Spaces:
Runtime error
Runtime error
File size: 2,135 Bytes
005a292 bb5dde5 005a292 9fd6e20 005a292 9fd6e20 bb5dde5 005a292 9fd6e20 005a292 bb5dde5 67436c8 5639669 bb5dde5 5639669 bb5dde5 005a292 67436c8 bb5dde5 5639669 9fd6e20 005a292 bb5dde5 005a292 9fd6e20 67436c8 9fd6e20 bb5dde5 9fd6e20 67436c8 9fd6e20 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
from abc import ABC, abstractmethod
from pydantic import BaseModel, ConfigDict, Field, field_validator
from typing import Any, final, Mapping, Optional, Self
from ctp_slack_bot.utils import to_deep_immutable
class Chunk(BaseModel):
"""A class representing a chunk of content."""
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=dict)
model_config = ConfigDict(frozen=True)
@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
"""
query_embeddings: tuple[float, ...]
k: int
score_threshold: float = Field(default=0.7)
filter_metadata: Mapping[str, Any] = Field(default_factory=dict)
model_config = ConfigDict(frozen=True)
@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(ABC, BaseModel):
"""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
|