src/ctp_slack_bot/models/base.py

from abc import abstractmethod
from pydantic import BaseModel, ConfigDict, Field, field_validator
from types import MappingProxyType
from typing import Any, final, Mapping, Optional, Self

from ctp_slack_bot.core import AbstractBaseModel
from ctp_slack_bot.utils import to_deep_immutable


class Chunk(BaseModel):
    """A class representing a chunk of content."""

    model_config = ConfigDict(frozen=True)

    text: str                   # The text representation
    parent_id: str              # The source content’s identity
    chunk_id: str               # This chunk’s identity—unique within the source content
    metadata: Mapping[str, Any] = Field(default_factory=lambda: MappingProxyType({}))

    @field_validator('metadata')
    @classmethod
    def __make_metadata_readonly(cls, value: Mapping[str, Any]) -> Mapping[str, Any]:
        return to_deep_immutable(value)


@final
class VectorQuery(BaseModel):
    """Model for vector database similarity search queries.
    
    Attributes:
        query_text: The text to be vectorized and used for similarity search
        k: Number of similar documents to retrieve
        score_threshold: Minimum similarity score threshold for inclusion in results
        filter_metadata: Optional filters for metadata fields
    """

    model_config = ConfigDict(frozen=True)

    query_embeddings: tuple[float, ...]
    k: int
    score_threshold: float = Field(default=0.7)
    filter_metadata: Mapping[str, Any] = Field(default_factory=lambda: MappingProxyType({}))

    @field_validator('filter_metadata')
    @classmethod
    def __make_metadata_readonly(cls, value: Mapping[str, Any]) -> Mapping[str, Any]:
        return to_deep_immutable(value)

    
@final
class VectorizedChunk(Chunk):
    """A class representing a vectorized chunk of content."""

    embedding: tuple[float, ...] # The vector representation


class Content(AbstractBaseModel):
    """An abstract base class for all types of content."""

    model_config = ConfigDict(frozen=True)

    @abstractmethod
    def get_id(self: Self) -> str:
        pass

    @abstractmethod
    def get_chunks(self: Self) -> tuple[Chunk, ...]:
        pass

    @abstractmethod
    def get_metadata(self: Self) -> Mapping[str, Any]:
        pass