74a422369c
This commit introduces a comprehensive configuration system that makes Graphiti more flexible and easier to configure across different providers and deployment environments. ## New Features - **Unified Configuration**: New GraphitiConfig class with Pydantic validation - **YAML Support**: Load configuration from .graphiti.yaml files - **Multi-Provider Support**: Easy switching between OpenAI, Azure, Anthropic, Gemini, Groq, and LiteLLM - **LiteLLM Integration**: Unified access to 100+ LLM providers - **Factory Functions**: Automatic client creation from configuration - **Full Backward Compatibility**: Existing code continues to work ## Configuration System - graphiti_core/config/settings.py: Pydantic configuration classes - graphiti_core/config/providers.py: Provider enumerations and defaults - graphiti_core/config/factory.py: Factory functions for client creation ## LiteLLM Client - graphiti_core/llm_client/litellm_client.py: New unified LLM client - Support for Azure OpenAI, AWS Bedrock, Vertex AI, Ollama, vLLM, etc. - Automatic structured output detection ## Documentation - docs/CONFIGURATION.md: Comprehensive configuration guide - examples/graphiti_config_example.yaml: Example configurations - DOMAIN_AGNOSTIC_IMPROVEMENT_PLAN.md: Future improvement roadmap ## Tests - tests/config/test_settings.py: 22 tests for configuration - tests/config/test_factory.py: 12 tests for factories - 33/34 tests passing (97%) ## Issues Addressed - #1004: Azure OpenAI support - #1006: Azure OpenAI reranker support - #1007: vLLM/OpenAI-compatible provider stability - #1074: Ollama embeddings support - #995: Docker Azure OpenAI support 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
83 lines
2.3 KiB
YAML
83 lines
2.3 KiB
YAML
# Graphiti Configuration Example
|
|
# Save this file as .graphiti.yaml or specify path via GRAPHITI_CONFIG_PATH environment variable
|
|
|
|
# LLM Configuration
|
|
llm:
|
|
# Provider: openai, azure_openai, anthropic, gemini, groq, litellm, custom
|
|
provider: anthropic
|
|
model: claude-sonnet-4-5-latest
|
|
small_model: claude-haiku-4-5-latest
|
|
temperature: 0.7
|
|
max_tokens: 8192
|
|
# api_key: "your-api-key" # Or set via ANTHROPIC_API_KEY environment variable
|
|
|
|
# Embedder Configuration
|
|
embedder:
|
|
# Provider: openai, azure_openai, voyage, gemini, custom
|
|
provider: voyage
|
|
model: voyage-3
|
|
dimensions: 1024
|
|
# api_key: "your-voyage-key" # Or set via VOYAGE_API_KEY environment variable
|
|
|
|
# Reranker Configuration
|
|
reranker:
|
|
# Provider: openai, azure_openai, custom
|
|
provider: openai
|
|
# api_key: "your-api-key" # Or set via OPENAI_API_KEY environment variable
|
|
|
|
# Database Configuration
|
|
database:
|
|
# Provider: neo4j, falkordb, neptune, custom
|
|
provider: neo4j
|
|
uri: "bolt://localhost:7687"
|
|
user: neo4j
|
|
password: password
|
|
database: graphiti
|
|
|
|
# General Settings
|
|
store_raw_episode_content: true
|
|
max_coroutines: null # null uses default
|
|
|
|
---
|
|
# Azure OpenAI Example
|
|
# Uncomment and modify for Azure OpenAI setup
|
|
|
|
# llm:
|
|
# provider: azure_openai
|
|
# base_url: "https://your-resource.openai.azure.com"
|
|
# azure_deployment: "gpt-4-deployment-name"
|
|
# azure_api_version: "2024-10-21"
|
|
# api_key: "your-azure-key" # Or set via AZURE_OPENAI_API_KEY
|
|
# temperature: 1.0
|
|
# max_tokens: 8192
|
|
|
|
# embedder:
|
|
# provider: azure_openai
|
|
# base_url: "https://your-resource.openai.azure.com"
|
|
# azure_deployment: "embedding-deployment-name"
|
|
# azure_api_version: "2024-10-21"
|
|
# model: text-embedding-3-small
|
|
# api_key: "your-azure-key" # Or set via AZURE_OPENAI_API_KEY
|
|
|
|
---
|
|
# LiteLLM Multi-Provider Example
|
|
# Use LiteLLM for unified access to 100+ LLM providers
|
|
|
|
# llm:
|
|
# provider: litellm
|
|
# litellm_model: "azure/gpt-4-deployment" # Or "bedrock/claude-3", "ollama/llama2", etc.
|
|
# base_url: "https://your-resource.openai.azure.com" # For Azure
|
|
# api_key: "your-key"
|
|
# temperature: 1.0
|
|
# max_tokens: 8192
|
|
|
|
---
|
|
# Local Models Example
|
|
# Use Ollama or other local models via LiteLLM
|
|
|
|
# llm:
|
|
# provider: litellm
|
|
# litellm_model: "ollama/llama2"
|
|
# base_url: "http://localhost:11434"
|
|
# temperature: 0.8
|
|
# max_tokens: 4096
|