Data extraction

from typing import Optional

from agno.agent import Agent
from agno.models.google import Gemini
from pydantic import BaseModel, Field


class Contact(BaseModel):
    name: Optional[str] = Field(None, description="Full name as written")
    email: Optional[str] = Field(None, description="Email address")
    phone: Optional[str] = Field(None, description="Phone number, raw format")
    company: Optional[str] = Field(None, description="Company or organization")
    title: Optional[str] = Field(None, description="Job title")


agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    instructions=(
        "Extract contact information from the input. Use exactly what the "
        "text shows. If a field is missing, leave it null. Do not guess."
    ),
    output_schema=Contact,
)

result = agent.run(
    "Hi - Sarah Johnson, VP of Marketing at Acme Corp. "
    "sarah@acme.com / +1-555-0102."
).content
# Contact(name='Sarah Johnson', email='sarah@acme.com',
#         phone='+1-555-0102', company='Acme Corp.', title='VP of Marketing')

from typing import List, Optional

from pydantic import BaseModel, Field


class ActionItem(BaseModel):
    owner: str = Field(..., description="Person responsible")
    description: str = Field(..., description="What needs to be done")
    due_date: Optional[str] = Field(None, description="Due date if stated")


class Meeting(BaseModel):
    action_items: List[ActionItem] = Field(default_factory=list)

from typing import Literal, Optional

from agno.agent import Agent
from agno.models.google import Gemini
from pydantic import BaseModel, Field


class ConfidentField(BaseModel):
    value: Optional[str] = None
    confidence: Literal["high", "medium", "low"] = Field(
        ..., description="Confidence in the extracted value"
    )


class Contact(BaseModel):
    name: ConfidentField
    email: ConfidentField
    company: ConfidentField


instructions = """\
Extract contact information from the input. For each field:
- value:      what the text shows; null if the field is missing
- confidence: high if explicit and unambiguous;
              medium if implied or partially formatted;
              low if guessed or ambiguous

Use exactly what the text shows. Do not normalize or paraphrase.
"""

confidence_agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    instructions=instructions,
    output_schema=Contact,
)

pip install lancedb tantivy