DashVector Vector Store

If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.

python

%pip install llama-index-vector-stores-dashvector

python

!pip install llama-index

python

import logging
import sys
import os

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

Creating a DashVector Collection

python

import dashvector

python

api_key = os.environ["DASHVECTOR_API_KEY"]
client = dashvector.Client(api_key=api_key)

python

# dimensions are for text-embedding-ada-002
client.create("llama-demo", dimension=1536)

python

dashvector_collection = client.get("quickstart")

Download Data

python

!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'

Load documents, build the DashVectorStore and VectorStoreIndex

python

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.dashvector import DashVectorStore
from IPython.display import Markdown, display

python

# load documents
documents = SimpleDirectoryReader("./data/paul_graham").load_data()

python

# initialize without metadata filter
from llama_index.core import StorageContext

vector_store = DashVectorStore(dashvector_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

Query Index

python

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")

python

display(Markdown(f"<b>{response}</b>"))