adding project files

.env

@@ -0,0 +1,4 @@
+ASSEMBLYAI_API_KEY= #get yours from https://www.assemblyai.com/
+HF_API_TOKEN= #get yours from https://huggingface.co/settings/tokens
+NVIDIA_API_KEY= #get yours from https://build.nvidia.com/explore/discover#llama3-70b
+api_key = #get yours from https://openai.com/

.gitignore

@@ -0,0 +1,5 @@
+.venv/
+__pycache__/
+.DS_Store
+#secrets.toml
+venv

.streamlit/secrets.toml

@@ -0,0 +1 @@
+api_key = 'add your api_key'

Chatbuddy.py

@@ -0,0 +1,135 @@
+from openai import OpenAI
+import streamlit as st
+import json
+from datetime import datetime
+import base64
+from fpdf import FPDF
+
+# Sidebar configuration
+with st.sidebar:
+    st.title(":orange[Welcome to ChatBuddy!]")
+    openai_api_key = st.text_input("OpenAI API Key", key="chatbot_api_key", type="password")
+    st.markdown("[Get an OpenAI API key](https://platform.openai.com/account/api-keys)")
+
+st.sidebar.caption("""
+### Get Started
+1. **Enter your OpenAI API Key**: To start chatting with ChatBuddy, you'll need to enter your OpenAI API key.
+2. **Chat with ChatBuddy**: Once you've entered your API key, you can start a conversation with ChatBuddy. Ask questions, seek advice, or just chat!
+3. **Download Your Conversation**: After your chat session, you have the option to download the entire conversation in PDF format.
+
+### How to Enter Your API Key
+- Paste your OpenAI API key in the input box below.
+- Click on "Submit chat query" to validate and start your session.
+
+### Privacy Notice
+- Your API key is stored securely during your session and is not shared with anyone.
+- Conversations are stored temporarily and can be downloaded in PDF format for your records.
+
+### Tips
+- Make sure your API key is active and has sufficient quota.
+- For best results, be clear and concise with your questions.
+
+:rainbow[Enjoy your conversation with ChatBuddy!]
+""")
+
+
+
+# Main chat interface
+st.markdown(
+    """
+    <style>
+        .chat-header {
+            font-size: 2em;
+            font-weight: bold;
+            color: #333;
+            animation: fadeIn 2s;
+        }
+        @keyframes fadeIn {
+            0% { opacity: 0; }
+            100% { opacity: 1; }
+        }
+        .chat-input {
+            margin-top: 20px;
+        }
+        .download-button {
+            background-color: #1D1D1D;
+            color: white;
+            padding: 10px 20px;
+            text-align: center;
+            text-decoration: none;
+            display: inline-block;
+            font-size: 16px;
+            margin: 4px 2px;
+            border-radius: 8px;
+            cursor: pointer;
+        }
+        .download-button:hover {
+            background-color: #000000;
+        }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+st.title("Your ChatBuddy🙋🏻💭")
+st.caption("####  :rainbow[**ChatBuddy powered by Streamlit x OpenAI**]")
+
+# Initialize session state if not already present
+if "messages" not in st.session_state:
+    st.session_state["messages"] = [{"role": "assistant", "content": "Hey Buddy! How can I help you today?"}]
+
+# Display messages in chat container
+st.markdown('<div class="chat-container">', unsafe_allow_html=True)
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+st.markdown('</div>', unsafe_allow_html=True)
+
+# Handle user input
+if prompt := st.chat_input(placeholder="Type your message..."):
+    if not openai_api_key:
+        st.info("Please add your OpenAI API key to continue.")
+        st.stop()
+
+    client = OpenAI(api_key=openai_api_key)
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    st.chat_message("user").write(prompt)
+
+    # Simulate loading state
+    with st.spinner('Generating response...'):
+        response = client.chat.completions.create(model="gpt-3.5-turbo", messages=st.session_state.messages)
+        msg = response.choices[0].message.content
+        st.session_state.messages.append({"role": "assistant", "content": msg})
+        st.chat_message("assistant").write(msg)
+
+# Function to download chat history as PDF
+def download_chat_history_pdf():
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", size=12)
+
+    for msg in st.session_state.messages:
+        if msg["role"] == "user":
+            pdf.set_text_color(0, 0, 255)  # Blue for user messages
+            pdf.multi_cell(0, 10, f'User: {msg["content"]}')
+        else:
+            pdf.set_text_color(255, 0, 0)  # Red for assistant messages
+            pdf.multi_cell(0, 10, f'Assistant: {msg["content"]}')
+
+    pdf_output = f"chat_history/chat_history_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
+    pdf.output(pdf_output)
+
+    with open(pdf_output, "rb") as f:
+        b64 = base64.b64encode(f.read()).decode()
+
+    href = f'<a href="data:application/octet-stream;base64,{b64}" download="{pdf_output}">Download PDF</a>'
+    return href
+
+# Download button
+st.markdown('<div class="chat-input">', unsafe_allow_html=True)
+st.markdown(f'<button class="download-button">{download_chat_history_pdf()}</button>', unsafe_allow_html=True)
+st.markdown('</div>', unsafe_allow_html=True)
+
+# Clear chat button
+if st.button('Clear Chat'):
+    st.session_state["messages"] = [{"role": "assistant", "content": ""}]
+    st.experimental_rerun()

DocAI_history/readme.txt

@@ -0,0 +1 @@
+This folder contains conversations from the DocAI Q&A RAG application in PDF format.

chat_history/readme.txt

@@ -0,0 +1 @@
+This folder contains the chat history from the ChatBuddy conversations.

htmltemplates.py

@@ -0,0 +1,35 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; 
+    border-radius: 0.5rem; 
+    margin-bottom: 1rem; 
+    display: flex;
+}
+.chat-message.user {
+    background-color: #2b313e;
+}
+.chat-message.bot {
+    background-color: #475063;
+}
+.chat-message .message {
+    width: 100%; /* Changed to 100% to fill the space previously occupied by the avatar */
+    padding: 0 1.5rem;
+    color: #fff;
+}
+</style>
+'''
+
+bot_template = '''
+<!-- Bot Template -->
+<div class="chat-message bot">
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<!-- User Template -->
+<div class="chat-message user">
+    <div class="message">{{MSG}}</div>
+</div>
+'''

pages/1_RAG_DocAI_Q&A.py

@@ -0,0 +1,201 @@
+import streamlit as st
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings, ChatNVIDIA
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from reportlab.lib.pagesizes import letter
+from reportlab.lib import colors
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+from reportlab.lib.styles import getSampleStyleSheet
+import base64
+import tempfile
+import os
+from htmltemplates import *
+from datetime import datetime
+
+
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vectorstore(text_chunks):
+    embeddings = NVIDIAEmbeddings()
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+def get_conversation_chain(vectorstore):
+    llm = ChatNVIDIA(model="meta/llama3-70b-instruct")
+    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory
+    )
+    return conversation_chain
+
+def save_chat_session(chat_history):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".txt") as temp_file:
+        for message in chat_history:
+            temp_file.write(message.content.encode("utf-8") + b"\n")
+        return temp_file.name
+
+def handle_userinput(user_question):
+    response = st.session_state.conversation({'question': user_question})
+    st.session_state.chat_history = response['chat_history']
+
+    for i, message in enumerate(st.session_state.chat_history):
+        if i % 2 == 0:
+            st.markdown(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
+        else:
+            st.markdown(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
+
+def download_pdf(chat_history):
+    pdf_filename = "chat_session.pdf"
+    doc = SimpleDocTemplate(pdf_filename, pagesize=letter)
+    styles = getSampleStyleSheet()
+    story = []
+
+    is_user_message = True
+    for message in chat_history:
+        if is_user_message:
+            paragraph = Paragraph(message.content, styles["Normal"])
+        else:
+            paragraph = Paragraph(message.content, styles["Normal"])
+            paragraph.textColor = colors.blue
+        story.append(paragraph)
+        story.append(Spacer(1, 12))
+        is_user_message = not is_user_message
+
+    doc.build(story)
+    with open(pdf_filename, "rb") as pdf_file:
+        pdf_contents = pdf_file.read()
+    return pdf_contents
+
+##---------------------------------------------------------------------------
+## V1 without using the file rename format.
+
+# def main():
+#     load_dotenv()
+#     st.set_page_config(page_title="Your Personalized Document Chatbot", page_icon=":books:")
+
+#     if "conversation" not in st.session_state:
+#         st.session_state.conversation = None
+#     if "chat_history" not in st.session_state:
+#         st.session_state.chat_history = None
+
+#     st.header("Your Personalized Document Chatbot :books:")
