Spaces:
Sleeping
Sleeping
File size: 8,150 Bytes
01a84b4 a272826 01a84b4 a272826 01a84b4 a272826 01a84b4 | 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 | #!/usr/bin/env python3
"""
Address Detection and Summarization API for Hugging Face Spaces
"""
from fastapi import FastAPI, HTTPException, Header
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel, Field
from openai import OpenAI
import os
from enum import Enum
from typing import Dict, Optional, Annotated
import logging
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
app = FastAPI(title="Address Detection and Summarization API")
# Add CORS middleware for Hugging Face Spaces
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
class Actions(Enum):
DETECT_ADDRESS = "detect_address"
SUMMARIZE = "summarize"
# Request model
class RequestModel(BaseModel):
entity_urn: str = Field(..., description="Unique identifier for the entity")
content: str = Field(..., description="Content to be processed")
# Response models
class ResponseModel(BaseModel):
message: str = Field(description="Result of the operation, e.g., 'success' or 'failure'")
result: str = Field(description="summary in case of summarization, or || separated addresses in case of address detection")
action_type: Actions = Field(..., description="Type of action performed")
entity_urn: str = Field(..., description="Unique identifier for the entity")
sentiment: Optional[Dict] = Field(default=None, description="Sentiment analysis result")
def get_openai_client(api_key: str) -> OpenAI:
"""Create OpenAI client with provided API key"""
if not api_key:
raise HTTPException(status_code=400, detail="x-api-key header is required")
return OpenAI(api_key=api_key)
def get_openai_response(api_key: str, prompt: str, max_tokens: int = 10000) -> str:
"""Get response from OpenAI API"""
try:
client = get_openai_client(api_key)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": prompt}],
max_tokens=max_tokens,
temperature=0.3
)
return response.choices[0].message.content.strip()
except Exception as e:
logger.error(f"OpenAI API error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Failed to connect to OpenAI: {str(e)}")
def detect_addresses(api_key: str, content: str) -> str:
"""Detect addresses from content using OpenAI"""
prompt = f"""
Extract all addresses from the following text. Return only the addresses, separated by ' || '.
If no addresses are found, return empty string.
Text: {content}
Addresses:
"""
try:
addresses = get_openai_response(api_key, prompt)
return addresses if addresses else ""
except Exception as e:
logger.error(f"Address detection error: {str(e)}")
return "Error detecting addresses"
def summarize_and_analyze_sentiment(api_key: str, content: str) -> tuple:
"""Summarize content and analyze sentiment using OpenAI"""
prompt = f"""
Please provide:
1. A concise summary of the following text
2. Sentiment analysis with label (POSITIVE/NEGATIVE) and score (-1.0 to 1.0)
3. Ensure the summary is clear and captures the main points
Format your response as:
SUMMARY: [your summary here]
SENTIMENT_LABEL: [POSITIVE or NEGATIVE]
SENTIMENT_SCORE: [score between -1.0 and 1.0]
Text: {content}
"""
try:
response = get_openai_response(api_key, prompt)
# Parse the response
summary = ""
sentiment_label = "neutral"
sentiment_score = 0.0
lines = response.split('\n')
for line in lines:
if line.startswith('SUMMARY:'):
summary = line.replace('SUMMARY:', '').strip()
elif line.startswith('SENTIMENT_LABEL:'):
sentiment_label = line.replace('SENTIMENT_LABEL:', '').strip()
elif line.startswith('SENTIMENT_SCORE:'):
try:
sentiment_score = float(line.replace('SENTIMENT_SCORE:', '').strip())
# Ensure score is within range
sentiment_score = max(-1.0, min(1.0, sentiment_score))
except ValueError:
sentiment_score = 0.0
# Ensure valid sentiment label
if sentiment_label not in ['POSITIVE', 'NEGATIVE']:
sentiment_label = 'POSITIVE' if sentiment_score >= 0 else 'NEGATIVE'
return summary, {"label": sentiment_label, "score": sentiment_score}
except Exception as e:
logger.error(f"Summarization error: {str(e)}")
return "Error generating summary"
@app.get("/")
async def root():
return {
"message": "Address Detection and Summarization API",
"version": "1.0.0",
"status": "healthy",
"endpoints": {
"address_detection": "/address-detection",
"summarization": "/summarize",
"health": "/health",
"docs": "/docs"
}
}
@app.get("/health")
async def health_check():
return {
"status": "healthy",
"service": "Address Detection and Summarization API",
"version": "1.0.0"
}
@app.post("/address-detection", response_model=ResponseModel)
async def address_detection(
request: RequestModel,
openai_api_key: Annotated[str, Header(alias="x-api-key")]
):
"""Endpoint for address detection"""
try:
logger.info(f"Processing address detection for entity_urn: {request.entity_urn}")
if not request.content.strip():
return ResponseModel(
message="failure",
result="Content is empty",
action_type=Actions.DETECT_ADDRESS,
entity_urn=request.entity_urn,
sentiment=None
)
addresses = detect_addresses(openai_api_key, request.content)
return ResponseModel(
message="success",
result=addresses,
action_type=Actions.DETECT_ADDRESS,
entity_urn=request.entity_urn,
sentiment=None
)
except Exception as e:
logger.error(f"Address detection endpoint error: {str(e)}")
return ResponseModel(
message="failure",
result=f"Error: {str(e)}",
action_type=Actions.DETECT_ADDRESS,
entity_urn=request.entity_urn,
sentiment=None
)
@app.post("/summarize", response_model=ResponseModel)
async def summarize(
request: RequestModel,
openai_api_key: Annotated[str, Header(alias="x-api-key")]
):
"""Endpoint for text summarization and sentiment analysis"""
try:
logger.info(f"Processing summarization for entity_urn: {request.entity_urn}")
if not request.content.strip():
return ResponseModel(
message="failure",
result="Content is empty",
action_type=Actions.SUMMARIZE,
entity_urn=request.entity_urn,
sentiment={}
)
summary, sentiment = summarize_and_analyze_sentiment(openai_api_key, request.content)
return ResponseModel(
message="success",
result=summary,
sentiment=sentiment,
action_type=Actions.SUMMARIZE,
entity_urn=request.entity_urn
)
except Exception as e:
logger.error(f"Summarization endpoint error: {str(e)}")
return ResponseModel(
message="failure",
result=f"Error: {str(e)}",
sentiment={},
action_type=Actions.SUMMARIZE,
entity_urn=request.entity_urn
)
if __name__ == "__main__":
import uvicorn
# Use port 7860 for Hugging Face Spaces, fallback to 8500 for local
port = int(os.getenv("PORT", 7860))
uvicorn.run(app, host="0.0.0.0", port=port)
|