# Mini RAG

## Docs

- [AgenticRAG](https://vivek-78ace06c.mintlify.app/api-reference/agentic-rag.md): Main orchestrator class for the RAG pipeline
- [Chunker](https://vivek-78ace06c.mintlify.app/api-reference/chunker.md): Smart text chunking with Chonkie
- [LLMConfig](https://vivek-78ace06c.mintlify.app/api-reference/config/llm-config.md): Configure the language model for answer generation
- [ObservabilityConfig](https://vivek-78ace06c.mintlify.app/api-reference/config/observability-config.md): Configure monitoring and tracing with Langfuse
- [RerankerConfig](https://vivek-78ace06c.mintlify.app/api-reference/config/reranker-config.md): Configure the reranking strategy
- [RetrievalConfig](https://vivek-78ace06c.mintlify.app/api-reference/config/retrieval-config.md): Configure retrieval behavior and search strategy
- [DocumentLoader](https://vivek-78ace06c.mintlify.app/api-reference/document-loader.md): Load documents from multiple file formats
- [EmbeddingModel](https://vivek-78ace06c.mintlify.app/api-reference/embedding-model.md): Generate embeddings using OpenAI-compatible APIs
- [API Reference](https://vivek-78ace06c.mintlify.app/api-reference/introduction.md): Complete API reference for Mini RAG library
- [Cohere Reranker](https://vivek-78ace06c.mintlify.app/api-reference/rerankers/cohere.md): Use Cohere's specialized reranking models
- [LLM Reranker](https://vivek-78ace06c.mintlify.app/api-reference/rerankers/llm.md): Use your LLM for reranking
- [Rerankers Overview](https://vivek-78ace06c.mintlify.app/api-reference/rerankers/overview.md): Overview of reranking strategies in Mini RAG
- [Sentence Transformer Reranker](https://vivek-78ace06c.mintlify.app/api-reference/rerankers/sentence-transformer.md): Local cross-encoder models for reranking
- [VectorStore](https://vivek-78ace06c.mintlify.app/api-reference/vector-store.md): Milvus-powered vector storage and retrieval
- [Text Chunking](https://vivek-78ace06c.mintlify.app/core/chunking.md): Split documents into optimal chunks for embedding and retrieval
- [Document Loading](https://vivek-78ace06c.mintlify.app/core/document-loading.md): Load and parse documents from multiple file formats
- [Embeddings](https://vivek-78ace06c.mintlify.app/core/embeddings.md): Generate vector embeddings for semantic search
- [Core Concepts](https://vivek-78ace06c.mintlify.app/core/overview.md): Understanding Mini RAG's architecture and components
- [Vector Store](https://vivek-78ace06c.mintlify.app/core/vector-store.md): Store and search embeddings with Milvus
- [Chatbot with Conversation History](https://vivek-78ace06c.mintlify.app/examples/chatbot.md): Build an intelligent chatbot that remembers conversation context
- [Document Q&A System](https://vivek-78ace06c.mintlify.app/examples/document-qa.md): Build a question-answering system over your documents
- [FastAPI REST API](https://vivek-78ace06c.mintlify.app/examples/fastapi-integration.md): Deploy Mini RAG as a production-ready REST API with FastAPI
- [Research Paper Assistant](https://vivek-78ace06c.mintlify.app/examples/research-assistant.md): Build an AI assistant for analyzing and extracting insights from research papers
- [Agentic RAG](https://vivek-78ace06c.mintlify.app/features/agentic-rag.md): Intelligent RAG with query rewriting, retrieval, and re-ranking
- [Observability](https://vivek-78ace06c.mintlify.app/features/observability.md): Monitor and trace your RAG pipeline with Langfuse integration
- [Query Rewriting](https://vivek-78ace06c.mintlify.app/features/query-rewriting.md): Automatically generate query variations for better retrieval
- [Re-ranking](https://vivek-78ace06c.mintlify.app/features/reranking.md): Improve retrieval quality with multiple re-ranking strategies
- [Basic Usage](https://vivek-78ace06c.mintlify.app/guides/basic-usage.md): Learn the fundamentals of using Mini RAG in your projects
- [Configuration](https://vivek-78ace06c.mintlify.app/guides/configuration.md): Comprehensive guide to configuring Mini RAG for your needs
- [Integration Guide](https://vivek-78ace06c.mintlify.app/guides/integration.md): Learn how to integrate Mini RAG into your existing applications
- [Production Deployment](https://vivek-78ace06c.mintlify.app/guides/production.md): Best practices for deploying Mini RAG to production
- [Mini RAG](https://vivek-78ace06c.mintlify.app/index.md): A lightweight, modular, and production-ready RAG library built with Python
- [Installation](https://vivek-78ace06c.mintlify.app/installation.md): Install Mini RAG and set up your development environment
- [Quick Start](https://vivek-78ace06c.mintlify.app/quickstart.md): Build your first RAG application with Mini RAG in minutes

## OpenAPI Specs

- [openapi](https://vivek-78ace06c.mintlify.app/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/vivek12345/mini-rag)
- [PyPI](https://pypi.org/project/mini-rag/)
- [Community](https://github.com/vivek12345/mini-rag/discussions)