Upload 4 files

Dockerfile

@@ -0,0 +1,18 @@
+# Use official Python image as base
+FROM python:3.10
+
+# Set working directory in container
+WORKDIR /app
+
+# Copy requirements file and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY . .
+
+# Expose port 7860 for FastAPI
+EXPOSE 7860
+
+# Command to run FastAPI app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,55 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import pandas as pd
+import numpy as np
+import faiss
+import requests
+import os
+
+app = FastAPI()
+
+# Load dataset
+df = pd.read_csv("news_dataset.csv")
+
+HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")  # Load from environment variable
+
+# Load FAISS index
+index = faiss.read_index("arabic_news_index")
+
+# Define request model
+class NewsQuery(BaseModel):
+    prompt: str
+
+def create_textual_representation(row):
+    """Convert a news article into a structured text representation."""
+    return f"""
+    الكاتب: {row['writer']},
+    الموقع: {row['location']},
+    التاريخ: {row['date']},
+    الوقت: {row['time']},
+    العنوان: {row['title']},
+    الخبر: {row['news']}
+    """
+
+@app.post("/recommend")
+async def recommend_articles(query: NewsQuery):
+    """Find similar news articles using FAISS with real Llama 3.1 embeddings."""
+    
+    # Call Llama 3.1 remotely for embeddings
+    res = requests.post("https://api-inference.huggingface.co/models/meta-llama/Llama-3.1-8B",
+                        headers={"Authorization": HUGGINGFACE_API_KEY},
+                        json={"inputs": query.prompt})
+    
+    if res.status_code != 200:
+        return {"error": "Failed to get embeddings from Llama 3.1"}
+
+    # Extract the real embedding
+    embedding = np.array([res.json()[0]['embedding']], dtype="float32")
+
+    # Search FAISS index for similar articles
+    D, I = index.search(embedding, 5)
+
+    # Retrieve recommended articles
+    recommendations = df.iloc[I.flatten()][['title', 'writer', 'news']].to_dict(orient="records")
+
+    return {"recommendations": recommendations}

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+pandas
+numpy
+faiss-cpu
+requests