pip install pinecone-client langchain-pinecone langchain-openai

export PINECONE_API_KEY="your-api-key"

from pinecone import Pinecone, ServerlessSpec
from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAIEmbeddings

# Initialize Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

# Create or connect to index
index_name = "agent-memory"
if index_name not in [i.name for i in pc.list_indexes()]:
    pc.create_index(
        name=index_name,
        dimension=1536,
        metric="cosine",
        spec=ServerlessSpec(cloud="aws", region="us-east-1"),
    )

# Build vector store
vectorstore = PineconeVectorStore.from_documents(
    documents=docs,
    embedding=OpenAIEmbeddings(),
    index_name=index_name,
)

# Retrieve relevant context
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
results = retriever.invoke("What did the agent discuss yesterday?")

# Store per-session memory
vectorstore = PineconeVectorStore(
    index=pc.Index(index_name),
    embedding=OpenAIEmbeddings(),
    namespace=f"session-{session_id}",
)

# Query across all sessions (no namespace filter)
all_memory = PineconeVectorStore(
    index=pc.Index(index_name),
    embedding=OpenAIEmbeddings(),
)
results = all_memory.similarity_search("relevant query", k=10)