src/web/app.py

"""
Gradio app for Norwegian RAG chatbot.
Provides a web interface for interacting with the chatbot.
"""

import os
import gradio as gr
import tempfile
from typing import List, Dict, Any, Tuple, Optional

from ..api.huggingface_api import HuggingFaceAPI
from ..document_processing.processor import DocumentProcessor
from ..rag.retriever import Retriever
from ..rag.generator import Generator

class ChatbotApp:
    """
    Gradio app for Norwegian RAG chatbot.
    """
    
    def __init__(
        self,
        api_client: Optional[HuggingFaceAPI] = None,
        document_processor: Optional[DocumentProcessor] = None,
        retriever: Optional[Retriever] = None,
        generator: Optional[Generator] = None,
        title: str = "Norwegian RAG Chatbot",
        description: str = "En chatbot basert på Retrieval-Augmented Generation (RAG) for norsk språk."
    ):
        """
        Initialize the chatbot app.
        
        Args:
            api_client: HuggingFaceAPI client
            document_processor: Document processor
            retriever: Retriever for finding relevant chunks
            generator: Generator for creating responses
            title: App title
            description: App description
        """
        # Initialize components
        self.api_client = api_client or HuggingFaceAPI()
        self.document_processor = document_processor or DocumentProcessor(api_client=self.api_client)
        self.retriever = retriever or Retriever(api_client=self.api_client)
        self.generator = generator or Generator(api_client=self.api_client)
        
        # App settings
        self.title = title
        self.description = description
        
        # Initialize Gradio app
        self.app = self._build_interface()
    
    def _build_interface(self) -> gr.Blocks:
        """
        Build the Gradio interface.
        
        Returns:
            Gradio Blocks interface
        """
        with gr.Blocks(title=self.title) as app:
            gr.Markdown(f"# {self.title}")
            gr.Markdown(self.description)
            
            with gr.Tabs():
                # Chat tab
                with gr.Tab("Chat"):
                    chatbot = gr.Chatbot(height=500)
                    
                    with gr.Row():
                        msg = gr.Textbox(
                            placeholder="Skriv din melding her...",
                            show_label=False,
                            scale=9
                        )
                        submit_btn = gr.Button("Send", scale=1)
                    
                    with gr.Accordion("Avanserte innstillinger", open=False):
                        temperature = gr.Slider(
                            minimum=0.1,
                            maximum=1.0,
                            value=0.7,
                            step=0.1,
                            label="Temperatur"
                        )
                    
                    clear_btn = gr.Button("Tøm chat")
                    
                    # Set up event handlers
                    submit_btn.click(
                        fn=self._respond,
                        inputs=[msg, chatbot, temperature],
                        outputs=[msg, chatbot]
                    )
                    
                    msg.submit(
                        fn=self._respond,
                        inputs=[msg, chatbot, temperature],
                        outputs=[msg, chatbot]
                    )
                    
                    clear_btn.click(
                        fn=lambda: None,
                        inputs=None,
                        outputs=chatbot,
                        queue=False
                    )
                
                # Document upload tab
                with gr.Tab("Last opp dokumenter"):
                    with gr.Row():
                        with gr.Column(scale=2):
                            file_output = gr.File(label="Opplastede dokumenter")
                            upload_button = gr.UploadButton(
                                "Klikk for å laste opp dokument",
                                file_types=["pdf", "txt", "html"],
                                file_count="multiple"
                            )
                        
                        with gr.Column(scale=3):
                            documents_list = gr.Dataframe(
                                headers=["Dokument ID", "Filnavn", "Dato", "Chunks"],
                                label="Dokumentliste",
                                interactive=False
                            )
                    
                    process_status = gr.Textbox(label="Status", interactive=False)
                    refresh_btn = gr.Button("Oppdater dokumentliste")
                    
                    # Set up event handlers
                    upload_button.upload(
                        fn=self._process_uploaded_files,
                        inputs=[upload_button],
                        outputs=[process_status, documents_list]
                    )
                    
                    refresh_btn.click(
                        fn=self._get_documents_list,
                        inputs=None,
                        outputs=[documents_list]
                    )
                
