src/summarization/schemas.py

from typing import Annotated, List, Optional
from pydantic import BaseModel, Field

class SegmentSchema(BaseModel):
    """Represents one chronological section of the video timeline."""
    title: str = Field(
        ...,
        description="A short, descriptive title for this chronological segment.",
    )
    summary: str = Field(
        ...,
        description="A concise summary of what is covered in this segment (2-3 sentences).",
    )
    key_insight: str = Field(
        ...,
        description="The single most important point or takeaway from this segment.",
    )
    why_it_matters: str = Field(
        ...,
        description="Brief explanation of the value or importance of this segment (1-2 sentences).",
    )

class SummarySchema(BaseModel):
    """Primary Summary response schema."""
    summary: str = Field(
        ...,
        description=(
            "A concise, high-level paragraph (3-5 sentences) that explains"
            " what the entire video is about, its main thesis, and its value."
        ),
    )

    segments: Annotated[
        List[SegmentSchema],
        Field(
            min_length=3,
            max_length=7,
            description=(
                "Chronological timeline sections of the video. Minimum 3,"
                " maximum 7. Must follow the natural progression of the transcript."
            ),
        ),
    ]

    suggested_category: str = Field(
        default="General",
        description=(
            "A single, concise category label (1-2 words max) that best"
            " describes the video content. Must always be in English."
        ),
    )

    conclusion: Optional[str] = Field(
        default=None,
        description="A final overall takeaway or closing conclusion in the transcript language.",
    )

    topics: List[str] = Field(
        default_factory=list,
        min_length=1,
        description=(
            "Dynamically extracted topics discussed in the video."
            " Examples: ['Python', 'Machine Learning', 'Neural Networks']."
        ),
    )