RAG Models & Pipelines
Explore popular RAG architectures and pre-built pipelines to accelerate your development.LangChain RAG
Build RAG applications with LangChain’s modular framework for document loading, splitting, embedding, and retrieval.
LlamaIndex
Data framework for LLM applications with advanced indexing and query capabilities.
Haystack
Open-source framework for building production-ready NLP pipelines with RAG support.
RAGatouille
Easy-to-use library for state-of-the-art ColBERT-based retrieval.
Embedding Models
Choose the right embedding model for your use case.OpenAI Embeddings
text-embedding-3-small and text-embedding-3-large for high-quality semantic search.
Cohere Embed
Multilingual embeddings optimized for search and retrieval.
Sentence Transformers
Open-source models for generating sentence and document embeddings.
Voyage AI
Domain-specific embeddings for legal, finance, code, and more.
Vector Databases
Store and query your embeddings efficiently.Pinecone
Managed vector database with hybrid search.
Weaviate
Open-source vector search engine.
Qdrant
High-performance vector similarity search.
Chroma
AI-native open-source embedding database.
Milvus
Scalable vector database for AI applications.
pgvector
Vector similarity search for PostgreSQL.
Ardie Resources
Tools and guides we’ve created to help you succeed with RAG.RAG Best Practices
Our comprehensive guide to building production-ready RAG systems.
Chunking Strategies
How to split documents for optimal retrieval performance.
Evaluation Metrics
Measure and improve your RAG pipeline’s accuracy.
Hybrid Search Guide
Combine keyword and semantic search for better results.
Blog Posts
Read our latest articles on RAG, knowledge bases, and AI-powered search.Visit the Ardie Blog
Explore all our articles on RAG architecture, implementation tips, and industry use cases.
Have a resource suggestion? Let us know and we’ll consider adding it to this page.