Faiss is a C++ library with Python and numpy wrappers for efficient similarity search and clustering of dense vectors, developed primarily at Meta's Fundamental AI Research group. It handles billions of embeddings within a fixed memory budget by offering two distinct scaling strategies: compact quantization codes that compress representations to fit in RAM (trading precision for scale), and graph-based indexes like HNSW and NSG that layer structure over raw vectors for speed.
- The GPU path is a drop-in replacement; swapping `IndexFlatL2` for `GpuIndexFlatL2` handles memory copies automatically
- The only hard dependency is a BLAS implementation; CUDA, ROCm, and the Python interface are all optional
- It explicitly includes tooling for parameter tuning rather than hiding the trade-offs, and maintains a dedicated troubleshooting page
- The GPU path is a drop-in replacement; swapping `IndexFlatL2` for `GpuIndexFlatL2` handles memory copies automatically
- The only hard dependency is a BLAS implementation; CUDA, ROCm, and the Python interface are all optional
- It explicitly includes tooling for parameter tuning rather than hiding the trade-offs, and maintains a dedicated troubleshooting page
SciPhi-AI/R2R is a framework for rapid development and deployment of production-ready RAG pipelines. The framework enables the deployment, customization, extension, autoscaling, and optimization of RAG pipeline systems, making it easier for the OSS community to use them. It includes several code examples and client applications that demonstrate application deployment and interaction. The core abstractions come in the form of ingestion, embedding, RAG, and eval pipelines.
