Filter Expressions

from agno.agent import Agent
from agno.filters import AND, EQ, IN, NOT
from agno.knowledge.knowledge import Knowledge
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.pgvector import PgVector

# Download sample documents
downloaded_csv_paths = download_knowledge_filters_sample_data(
    num_files=4, file_extension=SampleDataFileExtension.CSV
)

# Initialize vector database
vector_db = PgVector(
    table_name="recipes",
    db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
)

# Create knowledge base with documents and metadata
knowledge = Knowledge(
    name="CSV Knowledge Base",
    description="A knowledge base for CSV files",
    vector_db=vector_db,
)

knowledge.add_contents(
    [
        {
            "path": downloaded_csv_paths[0],
            "metadata": {
                "data_type": "sales",
                "quarter": "Q1",
                "year": 2024,
                "region": "north_america",
                "currency": "USD",
            },
        },
        {
            "path": downloaded_csv_paths[1],
            "metadata": {
                "data_type": "sales",
                "year": 2024,
                "region": "europe",
                "currency": "EUR",
            },
        },
        {
            "path": downloaded_csv_paths[2],
            "metadata": {
                "data_type": "survey",
                "survey_type": "customer_satisfaction",
                "year": 2024,
                "target_demographic": "mixed",
            },
        },
        {
            "path": downloaded_csv_paths[3],
            "metadata": {
                "data_type": "financial",
                "sector": "technology",
                "year": 2024,
                "report_type": "quarterly_earnings",
            },
        },
    ],
)

# Create agent with knowledge
sales_agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
)

# Example 1: Using IN operator
print("Using IN operator")
sales_agent.print_response(
    "Describe revenue performance for the region",
    knowledge_filters=[IN("region", ["north_america"])],
    markdown=True,
)

# Example 2: Using NOT operator
print("Using NOT operator")
sales_agent.print_response(
    "Describe revenue performance for the region",
    knowledge_filters=[NOT(IN("region", ["north_america"]))],
    markdown=True,
)

# Example 3: Using AND operator
print("Using AND operator")
sales_agent.print_response(
    "Describe revenue performance for the region",
    knowledge_filters=[
        AND(EQ("data_type", "sales"), NOT(EQ("region", "north_america")))
    ],
    markdown=True,
)

from agno.agent import Agent
from agno.filters import AND, IN, NOT
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.pdf_reader import PDFReader
from agno.models.openai import OpenAIChat
from agno.team.team import Team
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.pgvector import PgVector

# Download sample CVs
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

# Initialize vector database
vector_db = PgVector(
    table_name="recipes",
    db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
)

# Create knowledge base
knowledge_base = Knowledge(vector_db=vector_db)

# Add documents with metadata
knowledge_base.add_contents(
    [
        {
            "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": 2020,
            },
        },
        {
            "path": downloaded_cv_paths[4],
            "metadata": {
                "user_id": "alex_rivera",
                "document_type": "cv",
                "year": 2020,
            },
        },
    ],
    reader=PDFReader(chunk=True),
)

# Create knowledge search agent
web_agent = Agent(
    name="Knowledge Search Agent",
    role="Handle knowledge search",
    knowledge=knowledge_base,
    model=OpenAIChat(id="o3-mini"),
)

# Create team with knowledge
team_with_knowledge = Team(
    name="Team with Knowledge",
    instructions=["Always search the knowledge base for the most relevant information"],
    description="A team that provides information about candidates",
    members=[web_agent],
    model=OpenAIChat(id="o3-mini"),
    knowledge=knowledge_base,
    show_members_responses=True,
    markdown=True,
)

# Example 1: Using IN operator with teams
print("Using IN operator")
team_with_knowledge.print_response(
    "Tell me about the candidate's work and experience",
    knowledge_filters=[
        IN(
            "user_id",
            [
                "jordan_mitchell",
                "taylor_brooks",
                "morgan_lee",
                "casey_jordan",
                "alex_rivera",
            ],
        )
    ],
    markdown=True,
)

# Example 2: Using NOT operator with teams
print("Using NOT operator")
team_with_knowledge.print_response(
    "Tell me about the candidate's work and experience",
    knowledge_filters=[
        AND(
            IN("user_id", ["jordan_mitchell", "taylor_brooks"]),
            NOT(IN("user_id", ["morgan_lee", "casey_jordan", "alex_rivera"])),
        )
    ],
    markdown=True,
)