File size: 9,733 Bytes
8ba64a4 9bb2fc2 8ba64a4 9645c29 e85027d 8ba64a4 9645c29 8ba64a4 9645c29 8ba64a4 9645c29 8ba64a4 0dd08cb 8ba64a4 638f225 8ba64a4 b652f9c 8ba64a4 f124ae7 b652f9c f124ae7 8ba64a4 b652f9c 8ba64a4 9645c29 8ba64a4 9645c29 8ba64a4 9645c29 8ba64a4 9645c29 8ba64a4 0dd08cb 8ba64a4 9645c29 8ba64a4 9645c29 a9d8d74 b652f9c a9d8d74 b652f9c a9d8d74 b652f9c a9d8d74 9645c29 8ba64a4 e85027d 8ba64a4 e85027d 8ba64a4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 |
import json
import os
from typing import Any, Dict, List, Type, Union
import openai
import weave
from openai import AsyncOpenAI
from pydantic import BaseModel
from app.utils.converter import product_data_to_str
from app.utils.image_processing import (
get_data_format,
get_image_base64_and_type,
get_image_data,
)
from app.utils.logger import exception_to_str, setup_logger
from ..config import get_settings
from ..core import errors
from ..core.errors import BadRequestError, VendorError
from ..core.prompts import get_prompts
from .base import BaseAttributionService
ENV = os.getenv("ENV", "LOCAL")
if ENV == "LOCAL": # local or demo
weave_project_name = "cfai/attribution-exp"
elif ENV == "DEV":
weave_project_name = "cfai/attribution-dev"
elif ENV == "UAT":
weave_project_name = "cfai/attribution-uat"
elif ENV == "PROD":
pass
# if ENV != "PROD":
# weave.init(project_name=weave_project_name)
settings = get_settings()
prompts = get_prompts()
logger = setup_logger(__name__)
def get_response_format(json_schema: dict[str, any]) -> dict[str, any]:
# OpenAI requires each $def have to have additionalProperties set to False
json_schema["additionalProperties"] = False
# check if the schema has a $defs key
if "$defs" in json_schema:
for keys in json_schema["$defs"].keys():
json_schema["$defs"][keys]["additionalProperties"] = False
response_format = {
"type": "json_schema",
"json_schema": {"strict": True, "name": "GarmentSchema", "schema": json_schema},
}
return response_format
class OpenAIService(BaseAttributionService):
def __init__(self):
self.client = AsyncOpenAI(api_key=settings.OPENAI_API_KEY)
@weave.op
async def extract_attributes(
self,
attributes_model: Type[BaseModel],
ai_model: str,
img_urls: List[str],
product_taxonomy: str,
product_data: Dict[str, Union[str, List[str]]],
pil_images: List[Any] = None, # do not remove, this is for weave
img_paths: List[str] = None,
appended_prompt: str = "",
) -> Dict[str, Any]:
print("Prompt: ")
print(prompts.GET_PERCENTAGE_HUMAN_MESSAGE.format(product_taxonomy=product_taxonomy, product_data=product_data_to_str(product_data)) + appended_prompt)
text_content = [
{
"type": "text",
"text": prompts.EXTRACT_INFO_HUMAN_MESSAGE.format(
product_taxonomy=product_taxonomy,
product_data=product_data_to_str(product_data),
) + appended_prompt,
},
]
if img_urls is not None:
base64_data_list = []
data_format_list = []
for img_url in img_urls:
base64_data, data_format = get_image_base64_and_type(img_url)
base64_data_list.append(base64_data)
data_format_list.append(data_format)
image_content = [
{
"type": "image_url",
"image_url": {
"url": f"data:image/{data_format};base64,{base64_data}",
},
}
for base64_data, data_format in zip(base64_data_list, data_format_list)
]
elif img_paths is not None:
image_content = [
{
"type": "image_url",
"image_url": {
"url": f"data:image/{get_data_format(img_path)};base64,{get_image_data(img_path)}",
},
}
for img_path in img_paths
]
try:
logger.info("Extracting info via OpenAI...")
