Update app.py

app.py

@@ -1,6 +1,7 @@
 import os
 import requests
 import streamlit as st
+import PyMuPDF
 
 # Get the Hugging Face API Token from environment variables
 HF_API_TOKEN = os.getenv("HF_API_KEY")
@@ -16,6 +17,13 @@ def query_model(api_url, payload):
     response = requests.post(api_url, headers=HEADERS, json=payload)
     return response.json()
 
+def extract_pdf_text(uploaded_file):
+    pdf_text = ""
+    pdf_doc = PyMuPDF.open(uploaded_file)
+    for page_num in range(len(pdf_doc)):
+        pdf_text += pdf_doc.getPageText(page_num)
+    return pdf_text
+
 def add_message_to_conversation(user_message, bot_message, model_name):
     if "conversation" not in st.session_state:
         st.session_state.conversation = []
@@ -26,9 +34,20 @@ st.set_page_config(page_title="Gemma 27B-it Chatbot Interface", layout="wide")
 st.title("Gemma 27B-it Chatbot Interface")
 st.write("Gemma 27B-it Chatbot Interface")
 
-# Initialize session state for conversation
+# Initialize session state for conversation and uploaded file
 if "conversation" not in st.session_state:
     st.session_state.conversation = []
+if "uploaded_file" not in st.session_state:
+    st.session_state.uploaded_file = None
+
+# File uploader for PDF
+uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
+
+# Handle PDF upload and text extraction
+if uploaded_file:
+    pdf_text = extract_pdf_text(uploaded_file)
+    st.write("### PDF Text Extracted:")
+    st.write(pdf_text)
 
 # User input for question
 question = st.text_input("Question", placeholder="Enter your question here...")
@@ -40,7 +59,7 @@ if st.button("Send") and question:
             # Construct the chat history
             chat_history = " ".join([msg[1] for msg in st.session_state.conversation[-5:]]) + f"User: {question}\n"
             response = query_model(GEMMA_27B_API_URL, {"inputs": chat_history})
-            
+
             if isinstance(response, list):
                 answer = response[0].get("generated_text", "No response")
             elif isinstance(response, dict):
@@ -48,6 +67,10 @@ if st.button("Send") and question:
             else:
                 answer = "No response"
 
+            # Add PDF text to the chat history
+            if st.session_state.uploaded_file:
+                chat_history += f"Document Text: {pdf_text}\n"
+
             add_message_to_conversation(question, answer, "Gemma-2-27B-it")
     except ValueError as e:
         st.error(str(e))