                # Embed tab
                with gr.Tab("Integrer"):
                    gr.Markdown("## Integrer chatboten på din nettside")
                    
                    with gr.Row():
                        with gr.Column():
                            gr.Markdown("### iFrame-kode")
                            iframe_code = gr.Code(
                                label="iFrame",
                                language="html",
                                value='<iframe src="https://huggingface.co/spaces/username/norwegian-rag-chatbot" width="100%" height="500px"></iframe>'
                            )
                        
                        with gr.Column():
                            gr.Markdown("### JavaScript Widget")
                            js_code = gr.Code(
                                label="JavaScript",
                                language="html",
                                value='<script src="https://huggingface.co/spaces/username/norwegian-rag-chatbot/widget.js"></script>'
                            )
                    
                    gr.Markdown("### Forhåndsvisning")
                    gr.Markdown("*Forhåndsvisning vil være tilgjengelig etter at chatboten er distribuert til Hugging Face Spaces.*")
            
            gr.Markdown("---")
            gr.Markdown("Bygget med [Hugging Face](https://huggingface.co/) og [Gradio](https://gradio.app/)")
        
        return app
    
    def _respond(
        self,
        message: str,
        chat_history: List[Tuple[str, str]],
        temperature: float
    ) -> Tuple[str, List[Tuple[str, str]]]:
        """
        Generate a response to the user message.
        
        Args:
            message: User message
            chat_history: Chat history
            temperature: Temperature for text generation
            
        Returns:
            Empty message and updated chat history
        """
        if not message:
            return "", chat_history
        
        # Add user message to chat history
        chat_history.append((message, None))
        
        try:
            # Retrieve relevant chunks
            retrieved_chunks = self.retriever.retrieve(message)
            
            # Generate response
            response = self.generator.generate(
                query=message,
                retrieved_chunks=retrieved_chunks,
                temperature=temperature
            )
            
            # Update chat history with response
            chat_history[-1] = (message, response)
        except Exception as e:
            # Handle errors
            error_message = f"Beklager, det oppstod en feil: {str(e)}"
            chat_history[-1] = (message, error_message)
        
        return "", chat_history
    
    def _process_uploaded_files(
        self,
        files: List[tempfile._TemporaryFileWrapper]
    ) -> Tuple[str, List[List[str]]]:
        """
        Process uploaded files.
        
        Args:
            files: List of uploaded files
            
        Returns:
            Status message and updated documents list
        """
        if not files:
            return "Ingen filer lastet opp.", self._get_documents_list()
        
        processed_files = []
        
        for file in files:
            try:
                # Process the document
                document_id = self.document_processor.process_document(file.name)
                processed_files.append(os.path.basename(file.name))
            except Exception as e:
                return f"Feil ved behandling av {os.path.basename(file.name)}: {str(e)}", self._get_documents_list()
        
        if len(processed_files) == 1:
            status = f"Fil behandlet: {processed_files[0]}"
        else:
            status = f"{len(processed_files)} filer behandlet: {', '.join(processed_files)}"
        
        return status, self._get_documents_list()
    
    def _get_documents_list(self) -> List[List[str]]:
        """
        Get list of processed documents.
        
        Returns:
            List of document information
        """
        documents = self.document_processor.get_all_documents()
        
        # Format for dataframe
        documents_list = []
        for doc_id, metadata in documents.items():
            filename = metadata.get("filename", "N/A")
            processed_date = metadata.get("processed_date", "N/A")
            chunk_count = metadata.get("chunk_count", 0)
            
            documents_list.append([doc_id, filename, processed_date, chunk_count])
        
        return documents_list
    
    def launch(self, **kwargs):
        """
        Launch the Gradio app.
        
        Args:
            **kwargs: Additional arguments for gr.launch()
        """
        self.app.launch(**kwargs)


def create_app():
    """
    Create and configure the chatbot app.
    
    Returns:
        Configured ChatbotApp instance
    """
    # Initialize API client
    api_client = HuggingFaceAPI()
    
    # Initialize components
    document_processor = DocumentProcessor(api_client=api_client)
    retriever = Retriever(api_client=api_client)
    generator = Generator(api_client=api_client)
    
    # Create app
    app = ChatbotApp(
        api_client=api_client,
        document_processor=document_processor,
        retriever=retriever,
        generator=generator
    )
    
    return app