initial Commit

Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Expose port
+EXPOSE 7860
+
+# Command to run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,169 @@
+#!/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
+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")
+
+
+@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"
+    }
+
+def extract_address(text: str) -> str:
+    address_pattern = r'\d+\s+[A-Za-z\s]+(?:Street|St|Avenue|Ave|Road|Rd|Boulevard|Blvd|Lane|Ln|Drive|Dr|Court|Ct|Place|Pl)'
+    match = re.search(address_pattern, text, re.IGNORECASE)
+    return match.group().strip() if match else ""
+
+def extract_summary(text: str) -> str:
+    sentences = text.split(".")
+    return ". ".join(sentences[:3]).strip() + "." if sentences else ""
+
+
+@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 = extract_address(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 = extract_summary(request.content)
+
+        sentiment = {
+            "label": "POSITIVE",
+            "score": 0.95
+        }
+
+        
+        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)

requirements.txt

@@ -0,0 +1,5 @@
+fastapi==0.115.14
+uvicorn[standard]==0.34.3
+pydantic==2.11.7
+python-dotenv==1.1.1
+httpx==0.28.1