app/server/chat/schemas.py

from typing import Literal

from llama_index.schema import NodeWithScore
from pydantic import BaseModel, Field

from app.server.ingest.schemas import IngestedDoc


class Chunk(BaseModel):
    object: Literal["context.chunk"]
    score: float = Field(examples=[0.023])
    document: IngestedDoc
    text: str = Field(examples=["Outbound sales increased 20%, driven by new leads."])
    previous_texts: list[str] | None = Field(
        default=None,
        examples=[["SALES REPORT 2023", "Inbound didn't show major changes."]],
    )
    next_texts: list[str] | None = Field(
        default=None,
        examples=[
            [
                "New leads came from Google Ads campaign.",
                "The campaign was run by the Marketing Department",
            ]
        ],
    )

    @classmethod
    def from_node(cls: type["Chunk"], node: NodeWithScore) -> "Chunk":
        doc_id = node.node.ref_doc_id if node.node.ref_doc_id is not None else "-"
        return cls(
            object="context.chunk",
            score=node.score or 0.0,
            document=IngestedDoc(
                object="ingest.document",
                doc_id=doc_id,
                doc_metadata=node.metadata,
            ),
            text=node.get_content(),
        )


class Completion(BaseModel):
    response: str
    sources: list[Chunk] | None = None