File size: 11,544 Bytes
486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 b5407c0 486a9e9 |
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 |
import os
import re
import json
import gradio as gr
import requests
from typing import List, Dict
from googlesearch import search
import google.generativeai as genai
from google.generativeai.types import HarmCategory, HarmBlockThreshold
def initialize_gemini(api_key: str):
"""Initialize the Google Gemini API with appropriate configurations"""
genai.configure(api_key=api_key)
generation_config = {
"temperature": 0.2,
"top_p": 0.8,
"top_k": 40,
"max_output_tokens": 1024,
}
safety_settings = {
HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_NONE,
HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_NONE,
HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_NONE,
HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
}
model = genai.GenerativeModel(
model_name="gemini-1.5-flash",
generation_config=generation_config,
safety_settings=safety_settings
)
return model
def google_search_naics(company_name: str) -> List[str]:
"""Find potential NAICS codes for a company using Google search"""
query = f"NAICS code 2022 for {company_name}"
naics_codes = set()
try:
search_results = search(query, stop=5, pause=2)
for result_url in search_results:
try:
response = requests.get(result_url, timeout=5)
if response.status_code == 200:
# Extract 6-digit NAICS codes
found_codes = re.findall(r'\b\d{6}\b', response.text)
naics_codes.update(found_codes)
except Exception as e:
print(f"Error fetching {result_url}: {e}")
return list(naics_codes)[:5] # Return up to 5 extracted NAICS codes
except Exception as e:
print(f"Error performing Google search: {str(e)}")
return []
def get_naics_classification(model, company_name: str, context: str, candidates: List[str]) -> dict:
"""
Use Gemini AI to determine the most appropriate NAICS code from candidates
First provides reasoning, then multiple possibilities with confidence levels
"""
try:
# If we have candidate codes from Google search
if candidates:
prompt = f"""
You are a NAICS code classification expert. Based on the company information provided and the NAICS code candidates found from Google search, determine the most appropriate NAICS code.
Company Name: {company_name}
Context Information: {context}
NAICS Code Candidates from Google Search: {candidates}
First, explain your reasoning for which industry this company belongs to.
Then list 3 potential NAICS classifications with confidence percentages (must add up to 100%).
Finally, provide your final conclusion.
Your response should be in this format:
REASONING: [Your detailed reasoning about the company's industry classification]
POSSIBILITY_1: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
POSSIBILITY_2: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
POSSIBILITY_3: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
CONCLUSION: I am [XX]% confident this company is [industry description] which is NAICS code [6-digit code]
"""
# If no candidates were found from Google search
else:
prompt = f"""
You are a NAICS code classification expert. Based on the company information provided, determine the most appropriate NAICS code.
Company Name: {company_name}
Context Information: {context}
First, explain your reasoning for which industry this company belongs to.
Then list 3 potential NAICS classifications with confidence percentages (must add up to 100%).
Finally, provide your final conclusion.
Your response should be in this format:
REASONING: [Your detailed reasoning about the company's industry classification]
POSSIBILITY_1: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
POSSIBILITY_2: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
POSSIBILITY_3: [Industry name] - NAICS Code [6-digit code] - [XX]% confidence
CONCLUSION: I am [XX]% confident this company is [industry description] which is NAICS code [6-digit code]
"""
response = model.generate_content(prompt)
response_text = response.text.strip()
# Extract reasoning
reasoning_match = re.search(r'REASONING:(.*?)POSSIBILITY_1:', response_text, re.DOTALL | re.IGNORECASE)
reasoning = reasoning_match.group(1).strip() if reasoning_match else "No reasoning provided."
# Extract possibilities
possibilities = []
# Try to extract possibility 1
poss1_match = re.search(r'POSSIBILITY_1:(.*?)POSSIBILITY_2:', response_text, re.DOTALL | re.IGNORECASE)
if poss1_match:
possibilities.append(poss1_match.group(1).strip())
# Try to extract possibility 2
poss2_match = re.search(r'POSSIBILITY_2:(.*?)POSSIBILITY_3:', response_text, re.DOTALL | re.IGNORECASE)
if poss2_match:
possibilities.append(poss2_match.group(1).strip())
# Try to extract possibility 3
poss3_match = re.search(r'POSSIBILITY_3:(.*?)CONCLUSION:', response_text, re.DOTALL | re.IGNORECASE)
if poss3_match:
possibilities.append(poss3_match.group(1).strip())
# Extract conclusion
conclusion_match = re.search(r'CONCLUSION:(.*?)
except Exception as e:
print(f"Error getting NAICS classification: {str(e)}")
return {
"naics_code": "000000",
"reasoning": f"Error analyzing company: {str(e)}"
}
def find_naics_code(api_key, company_name, company_description):
"""Main function to find NAICS code that will be called by Gradio"""
if not api_key or not company_name:
return "Please provide both API key and company name."
