FAISS Similarity Search

What it does

When your agent uses it

• Building fast k-nearest-neighbor search over millions of embeddings
• Choosing between Flat, IVF and HNSW indexes for a dataset size
• Cutting the memory use of a large vector index with product quantization
• Moving a vector index to the GPU for faster queries

Example prompts

• “Build a FAISS index over these few million sentence embeddings and fetch the ten nearest neighbors for a query.”
• “Switch my Flat index to IVF and tell me how to set nprobe.”
• “Save the trained FAISS index to disk and load it again in the search service.”
• “Use FAISS as the vector store in my LlamaIndex pipeline.”

Requirements

• Python with `faiss-cpu` installed
• NumPy

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Flat (exact search)
2. 2IVF (inverted file) - Fast approximate
3. 3HNSW (Hierarchical NSW) - Best quality/speed
4. 4Product Quantization - Memory efficient

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

FAISS Similarity Search loads about 1.3k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 210 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 210 words, ~1,261 tokens.

name

faiss

description

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.

version

1.0.0

author

Orchestra Research

license

MIT

tags

RAG, FAISS, Similarity Search, Vector Search, Facebook AI, GPU Acceleration, Billion-Scale, K-NN, HNSW, High Performance, Large Scale

dependencies

faiss-cpu, faiss-gpu, numpy

# CPU only
pip install faiss-cpu

# GPU support
pip install faiss-gpu

import faiss
import numpy as np

# Create sample data (1000 vectors, 128 dimensions)
d = 128
nb = 1000
vectors = np.random.random((nb, d)).astype('float32')

# Create index
index = faiss.IndexFlatL2(d)  # L2 distance
index.add(vectors)             # Add vectors

# Search
k = 5  # Find 5 nearest neighbors
query = np.random.random((1, d)).astype('float32')
distances, indices = index.search(query, k)

print(f"Nearest neighbors: {indices}")
print(f"Distances: {distances}")

# L2 (Euclidean) distance
index = faiss.IndexFlatL2(d)

# Inner product (cosine similarity if normalized)
index = faiss.IndexFlatIP(d)

# Slowest, most accurate

# Create quantizer
quantizer = faiss.IndexFlatL2(d)

# IVF index with 100 clusters
nlist = 100
index = faiss.IndexIVFFlat(quantizer, d, nlist)

# Train on data
index.train(vectors)

# Add vectors
index.add(vectors)

# Search (nprobe = clusters to search)
index.nprobe = 10
distances, indices = index.search(query, k)

# HNSW index
M = 32  # Number of connections per layer
index = faiss.IndexHNSWFlat(d, M)

# No training needed
index.add(vectors)

# Search
distances, indices = index.search(query, k)

# PQ reduces memory by 16-32×
m = 8   # Number of subquantizers
nbits = 8
index = faiss.IndexPQ(d, m, nbits)

# Train and add
index.train(vectors)
index.add(vectors)

# Save index
faiss.write_index(index, "large.index")

# Load index
index = faiss.read_index("large.index")

# Continue using
distances, indices = index.search(query, k)

# Single GPU
res = faiss.StandardGpuResources()
index_cpu = faiss.IndexFlatL2(d)
index_gpu = faiss.index_cpu_to_gpu(res, 0, index_cpu)  # GPU 0

# Multi-GPU
index_gpu = faiss.index_cpu_to_all_gpus(index_cpu)

# 10-100× faster than CPU

from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings

# Create FAISS vector store
vectorstore = FAISS.from_documents(docs, OpenAIEmbeddings())

# Save
vectorstore.save_local("faiss_index")

# Load
vectorstore = FAISS.load_local(
    "faiss_index",
    OpenAIEmbeddings(),
    allow_dangerous_deserialization=True
)

# Search
results = vectorstore.similarity_search("query", k=5)

from llama_index.vector_stores.faiss import FaissVectorStore
import faiss

# Create FAISS index
d = 1536
faiss_index = faiss.IndexFlatL2(d)

vector_store = FaissVectorStore(faiss_index=faiss_index)

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in 15-rag/faiss of Orchestra-Research/AI-Research-SKILLs.

• SKILL.md
• references/index_types.md

Open the folder on GitHubat commit 773a529

Used in 6 other repositories

We found 6 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in Orchestra-Research/AI-Research-SKILLs, which our catalogue first saw on October 7, 2026.

• Tommy-yw/RunbookHermesoptional-skills/mlops/faiss
• Luciole-Studio/Misaka-Agentmisaka/core/skills/assets/optional/mlops/faiss
• davila7/claude-code-templatescli-tool/components/skills/ai-research/rag-faiss
• NousResearch/hermes-agentoptional-skills/mlops/faiss
• johnson7788/MultiUserClawhermes-agent/optional-skills/mlops/faiss
• OpenLAIR/dr-clawskills/rag/faiss