Pinecone Embeddings
Pinecone's inference API can be accessed viaPineconeEmbeddings. Providing text embeddings via the Pinecone service. We start by installing prerequisite libraries:
!pip install-qU"langchain-pinecone>=0.2.0"
Next, wesign up / log in to Pinecone to get our API key:
import os
from getpassimport getpass
os.environ["PINECONE_API_KEY"]= os.getenv("PINECONE_API_KEY")or getpass(
"Enter your Pinecone API key: "
)
Check the document for availablemodels. Now we initialize our embedding model like so:
from langchain_pineconeimport PineconeEmbeddings
embeddings= PineconeEmbeddings(model="multilingual-e5-large")
API Reference:PineconeEmbeddings
From here we can create embeddings either sync or async, let's start with sync! We embed a single text as a query embedding (ie what we search with in RAG) usingembed_query:
docs=[
"Apple is a popular fruit known for its sweetness and crisp texture.",
"The tech company Apple is known for its innovative products like the iPhone.",
"Many people enjoy eating apples as a healthy snack.",
"Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.",
"An apple a day keeps the doctor away, as the saying goes.",
]
doc_embeds= embeddings.embed_documents(docs)
doc_embeds
query="Tell me about the tech company known as Apple"
query_embed= embeddings.embed_query(query)
query_embed
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides