Added the files

Dockerfile

@@ -0,0 +1,18 @@
+# Use an official Python runtime as a parent image
+FROM python:3.11-slim
+
+# Set the working directory in the container
+WORKDIR /code
+
+# Copy the requirements file into the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy the rest of the application's code into the container at /code
+COPY . /code/
+
+# Tell uvicorn to run on all available network interfaces (0.0.0.0)
+# and on the port Hugging Face Spaces expects (7860).
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -7,5 +7,3 @@ sdk: docker
 pinned: false
 license: apache-2.0
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,196 @@
+from fastapi import FastAPI, HTTPException, Query
+from fastapi.middleware.cors import CORSMiddleware
+import requests
+import pandas as pd
+from datetime import datetime
+import google.generativeai as genai
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+app = FastAPI()
+
+origins = ["*"] 
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+FLIGHT_API_KEY = os.getenv("FLIGHT_API_KEY")
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+
+# print(f"--- DEBUG: Loaded Gemini Key: {GEMINI_API_KEY} ---") 
+if GEMINI_API_KEY:
+    try:
+        genai.configure(api_key=GEMINI_API_KEY)
+    except Exception as e:
+        print(f"Could not configure Gemini API: {e}")
+
+
+AUSTRALIAN_CITY_CODES = {
+    "Sydney": "SYD", "Melbourne": "MEL", "Brisbane": "BNE", "Perth": "PER",
+    "Adelaide": "ADL", "Canberra": "CBR", "Gold Coast": "OOL", "Cairns": "CNS",
+    "Hobart": "HBA", "Darwin": "DRW"
+}
+
+def fetch_flight_data(api_key, departure_airport, arrival_airport, date_str):
+    url = f"https://api.flightapi.io/onewaytrip/{api_key}/{departure_airport}/{arrival_airport}/{date_str}/1/0/0/Economy/AUD"
+    try:
+        response = requests.get(url, timeout=30)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching flight data: {e}")
+        return None
+
+def parse_and_process_data(data, origin_code, dest_code, search_date):
+    if not data or 'itineraries' not in data:
+        return pd.DataFrame()
+
+    carriers = {c['id']: c for c in data.get('carriers', [])}
+    places = {p['id']: p['name'] for p in data.get('places', [])}
+
+    flight_options = []
+    
+    if not data.get('itineraries'):
+        return pd.DataFrame()
+
+    for i, itinerary in enumerate(data.get('itineraries', [])):
+        if not itinerary.get('pricing_options'):
+            continue
+        
+        price_info = itinerary['pricing_options'][0].get('price', {})
+        price = price_info.get('amount')
+
+        if not itinerary.get('leg_ids'):
+            continue
+            
+        leg_id = itinerary['leg_ids'][0]
+        leg = next((l for l in data.get('legs', []) if l['id'] == leg_id), None)
+        
+        if not leg or not price:
+            continue
+            
+        marketing_carrier_id = leg.get('marketing_carrier_ids', [None])[0]
+        carrier_info = carriers.get(marketing_carrier_id, {})
+        airline_name = carrier_info.get('name', "Unknown Airline")
+        
+        flight_number = "N/A"
+        if leg.get('segment_ids'):
+            segment_id = leg['segment_ids'][0]
+            segment = next((s for s in data.get('segments', []) if s['id'] == segment_id), None)
+            if segment:
+                carrier_code = carrier_info.get('code', "XX")
+                flight_num_part = segment.get('marketing_flight_number', leg['id'][:3])
+                flight_number = f"{carrier_code}{flight_num_part}"
+
+        flight_options.append({
+            "id": i,
+            "airline": airline_name,
+            "flight": flight_number,
+            "departure": pd.to_datetime(leg['departure']).strftime('%H:%M'),
+            "arrival": pd.to_datetime(leg['arrival']).strftime('%H:%M'),
+            "price": price
+        })
+
+    if not flight_options:
+        return pd.DataFrame()
+        
+    df = pd.DataFrame(flight_options)
+    return df.sort_values(by="price").reset_index(drop=True)
+
+
+def get_ai_insights(df, origin, destination, date):
