app.py

app.py

@@ -1,64 +1,79 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import pandas as pd
+from transformers import pipeline
+from bs4 import BeautifulSoup
+import requests
+from PyPDF2 import PdfReader
+import docx
+from pptx import Presentation
+import openpyxl
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Load the model
+model = pipeline("question-answering", model="facebook/llama-7b-hf")
 
+# Function to read text from uploaded documents
+def read_text_from_document(file):
+    if file.name.endswith('.txt'):
+        text = file.read().decode('utf-8')
+    elif file.name.endswith('.pdf'):
+        reader = PdfReader(file)
+        text = ''
+        for page in reader.pages:
+            text += page.extract_text()
+    elif file.name.endswith('.docx'):
+        doc = docx.Document(file)
+        text = ''
+        for para in doc.paragraphs:
+            text += para.text
+    elif file.name.endswith('.pptx'):
+        presentation = Presentation(file)
+        text = ''
+        for slide in presentation.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text += shape.text
+    elif file.name.endswith('.xlsx'):
+        wb = openpyxl.load_workbook(file)
+        sheet = wb.active
+        text = ''
+        for row in sheet.rows:
+            for cell in row:
+                text += str(cell.value) + ' '
+    return text
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Function to scrape URL
+def scrape_url(url):
+    try:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.text, 'html.parser')
+        text = soup.get_text()
+        return text
+    except Exception as e:
+        return str(e)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Function to answer questions based on input data
+def answer_questions(data, question):
+    if data:
+        try:
+            result = model(question=question, context=data)
+            return result['answer']
+        except Exception as e:
+            return str(e)
+    else:
+        return "No data provided"
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# Gradio interface
+demo = gr.Interface(
+    fn=lambda data, url, question: answer_questions(read_text_from_document(data) if data else scrape_url(url), question),
+    inputs=[
+        gr.File(label="Upload Document (.txt, .pdf, .docx, .pptx, .xlsx)"),
+        gr.Textbox(label="Enter URL"),
+        gr.Textbox(label="Ask a question")
     ],
+    outputs=gr.Textbox(label="Answer"),
+    title="LLM Chatbot",
+    description="Upload a document or enter a URL and ask a question"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the demo
+demo.launch()