Update app.py

app.py

@@ -1,28 +1,25 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import os
-from langchain import PromptTemplate
-from langchain import LLMChain
+from langchain import PromptTemplate, LLMChain
 from langchain_together import Together
-import re
 import pdfplumber
-# Set the API key with double quotes
 
+# Set the API key
 os.environ['TOGETHER_API_KEY'] = "c2f52626b97118b71c0c36f66eda4f5957c8fc475e760c3d72f98ba07d3ed3b5"
 
-text = ""
-max_pages = 7
-with pdfplumber.open("Diabetes Type 1.pdf") as pdf:
+def extract_text_from_pdf(pdf_file, max_pages=16):
+    text = ""
+    with pdfplumber.open(pdf_file) as pdf:
         for i, page in enumerate(pdf.pages):
             if i >= max_pages:
                 break
             text += page.extract_text() + "\n"
+    return text
 
-def Bot(Questions):
+def Bot(text, question):
     chat_template = """
     Based on the provided context: {text}
     Please answer the following question: {Questions}
-
     Only provide answers that are directly related to the context. If the question is unrelated, respond with "I don't know".
     """
     prompt = PromptTemplate(
@@ -35,7 +32,7 @@ def Bot(Questions):
     try:
         response = Generated_chat.invoke({
             "text": text,
-            "Questions": Questions
+            "Questions": question
         })
 
         response_text = response['text']
@@ -55,43 +52,33 @@ def Bot(Questions):
     except Exception as e:
         return f"Error in generating response: {e}"
 
-def ChatBot(Questions):
-  greetings = ["hi", "hello", "hey", "greetings", "what's up", "howdy"]
-    # Check if the input question is a greeting
-  question_lower = Questions.lower().strip()
-  if question_lower in greetings or any(question_lower.startswith(greeting) for greeting in greetings):
-        return "Hello! How can I assist you with the document today?"
-  else:
-    response=Bot(Questions)
-    print(response)
-    return response.translate(str.maketrans('', '', '\n'))
-  # text_embedding = model.encode(text, convert_to_tensor=True)
-  # statement_embedding = model.encode(statement, convert_to_tensor=True)
-
-  # # Compute the cosine similarity between the embeddings
-  # similarity = util.pytorch_cos_sim(text_embedding, statement_embedding)
-
-  # # Print the similarity score
-  # print(f"Cosine similarity: {similarity.item()}")
-
-  # # Define a threshold for considering the statement as related
-  # threshold = 0.7
+def ChatBot(history, document, question):
+    greetings = ["hi", "hello", "hey", "greetings", "what's up", "howdy"]
+    question_lower = question.lower().strip()
+    if question_lower in greetings or any(question_lower.startswith(greeting) for greeting in greetings):
+        return history + [("User", question), ("Bot", "Hello! How can I assist you with the document today?")]
+
+    # Extract text from the uploaded PDF document
+    text = extract_text_from_pdf(document)
+    
+    # Generate the bot response based on the question and extracted text
+    response = Bot(text, question)
+    
+    # Update chat history with the user's question and bot's response
+    history.append(("User", question))
+    history.append(("Bot", response))
+    
+    return history
+
+# Set up the Gradio interface using Blocks
+with gr.Blocks() as iface:
+    chatbot = gr.Chatbot()
+    document = gr.File(label="Upload PDF Document", type="filepath")
+    question = gr.Textbox(label="Ask a Question", placeholder="Type your question here...")
+
+    def respond(history, document, question):
+        return ChatBot(history, document, question)
+
+    question.submit(respond, [chatbot, document, question], chatbot)
 
-  # if similarity.item() > threshold:
-  #   response=Bot(Questions)
-  #   return response
-  # else:
-  #   response="The statement is not related to the text."
-  #   return response
-
-iface = gr.Interface(fn=ChatBot, inputs="text", outputs="text", title="Chatbot")
 iface.launch(debug=True)
-
-
-
-
-
-
-
-
-