+    if df.empty:
+        return "No flight data was available to analyze."
+    
+    if not GEMINI_API_KEY:
+        return "**AI Analysis Skipped:** Gemini API key not configured on the backend."
+
+    summary_df = df.head(10)
+    data_summary = f"""
+    Flight Price Data Summary:
+    - Route: {origin} to {destination}
+    - Date: {date}
+    - Number of flights found: {len(df)}
+    - Cheapest flight: AUD {df['price'].min()} on {df.loc[df['price'].idxmin(), 'airline']}
+    - Average price of top 10 cheapest: AUD {summary_df['price'].mean():.2f}
+    """
+    
+    prompt = f"""
+    You are a market analyst for a chain of Australian hostels. Your goal is to provide a brief, actionable report based on flight data.
+
+    **Data Provided:**
+    {data_summary}
+
+    **Your Task:**
+    Provide a bullet-point summary in Markdown format for a hostel manager. The tone should be concise and professional. Focus on:
+    - **Top Insight:** What is the single most important takeaway? (e.g., "The route is highly competitive today, driving prices down.")
+    - **Price Trends:** Is it a good day to travel for budget-conscious guests? What is the cheapest price found?
+    - **Key Airlines:** Which 1-2 airlines are dominating the budget-friendly options?
+    - **Actionable Advice:** Give one concrete recommendation. (e.g., "Target marketing efforts towards customers arriving on Rex or Jetstar flights.")
+    """
+
+    try:
+        model = genai.GenerativeModel('gemini-1.5-flash-latest')
+        response = model.generate_content(prompt)
+        report_header = f"Based on the data for **{origin} to {destination}** on **{date}**, here are the key insights:"
+        return f"{report_header}\n\n{response.text}"
+    except Exception as e:
+        return f"Could not generate AI insights. Error: {e}"
+
+@app.get("/api/analyze-demand")
+def analyze_demand(
+    origin: str = Query(..., description="Origin city name, e.g., Sydney"),
+    destination: str = Query(..., description="Destination city name, e.g., Melbourne"),
+    date: str = Query(..., description="Departure date in YYYY-MM-DD format")
+):
+    if not FLIGHT_API_KEY:
+        raise HTTPException(status_code=500, detail="Flight API key not configured on the server.")
+
+    origin_code = AUSTRALIAN_CITY_CODES.get(origin)
+    dest_code = AUSTRALIAN_CITY_CODES.get(destination)
+
+    if not origin_code or not dest_code:
+        raise HTTPException(status_code=400, detail="Invalid origin or destination city name.")
+
+    raw_data = fetch_flight_data(FLIGHT_API_KEY, origin_code, dest_code, date)
+    if not raw_data:
+        raise HTTPException(status_code=404, detail="No flight data found for the specified route and date.")
+
+    flight_df = parse_and_process_data(raw_data, origin_code, dest_code, date)
+    if flight_df.empty:
+         raise HTTPException(status_code=404, detail="No flight options could be parsed for this route.")
+
+    ai_report = get_ai_insights(flight_df, origin, destination, date)
+
+    cheapest_flight_row = flight_df.loc[flight_df['price'].idxmin()]
+    insight_cards = {
+        "cheapestFlight": {
+            "price": cheapest_flight_row['price'],
+            "airline": cheapest_flight_row['airline'],
+            "flightNumber": cheapest_flight_row['flight']
+        },
+        "busiestAirline": {
+            "name": flight_df['airline'].mode()[0],
+            "flightCount": len(flight_df)
+        },
+        "bestDeal": {
+            "name": cheapest_flight_row['airline'],
+            "savings": "Top Value"
+        }
+    }
+
+    chart_data = flight_df.groupby('airline')['price'].min().reset_index()
+    chart_data.rename(columns={'airline': 'name', 'price': 'price'}, inplace=True)
+
+    return {
+        "insightCards": insight_cards,
+        "aiAnalystReport": ai_report,
+        "flightPriceChart": chart_data.to_dict('records'),
+        "flightDataTable": flight_df.to_dict('records')
+    }

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn[standard]
+python-dotenv
+requests
+pandas
+google-generativeai