The Smarter Database for AI.

The vector database that extends the knowledge of Generative AI applications with contextual search at scale.

Hero image

import pandas as pd
import numpy as np

df = pd.DataFrame({
	'id': ['id1', 'id2', 'id3'],
	'tag': ['tag1', 'tag2', 'tag3'],
	'text': ['text1', 'text2', 'text3'],
	'embeddings': np.random.rand(3, 1536).tolist()

schema = {
		{'name': 'id', 'pytype': 'str'},
		{'name': 'tag', 'pytype': 'str'},
		{'name': 'text', 'pytype': 'bytes'},
		{'name': 'embeddings', 'vectorIndex': {
			'type': 'hnsw',
			'metric': 'L2',
			'dims': 1536 }}
table = session.create_table('documents', schema)

query = np.random.rand(1, 1536).tolist(), n=1)

Explore our Cloud Starter Edition for experimentation, or opt for the customizable Server Edition to deploy at scale.

Review documentation

Explore our Samples

Turn unstructured data into actionable insights with accuracy and speed. Here’s why developers are choosing KDB.AI:


Simplify querying using Python or REST APIs


Scale to billion vector search across your enterprise data


Prefilter search with fast, targeted data selection


Analyze, search, and index with real-time processing

Perfect for Retrieval Augmented Generation, KDB.AI extends knowledge bases for LLMs so you can develop enterprise-grade Generative AI solutions.

Boost performance with a variety of indexing methods and fast ingestion

Use popular tools like LangChain or OpenAI

Compare data from different moments in time to analyze trends or changes

Use metadata pre-filtering to optimize search performance and accuracy

Store, index, and query all data types including text, video, audio, and images

More data compression and reduced memory usage, all without needing GPU

Vector Wireframe Brain

New to vector databases? Master the basics and explore key use cases like semantic search, recommendation systems, and anomaly detection.