Integrating with LangChain

pip install langchain langchain-pinecone langchain-openai

from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAIEmbeddings

emb = OpenAIEmbeddings(model="text-embedding-3-small")
vs = PineconeVectorStore(
    index_name="docs", embedding=emb, namespace="kb",
)

from langchain_core.documents import Document

docs = [Document(page_content=t, metadata={"source": s})
        for t, s in pairs]
vs.add_documents(docs)

docs = vs.similarity_search("how does retrieval work?", k=5)
for d in docs:
    print(d.metadata, d.page_content[:120])

docs = vs.max_marginal_relevance_search(
    "vector dbs", k=5, fetch_k=20, lambda_mult=0.5,
)

docs = vs.similarity_search(
    query, k=5,
    filter={"source": {"$eq": "wiki"}, "language": "en"},
)

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini")
retriever = vs.as_retriever(search_kwargs={"k": 5})
prompt = ChatPromptTemplate.from_template(
    "Answer based on context.\n\n{context}\n\nQ: {question}")

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt | llm
)
print(chain.invoke("What is RAG?").content)

from langchain_huggingface import HuggingFaceEmbeddings

emb = HuggingFaceEmbeddings(model_name="BAAI/bge-large-en-v1.5")
vs = PineconeVectorStore(index_name="docs", embedding=emb)