DashVector Vector Store - Hybrid Search#

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

!pip3 install llama-index dashvector dashtext

import logging
import sys
import os

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

Create a DashVector Collection#

import dashvector

api_key = os.environ["DASHVECTOR_API_KEY"]
endpoint = os.environ["DASHVECTOR_ENDPOINT"]

client = dashvector.Client(api_key=api_key, endpoint=endpoint)

# delete if needed
# client.delete("quickstart")

# dimensions are for text-embedding-ada-002
# NOTE: Sparse Vector only supported for dotproduct metric
client.create("quickstart", dimension=1536, metric="dotproduct")

dashvector_collection = client.get("quickstart")

Download 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'

Load documents#

from llama_index import SimpleDirectoryReader

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

Build The VectorStoreIndex with DashVectorStore#

from llama_index import VectorStoreIndex
from llama_index.vector_stores import DashVectorStore
from llama_index.storage.storage_context import StorageContext

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

Query with Default Query Engine#

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")

from IPython.display import Markdown, display

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

The author, growing up, worked on writing and programming outside of school. They wrote short stories and tried writing programs on an IBM 1401 computer. They later got a microcomputer and started programming more extensively, writing simple games and a word processor.

Query with Hybrid Query Mode#

query_engine = index.as_query_engine(vector_store_query_mode="hybrid")
response = query_engine.query("What did the author do growing up?")

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

The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade.