Upload 2 files

app.py

@@ -0,0 +1,150 @@
+from langchain_groq import ChatGroq
+import os
+import gradio as gr
+from langchain.chains import ConversationChain
+from langchain.memory import ConversationBufferMemory
+from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
+from langchain.document_loaders import PyPDFLoader
+from langchain_experimental.text_splitter import SemanticChunker
+from langchain.vectorstores import FAISS
+from gtts import gTTS
+import tempfile
+
+# Set your API key from Hugging Face Secrets
+# DO NOT hardcode your API key here
+GROQ_API_KEY = os.environ.get('GROQ_API_KEY')
+
+# Initialize Groq LLM
+llm = ChatGroq(
+    model_name="llama3-70b-8192",
+    temperature=0.7,
+    api_key=GROQ_API_KEY
+)
+
+# Initialize memory
+memory = ConversationBufferMemory()
+conversation = ConversationChain(llm=llm, memory=memory)
+
+# Load PDF and create embeddings
+def initialize_rag():
+    try:
+        # Load the PDF document
+        loader = PyPDFLoader("TourismChatbot.pdf")
+        pages = loader.load_and_split()
+        
+        # Create embeddings
+        embed_model = FastEmbedEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
+        
+        # Create semantic chunks
+        semantic_chunker = SemanticChunker(embed_model, breakpoint_threshold_type="percentile")
+        semantic_chunks = semantic_chunker.create_documents([d.page_content for d in pages])
+        
+        # Create vector store
+        vectorstore = FAISS.from_documents(documents=semantic_chunks, embedding=embed_model)
+        
+        return vectorstore, embed_model
+    except Exception as e:
+        print(f"Error initializing RAG: {e}")
+        # Return None if initialization fails
+        return None, None
+
+# Initialize RAG components
+vectorstore, embed_model = initialize_rag()
+
+# Function to retrieve relevant information from the vector store
+def retrieve_relevant_chunks(query, top_k=3):
+    try:
+        if vectorstore is not None:
+            documents = vectorstore.similarity_search(query, k=top_k)
+            return [doc.page_content for doc in documents]
+        else:
+            # Fallback content if vectorstore is not available
+            return ["Rajasthan is a state in India known for its forts, palaces, and desert landscapes."]
+    except Exception as e:
+        print(f"Error retrieving chunks: {e}")
+        return ["Rajasthan is a state in India known for its forts, palaces, and desert landscapes."]
+
+def generate_rag_response(query, language="English"):
+    retrieved_chunks = retrieve_relevant_chunks(query)
+    context = "\n".join(retrieved_chunks)
+    prompt = f"""
+    Please provide the answer in **{language}**.
+
+    You are a helpful AI assistant providing tourism information about Rajasthan.
+    Answer based on the following context. If information is unavailable, say "I don't know."
+
+    Context: {context}
+    Question: {query}
+
+    Answer:
+    """
+    response = conversation.run(prompt)
+    return response.strip()
+
+def generate_speech(text, language):
+    lang_map = {"English": "en", "Hindi": "hi", "Spanish": "es", "French": "fr", "German": "de", "Tamil": "ta"}
+    lang_code = lang_map.get(language, "en")
+    tts = gTTS(text, lang=lang_code)
+    temp_audio_path = tempfile.NamedTemporaryFile(suffix=".mp3", delete=False).name
+    tts.save(temp_audio_path)
+    return temp_audio_path
+
+def chatbot_interface(query, language, chat_history):
+    response = generate_rag_response(query, language)
+    speech_path = generate_speech(response, language)
+
+    # Just append a 🔊 icon and use Gradio to handle the file
+    response_with_audio = f"{response} 🔊 (Click play below)"
+    chat_history.append((query, response_with_audio))
+
+    return chat_history, speech_path, ""  # Return file path as separate gr.Audio
+
