A curated list of awesome resources for Retrieval-Augmented Generation (RAG) in Large Language Models. Each resource is carefully selected and includes relevant information.
This repository is actively maintained and welcomes contributions from the community to keep the resource list up-to-date with the latest developments in RAG technology😄.
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| 🔥[Survey] Retrieval-Augmented Generation for Large Language Models: A Survey | [pdf] | 2023.12 | ��️ | |
| [Survey] Retrieval-Augmented Generation for AI-Generated Content: A Survey | [pdf] | 2024.02 | [RAG-Survey]  |
⭐️ |
| 🔥[Survey] A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions | [pdf] | 2024.10 | ⭐️⭐️ | |
| [Survey] Survey of Vector Database Management Systems | [pdf] | 2023.10 | ⭐️ |
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| Query Rewriting for Retrieval-Augmented Large Language Models | [pdf] | 2023.05 | ⭐️ | |
| Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks | [pdf] | 2024.07 | ⭐️ | |
| RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation | [pdf] | 2024.08 | [RAGFoundry]  |
⭐️ |
| A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data | [pdf] | 2024.12 | ��️ | ⭐️ |
| 🔥Generate rather than Retrieve: Large Language Models are Strong Context Generators | [pdf] | 2022.09 | [GenRead]  |
⭐️⭐️ |
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| 🔥TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT | [pdf] | 2023.07 | ⭐️⭐️ | |
| KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases | [pdf] | 2023.08 | ⭐️ | |
| Knowledge Graph Prompting for Multi-Document Question Answering | [pdf] | 2023.08 | [KG-LLM-MDQA]  |
⭐️ |
| G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering | [pdf] | 2024.02 | [G-Retriever]  |
⭐️ |
| Chain-of-Verification Reduces Hallucination in Large Language Models | [pdf] | 2023.09 | ����� | ⭐️ |
| 🔥Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine | [pdf] | 2024.01 | ⭐️⭐️ | |
| Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata | [pdf] | 2024.06 | [Multi-Meta-RAG]  |
⭐️ |
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| 🔥Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking | [pdf] | 2023.10 | [llm-qlm]  |
⭐️⭐️ |
| LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression | [pdf] | 2023.10 | ⭐️ | |
| Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! | [pdf] | 2023.03 | ⭐️ |
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions | [pdf] | 2022.12 | [ircot]  |
⭐️ |
| 🔥Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy | [pdf] | 2023.05 | ⭐️⭐️ | |
| 🔥Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection | [pdf] | 2023.10 | ⭐️⭐️ |
| Title | Paper | Date | Code | Domain | Recom |
|---|---|---|---|---|---|
| Improving language models by retrieving from trillions of tokens | [pdf] | 2021.12 | QA | ⭐️ | |
| DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services | [pdf] | 2023.09 | [DISC-LawLLM]  |
Law | ⭐️ |
| 🔥EVOR: Evolving Retrieval for Code Generation | [pdf] | 2024.02 | [arks]  |
Code | ⭐️⭐️ |
| 🔥CodeS: Towards Building Open-source Language Models for Text-to-SQL | [pdf] | 2024.02 | SQL | ⭐️⭐️ | |
| 🔥Retrieval-Augmented Text-to-Audio Generation | [pdf] | 2023.09 | Audio | ⭐️⭐️ | |
| An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval | [pdf] | 2024.07 | Video | ⭐️ | |
| 🔥Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners | [pdf] | 2022.05 | [VidIL]  |
Video | ⭐️⭐️ |
| Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension | [pdf] | 2024.11 | Video | ⭐️ |
| Title | Paper | Date | Code | Recom |
|---|---|---|---|---|
| Benchmarking Large Language Models in Retrieval-Augmented Generation | [pdf] | 2023.09 | ⭐️ | |
| 🔥Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering | [pdf] | 2024.11 | ⭐️⭐️ | |
| RAGAS: Automated Evaluation of Retrieval Augmented Generation | [pdf] | 2023.09 | [ragas]  |
⭐️ |
| CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | [pdf] | 2024.12 | ⭐️ | |
| 🔥RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework | [pdf] | 2024.08 | [RAGEval]  |
⭐️⭐️ |
- What is RAG? - Pinecone's comprehensive introduction to RAG
- RAG Architecture Guide - DataStax's detailed RAG architecture explanation
- RAG Best Practices - Anyscale's comprehensive guide for RAG applications
- Best Practices for LLM Evaluation of RAG Applications - Databricks' guide on RAG evaluation
- OpenAI Cookbook RAG Examples - How to Combine GPT-4o Mini with RAG - Create a Clothing Matchmaker App
- Optimizing RAG Applications - Secrets to Optimizing RAG LLM Apps for Better Performance, Accuracy and Lower Costs!
| Name | Description | Pros | Cons | Stars |
|---|---|---|---|---|
| ChromaDB | Open-source embedding database | • Lightweight deployment • Easy integration • Local & server modes |
• Limited scalability • Not for large-scale production |
 |
| FAISS | Library for efficient similarity search | • High performance • Memory efficient • GPU acceleration |
• Steep learning curve • Storage layer needed |
 |
| Milvus | Highly scalable vector database | • High scalability • Rich index types • Production-ready |
• Complex deployment • Resource intensive |
 |
| Weaviate | Vector database with generative search | • Built-in generative search • GraphQL interface • Modular design |
• Complex configuration • High memory usage |
 |
| Qdrant | Vector similarity search engine | • Powerful filtering • High performance • Easy deployment |
• Smaller community • Newer features |
 |
| Vespa | Real-time data processing engine | • Strong real-time processing • Feature-rich • High availability |
• Complex setup • Steep learning curve |
 |
| pgvector | PostgreSQL vector extension | • PostgreSQL integration • Transaction support • Familiar SQL interface |
• Average performance • Limited scalability |
 |
| LanceDB | Serverless vector database | • Developer friendly • Serverless architecture • Lightweight |
• Basic features • Newer community |
 |
| Pinecone | Managed vector database | • Zero maintenance • Good scalability • Enterprise support |
• Paid service • Storage limitations • Variable latency |
| Name | Description | Pros | Cons | Stars |
|---|---|---|---|---|
| LangChain | Framework for developing LLM applications | • Rich ecosystem • Active community • Extensive integrations |
• Complex architecture • Steep learning curve |
 |
| LlamaIndex | Data framework for LLM applications | • Data-centric design • Easy to use • Good documentation |
• Less flexible • Limited customization |
 |
| Unstructured | Data preprocessing library | • Multiple file formats • Clean extraction • Easy integration |
• Limited advanced features • Processing speed |
 |
| txtai | All-in-one embeddings database | • Lightweight • Simple API • Built-in workflows |
• Less enterprise features • Smaller community |
 |
| Semantic Kernel | Microsoft's orchestration SDK | • Strong Microsoft integration • Memory management • Enterprise support |
• Microsoft ecosystem focused • Less community plugins |
 |
| Embedchain | RAG framework | • Easy to use • Data source adaptors • Quick prototyping |
• Less production features • Limited customization |
 |
| Ragatouille | RAG experimentation toolkit | • Research focused • Advanced RAG features • Flexible architecture |
• Early stage • Less documentation |
 |
Feel free to submit Pull Requests to help grow this list! Please ensure:
- 📚The resource is relevant to RAG
- ✅ Follow the existing format
- ✅ Check for duplicates before submitting
Let's make this resource list even better together! 🌟
