THE DATASTAX DIFFERENCE

Make Wild Things,
Possible

Take your ideas from concept to production with data that yields 20% higher relevance, and up to 74x faster response time with a one-stop Generative AI RAG + Vector stack.

Demo

Generative AI Leaders Shaping Their Industries

Skypoint
Hornet
Priceline
Dataworkz
PW
Capital One
Sourcetable
Hey YOU
Macquarie
concide
Restworld
Skypoint
Hornet
Priceline
Dataworkz
PW
Capital One
Sourcetable
Hey YOU
Macquarie
concide
Restworld
Skypoint
Hornet
Priceline
Dataworkz
PW
Capital One
Sourcetable
Hey YOU
Macquarie
concide
Restworld

One-stop GenAI Stack

A RAG API with all the data, tools, and an opinionated stack that just works. Both vector and structured data, secure, compliant, scalable, and supported. Integrated with LangChain, Vercel, GitHub Copilot and AI ecosystem leaders.

Video preview

Relevant GenAI FTW

Minimize hallucinations with up to 20% higher relevance, 74x faster response time, and 9x higher throughput than Pinecone all at 80% lower TCO. Read while indexing to make data updates available with zero delay.

Relevant GenAI FTW

"Astra DB isn't just a tool; it's an empowering force for developers to fully leverage GenAI's potential."

Santosh Maddila
Principal Data Scientist at Aviso AI

Fast Path to Production

Quickly take your GenAI idea into production. Deploy on the leader in production AI workloads and support global-scale on any cloud with enterprise level security and compliance.

Fast Path to Production

Shape the Wild

GenAI should be fun! An awesome developer experience for any JavaScript, Python, Java, and C++ dev to build production GenAI apps with LangChain, GitHub, Vercel, and the leading AI ecosystem partners.

Shape the Wild

Developers

RAG Made Easier

An intuitive API and powerful integrations for production-level RAG and FLARE.

Install

Install the Astra library

pythonjavascriptjava
pip install astrapy
npm install @datastax/astra-db-ts
Maven:
    <dependency>
        <groupId>com.datastax.astra</groupId>
        <artifactId>astra-db-client</artifactId>
        <version>1.2.4</version>
    </dependency>

Gradle:
    dependencies {
        implementation 'com.datastax.astra:astra-db-client:1.2.4'
    }

Create

Create or connect to existing collection

pythonjavascriptjava
# The return of create_collection() will return the collection
collection = astra_db.create_collection(
    collection_name="collection_test", dimension=5
)

# Or you can connect to an existing connection directly
collection = AstraDBCollection(
    collection_name="collection_test", astra_db=astra_db
)

# You don't even need the astra_db object
collection = AstraDBCollection(
    collection_name="collection_test", token=token, api_endpoint=api_endpoint
)
// Create a vector collection
const collection = await db.createCollection("collection_test", {
    vector: {
        dimension: 5,
        metric: "cosine",
    },
});

// Or you can connect to an existing collection
const collection = await db.collection('collection_test');
AstraDB db = new AstraDB("token", "endpoint");
AstraDBCollection collection = db.createCollection("vector_test", 5);

Insert

Inserting a vector object into your vector store (collection)

pythonjavascriptjava
collection.insert_one(
    {
        "_id": "5",
        "name": "Coded Cleats Copy",
        "description": "ChatGPT integrated sneakers that talk to you",
        "$vector": [0.25, 0.25, 0.25, 0.25, 0.25],
    }
)
const doc = await collection.insertOne({
    "_id": "5",
    "$vector":  [0.25, 0.25, 0.25, 0.25, 0.25],
    "name": "Coded Cleats Copy",
    "description": "ChatGPT integrated sneakers that talk to you",
});
collection.insertOne(new JsonDocument()
    .put("text", "ChatGPT integrated sneakers that talk to you")
    .vector(new float[]{0.1f, 0.15f, 0.3f, 0.12f, 0.05f}));

Find

Find documents using vector search

pythonjavascriptjava
documents = collection.vector_find(
    [0.15, 0.1, 0.1, 0.35, 0.55],
    limit=100,
)
const results = await collection.find(null, {
    sort: {
        $vector: [0.15, 0.1, 0.1, 0.35, 0.55],
    },
    limit: 100,
})
.toArray();
float[] embeddings = new float[] {0.1f, 0.15f, 0.3f, 0.12f, 0.05f};
Filter metadataFilter = new Filter().where("text", EQUALS_TO, "ChatGPT");
Stream<JsonDocumentResult> rag = 
  collection.findVector(embeddings, metadataFilter, 10);
Try For Free
Try For Free

$300/year in free credit and no credit card required.

Explore examples
Explore examples

Tutorials and sample Generative AI apps with best practices.

DOCS
DOCS

Get started in minutes with Generative AI and RAG.

What’s New

Ready to get started with Vector Search? 

Deliver Generative AI apps on the world’s most powerful, most scalable vector database.