aivrar/portable-hermes-agent/faiss

# 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)