vector store

A database optimized for storing and querying high-dimensional embedding vectors using approximate nearest-neighbor (ANN) search algorithms.

Syntax

rag

store.add(id, vector, metadata)
results = store.search(query_vector, top_k=5)

Example

rag

# Chroma vector store:
import chromadb

client = chromadb.Client()
collection = client.create_collection("docs")

# Add embeddings:
collection.add(
    documents=chunk_texts,
    embeddings=embeddings.tolist(),
    ids=[f"chunk_{i}" for i in range(len(chunk_texts))]
)

# Query:
results = collection.query(
    query_embeddings=[query_embedding],
    n_results=3
)