Update app.py

app.py

@@ -1,412 +1,224 @@
-✨🚀 The ULTIMATE Step-by-Step V1.0 Build Guide for Your AI Travel Bot (Granular for Beginners)
-
-Welcome, future coder! 🎉 This guide contains every single step and command you need—no external references required. Follow along on Windows 11, and you'll have a working AI Travel Bot by the end.
-
-📋 Prerequisites (Install Everything First)
-
-Before we begin, install all tools below. Each is required for the project.
-
-Git
-
-Open your browser to https://git-scm.com/downloads
-
-Click Download for Windows.
-
-Run the downloaded installer (Git-*.exe).
-
-In each dialog: click Next, accept defaults, then Finish.
-
-Verify by opening Command Prompt and running:
-
-
-
-git --version
-```
-You should see git version 2.x.x.
-
-Python 3.10+
-
-Go to https://python.org/downloads
-
-Click Download Python 3.10.x.
-
-Run the installer.
-
-Important: Check Add Python to PATH.
-
-Click Install Now.
-
-Verify:
-
-
-
-python --version
-```
-You should see Python 3.10.x.
-
-Node.js (LTS)
-
-Visit https://nodejs.org/en/download/
-
-Download Windows Installer (.msi) for LTS.
-
-Run the installer: Next → Next → Install → Finish.
-
-Verify:
-
-
-
-node --version
-npm --version
-```
-You should see versions (e.g., v18.x.x, 8.x.x).
-
-Hugging Face Account
-
-Open https://huggingface.co/ and click Sign up.
-
-Register with your email or GitHub.
-
-Confirm your email and log in.
-
-1️⃣ Create Your Online Home: Hugging Face Space
-
-In your browser, go to https://huggingface.co/spaces.
-
-Click Create new Space (blue button top right).
-
-Fill in:
-
-Space name: WanderlustAI-v1
-
-SDK: select Gradio
-
-Visibility: choose Public for now
-
-Click Create Space.
-
-Wait until you see the file explorer panel on the left. That’s your project directory.
-
-2️⃣ Set Up Your Project Files (The Skeleton)
-
-In the Hugging Face Space file explorer, create these files one at a time:
-
-app.py
-
-Click Add file → Create file.
-
-Enter app.py → click Create.
-
-README.md
-
-Add file → README.md → Create.
-
-.env.example
-
-Add file → .env.example → Create.
-
-requirements.txt
-
-Add file → requirements.txt → Create.
-
-packages.txt
-
-Add file → packages.txt → Create.
-
-Confirm all five files appear in the list.
-
-3️⃣ Document the Essentials (Fill In Templates)
-
-3.1 README.md
-
-Click README.md → pencil icon to edit.
-
-Paste:
-
-# AI Travel Bot
-This project builds an AI-powered travel assistant using ChatGPT and web scraping.
-
-## How to Use
-1. Set up secrets in `.env`.
-2. Run `python app.py` locally or deploy on Hugging Face.
-
-Click Commit changes.
-
-3.2 .env.example
-
-Open .env.example → edit.
-
-Paste:
-
-OPENAI_API_KEY=YOUR_OPENAI_KEY_HERE
-GOOGLE_API_KEY=YOUR_GOOGLE_KEY_HERE
-
-Commit changes.
-
-4️⃣ List Your Tools (Dependencies)
-
-4.1 requirements.txt
-
-Open requirements.txt → edit.
-
-Paste exactly:
-
-gradio
-langchain
-langchain-openai
-langchain-google-genai
-langchain-community
-playwright
-scrapy
-beautifulsoup4
-lxml
-requests
-python-dotenv
-cachetools
-tenacity
-
-Commit changes.
-
-4.2 packages.txt
-
-Open packages.txt → edit.
-
-Paste:
-
-chromium-driver
-
-Commit changes.
-
-5️⃣ Secure Your Secrets (Add Real Keys)
-
-In the Space UI, click Settings (top menu).
-
-Scroll to Repository secrets → click New secret.
-
-Add:
-
-Name: OPENAI_API_KEY
-
-Value: paste your actual key
-
-Click Add secret.
-
-Repeat for:
-
-GOOGLE_API_KEY
-
-🔒 Secrets are hidden; your code will read them via os.environ.
-
-6️⃣ Build the Brain: Full app.py Code (One Paste)
-
-Open app.py → click pencil.
-
-Delete any existing text.
