDER=fastembed
# Local embedding model (fastembed). 384-dim, no API key required.
CODERAG_MODEL=BAAI/bge-small-en-v1.5
# Where downloaded local models are cached.
# CODERAG_CACHE_DIR=~/.cache/coderag

# --- Locations ---
# The codebase to index/search (defaults to the current directory).
CODERAG_WATCHED_DIR=/path/to/your/codebase
# Where the index + database are stored (defaults to ./.coderag).
# CODERAG_STORE_DIR=./.coderag

# --- Vector index (scale) ---
# auto | flat | ivf. "auto" uses exact Flat search and switches to approximate
# IVF automatically once the corpus grows past CODERAG_IVF_THRESHOLD vectors.
# CODERAG_INDEX_TYPE=auto
# CODERAG_IVF_THRESHOLD=50000

# --- Retrieval ---
# CODERAG_TOP_K=8

# --- Optional: OpenAI (only needed for `--provider openai` or LLM answers) ---
# OPENAI_API_KEY=sk-...
# CODERAG_OPENAI_MODEL=text-embedding-3-small
# CODERAG_CHAT_MODEL=gpt-4o-mini