Skip to main content

Faiss

Skill Verified Active

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Purpose

To guide users on implementing efficient, high-performance similarity search for large vector datasets using Facebook's FAISS library.

Features

  • Explanation of FAISS library and its purpose
  • Guidance on selecting appropriate index types (Flat, IVF, HNSW, PQ)
  • Instructions for GPU acceleration and multi-GPU setups
  • Code examples for installation, basic usage, and framework integration

Use Cases

  • Implementing fast k-NN search on large vector datasets
  • Leveraging GPU acceleration for billion-scale vector retrieval
  • Performing pure vector similarity search without metadata filtering
  • Integrating FAISS into applications using LangChain or LlamaIndex

Non-Goals

  • Providing metadata filtering capabilities (direct users to Chroma/Pinecone)
  • Offering full database features (direct users to Weaviate)
  • Serving as a simpler alternative for smaller datasets (direct users to Annoy)

Trust

  • info:Issues AttentionThere are 17 open issues and 4 closed issues in the last 90 days, indicating a closure rate below 50% with a moderate number of open issues.

Execution

  • info:Pinned dependenciesThe SKILL.md lists dependencies like 'faiss-cpu', 'faiss-gpu', and 'numpy', but does not explicitly pin versions or provide a lockfile for these dependencies. The README installation uses 'pip install' which might not pin versions by default.

Practical Utility

  • info:Edge casesWhile the documentation covers index types and best practices, explicit documentation of failure modes (e.g., malformed input, missing dependency, rate-limit hits) with symptoms and recovery steps is absent.

Installation

npx skills add davila7/claude-code-templates

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified
94 /100
Analyzed 1 day ago

Trust Signals

Last commit1 day ago
Stars27.2k
LicenseMIT
Status
View Source

Similar Extensions

Faiss

98

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Skill
Orchestra-Research

Rag Architect

100

Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.

Skill
alirezarezvani

AgentDB Vector Search

99

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Skill
ruvnet

Qdrant Vector Search

95

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Skill
Orchestra-Research

TimesFM Forecasting

100

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Skill
K-Dense-AI

SHAP Model Interpretability

100

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Skill
K-Dense-AI

© 2025 SkillRepo · Find the right skill, skip the noise.