-
-Copy & paste the ENTIRE code below in one go:
-
-# 1. IMPORTS & SETUP
+import gradio as gr
+import os
 import asyncio
+import json
 import datetime
-import logging
-import os
-import gradio as gr
-from cachetools import TTLCache
-from langchain_core.output_parsers import JsonOutputParser
+from dotenv import load_dotenv
+
+# --- Langchain Imports ---
 from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_openai import ChatOpenAI
-
-# Configure logging
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(levelname)s - %(message)s'
-)
-
-# Simple in-memory cache
-ttl_cache = TTLCache(maxsize=100, ttl=3600)
-
-# 2. DATA MODEL
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_core.messages import SystemMessage, HumanMessage
+
+# Load environment variables from .env file (for local testing)
+# On Hugging Face Spaces, secrets are automatically available as env vars.
+load_dotenv()
+
+# --- 1. API KEY CHECK ---
+# This will make the app fail early if the key isn't set
+try:
+    openai_api_key = os.environ["OPENAI_API_KEY"]
+except KeyError:
+    raise EnvironmentError("Missing OPENAI_API_KEY. Please set it in a .env file locally, or in Hugging Face Space secrets.")
+
+# --- 2. PYDANTIC DATA STRUCTURE DEFINITION ---
+# Defines the JSON structure we want the LLM to output
 class TravelRequest(BaseModel):
-    origin_city: str = Field(description="Starting city or airport")
-    destination_city: str = Field(description="Destination city or airport")
-    start_date: str = Field(description="Trip start date (YYYY-MM-DD)")
-    end_date: str = Field(description="Trip end date (YYYY-MM-DD)")
-    budget: int = Field(description="Total budget in USD")
-    interests: list[str] = Field(description="List of interests like 'hiking', 'museums'")
-
-# 3. PARSE USER INPUT
-async def _extract_user_request(question: str) -> dict:
-    llm = ChatOpenAI(model="gpt-4o", temperature=0)
-    parser = JsonOutputParser(pydantic_object=TravelRequest)
-    prompt = ChatPromptTemplate.from_messages([
-        ("system", "You are a travel assistant. Extract details into JSON."),
-        ("human", "{format_instructions}\n{request}")
-    ]).partial(format_instructions=parser.get_format_instructions())
-    date_str = datetime.date.today().isoformat()
-    logging.info(f"Extracting: {question}")
-    return await (prompt | llm | parser).ainvoke({
-        "request": question,
-        "current_date": date_str
-    })
-
-# 4. SEARCH HELPERS
-async def _cached_search(func, details):
-    key = (func.__name__, str(details))
-    if key in ttl_cache:
-        logging.info(f"Cache hit for {func.__name__}")
-        return ttl_cache[key]
-    logging.info(f"Cache miss for {func.__name__}")
-    res = await func(details)
-    ttl_cache[key] = res
-    return res
-
-async def _search_skyscanner(details: dict) -> list:
+    departure_city: str = Field(description="The city or airport of departure. Infer if not specified.")
+    destination_city: str = Field(description="The city or airport of the travel destination.")
+    departure_date: str = Field(description="The departure date or general time frame (e.g., 'August 2025').")
+    return_date: str = Field(description="The return date or general time frame.")
+    duration_days_approx: str = Field(description="Approximate duration of the trip in days.")
+    budget_preference: str = Field(description="User's budget preference (e.g., 'cheap', 'luxury').")
+    flight_preferences: str = Field(description="Specific flight preferences (e.g., 'direct flights', 'few stops').")
+    accommodation_type: str = Field(description="Preferred accommodation (e.g., 'hotel', 'hostel', 'resort').")
+    number_of_travelers: int = Field(description="Number of adults traveling. Default to 1 if not specified.")
+    activity_interests: str = Field(description="Specific interests for activities (e.g., 'museums', 'hiking').")
+
+# --- 3. CONCEPTUAL ASYNC SEARCH FUNCTIONS ---
+# You will implement the real logic for each of these. For now, they simulate a delay.
