Spaces:
Running
Running
File size: 4,451 Bytes
0231daa ee35e05 0231daa ee35e05 0231daa |
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 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
"""
Response schemas for API endpoints.
This module defines all Pydantic models for API responses,
ensuring consistent output format across all endpoints.
"""
from typing import List
from pydantic import BaseModel, Field
from .common import SparseEmbedding, ModelInfo
class BaseEmbedResponse(BaseModel):
"""
Base class for embedding responses.
Attributes:
model_id: Identifier of the model used
processing_time: Time taken to process the request (seconds)
"""
model_id: str = Field(..., description="Model identifier used")
processing_time: float = Field(..., description="Processing time in seconds", ge=0)
class DenseEmbedResponse(BaseEmbedResponse):
"""
Response model for single/batch dense embeddings.
Used for /embed & /query endpoint with dense models.
Attributes:
embeddings: List of generated dense embedding vectors
dimension: Dimensionality of the embeddings
count: Number of embeddings returned
model_id: Identifier of the model used
processing_time: Time taken to process the request
"""
embeddings: List[List[float]] = Field(
..., description="List of dense embedding vectors"
)
dimension: int = Field(..., description="Embedding dimensionality", ge=1)
count: int = Field(..., description="Number of embeddings", ge=1)
class Config:
json_schema_extra = {
"example": {
"embeddings": [
[0.123, -0.456, 0.789],
[0.234, 0.567, -0.890],
[0.345, -0.678, 0.901],
],
"dimension": 768,
"count": 3,
"model_id": "qwen3-0.6b",
"processing_time": 0.1245,
}
}
class SparseEmbedResponse(BaseEmbedResponse):
"""
Response model for single/batch sparse embeddings.
Used for /embed and /query endpoint with sparse models.
Attributes:
embeddings: List of generated sparse embeddings
count: Number of embeddings returned
model_id: Identifier of the model used
processing_time: Time taken to process the request
"""
embeddings: List[SparseEmbedding] = Field(
..., description="List of sparse embeddings"
)
count: int = Field(..., description="Number of embeddings", ge=1)
class Config:
json_schema_extra = {
"example": {
"embeddings": [
{
"indices": [10, 25, 42],
"values": [0.85, 0.62, 0.91],
"text": "first text",
},
{
"indices": [15, 30, 50],
"values": [0.73, 0.88, 0.65],
"text": "second text",
},
],
"count": 2,
"model_id": "splade-pp-v2",
"processing_time": 0.0892,
}
}
class ModelsListResponse(BaseModel):
"""
Response model for listing available models.
Attributes:
models: List of available models with their info
total: Total number of models
"""
models: List[ModelInfo] = Field(..., description="List of available models")
total: int = Field(..., description="Total number of models", ge=0)
class Config:
json_schema_extra = {
"example": {
"models": [
{
"id": "qwen3-0.6b",
"name": "Qwen/Qwen3-Embedding-0.6B",
"type": "embeddings",
"loaded": True,
}
],
"total": 1,
}
}
class RootResponse(BaseModel):
"""
Response model for root endpoint.
Attributes:
message: Welcome message
version: API version
docs_url: URL to API documentation
"""
message: str = Field(..., description="Welcome message")
version: str = Field(..., description="API version")
docs_url: str = Field(..., description="Documentation URL")
class Config:
json_schema_extra = {
"example": {
"message": "Unified Embedding API - Dense & Sparse Embeddings",
"version": "3.0.0",
"docs_url": "/docs",
}
}
|