Qdrant Vector Store

Creating a Qdrant client

%pip install llama-index-vector-stores-qdrant llama-index-readers-file llama-index-embeddings-fastembed llama-index-llms-openai

import logging
import sys
import os

import qdrant_client
from IPython.display import Markdown, display
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core import StorageContext
from llama_index.vector_stores.qdrant import QdrantVectorStore
from llama_index.embeddings.fastembed import FastEmbedEmbedding
from llama_index.core import Settings

Settings.embed_model = FastEmbedEmbedding(model_name="BAAI/bge-base-en-v1.5")

If running for the first, time, install the dependencies using:

!pip install -U qdrant_client fastembed

Set your OpenAI key for authenticating the LLM

%env OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>

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

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 the documents

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

Build the VectorStoreIndex

client = qdrant_client.QdrantClient(
    # you can use :memory: mode for fast and light-weight experiments,
    # it does not require to have Qdrant deployed anywhere
    # but requires qdrant-client >= 1.1.1
    location=":memory:"
    # otherwise set Qdrant instance address with:
    # uri="http://<host>:<port>"
    # set API KEY for Qdrant Cloud
    # api_key="<qdrant-api-key>",
)

vector_store = QdrantVectorStore(client=client, collection_name="paul_graham")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
)

Query Index

# 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?")

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

The author worked on writing and programming before college.

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query(
    "What did the author do after his time at Viaweb?"
)

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

The author arranged to do freelance work for a group that did projects for customers after his time at Viaweb.

Build the VectorStoreIndex asynchronously

# To connect to the same event-loop,
# allows async events to run on notebook

import nest_asyncio

nest_asyncio.apply()

aclient = qdrant_client.AsyncQdrantClient(
    # you can use :memory: mode for fast and light-weight experiments,
    # it does not require to have Qdrant deployed anywhere
    # but requires qdrant-client >= 1.1.1
    location=":memory:"
    # otherwise set Qdrant instance address with:
    # uri="http://<host>:<port>"
    # set API KEY for Qdrant Cloud
    # api_key="<qdrant-api-key>",
)

vector_store = QdrantVectorStore(
    aclient=aclient, collection_name="paul_graham", prefer_grpc=True
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
    use_async=True,
)

Async Query Index

query_engine = index.as_query_engine(use_async=True)
response = await query_engine.aquery("What did the author do growing up?")

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

The author worked on writing short stories and programming, particularly on an IBM 1401 computer in 9th grade using an early version of Fortran. Later, the author transitioned to working on microcomputers, starting with a TRS-80 in about 1980, where they wrote simple games, programs, and a word processor.

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(use_async=True)
response = await query_engine.aquery(
    "What did the author do after his time at Viaweb?"
)

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

The author went on to co-found Y Combinator after his time at Viaweb.