Build optimized vector indexes for billion-scale similarity search with FAISS.
npx skills add https://github.com/Signmanal/VIGIL --skill faiss-signmanal
Please help me install this Agent Skill. Skill: faiss Source: https://github.com/Signmanal/VIGIL/tree/main/optional-skills/mlops/faiss Command: npx skills add https://github.com/Signmanal/VIGIL --skill faiss-signmanal
Manually implementing efficient similarity search for large dense vector datasets is slow, unscalable, and requires deep expertise in index optimization and hardware acceleration, creating a major bottleneck for AI applications like retrieval-augmented generation, recommendation systems, and large-scale semantic search that need to retrieve relevant results in milliseconds even with billions of vectors.
Use the faiss skill to build an optimized vector index for your 1M+ text embedding dataset and run fast similarity searches to retrieve the most relevant documents for your RAG application.
High-intent search queries and answers about installing and using this skill.
Vector similarity search at billion-scale requires memory-efficient approximate search using product quantization and hierarchical graph-based index structures to retrieve relevant results in milliseconds.
K-nearest neighbor retrieval can be accelerated 10-100x using GPU hardware for indexing and search operations, enabling real-time similarity matching for production AI workloads.
Vector similarity search integrates natively with LangChain and LlamaIndex, allowing you to plug optimized vector indexing directly into existing retrieval-augmented generation pipelines.
Yes, multiple specialized index structures including Flat, IVF, HNSW, and Product Quantization allow you to balance search speed, memory usage, and accuracy for different dataset sizes.
Approximate nearest neighbor search supports L2 distance, inner product, and other common distance metrics for datasets ranging from thousands to billions of dense vectors.
GPU acceleration is ideal for real-time, high-throughput similarity matching in production workloads where 10-100x speedup for indexing and search operations is required.
AlvaroBianoBuild and query FAISS indices for billion-scale vector similarity search.
ldzhhxxIndex vectors from data/vectors.csv and search for similar vectors.
caio-moliveiraConstruct end-to-end RAG pipelines with LangChain for document question-answering.
robertbr123Implement vector similarity search with FAISS and NumPy.
