Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

Awesome-RAG

😎 Awesome list of Retrieval-Augmented Generation (RAG) applications in Generative AI.
https://github.com/Danielskry/Awesome-RAG

Last synced: about 5 hours ago
JSON representation

💾 Databases
- Benchmarks
  - Picking a vector database
- Other Database Systems:
  - Neo4j
  - Qdrant - source vector database designed for similarity search.
  - Redis Stack - memory data structure store used as a database, cache, and message broker.
  - Azure Cosmos DB - model database service with integrated vector search.
  - Couchbase
  - Lantern - aware personal search engine.
  - LlamaIndex - memory vector store for rapid experimentation.
  - SurrealDB - model database optimized for time-series data.
  - Weaviate - source cloud-native vector search engine.
- Distributed Data Processing and Serving Engines:
  - Apache Cassandra
  - MongoDB Atlas - model database service with integrated vector search.
  - Vespa - source big data processing and serving engine designed for real-time applications.
- Search Engines with Vector Capabilities:
  - Elasticsearch
  - OpenSearch
- Vector Databases:
  - Chroma DB - native open-source embedding database.
  - Milvus - source vector database for AI-powered applications.
  - Pinecone
  - Oracle AI Vector Search
- Relational Database Extensions:
  - Pgvector - source extension for vector similarity search in PostgreSQL.
- Vector Search Libraries and Tools:
  - FAISS - scale datasets and optimized for fast retrieval of nearest neighbors.
🛠️ Techniques
- Prompting
- Chunking
- Embeddings
  - MTEB Leaderboard
- Retrieval
- Data cleaning
  - Data cleaning techniques - processing steps to refine input data and improve model performance.
🎯 Approaches
- RAG Fusion
- Temporal Augmented Retrieval - sensitive data in retrieval processes.
- Plan-then-RAG
- GraphRAG
- FLARE - An approach that incorporates active retrieval-augmented generation to improve response quality.
- Contextual Retrieval - Improves retrieval by adding relevant context to document chunks before retrieval, enhancing the relevance of information retrieved from large knowledge bases.
- Corrective RAG
- Retrieval-Augmented Fine-Tuning - tune LLMs specifically for enhanced retrieval and generation tasks.
- Self Reflective RAG
- Agentic RAG
- GNN-RAG
🧰 Frameworks that Facilitate RAG
- Haystack - LLM orchestration framework to build customizable, production-ready LLM applications.
- LangChain - An all-purpose framework for working with LLMs.
- Semantic Kernel - An SDK from Microsoft for developing Generative AI applications.
- LlamaIndex - Framework for connecting custom data sources to LLMs.
- Cognita - Open-source RAG framework for building modular and production ready applications.
- Verba - Open-source application for RAG out of the box.
- Mastra - Typescript framework for building AI applications.
📊 Metrics
- Search metrics
- Response Evaluation Metrics
  - LangFuse - source tool for tracking LLM metrics, observability, and prompt management.
  - LangSmith - grade LLM applications, allows you to closely monitor and evaluate your application.
  - Hugging Face Evaluate
  - Weights & Biases
  - Ragas

Programming Languages

Python 7 Go 2 Rust 2 Java 2 TypeScript 2 C++ 1 C 1 C# 1

Categories

🛠️ Techniques 25 💾 Databases 21 🎯 Approaches 11 📊 Metrics 10 🧰 Frameworks that Facilitate RAG 7

Sub Categories

Chunking 10 Other Database Systems: 9 Prompting 8 Search metrics 5 Response Evaluation Metrics 5 Retrieval 5 Vector Databases: 4 Distributed Data Processing and Serving Engines: 3 Search Engines with Vector Capabilities: 2 Embeddings 1 Data cleaning 1 Vector Search Libraries and Tools: 1 Benchmarks 1 Relational Database Extensions: 1

Keywords

llm 6 ai 4 rag 3 nearest-neighbor-search 3 machine-learning 3 semantic-search 2 openai 2 search-engine 2 deep-learning 2 llmops 2 mlops 2 approximate-nearest-neighbor-search 2 typescript 2 vector-search 2 vector-database 2 image-search 2 hnsw 2 distributed 2 evaluation 2 analytics 2 gpt 2 database 2 llms 2 graph-database 2 generative-ai 2 information-retrieval 2 language-model 2 large-language-models 2 python 2 pytorch 2 nosql 2 retrieval-augmented-generation 2 playground 1 llm-evaluation 1 llama-index 1 prompt-engineering 1 llm-observability 1 langchain 1 monitoring 1 prompt-management 1 observability 1 open-source 1 self-hosted 1 ycombinator 1 gpt-4 1 gpt4 1 graphrag 1 bert 1 chatgpt 1 gpt-3 1