Pinecone Vector Store - Hybrid Search

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

python

%pip install llama-index-vector-stores-pinecone "transformers[torch]"

Creating a Pinecone Index

python

from pinecone import Pinecone, ServerlessSpec

python

import os

os.environ["PINECONE_API_KEY"] = "..."
os.environ["OPENAI_API_KEY"] = "sk-..."

api_key = os.environ["PINECONE_API_KEY"]

pc = Pinecone(api_key=api_key)

python

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

python

# 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-east-1"),
)

# 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
# 	 )
# )
#

python

pinecone_index = pc.Index("quickstart")

Download Data

python

!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

When add_sparse_vector=True, the PineconeVectorStore will compute sparse vectors for each document.

By default, it is using simple token frequency for the sparse vectors. But, you can also specify a custom sparse embedding model.

python

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

python

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

python

# set add_sparse_vector=True to compute sparse vectors during upsert
from llama_index.core 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
)

Query Index

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

python

# 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?")

python

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

Changing the sparse embedding model

python

%pip install llama-index-sparse-embeddings-fastembed

python

# Clear the vector store
vector_store.clear()

python

from llama_index.sparse_embeddings.fastembed import FastEmbedSparseEmbedding

sparse_embedding_model = FastEmbedSparseEmbedding(
    model_name="prithivida/Splade_PP_en_v1"
)

vector_store = PineconeVectorStore(
    pinecone_index=pinecone_index,
    add_sparse_vector=True,
    sparse_embedding_model=sparse_embedding_model,
)

python

index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

Wait a mininute for things to upload..

python

response = query_engine.query("What happened at Viaweb?")
display(Markdown(f"<b>{response}</b>"))