File size: 10,821 Bytes
b34efa5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 |
"""
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
|