Update app.py

app.py

@@ -1,13 +1,8 @@
-import os
-from huggingface_hub import Repository
-import streamlit.components.v1 as components
-from datasets import load_dataset
-import random
+import streamlit as st
+from dotenv import load_dotenv
 import pickle
-from nltk.tokenize import sent_tokenize
-import nltk
+from huggingface_hub import Repository
 from PyPDF2 import PdfReader
-import streamlit as st
 from streamlit_extras.add_vertical_space import add_vertical_space
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings.openai import OpenAIEmbeddings
@@ -15,9 +10,7 @@ from langchain.vectorstores import FAISS
 from langchain.llms import OpenAI
 from langchain.chains.question_answering import load_qa_chain
 from langchain.callbacks import get_openai_callback
-from my_component import my_component
-
-nltk.download('punkt')
+import os
 
 # Step 1: Clone the Dataset Repository
 repo = Repository(
@@ -34,39 +27,49 @@ repo.git_pull()  # Pull the latest changes (if any)
 pdf_file_path = "Private_Book/Glossar_PDF_webscraping.pdf"  # Replace with your PDF file path
 
 
+
 # Sidebar contents
 with st.sidebar:
-    st.title(':orange_book: BinDoc GmbH')
-    
-
-    api_key = os.getenv("OPENAI_API_KEY")
-    # Retrieve the API key from st.secrets
-    
-
-    if not api_key:
-        st.warning('API key is required to proceed.')
-        st.stop()  # Stop the app if the API key is not provided
+    st.title(':orange[BinDoc GmbH]')
+    st.markdown(
+        "Experience the future of document interaction with the revolutionary"
+    )
 
-    st.markdown("Experience the future of document interaction with the revolutionary")
     st.markdown("**BinDocs Chat App**.")
+
+        
     st.markdown("Harnessing the power of a Large Language Model and AI technology,")
+       
+
+
     st.markdown("this innovative platform redefines PDF engagement,")
+
     st.markdown("enabling dynamic conversations that bridge the gap between")
     st.markdown("human and machine intelligence.")
 
+    
+    
     add_vertical_space(3)  # Add more vertical space between text blocks
-    st.write('Made with ❤️ by BinDoc GmbH')
+    st.write('Made with ❤️ by Anne')
+
+    api_key = os.getenv("OPENAI_API_KEY")
+    # Retrieve the API key from st.secrets
 
 def load_pdf(file_path):
     pdf_reader = PdfReader(file_path)
-    chunks = []
+    text = ""
     for page in pdf_reader.pages:
-        text = page.extract_text()
-        if text:
-            chunks.append(text)
-    
-    store_name = os.path.basename(file_path)[:-4]
-    
+        text += page.extract_text()
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+    chunks = text_splitter.split_text(text=text)
+
+    store_name, _ = os.path.splitext(os.path.basename(file_path))
+
     if os.path.exists(f"{store_name}.pkl"):
         with open(f"{store_name}.pkl", "rb") as f:
             VectorStore = pickle.load(f)
@@ -79,86 +82,78 @@ def load_pdf(file_path):
     return VectorStore
 
 
-def load_chatbot(max_tokens=300):
-    return load_qa_chain(llm=OpenAI(temperature=0.1, max_tokens=max_tokens), chain_type="stuff") 
-    
-
-def display_chat_history(chat_history):
-    for chat in chat_history:
-        background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
-        st.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
-
-def remove_incomplete_sentences(text):
-    sentences = sent_tokenize(text)
-    complete_sentences = [sent for sent in sentences if sent.endswith(('.', '!', '?'))]
-    return ' '.join(complete_sentences)
-
-def remove_redundant_information(text):
-    sentences = sent_tokenize(text)
-    unique_sentences = list(set(sentences))
-    return ' '.join(unique_sentences)
-
-# Define a maximum token limit to avoid infinite loops
-MAX_TOKEN_LIMIT = 400
-
-import random
 
