File size: 10,173 Bytes
f7d4608
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# from pydantic import BaseModel
# from openai import OpenAI
# from typing import List, Dict, Optional, Union

# client = OpenAI()

# class GHGParameter(BaseModel):
#     parameter: str
#     data_type: str
#     synonyms: Optional[List[str]] = None
#     uom: Optional[str] = None
#     description: Optional[str] = None
#     value: Union[int, str, None]


# class GHGCategory(BaseModel):
#     category: str
#     parameters: List[GHGParameter]

# SCHEMA = """{
#   "Gas (GHG)": {
#     "Total GHG Emissions": {
#       "data_type": "Numeric",
#       "synonyms": ["Carbon Footprint"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Total greenhouse gases emitted by the organization.",
#       "value": null
#     }"""

# PROMPT = (f"""You are a PDF parsing agent.
#             Fetch the following data from pdf : {SCHEMA}"""
#             )

# def extract_emissions_data_as_json(api, model, file_input):
#     if api.lower() == "openai":
#         file = client.files.create(
#             file=("uploaded.pdf", file_input),
#             purpose="assistants"
#         )

#         completion = client.beta.chat.completions.parse(
#             model="gpt-4o-2024-08-06",
#             messages=[
#                 {
#                     "role": "user",
#                     "content": [
#                         {
#                             "type": "file",
#                             "file": {
#                                 "file_id": file.id,
#                             }
#                         },
#                         {
#                             "type": "text",
#                             "text":PROMPT,
#                         },
#                     ]
#                 }
#             ],
#             response_format=GHGCategory,
#         )

#         research_paper = completion.choices[0].message.parsed
#         return research_paper

# from pydantic import BaseModel
# from openai import OpenAI

# client = OpenAI()

# class CalendarEvent(BaseModel):
#     name: str
#     date: str
#     participants: list[str]

# def extract_emissions_data_as_json(api, model, file_input):
#     if api.lower() == "openai":
#             file = client.files.create(
#                 file=("uploaded.pdf", file_input),
#                 purpose="assistants"
#             )

#     completion = client.beta.chat.completions.parse(
#         model="gpt-4o-2024-08-06",
#         messages=[
#                     {
#                         "role": "user",
#                         "content": [
#                             {
#                                 "type": "file",
#                                 "file": {
#                                     "file_id": file.id,
#                                 }
#                             },
#                             {
#                                 "type": "text",
#                                 "text":PROMPT,
#                             },
#                         ]
#                     }
#                 ],
#         response_format=GHGCategory,
#     )

#     event = completion.choices[0].message.parsed

# response = client.chat.completions.create(
#     model="gpt-4o-2024-08-06",
#     messages=[
#         {"role": "system", "content": "You are a helpful math tutor. Guide the user through the solution step by step."},
#         {"role": "user", "content": "how can I solve 8x + 7 = -23"}
#     ],
#     response_format={
#         "type": "json_schema",
#         "json_schema": {
#             "name": "GHGCategory",
#             "schema": {
#                 "type": "object",
#                 "properties": {
#                     "steps": {
#                         "type": "array",
#                         "items": {
#                             "type": "object",
#                             "properties": {
#                                 "explanation": {"type": "string"},
#                                 "output": {"type": "string"}
#                             },
#                             "required": ["explanation", "output"],
#                             "additionalProperties": False
#                         }
#                     },
#                     "final_answer": {"type": "string"}
#                 },
#                 "required": ["steps", "final_answer"],
#                 "additionalProperties": False
#             },
#             "strict": True
#         }
#     }
# )

# print(response.choices[0].message.content)


# response = await async_client.responses.create(
#             model="gpt-4o",
#             input=[
#                 {
#                     "role": "user",
#                     "content": [
#                         {
#                             "type": "input_file",
#                             "file_id": uploaded_file.id,
#                         },
#                         {
#                             "type": "input_text",
#                             "text": """
#                             You are an intelligent PDF data extractor designed to extract structured information from Brand Books. A Brand Book contains guidelines and details about a brand's identity, including its logo, colors, typography, messaging, and more.
#                             Ensure the extracted data follows this schema strictly.
#                             Return the extracted brand information in JSON format with no explaination.
#                             For brand_logo and favicon, always provide a direct URL to the image instead of just the image name or a placeholder. If no valid URLs are found, return an empty array.                        """
#                         }
#                     ]
#                 }
#             ],
#             text={
#                 "format": {
#                     "type": "json_schema",
#                     "name": "BrandBook",
#                     "strict": True,
#                     "schema": {
#                         "type": "object",
#                         "properties": {
#                             "brand_url": {
#                                 "type": "string",
#                                 "description": "The URL associated with the brand."
#                             },
#                             "brand_name": {
#                                 "type": "string",
#                                 "description": "The name of the brand."
#                             },
#                             "brand_category": {
#                                 "type": "array",
#                                 "description": "A list of categories that the brand belongs to.",
#                                 "items": {
#                                     "type": "string"
#                                 }
#                             },
#                             "brand_description": {
#                                 "type": "string",
#                                 "description": "A brief description of the brand."
#                             },
#                             "brand_colors": {
#                                 "type": "array",
#                                 "description": "A list of colors associated with the brand.",
#                                 "items": {
#                                     "type": "string"
#                                 }
#                             },
#                             "brand_fonts": {
#                                 "type": "array",
#                                 "description": "A list of fonts used by the brand.",
#                                 "items": {
#                                     "type": "string"
#                                 }
#                             },
#                             "brand_logo": {
#                                 "type": "array",
#                                 "description": "A list of logo urls associated with the brand.",
#                                 "items": {
#                                     "type": "string"
#                                 }
#                             },
#                             "target_audience": {
#                                 "type": "string",
#                                 "description": "The target audience for the brand."
#                             },
#                             "competitors": {
#                                 "type": "string",
#                                 "description": "The competitors of the brand."
#                             },
#                             "aspirational_brands": {
#                                 "type": "string",
#                                 "description": "Brands that the brand aspires to be like."
#                             },
#                             "favicon": {
#                                 "type": "array",
#                                 "description": "A list of favicon URLs associated with the brand.",
#                                 "items": {
#                                     "type": "string"
#                                 }
#                             }
#                         },
#                         "required": [
#                             "brand_url",
#                             "brand_name",
#                             "brand_category",
#                             "brand_description",
#                             "brand_colors",
#                             "brand_fonts",
#                             "brand_logo",
#                             "target_audience",
#                             "competitors",
#                             "aspirational_brands",
#                             "favicon"
#                         ],
#                         "additionalProperties": False
#                     }
#                 }
#             }
#         )