Astra DB

DataStax Astra DB is a serverless vector-capable database built on Apache Cassandra and accessed through an easy-to-use JSON API.

To run this notebook you need a DataStax Astra DB instance running in the cloud (you can get one for free at datastax.com).

You should ensure you have llama-index and astrapy installed:

!pip install llama-index
!pip install "astrapy>=0.6.0"

Please provide database connection parameters and secrets:

import os
import getpass

api_endpoint = input(
    "\nPlease enter your Database Endpoint URL (e.g. 'https://4bc...datastax.com'):"
)

token = getpass.getpass(
    "\nPlease enter your 'Database Administrator' Token (e.g. 'AstraCS:...'):"
)

os.environ["OPENAI_API_KEY"] = getpass.getpass(
    "\nPlease enter your OpenAI API Key (e.g. 'sk-...'):"
)

Import needed package dependencies:

from llama_index import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    StorageContext,
)
from llama_index.vector_stores import AstraDBVectorStore

Load some example data:

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

Read the data:

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
print(f"Total documents: {len(documents)}")
print(f"First document, id: {documents[0].doc_id}")
print(f"First document, hash: {documents[0].hash}")
print(
    "First document, text"
    f" ({len(documents[0].text)} characters):\n{'='*20}\n{documents[0].text[:360]} ..."
)

Create the Astra DB Vector Store object:

astra_db_store = AstraDBVectorStore(
    token=token,
    api_endpoint=api_endpoint,
    collection_name="astra_v_table",
    embedding_dimension=1536,
)

Build the Index from the Documents:

storage_context = StorageContext.from_defaults(vector_store=astra_db_store)

index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

Query using the index:

query_engine = index.as_query_engine()
response = query_engine.query("Why did the author choose to work on AI?")

print(response.response)