Curated papers, articles, and blogs on Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) in production. 🚀
Learn how organizations implement RAG with LLMs:
- How RAG is integrated with LLMs 🔎
- What techniques and architectures worked ✅ (and sometimes, what didn't ❌)
- Why it works, the science behind it with research, literature, and references 📂
- What real-world results were achieved (so you can better assess ROI ⏰💰📈)
- RAG Fundamentals
- Retrieval Techniques
- Document Processing
- Embedding Models
- Vector Databases
- Prompt Engineering for RAG
- LLM Integration
- Evaluation and Metrics
- Scaling and Optimization
- Use Cases and Applications
- Challenges and Limitations
- Tools and Frameworks
- Best Practices
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Paper)
- Improving language models by retrieving from trillions of tokens (Paper)
- Retrieval-Augmented Generation: A Survey (Paper)
- Awesome-RAG: A curated list of Retrieval Augmented Generation (RAG) resources
- RAG-Survey: A collection of papers and resources on Retrieval-Augmented Generation (RAG)
- Cohere RAG Guide: Comprehensive guide on implementing RAG
- Dense Passage Retrieval for Open-Domain Question Answering (Paper)
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval (Paper)
- ANCE: Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- FAISS: A library for efficient similarity search and clustering of dense vectors
- LangChain: Building applications with LLMs through composability
- Unstructured: Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, and transforming unstructured data
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (Paper)
- OpenAI API - Embeddings
- Sentence-Transformers: Compute dense vector representations for sentences, paragraphs, and images
- Pinecone: Vector Database for Machine Learning Applications
- Weaviate: Open Source Vector Database
- Pinecone Learning Center: RAG
- Hugging Face Transformers: State-of-the-art Machine Learning for PyTorch, TensorFlow, and JAX
- OpenAI API Documentation
- LaMDA: Language Models for Dialog Applications
- BlenderBot 3: A deployed conversational agent that continually learns to responsibly engage
- WebGPT: Browser-assisted question-answering with human feedback
- Constitutional AI: Harmlessness from AI Feedback
- DeepSpeed: Deep learning optimization library
- Optimizing RAG: Strategies for Production-Ready Systems
- Implementing Efficient RAG Systems: Best Practices and Optimization Techniques
- Building a Large Language Model Based Dialogue System with Retrieval Augmented Generation (Paper)
- RAG for Enterprise Search: Enhancing Information Retrieval with LLMs
- Revolutionizing Search: The Impact of Retrieval Augmented Generation (RAG) in AI
- Challenges and Applications of Large Language Models (Paper)
- On the Limitations of Large Language Models for Retrieval Tasks (Paper)