a7f2c92bb4
- Introduced CHUTES_API_TOKEN in .env.example files for configuration. - Updated README.md in quickstart example to include Chutes API setup. - Created quickstart_chutes.py example for demonstrating Chutes integration. - Added ChutesEmbedder and ChutesClient classes for embedding and LLM functionalities. - Updated LLM and embedder provider configurations to support Chutes. - Enhanced factories to include Chutes client and embedder. - Modified schema.py to define Chutes provider configuration. - Updated mcp_server configuration files to integrate Chutes API. - Added necessary dependencies in pyproject.toml for Chutes support.
52 lines
1.7 KiB
Text
52 lines
1.7 KiB
Text
# Graphiti MCP Server Environment Configuration
|
|
|
|
# Neo4j Database Configuration
|
|
# These settings are used to connect to your Neo4j database
|
|
NEO4J_URI=neo4j+s://6a25b5ba.databases.neo4j.io
|
|
NEO4J_USER=neo4j
|
|
NEO4J_PASSWORD=YuU8ypE1yzjVbn5LPaNkLcotsLL4aAOILGIQtSG2KAY
|
|
|
|
# OpenAI API Configuration
|
|
# Required for LLM operations
|
|
OPENAI_API_KEY=dummy-key
|
|
MODEL_NAME=gpt-4.1-mini
|
|
|
|
# Optional: Only needed for non-standard OpenAI endpoints
|
|
# OPENAI_BASE_URL=https://api.openai.com/v1
|
|
|
|
# Optional: Group ID for namespacing graph data
|
|
# GROUP_ID=my_project
|
|
|
|
# Concurrency Control
|
|
# Controls how many episodes can be processed simultaneously
|
|
# Default: 10 (suitable for OpenAI Tier 3, mid-tier Anthropic)
|
|
# Adjust based on your LLM provider's rate limits:
|
|
# - OpenAI Tier 1 (free): 1-2
|
|
# - OpenAI Tier 2: 5-8
|
|
# - OpenAI Tier 3: 10-15
|
|
# - OpenAI Tier 4: 20-50
|
|
# - Anthropic default: 5-8
|
|
# - Anthropic high tier: 15-30
|
|
# - Ollama (local): 1-5
|
|
# See README.md "Concurrency and LLM Provider 429 Rate Limit Errors" for details
|
|
SEMAPHORE_LIMIT=10
|
|
|
|
# Optional: Path configuration for Docker
|
|
# PATH=/root/.local/bin:${PATH}
|
|
|
|
# Optional: Memory settings for Neo4j (used in Docker Compose)
|
|
# NEO4J_server_memory_heap_initial__size=512m
|
|
# NEO4J_server_memory_heap_max__size=1G
|
|
# NEO4J_server_memory_pagecache_size=512m
|
|
|
|
# Azure OpenAI configuration
|
|
# Optional: Only needed for Azure OpenAI endpoints
|
|
# AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint_here
|
|
# AZURE_OPENAI_API_VERSION=2025-01-01-preview
|
|
# AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-gpt-4o-mini-deployment
|
|
# AZURE_OPENAI_EMBEDDING_API_VERSION=2023-05-15
|
|
# AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=text-embedding-3-large-deployment
|
|
# AZURE_OPENAI_USE_MANAGED_IDENTITY=false
|
|
|
|
# Chutes AI Configuration
|
|
CHUTES_API_KEY=
|