The AI Platform as a Service
Announcing NVIDIA NeMo Retriever NIM Now Included with Astra DB
DataStax AI PaaS helps you build RAG apps more quickly, from ingestion to production. We're excited to announce our integrations with NVIDIA's NeMo and our new AI Terraform Module.
Generative AI Leaders Shaping Their Industries
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.
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.
Developers
RAG Made Easier
An intuitive API and powerful integrations for production-level RAG workloads.
Install
Install the API clients
pip install astrapy
Connect
Create or connect to your database & collections
# The DataAPIClient lets you connect to your database
client = DataAPIClient("AstraCS:...")
db = client.get_database(
"https://<id>-<region>.apps.astra.datastax.com"
)
# create_collection() will return the newly created collection
collection = db.create_collection(
name="collection_test",
dimension=5,
)
# Or you can connect to an existing connection directly
collection = astra_db.get_collection("collection_test")
Insert
Insert into your vector store (collection)
collection.insert_one(
{
"name": "Coded Cleats",
"description": "Chat bot integrated sneakers that talk to you",
"$vector": [0.1, 0.15, 0.3, 0.12, 0.05],
}
)
Find
Find documents using vector search
documents = list(collection.find(
sort={"$vector": [0.15, 0.1, 0.1, 0.35, 0.55]},
limit=100,
))
$300/year in free credit and no credit card required.
Tutorials and sample generative AI apps with best practices.
Get started in minutes with generative AI and RAG.
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.
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.