+async def search_skyscanner(details):
+    # Simulate network delay and return mock data for a flight
+    print(f"Searching Skyscanner for: {details['destination_city']}")
+    await asyncio.sleep(2)
+    return [{"source": "Skyscanner", "type": "flight", "details": "Flight to Paris", "price": 850.00, "link": "https://www.skyscanner.com"}]
+
+async def search_expedia(details):
+    # Simulate network delay and return mock data for a hotel
+    print(f"Searching Expedia for: {details['destination_city']}")
+    await asyncio.sleep(1.5)
+    return [{"source": "Expedia", "type": "hotel", "details": "Hotel in Paris", "price": 150.00, "link": "https://www.expedia.com"}]
+
+async def scrape_Google_Flights(details):
+    # Simulate network delay and return mock data for a scraped flight
+    print(f"Scraping Google Flights for: {details['destination_city']}")
+    await asyncio.sleep(3)
+    return [{"source": "Google Flights (Scraped)", "type": "flight", "details": "Cheaper Flight to Paris", "price": 814.00, "link": "https://www.google.com/flights"}]
+
+async def search_get_your_guide(details):
+    # Simulate network delay and return mock data for an activity
+    print(f"Searching GetYourGuide for: {details['activity_interests']}")
+    await asyncio.sleep(1)
+    return [{"source": "GetYourGuide", "type": "activity", "details": "Eiffel Tower Tour", "price": 50.00, "link": "https://www.getyourguide.com"}]
+
+async def search_llm_redundancy(details, llm, llm_name):
+    # Query another LLM for additional, general travel ideas
+    print(f"Querying {llm_name} for additional ideas...")
+    prompt = f"""As a helpful travel assistant, provide some brief travel suggestions for a trip based on these details: {details}.
+    Focus on general tips, hidden gems, or activity ideas. Do not suggest specific prices or flights."""
+    messages = [SystemMessage(content=prompt), HumanMessage(content="What are your suggestions?")]
+    response = await llm.ainvoke(messages)
+    return {"source": llm_name, "type": "insight", "details": response.content}
+
+# --- 4. MAIN BOT LOGIC ---
+async def ask_bot(question):
+    """
+    This is the main ASYNCHRONOUS function for the bot.
+    It orchestrates the extraction, search, and output formatting.
+    """
+    # Part 1: Extract structured data from user request using an LLM
     try:
-        logging.info(f"Skyscanner: {details['destination_city']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "Skyscanner",
-            "type": "flight",
-            "details": f"Round-trip to {details['destination_city']}",
-            "price": 800,
-            "link": "https://skyscanner.com"
-        }]
+        # Initialize the LLM for extraction (GPT-4o for precise JSON output)
+        llm_extractor = ChatOpenAI(model="gpt-4o", temperature=0)
+        # Define the parser for the Pydantic data model
+        parser = JsonOutputParser(pydantic_object=TravelRequest)
+        # Create the prompt template for extraction, including format instructions
+        extraction_prompt = ChatPromptTemplate.from_messages([
+            ("system", "You are a helpful travel assistant. Your goal is to accurately extract travel details from a user's natural language request and output them as a JSON object, following the specified schema. Be precise and infer intelligently. The current date is {current_date}."),
+            ("human", "Extract travel details from this request:\n\n{format_instructions}\n\nUser request: {request}"),
+        ]).partial(format_instructions=parser.get_format_instructions())
+        # Create the LangChain expression language chain
+        extraction_chain = extraction_prompt | llm_extractor | parser
+        # Get the current date to help the LLM with date parsing
+        current_date_str = datetime.date.today().strftime("%Y-%m-%d")
+        # Invoke the chain to get the structured request
+        structured_request = await extraction_chain.ainvoke({"request": question, "current_date": current_date_str})
     except Exception as e:
-        logging.error(e)
-        return []
+        # Handle errors during the extraction phase
+        return f"Error extracting request details: {e}. Please try rephrasing your request."
