src/api/models/embedding_models.py

from pydantic import BaseModel
from typing import List, Dict, Optional


# Pydantic models for request validation
class CreateEmbeddingRequest(BaseModel):
    query: str
    target_column: str = "product_type"
    output_column: str = "embedding"
    model: str = "text-embedding-3-small"
    batch_size: int = 10
    max_concurrent_requests: int = 10
    dataset_name: str = "re-mind/product_type_embedding"


class ReadEmbeddingRequest(BaseModel):
    dataset_name: str


# class UpdateEmbeddingRequest(BaseModel):
#     updates: Dict[str, List]  # Column name -> List of values
#     target_column: str = "product_type"
#     output_column: str = "embedding"
#     model: str = "text-embedding-3-small"
#     batch_size: int = 10
#     max_concurrent_requests: int = 10
#     dataset_name: str = "re-mind/product_type_embedding"


class UpdateEmbeddingRequest(BaseModel):
    dataset_name: str = "re-mind/product_type_embedding"
    updates: Dict[
        str, List
    ]  # Dictionary of column names and their corresponding values
    target_column: str = (
        "product_type"  # Column in the new data to generate embeddings for
    )
    output_column: str = "embedding"  # Column to store the generated embeddings


class DeleteEmbeddingRequest(BaseModel):
    dataset_name: str


# Request model for the /embed endpoint
class EmbedRequest(BaseModel):
    texts: List[str]  # List of strings to generate embeddings for
    output_column: str = (
        "embedding"  # Column to store embeddings (default: "embeddings")
    )


class SearchEmbeddingRequest(BaseModel):
    texts: List[str]  # List of texts to search for
    target_column: str  # Column to return in the results
    embedding_column: str  # Column containing the embeddings to search against
    num_results: int  # Number of results to return
    dataset_name: str  # Name of the dataset to search in
    additional_columns: Optional[List[str]] = (
        None  # Optional list of additional columns to include in the results
    )