+def handle_menu_click(topic, language, chat_history):
+    query = f"Give me information about {topic} in Rajasthan."
+    return chatbot_interface(query, language, chat_history)
+
+# Define language and menu options
+language_options = ['English', 'Hindi', 'Spanish', 'French', 'German', 'Tamil']
+menu_options = ["Places to Visit", "Best Time to Visit", "Festivals", "Cuisine", "Travel Tips"]
+
+# Create the Gradio interface
+with gr.Blocks(css="""
+    body {background-color: #FFF2E1; font-family: Arial, sans-serif;}
+    .gradio-container {max-width: 800px; margin: auto; padding: 20px; background: #FFF2E1;
+        border-radius: 15px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);}
+    .gradio-title {color: #462f22; text-align: center; font-size: 24px; font-weight: bold;
+        padding-bottom: 10px;}
+    .gradio-chat {border: 1px solid #e1c7a6; border-radius: 10px; padding: 10px; background: #fff;
+        min-height: 250px; color:#462f22}
+    .gr-button {background-color:#FFFCF5; color: #ec8d12; font-size: 14px; border-radius: 8px;
+        padding: 8px; border: 2px solid #e6ac55; cursor: pointer;}
+    .gr-button:hover {background-color: #ec8d12;color:#fff}
+    .clear-chat {float: right; background: #fff3e0; border: 1px solid #ed5722; color: #ed5722;
+        font-weight: bold; border-radius: 6px; padding: 5px 10px; cursor: pointer;}
+    .chat-input {width: 100%; padding: 10px; border-radius: 8px; border: 1px solid #e1c7a6;}
+""") as demo:
+
+    gr.Markdown("<h2 class='gradio-title'>🐪 Rajasthan Tourism Chatbot</h2>")
+
+    language_selector = gr.Dropdown(language_options, value="English", label="Select Language")
+    chatbot = gr.Chatbot(label="Rajasthan Tourism Assistant", elem_classes="gradio-chat")
+
+    with gr.Row():
+        for topic in menu_options:
+            btn = gr.Button(topic, elem_classes="gr-button")
+            btn.click(handle_menu_click,
+                      inputs=[gr.Textbox(value=topic, visible=False), language_selector, chatbot],
+                      outputs=[chatbot, gr.Audio(label="🔊 Audio Response", type="filepath"), gr.Textbox()])
+
+    query_input = gr.Textbox(placeholder="Ask about Rajasthan...", label="Enter your query", elem_classes="chat-input")
+    audio_output = gr.Audio(label="🔊 Audio Response", type="filepath", visible=True)
+
+    query_input.submit(
+        chatbot_interface,
+        inputs=[query_input, language_selector, chatbot],
+        outputs=[chatbot, audio_output, query_input]
+    )
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()

readme.txt

@@ -0,0 +1,34 @@
+# Rajasthan Tourism Chatbot
+
+This is a RAG-powered chatbot that provides information about tourism in Rajasthan, India. The application uses Groq LLM for text generation and supports multiple languages.
+
+## Features
+
+- Question answering about Rajasthan tourism
+- Multi-language support (English, Hindi, Spanish, French, German, Tamil)
+- Text-to-speech output in the selected language
+- Quick access buttons for common tourism queries
+- RAG (Retrieval Augmented Generation) integration using FastEmbed and FAISS
+
+## Technical Details
+
+- Built with LangChain and Groq API
+- Uses FastEmbed for embedding generation
+- Semantic chunking for better text segmentation
+- FAISS vector database for efficient similarity search
+- Gradio for the user interface
+
+## Required API Key
+
+This application requires a Groq API key to function. The key should be added as a secret in Hugging Face Spaces.
+
+## Usage
+
+1. Select your preferred language from the dropdown
+2. Use the quick access buttons for common queries
+3. Or type your own question in the text field
+4. Listen to the audio response by clicking the play button
+
+## Data Sources
+
+The chatbot is trained on tourism information about Rajasthan, stored in the TourismChatbot.pdf file.