Example

import os
import typer
from typing import Optional
from rich.prompt import Prompt

from phi.agent import Agent
from phi.knowledge.pdf import PDFUrlKnowledgeBase
from phi.vectordb.pineconedb import PineconeDB

api_key = os.getenv("PINECONE_API_KEY")
index_name = "thai-recipe-hybrid-search"

vector_db = PineconeDB(
    name=index_name,
    dimension=1536,
    metric="cosine",
    spec={"serverless": {"cloud": "aws", "region": "us-east-1"}},
    api_key=api_key,
    use_hybrid_search=True,
    hybrid_alpha=0.5,
)

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=vector_db,
)

# Comment out after first run
knowledge_base.load(recreate=True, upsert=True)


def pinecone_agent(user: str = "user"):
    run_id: Optional[str] = None

    agent = Agent(
        run_id=run_id,
        user_id=user,
        knowledge=knowledge_base,
        show_tool_calls=True,
        debug_mode=True,
    )

    if run_id is None:
        run_id = agent.run_id
        print(f"Started Run: {run_id}\n")
    else:
        print(f"Continuing Run: {run_id}\n")

    while True:
        message = Prompt.ask(f"[bold] :sunglasses: {user} [/bold]")
        if message in ("exit", "bye"):
            break
        agent.print_response(message)


if __name__ == "__main__":
    typer.run(pinecone_agent)


PineconeDB Params

ParameterTypeDefaultDescription
namestr-The name of the table to use.
dimensionint-The dimension of the table to use.
specUnion[Dict, ServerlessSpec, PodSpec]-The spec of the table to use.
embedderOptional[Embedder]NoneThe embedder to use for encoding vectors. If not provided, a default embedder will be used.
metricOptional[str]"cosine"The distance metric to use for similarity search.
additional_headersOptional[Dict[str, str]]NoneAdditional headers to include in API requests.
pool_threadsOptional[int]1The number of threads to use for the connection pool.
namespaceOptional[str]NoneThe namespace to use for the index.
timeoutOptional[int]NoneThe timeout for API requests in seconds.
index_apiOptional[Any]NoneA custom index API implementation to use instead of the default.
api_keyOptional[str]NoneThe API key for authentication with Pinecone.
hostOptional[str]NoneThe host URL for the Pinecone service.
configOptional[Config]NoneAdditional configuration options for the Pinecone client.
use_hybrid_searchboolFalseWhether to use hybrid search (combining vector and keyword search).
hybrid_alphafloat0.5The alpha parameter for hybrid search, balancing between vector and keyword search.