Expand description
Configuration schema for RAG search pipeline
Provides comprehensive configuration for embedding providers, vector backends, hybrid retrieval, reranking, and context compression.
Structs§
- AiIngestion
Config - AI-powered ingestion configuration
- Anthropic
LlmConfig - Anthropic Claude LLM configuration
- Backend
Config - Backend configuration
- Context
Config - Context compression configuration
- Embedding
Config - Embedding configuration
- File
Config - File-based vector store configuration
- Index
Config - Index configuration
- Ollama
LlmConfig - Ollama LLM configuration
- Open
AiLlm Config - OpenAI LLM configuration
- Qdrant
Config - Qdrant-specific configuration
- Reranker
Config - Reranker configuration
- Retrieval
Config - Retrieval configuration
- Search
Config - Root search configuration
Enums§
- AiProvider
- LLM provider for AI-powered example generation
- Backend
Type - Vector store backend type
- Compression
Strategy - Compression strategy
- Fusion
Method - Fusion method for combining search results