 
-async def _search_expedia(details: dict) -> list:
-    try:
-        logging.info(f"Expedia: {details['destination_city']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "Expedia",
-            "type": "hotel",
-            "details": f"Hotel in {details['destination_city']}",
-            "price": 1200,
-            "link": "https://expedia.com"
-        }]
-    except Exception as e:
-        logging.error(e)
-        return []
+    # Part 2: Gather all search tasks to run concurrently
+    # Initialize LLM instances for redundancy search (e.g., creative suggestions)
+    llm_openai_creative = ChatOpenAI(model="gpt-4o", temperature=0.7)
+    # To enable Gemini redundancy, uncomment the line below and ensure GOOGLE_API_KEY is set in your .env
+    # llm_gemini_search = ChatGoogleGenerativeAI(model="gemini-1.5-flash", temperature=0.7)
 
-async def _search_getyourguide(details: dict) -> list:
-    try:
-        logging.info(f"GetYourGuide: {details['interests']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "GetYourGuide",
-            "type": "activity",
-            "details": f"Tour: {details['interests']}",
-            "price": 150,
-            "link": "https://getyourguide.com"
-        }]
-    except Exception as e:
-        logging.error(e)
-        return []
-
-# 5. GATHER ALL RESULTS
-async def _gather_travel_data(req: dict) -> list:
     tasks = [
-        _cached_search(_search_skyscanner, req),
-        _cached_search(_search_expedia, req),
-        _cached_search(_search_getyourguide, req)
+        search_skyscanner(structured_request),          # Flight search
+        search_expedia(structured_request),             # Hotel search
+        scrape_Google_Flights(structured_request),      # Another flight source (simulated scraping)
+        search_get_your_guide(structured_request),      # Activities search
+        search_llm_redundancy(structured_request, llm_openai_creative, "ChatGPT (Creative)"), # AI insights
+        # search_llm_redundancy(structured_request, llm_gemini_search, "Gemini"), # Uncomment for Gemini insights
     ]
+
+    # Part 3: Run all tasks concurrently and collect results
     results = await asyncio.gather(*tasks, return_exceptions=True)
-    combined = []
-    for r in results:
-        if isinstance(r, Exception):
-            logging.error(r)
-        else:
-            combined.extend(r)
-    return combined
 
-# 6. FORMAT OUTPUT
-def _format_response(req: dict, data: list) -> str:
-    dest = req['destination_city']
-    text = f"## Travel Plan for {dest}\n"
-    flights = [i for i in data if i['type']=='flight']
-    hotels = [i for i in data if i['type']=='hotel']
-    acts = [i for i in data if i['type']=='activity']
+    # Part 4: Normalize, filter, and rank results
+    all_results = []
+    for res in results:
+        if isinstance(res, Exception):
+            # Log any exceptions from the concurrent tasks
+            print(f"A search task failed: {res}")
+        elif res:
+            # Extend the combined results list if the task was successful
+            all_results.extend(res)
+
+    # Separate and sort results by type (e.g., flights by price)
+    flights = sorted([r for r in all_results if r['type'] == 'flight'], key=lambda x: x['price'])
+    hotels = sorted([r for r in all_results if r['type'] == 'hotel'], key=lambda x: x['price'])
+    activities = [r for r in all_results if r['type'] == 'activity']
+    insights = [r for r in all_results if r['type'] == 'insight']
+
+    # Part 5: Generate the final formatted output in Markdown
+    dest_city = structured_request['destination_city']
+    output_text = f"## ✨ Your Personalized Travel Plan to {dest_city}! ✨\n\n"
+
+    # Format Flights section
+    output_text += f"### ✈️ Top Flights\n"
     if flights:
-        text += "\n### Flights:\n"
-        for f in flights:
-            text += f"- {f['details']} (${f['price']}) [Book]({f['link']})\n"
+        for flight in flights[:3]: # Display top 3 flights
+            output_text += f"* **{flight['details']}** from **{flight['source']}**\n"
+            output_text += f"  * Price: **C${flight['price']:,.2f}**\n"
+            output_text += f"  * 🔗 [**View Deal**]({flight['link']})\n"
+    else:
+        output_text += "_No flights found matching your criteria. Try adjusting the dates._\n"
+    output_text += "\n"
+
+    # Format Hotels section
+    output_text += f"### 🏨 Top Accommodations\n"
     if hotels:
-        text += "\n### Hotels:\n"
-        for h in hotels:
-            text += f"- {h['details']} (${h['price']}) [Book]({h['link']})\n"
-    if acts:
-        text += "\n### Activities:\n"
-        for a in acts:
-            text += f"- {a['details']} (${a['price']}) [Book]({a['link']})\n"
-    return text
-
-# 7. MAIN ORCHESTRATOR & UI
-async def ask_bot(question: str) -> str:
-    if not question:
-        return "Tell me your trip!"
-    try:
-        req = await _extract_user_request(question)
-        data = await _gather_travel_data(req)
-        return _format_response(req, data)
-    except Exception as e:
-        logging.error(e)
-        return "Error. Try again."
