Filtering on Pinecone

from os import getenv

from agno.agent import Agent
from agno.knowledge.pdf import PDFKnowledgeBase
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.pineconedb import PineconeDb

# Download all sample CVs and get their paths
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

# Initialize Pinecone
api_key = getenv("PINECONE_API_KEY")
index_name = "thai-recipe-index"

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


# Step 1: Initialize knowledge base with documents and metadata
knowledge_base = PDFKnowledgeBase(
    path=[
        {
            "path": downloaded_cv_paths[0],
            "metadata": {
                "user_id": "jordan_mitchell",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[1],
            "metadata": {
                "user_id": "taylor_brooks",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[2],
            "metadata": {
                "user_id": "morgan_lee",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[3],
            "metadata": {
                "user_id": "casey_jordan",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[4],
            "metadata": {
                "user_id": "alex_rivera",
                "document_type": "cv",
                "year": 2025,
            },
        },
    ],
    vector_db=vector_db,
)

# Load all documents into the vector database
knowledge_base.load(recreate=True, upsert=True)

# Step 2: Query the knowledge base with different filter combinations
# ------------------------------------------------------------------------------

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)

agent.print_response(
    "Tell me about Jordan Mitchell's experience and skills",
    knowledge_filters={"user_id": "hey"},
    markdown=True,
)