response = await self.client.beta.chat.completions.parse(
model=ai_model,
messages=[
{
"role": "system",
"content": prompts.GET_PERCENTAGE_SYSTEM_MESSAGE,
},
{
"role": "user",
"content": text_content + image_content,
},
],
max_tokens=1000,
response_format=attributes_model,
logprobs=False,
# top_logprobs=2,
# temperature=0.0,
top_p=1e-45,
)
except openai.BadRequestError as e:
error_message = exception_to_str(e)
raise BadRequestError(error_message)
except Exception as e:
raise VendorError(
errors.VENDOR_THROW_ERROR.format(error_message=exception_to_str(e))
)
try:
content = response.choices[0].message.content
parsed_data = json.loads(content)
except:
raise VendorError(errors.VENDOR_ERROR_INVALID_JSON)
return parsed_data
async def reevaluate_atributes(
self,
attributes_model: Type[BaseModel],
ai_model: str,
img_urls: List[str],
product_taxonomy: str,
product_data: str,
pil_images: List[Any] = None, # do not remove, this is for weave
img_paths: List[str] = None,
appended_prompt: str = "",
) -> Dict[str, Any]:
print("Prompt: ")
print(prompts.REEVALUATE_HUMAN_MESSAGE.format(product_taxonomy=product_taxonomy, product_data=product_data) + appended_prompt)
text_content = [
{
"type": "text",
"text": prompts.REEVALUATE_HUMAN_MESSAGE.format(
product_taxonomy=product_taxonomy,
product_data=product_data,
) + appended_prompt,
},
]
if img_urls is not None:
base64_data_list = []
data_format_list = []
for img_url in img_urls:
base64_data, data_format = get_image_base64_and_type(img_url)
base64_data_list.append(base64_data)
data_format_list.append(data_format)
image_content = [
{
"type": "image_url",
"image_url": {
"url": f"data:image/{data_format};base64,{base64_data}",
},
}
for base64_data, data_format in zip(base64_data_list, data_format_list)
]
elif img_paths is not None:
image_content = [
{
"type": "image_url",
"image_url": {
"url": f"data:image/{get_data_format(img_path)};base64,{get_image_data(img_path)}",
},
}
for img_path in img_paths
]
try:
logger.info("Extracting info via OpenAI...")
response = await self.client.beta.chat.completions.parse(
model=ai_model,
messages=[
{
"role": "system",
"content": prompts.REEVALUATE_SYSTEM_MESSAGE,
},
{
"role": "user",
"content": text_content + image_content,
},
],
max_tokens=1000,
response_format=attributes_model,
logprobs=False,
# top_logprobs=2,
# temperature=0.0,
top_p=1e-45,
)
except openai.BadRequestError as e:
error_message = exception_to_str(e)
raise BadRequestError(error_message)
except Exception as e:
raise VendorError(
errors.VENDOR_THROW_ERROR.format(error_message=exception_to_str(e))
)
try:
content = response.choices[0].message.content
parsed_data = json.loads(content)
except:
raise VendorError(errors.VENDOR_ERROR_INVALID_JSON)
return parsed_data
@weave.op
async def follow_schema(
self, schema: Dict[str, Any], data: Dict[str, Any]
) -> Dict[str, Any]:
logger.info("Following structure via OpenAI...")
text_content = [
{
"type": "text",
"text": prompts.FOLLOW_SCHEMA_HUMAN_MESSAGE.format(json_info=data),
},
]
try:
response = await self.client.beta.chat.completions.parse(
model="gpt-4o-2024-11-20",
messages=[
{
"role": "system",
"content": prompts.FOLLOW_SCHEMA_SYSTEM_MESSAGE,
},
{
"role": "user",
"content": text_content,
},
],
max_tokens=1000,
response_format=get_response_format(schema),
logprobs=False,
# top_logprobs=2,
temperature=0.0,
)
except Exception as e:
raise VendorError(
errors.VENDOR_THROW_ERROR.format(error_message=exception_to_str(e))
)
if response.choices[0].message.refusal:
logger.info("OpenAI refused to respond to the request")
return {"status": "refused"}
try:
content = response.choices[0].message.content
parsed_data = json.loads(content)
except:
raise ValueError(errors.VENDOR_ERROR_INVALID_JSON)
return parsed_data
|