-
-iface = gr.Interface(
-    fn=ask_bot,
-    inputs=gr.Textbox(lines=4, label="Your dream trip?"),
-    outputs=gr.Markdown(),
-    title="AI Travel Bot"
-)
-
+        for hotel in hotels[:2]: # Display top 2 hotels
+            output_text += f"* **{hotel['details']}** from **{hotel['source']}**\n"
+            output_text += f"  * Price: **C${hotel['price']:,.2f}** / night\n"
+            output_text += f"  * 🔗 [**View Deal**]({hotel['link']})\n"
+    else:
+        output_text += "_No accommodations found matching your criteria._\n"
+    output_text += "\n"
+
+    # Format Activities section
+    output_text += f"### 🎉 Fun Activities\n"
+    if activities:
+        for activity in activities[:2]: # Display top 2 activities
+            output_text += f"* **{activity['details']}** from **{activity['source']}**\n"
+            output_text += f"  * Price: **C${activity['price']:,.2f}**\n"
+            output_text += f"  * 🔗 [**View Activity**]({activity['link']})\n"
+    else:
+        output_text += "_No specific activities found, but there's always something to explore!_\n"
+    output_text += "\n"
+
+    # Format AI Insights section (from redundant LLMs)
+    output_text += "### 💡 Additional AI Insights (for Redundancy)\n"
+    if insights:
+        for insight in insights:
+            output_text += f"* **{insight['source']} says:** {insight['details']}\n"
+    else:
+        output_text += "_No additional AI insights available._\n"
+    output_text += "\n"
+
+    # Add a disclaimer
+    output_text += "> **Disclaimer:** Prices and availability change rapidly. Click the links for the most up-to-date information. Happy travels! 🚀"
+
+    return output_text
+
+# --- 5. DEFINE THE GRADIO INTERFACE ---
+# Using gr.Blocks for a more customizable layout compared to gr.Interface
+with gr.Blocks(theme=gr.themes.Soft()) as iface:
+    # Main title for the application
+    gr.Markdown(
+        """
+        # ✨ The Ultimate Global Travel Planner Bot ✨
+        Your smart AI assistant for finding the best flights, hotels, and activities worldwide!
+        """
+    )
+    with gr.Row():
+        # User input text box with more lines and a guiding placeholder
+        user_input = gr.Textbox(lines=5, label="✈️ Tell me about your dream trip!", placeholder="e.g., I wanna go to Paris from Halifax, maybe around August for a week or so. Cheap as possible, no crazy layovers!")
+    with gr.Row():
+        # Submit button to trigger the bot's logic
+        submit_button = gr.Button("Find My Trip!", variant="primary")
+    with gr.Row():
+        # Area to display the Markdown formatted output
+        output_display = gr.Markdown(label="🌟 Your Travel Plan:")
+    
+    # Examples to help users understand how to phrase their requests
+    gr.Examples(
+        examples=[
+            ["I need a cheap flight from Toronto to London around July for 5 days."],
+            ["Looking for a beach resort in Mexico for 2 people in December, not too expensive."],
+            ["Find me some cool things to do in Tokyo in spring."]
+        ],
+        inputs=user_input # Connect examples to the user input box
+    )
+    
+    # Connect the submit button's click event to the ask_bot function
+    submit_button.click(fn=ask_bot, inputs=user_input, outputs=output_display)
+
+# --- 6. LAUNCH THE APP ---
+# This block ensures the Gradio app runs when the script is executed
 if __name__ == "__main__":
-    iface.launch(server_name="0.0.0.0", server_port=7860)
-
-Click Commit changes to save and trigger build.
-
-7️⃣ Local Smoke Test (Catch Errors Early)
-
-On Windows Command Prompt:
-
-git clone https://huggingface.co/spaces/YOUR_USERNAME/WanderlustAI-v1
-cd WanderlustAI-v1
-copy .env.example .env
-# Open .env in Notepad and paste real keys
-pip install -r requirements.txt
-python app.py
-
-A browser window opens with your bot.
-
-Type e.g. "Cheap flight from NYC to Paris" → Submit.
-
-Check console: you should see INFO logs like "Extracting:" and "Skyscanner:".
-
-If it runs without errors, move to deployment.
-
-8️⃣ Deploy to Hugging Face
-
-git add .
-git commit -m "V1 ready"
-git push origin main
-
-In your Space on the web, click App tab.
-
-Wait ~60 seconds for build.
-
-Test live UI again.
-
-🎯 Roadmap to V2.0
-
-Split code into modules (extract.py, search.py, format.py).
-
-Write tests with pytest & vcrpy.
-
-Add retry/backoff examples using tenacity.
-
-Automate CI/CD with GitHub Actions.
-
-Congratulations! You've got every step—install, code, test, deploy—all in one place. Now build your AI Travel Bot! 🌍✨
-
+    iface.launch()