Zvec

import zvec

schema = zvec.CollectionSchema(
    name="example",
    vectors=zvec.VectorSchema("embedding", zvec.DataType.VECTOR_FP32, 4),
)
collection = zvec.create_and_open(path="./zvec_example", schema=schema)

import zvecschema = zvec.CollectionSchema(    name="example",    vectors=zvec.VectorSchema("embedding", zvec.DataType.VECTOR_FP32, 4),)collection = zvec.create_and_open(path="./zvec_example", schema=schema)

import zvec

collection = zvec.open("./zvec_example")
collection.insert(zvec.Doc(id="1", vectors={"embedding": [0.1, 0.2, 0.3, 0.4]}))

import zveccollection = zvec.open("./zvec_example")collection.insert(zvec.Doc(id="1", vectors={"embedding": [0.1, 0.2, 0.3, 0.4]}))

import zvec

collection = zvec.open("./zvec_example")
results = collection.query(
    vectors=zvec.VectorQuery("embedding", vector=[0.4, 0.3, 0.3, 0.1]),
    topk=10,
)

import zveccollection = zvec.open("./zvec_example")results = collection.query(    vectors=zvec.VectorQuery("embedding", vector=[0.4, 0.3, 0.3, 0.1]),    topk=10,)

Blazing-Fast Performance

Benchmarked on the Cohere 10M vector dataset —— View full benchmark report

10MTotal Vectors Indexed

~1 HourIndex Build Time

8500+Queries per Second (QPS)

Build Powerful AI Applications

📚

RAG (Retrieval-Augmented Generation)

Enhance LLM responses with information retrieved from your knowledge base

🖼️

Image Search

Find visually or semantically similar images at scale

💻

Code Search

Find code snippets by describing what you want in natural language