Qdrant Vector Store

Creating a Qdrant client

import logging
import os
import sys

import qdrant_client
from IPython.display import Markdown, display
from llama_index import (VectorStoreIndex, LLMPredictor, ServiceContext,
                         SimpleDirectoryReader)
from llama_index.storage.storage_context import StorageContext
from llama_index.vector_stores.qdrant import QdrantVectorStore

If running this for the first, time, install using this command:

!pip install -U 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>",
)

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

Load documents, build the VectorStoreIndex

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

service_context = ServiceContext.from_defaults()
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, service_context=service_context
)

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: 1966 tokens
> [get_response] Total LLM token usage: 1966 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 was also haunted by the idea that "No one works harder than the boss," and worked hard even at the parts of the job he didn't like. Eventually, he took Robert Morris' advice and decided to make sure Y Combinator wasn't the last cool thing he did.