try:
# Initialize Gemini API
model = initialize_gemini(api_key)
# Search for NAICS candidates
naics_candidates = google_search_naics(company_name)
# Get classification
if not naics_candidates:
result = get_naics_classification(model, company_name, company_description, [])
else:
result = get_naics_classification(model, company_name, company_description, naics_candidates)
# Format the output
output = f"## NAICS Code for {company_name}\n\n"
output += f"**NAICS Code:** {result['naics_code']}\n\n"
output += f"**Reasoning:**\n{result['reasoning']}\n\n"
# Add possibilities section
if 'possibilities' in result and result['possibilities']:
output += f"**Possible Classifications:**\n\n"
for i, possibility in enumerate(result['possibilities'], 1):
output += f"{i}. {possibility}\n\n"
# Add conclusion
if 'conclusion' in result and result['conclusion']:
output += f"**Conclusion:**\n{result['conclusion']}\n\n"
if naics_candidates:
output += f"**Candidate NAICS Codes Found from Google:**\n{', '.join(naics_candidates)}"
return output
except Exception as e:
return f"Error: {str(e)}"
# Create Gradio Interface
with gr.Blocks(title="NAICS Code Finder") as app:
gr.Markdown("# NAICS Code Finder")
gr.Markdown("This app helps you find the appropriate NAICS code for a company based on its name and description.")
with gr.Row():
with gr.Column():
api_key = gr.Textbox(label="Google Gemini API Key", placeholder="Enter your Gemini API key here", type="password")
company_name = gr.Textbox(label="Company Name", placeholder="Enter the company name")
company_description = gr.Textbox(label="Company Description", placeholder="Enter a brief description of the company", lines=5)
submit_btn = gr.Button("Find NAICS Code")
with gr.Column():
output = gr.Markdown(label="Result")
submit_btn.click(
fn=find_naics_code,
inputs=[api_key, company_name, company_description],
outputs=output
)
if __name__ == "__main__":
app.launch()
, response_text, re.DOTALL | re.IGNORECASE)
conclusion = conclusion_match.group(1).strip() if conclusion_match else "No conclusion provided."
# Extract final NAICS code from conclusion
naics_match = re.search(r'NAICS code (\d{6})', conclusion)
if naics_match:
naics_code = naics_match.group(1)
else:
# Try to find any 6-digit code in the conclusion
code_match = re.search(r'\b(\d{6})\b', conclusion)
naics_code = code_match.group(1) if code_match else "000000"
return {
"naics_code": naics_code,
"reasoning": reasoning,
"possibilities": possibilities,
"conclusion": conclusion
}
except Exception as e:
print(f"Error getting NAICS classification: {str(e)}")
return {
"naics_code": "000000",
"reasoning": f"Error analyzing company: {str(e)}"
}
def find_naics_code(api_key, company_name, company_description):
"""Main function to find NAICS code that will be called by Gradio"""
if not api_key or not company_name:
return "Please provide both API key and company name."
try:
# Initialize Gemini API
model = initialize_gemini(api_key)
# Search for NAICS candidates
naics_candidates = google_search_naics(company_name)
# Get classification
if not naics_candidates:
result = get_naics_classification(model, company_name, company_description, [])
else:
result = get_naics_classification(model, company_name, company_description, naics_candidates)
# Format the output
output = f"## NAICS Code for {company_name}\n\n"
output += f"**NAICS Code:** {result['naics_code']}\n\n"
output += f"**Reasoning:**\n{result['reasoning']}\n\n"
if naics_candidates:
output += f"**Candidate NAICS Codes Found:**\n{', '.join(naics_candidates)}"
return output
except Exception as e:
return f"Error: {str(e)}"
# Create Gradio Interface
with gr.Blocks(title="NAICS Code Finder") as app:
gr.Markdown("# NAICS Code Finder")
gr.Markdown("This app helps you find the appropriate NAICS code for a company based on its name and description.")
with gr.Row():
with gr.Column():
api_key = gr.Textbox(label="Google Gemini API Key", placeholder="Enter your Gemini API key here", type="password")
company_name = gr.Textbox(label="Company Name", placeholder="Enter the company name")
company_description = gr.Textbox(label="Company Description", placeholder="Enter a brief description of the company", lines=5)
submit_btn = gr.Button("Find NAICS Code")
with gr.Column():
output = gr.Markdown(label="Result")
submit_btn.click(
fn=find_naics_code,
inputs=[api_key, company_name, company_description],
outputs=output
)
if __name__ == "__main__":
app.launch() |