Spaces:
Running
Running
File size: 1,528 Bytes
2cb9dec bc82930 2cb9dec 192ee60 6f4f307 2cb9dec 6f4f307 2cb9dec 6f4f307 5c144a1 6f4f307 |
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 |
from pydantic import BaseModel
from typing import List, Dict
# 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")
)
|