+#     st.markdown(css, unsafe_allow_html=True)  # Applying custom CSS
+
+#     user_question = st.text_input("Ask a question about your documents:")
+#     if user_question:
+#         handle_userinput(user_question)
+
+#     with st.sidebar:
+#         st.subheader("Your documents")
+#         pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
+#         if st.button("Process"):
+#             with st.spinner("Processing"):
+#                 raw_text = get_pdf_text(pdf_docs)
+#                 text_chunks = get_text_chunks(raw_text)
+#                 vectorstore = get_vectorstore(text_chunks)
+#                 st.session_state.conversation = get_conversation_chain(vectorstore)
+#                 st.success("Vector Store DB Is Ready")
+
+#     if st.session_state.chat_history is not None:
+#         pdf_contents = download_pdf(st.session_state.chat_history)
+#         st.download_button(
+#             "Download above Conversation",
+#             pdf_contents,
+#             "chat_session.pdf",
+#             "application/pdf",
+#             key="download"
+#         )
+
+
+##---------------------------------------------------------------------------
+
+def generate_file_name():
+    now = datetime.now()
+    return now.strftime("chat_session_%Y%m%d_%H%M%S.pdf")
+
+def save_pdf_to_folder(pdf_content, folder_path):
+    if not os.path.exists(folder_path):
+        os.makedirs(folder_path)
+    file_name = generate_file_name()
+    file_path = os.path.join(folder_path, file_name)
+    with open(file_path, "wb") as f:
+        f.write(pdf_content)
+    return file_path
+
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Your Personalized Document Chatbot", page_icon=":books:")
+
+    if "conversation" not in st.session_state:
+        st.session_state.conversation = None
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = None
+
+    st.header("Your Personalized Document Chatbot :books:")
+    st.caption("**Harness the power of Retrieval-Augmented Generation to answer questions from your documents with AI precision and efficiency.**")
+    st.markdown(css, unsafe_allow_html=True)  # Applying custom CSS
+
+    user_question = st.text_input("Ask a question about your documents:")
+    if user_question:
+        handle_userinput(user_question)
+
+    with st.sidebar:
+        st.sidebar.caption(""" ### :orange[Welcome to DocAI Q&A!] """)
+        st.sidebar.caption("""Harness the power of Retrieval-Augmented Generation to answer questions from your documents with AI precision and efficiency.""")
+        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                vectorstore = get_vectorstore(text_chunks)
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+                st.success("Vector Store DB Is Ready")
+
+
+
+    st.sidebar.caption("""
+    ### How to Use
+    1. **Upload Your Documents**: Easily upload your documents to the app.
+    2. **Ask Questions**: Query the content of your documents using natural language.
+    3. **Get Accurate Answers**: Receive precise and relevant answers generated by AI.
+    4. **Download Conversations**: Save your query and answer sessions by downloading them in PDF format.
+
+    :rainbow[Enjoy a seamless and intelligent way to interact with your documents!]
+    """)
+
+
+    if st.session_state.chat_history is not None:
+        pdf_contents = download_pdf(st.session_state.chat_history)
+        save_folder = os.path.join(os.getcwd(), "DocAI_history")
+        saved_file_path = save_pdf_to_folder(pdf_contents, save_folder)
+
+        st.download_button(
+            "Download above Conversation",
+            pdf_contents,
+            saved_file_path,
+            "application/pdf",
+            key="download"
+        )
+if __name__ == '__main__':
+    main()