+def load_chatbot():
+    return load_qa_chain(llm=OpenAI(), chain_type="stuff")
 
 def main():
     st.title("BinDocs Chat App")
 
+
+    # Directly specifying the path to the PDF file
+    pdf_path = pdf_file_path
+    if not os.path.exists(pdf_path):
+        st.error("File not found. Please check the file path.")
+        return
+
     if "chat_history" not in st.session_state:
         st.session_state['chat_history'] = []
 
     display_chat_history(st.session_state['chat_history'])
 
+    st.write("<!-- Start Spacer -->", unsafe_allow_html=True)
+    st.write("<div style='flex: 1;'></div>", unsafe_allow_html=True)
+    st.write("<!-- End Spacer -->", unsafe_allow_html=True)
+
     new_messages_placeholder = st.empty()
 
-    query = st.text_input("Ask questions about your PDF file (in any preferred language):")
+    if pdf_path is not None:
+        query = st.text_input("Ask questions about your PDF file (in any preferred language):")
 
-    if st.button("Was genau ist ein Belegarzt?"):
-        query = "Was genau ist ein Belegarzt?"
-    if st.button("Wofür wird die Alpha-ID verwendet?"):
-        query = "Wofür wird die Alpha-ID verwendet?"
-    if st.button("Was sind die Vorteile des ambulanten operierens?"):
-        query = "Was sind die Vorteile des ambulanten operierens?"
+        if st.button("Was genau ist ein Belegarzt?"):
+            query = "Was genau ist ein Belegarzt?"
+        if st.button("Wofür wird die Alpha-ID verwendet?"):
+            query = "Wofür wird die Alpha-ID verwendet?"
+        if st.button("Was sind die Vorteile des ambulanten operierens?"):
+            query = "Was sind die Vorteile des ambulanten operierens?"
+        
+        if st.button("Ask") or (not st.session_state['chat_history'] and query) or (st.session_state['chat_history'] and query != st.session_state['chat_history'][-1][1]):
+            st.session_state['chat_history'].append(("User", query, "new"))
 
-    if query:
-        st.session_state['last_input'] = query
-        st.session_state['chat_history'].append(("User", query, "new"))
+            loading_message = st.empty()
+            loading_message.text('Bot is thinking...')
 
-        loading_message = st.empty()
-        loading_message.text('Bot is thinking...')
-        
-        VectorStore = load_pdf(pdf_file_path)
-        max_tokens = 120
-        chain = load_chatbot(max_tokens=max_tokens)
-        docs = VectorStore.similarity_search(query=query, k=2)
-        
-        with get_openai_callback() as cb:
-            response = chain.run(input_documents=docs, question=query)
+            VectorStore = load_pdf(pdf_path)
+            chain = load_chatbot()
+            docs = VectorStore.similarity_search(query=query, k=3)
+            with get_openai_callback() as cb:
+                response = chain.run(input_documents=docs, question=query)
 
-            # Post-processing to remove incomplete sentences and redundant information
-            filtered_response = remove_incomplete_sentences(response)
-            filtered_response = remove_redundant_information(filtered_response)
-            
-            st.session_state['chat_history'].append(("Bot", filtered_response, "new"))
+            st.session_state['chat_history'].append(("Bot", response, "new"))
 
+            # Display new messages at the bottom
             new_messages = st.session_state['chat_history'][-2:]
             for chat in new_messages:
                 background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
                 new_messages_placeholder.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
 
+            # Scroll to the latest response using JavaScript
             st.write("<script>document.getElementById('response').scrollIntoView();</script>", unsafe_allow_html=True)
 
             loading_message.empty()
 
+            # Clear the input field by setting the query variable to an empty string
             query = ""
-    else:
-        st.warning("Please enter a query before asking questions.")
 
-    st.session_state['chat_history'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history']]
-    
+        # Mark all messages as old after displaying
+        st.session_state['chat_history'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history']]
+
+
+
+def display_chat_history(chat_history):
+    for chat in chat_history:
+        background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
+        st.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
 
 if __name__ == "__main__":
-    main()
+    main()