62 lines
2.6 KiB
Plaintext
62 lines
2.6 KiB
Plaintext
# ===== LLM Configuration =====
|
|
# Any OpenAI-compatible API is supported
|
|
LLM_API_KEY=your_api_key_here
|
|
LLM_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
|
|
LLM_MODEL_NAME=qwen-plus
|
|
|
|
# --- Gemini (Google AI Studio) ---
|
|
# Set LLM_PROVIDER=gemini to auto-configure the Google AI Studio endpoint.
|
|
# Get a free API key at: https://aistudio.google.com/
|
|
# LLM_PROVIDER=gemini
|
|
# LLM_API_KEY=AIza...
|
|
# LLM_MODEL_NAME=gemini-3.1-flash-lite-preview
|
|
|
|
# ===== Graph Backend =====
|
|
# GRAPH_BACKEND=zep (default) — Zep Cloud managed memory graph
|
|
# GRAPH_BACKEND=graphiti — Self-hosted Neo4j + Graphiti (requires graphiti extras)
|
|
GRAPH_BACKEND=zep
|
|
|
|
# --- Zep Cloud (default backend) ---
|
|
# Free tier available: https://app.getzep.com/
|
|
ZEP_API_KEY=your_zep_api_key_here
|
|
|
|
# --- Graphiti + Neo4j (alternative backend) ---
|
|
# Install extras: pip install "mirofish-backend[graphiti]"
|
|
# NEO4J_URI=bolt://localhost:7687
|
|
# NEO4J_USER=neo4j
|
|
# NEO4J_PASSWORD=your_neo4j_password_here
|
|
# GRAPHITI_BATCH_SIZE=10 # chunks per bulk call; higher = faster but more LLM parallelism
|
|
|
|
# --- Embedding LLM (used by Graphiti for vector indexing) ---
|
|
# Falls back to LLM_API_KEY / LLM_BASE_URL if not set.
|
|
# Use a dedicated embedding deployment when your LLM_BASE_URL points to a generative model.
|
|
# LLM_EMBED_API_KEY=your_embed_api_key_here
|
|
# LLM_EMBED_BASE_URL=https://<resource>.cognitiveservices.azure.com/openai/deployments/<embed-deployment>/embeddings?api-version=2024-05-01-preview
|
|
# LLM_EMBED_MODEL_NAME=text-embedding-3-small
|
|
|
|
# --- Small/fast LLM (used by Graphiti for reranking and lightweight tasks) ---
|
|
# Falls back to LLM_API_KEY / LLM_BASE_URL / LLM_MODEL_NAME if not set.
|
|
# Use a cheaper model (e.g. gpt-4o-mini, gpt-5-mini) to reduce costs.
|
|
# LLM_SMALL_API_KEY=your_small_api_key_here
|
|
# LLM_SMALL_BASE_URL=https://<resource>.cognitiveservices.azure.com/openai/deployments/<small-model>/chat/completions?api-version=2024-05-01-preview
|
|
# LLM_SMALL_MODEL_NAME=gpt-4o-mini
|
|
|
|
# ===== Ontology limits =====
|
|
# ONTOLOGY_MAX_ENTITY_TYPES=12 # total entity types (specific + 2 fallback); Zep Cloud max is 10 specific + 2 = 12
|
|
# ONTOLOGY_MAX_EDGE_TYPES=10 # max relationship types; Zep Cloud max is 10
|
|
|
|
# ===== Boost LLM (optional) =====
|
|
# Secondary faster LLM — omit these lines entirely if not used
|
|
LLM_BOOST_API_KEY=your_api_key_here
|
|
LLM_BOOST_BASE_URL=your_base_url_here
|
|
LLM_BOOST_MODEL_NAME=your_model_name_here
|
|
|
|
# ===== Authentication =====
|
|
# Password for the "demo" user — REQUIRED in production
|
|
# Empty default = login disabled until set
|
|
DEMO_PASSWORD=
|
|
|
|
# Flask secret key — used to sign JWT tokens
|
|
# Generate with: python -c "import secrets; print(secrets.token_hex(32))"
|
|
SECRET_KEY=your-secret-key-here
|