Qdrant Vector Store

Creating a Qdrant client

import logging
import sys

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

import qdrant_client

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>",
)

Load documents, build the GPTQdrantIndex

from llama_index import GPTVectorStoreIndex, SimpleDirectoryReader
from IPython.display import Markdown, display

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

from llama_index.vector_stores.qdrant import QdrantVectorStore


vector_store = QdrantVectorStore(client=client, collection_name='paul_graham')
index = GPTVectorStoreIndex.from_documents(documents)

INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens
> [build_index_from_nodes] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 20729 tokens
> [build_index_from_nodes] Total embedding token usage: 20729 tokens

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?")

INFO:llama_index.token_counter.token_counter:> [retrieve] Total LLM token usage: 0 tokens
> [retrieve] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [retrieve] Total embedding token usage: 8 tokens
> [retrieve] Total embedding token usage: 8 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total LLM token usage: 1920 tokens
> [get_response] Total LLM token usage: 1920 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total embedding token usage: 0 tokens
> [get_response] Total embedding token usage: 0 tokens

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

Growing up, the author wrote short stories, programmed on an IBM 1401, and nagged his father to buy him a TRS-80 microcomputer. He wrote simple games, a program to predict how high his model rockets would fly, and a word processor. He also studied philosophy in college, but switched to AI after becoming bored with it. He then took art classes at Harvard and applied to art schools, eventually attending RISD.

# 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 Y Combinator?")

INFO:llama_index.token_counter.token_counter:> [retrieve] Total LLM token usage: 0 tokens
> [retrieve] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [retrieve] Total embedding token usage: 14 tokens
> [retrieve] Total embedding token usage: 14 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total LLM token usage: 1931 tokens
> [get_response] Total LLM token usage: 1931 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total embedding token usage: 0 tokens
> [get_response] Total embedding token usage: 0 tokens

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

After his time at Y Combinator, the author continued to write essays and work on other projects. He also wrote Hacker News in Arc, a programming language, and worked on a new version of Arc. He also continued to work on other projects, such as a news aggregator for startup founders. He eventually took Robert Morris' advice and made sure Y Combinator wasn't the last cool thing he did.