Pinecone Vector Store - Hybrid Search

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

!pip install llama-index>=0.9.31 pinecone-client>=3.0.0 "transformers[torch]"

Creating a Pinecone Index

import logging
import sys

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

from pinecone import Pinecone, ServerlessSpec

import os

os.environ[
    "PINECONE_API_KEY"
] = #"<Your Pinecone API key, from app.pinecone.io>"
os.environ[
    "OPENAI_API_KEY"
] = "sk-..."

api_key = os.environ["PINECONE_API_KEY"]

pc = Pinecone(api_key=api_key)

# delete if needed
# pc.delete_index("quickstart")

# dimensions are for text-embedding-ada-002
# NOTE: needs dotproduct for hybrid search

pc.create_index(
    name="quickstart",
    dimension=1536,
    metric="dotproduct",
    spec=ServerlessSpec(cloud="aws", region="us-west-2"),
)

# If you need to create a PodBased Pinecone index, you could alternatively do this:
#
# from pinecone import Pinecone, PodSpec
#
# pc = Pinecone(api_key='xxx')
#
# pc.create_index(
# 	 name='my-index',
# 	 dimension=1536,
# 	 metric='cosine',
# 	 spec=PodSpec(
# 		 environment='us-east1-gcp',
# 		 pod_type='p1.x1',
# 		 pods=1
# 	 )
# )
#

pinecone_index = pc.Index("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, build the PineconeVectorStore

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores import PineconeVectorStore
from IPython.display import Markdown, display

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

# set add_sparse_vector=True to compute sparse vectors during upsert
from llama_index.storage.storage_context import StorageContext

if "OPENAI_API_KEY" not in os.environ:
    raise EnvironmentError(f"Environment variable OPENAI_API_KEY is not set")

vector_store = PineconeVectorStore(
    pinecone_index=pinecone_index,
    add_sparse_vector=True,
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"

Query Index

May need to wait a minute or two for the index to be ready

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(vector_store_query_mode="hybrid")
response = query_engine.query("What happened at Viaweb?")

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

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

At Viaweb, Lisp was used as a programming language. The speaker gave a talk at a Lisp conference about how Lisp was used at Viaweb, and afterward, the talk gained a lot of attention when it was posted online. This led to a realization that publishing essays online could reach a wider audience than traditional print media. The speaker also wrote a collection of essays, which was later published as a book called “Hackers & Painters.”