Delete src

src/OCR.py

@@ -1,85 +0,0 @@
-import numpy as np
-import pandas as pd
-import easyocr
-import streamlit as st
-from PIL import Image
-import cv2
-from utils.qa import chain
-from langchain.memory import ConversationBufferWindowMemory
-from langchain_community.chat_message_histories import StreamlitChatMessageHistory
-
-def I_OCR():
-    # Function to display the OCR image with bounding boxes and text
-    def display_ocr_image(img, results):
-        img_np = np.array(img)
-        for detection in results:
-            top_left = tuple([int(val) for val in detection[0][0]])
-            bottom_right = tuple([int(val) for val in detection[0][2]])
-            text = detection[1]
-            font = cv2.FONT_HERSHEY_COMPLEX
-            cv2.rectangle(img_np, top_left, bottom_right, (0, 255, 0), 5)
-            cv2.putText(img_np, text, top_left, font, 1, (125, 29, 241), 2, cv2.LINE_AA)
-        st.image(img_np, channels="BGR", use_column_width=True)
-
-    # Function to extract text from DataFrame column
-    def extracted_text(col):
-        return " , ".join(img_df[col])
-
-    # Function to initialize session state
-    def initialize_session_state():
-        if "messages" not in st.session_state:
-            st.session_state.messages = [
-                {"role": "assistant", "content": "Hi! How may I assist you today?"}
-            ]
-
-    # Function to get answer from QA model
-    def get_answer(query):
-        response = chain.invoke(query)
-        return response["result"]
-
-    # Streamlit app
-    st.title("Question in image")
-
-    file = st.file_uploader(label= "Upload Image Here (png/jpg/jpeg) : ", type=['png', 'jpg', 'jpeg'])
-
-    if file is not None:
-        image = Image.open(file)
-        st.image(image)
-
-        reader = easyocr.Reader(['en', 'hi'], gpu=False)
-        results = reader.readtext(np.array(image))
-
-        img_df = pd.DataFrame(results, columns=['bbox', 'Predicted Text', 'Prediction Confidence'])
-
-        text_combined = extracted_text(col='Predicted Text')
-        st.write("Text Generated :- ", text_combined)
-
-        display_ocr_image(image, results)
-
-    else:
-        st.warning("!! Please Upload your image !!")
-
-    initialize_session_state()
-
-    memory_storage = StreamlitChatMessageHistory(key="chat_messages")
-    memory = ConversationBufferWindowMemory(memory_key="chat_history", human_prefix="User", chat_memory=memory_storage, k=3)
-
-    for i, msg in enumerate(memory_storage.messages):
-        name = "user" if i % 2 == 0 else "assistant"
-        st.chat_message(name).markdown(msg.content)
-
-    if user_input := st.chat_input("User Input"):
-        with st.chat_message("user"):
-            st.markdown(user_input)
-
-        with st.spinner("Generating Response..."):
-            with st.chat_message("assistant"):
-                response = get_answer(user_input)
-                answer = response
-                st.markdown(answer)
-
-    #if st.sidebar.button("Clear Chat History"):
-    #    memory_storage.clear()
-
-# Run the OCR function
-#OCR()

src/about.py

@@ -1,29 +0,0 @@
-virtual_tutor_markdown = """
-# Virtual Tutor Project
-
-Welcome to the Virtual Tutor Project! Our mission is to revolutionize education through personalized and interactive virtual tutoring experiences.
-
-## Introduction
-The Virtual Tutor Project utilizes cutting-edge technology, including Large Language Models (LLMs), to create a dynamic learning environment tailored to each student's needs.
-
-## Key Features
-- **Personalized Learning:** Our virtual tutor adapts to the individual learning pace and style of each student, providing customized learning experiences.
-- **Interactive Sessions:** Engaging lessons with interactive elements such as quizzes, games, and simulations enhance learning retention.
-- **Real-time Feedback:** Immediate feedback on assignments and assessments helps students track their progress and identify areas for improvement.
-- **24/7 Availability:** Accessible anytime, anywhere, our virtual tutor ensures learning continuity and flexibility.
-- **Comprehensive Subjects:** Covering a wide range of subjects and topics, from mathematics and science to languages and humanities, catering to diverse educational needs.
-- **OCR for Questionnaires:** Utilize Optical Character Recognition (OCR) technology to facilitate the processing of questionnaires for improved assessment and feedback.
-- **Audio-to-Audio Query Window:** Incorporate an audio-to-audio query window feature, enabling students to ask questions verbally and receive audio responses from the virtual tutor.
-
-## Benefits
-- **Enhanced Learning Outcomes:** Personalized learning experiences foster deeper understanding and improved academic performance.
-- **Convenience and Flexibility:** Students can learn at their own pace and schedule, eliminating barriers to education.
-- **Engagement and Motivation:** Interactive lessons and real-time feedback keep students engaged and motivated to learn.
-- **Accessibility:** The virtual tutor provides access to quality education to students worldwide, regardless of geographical location or socioeconomic background.
-
-## Get in Touch
-Have questions or feedback? Feel free to contact us at [virtual-tutor@vt.com](mailto:naresh.is21@bmsce.ac.in).
-
-## Join the Virtual Tutor Revolution!
-Experience the future of education with our Virtual Tutor Project. Start your journey to academic success today!
-"""

src/audio.py

@@ -1,72 +0,0 @@
-import streamlit as st
-import base64
-from audio_recorder_streamlit import audio_recorder
-from streamlit_float import *
-from utils.stt import speech_to_text
-from utils.tts import text_to_speech
-from utils.qa import chain
-
-recorded_audio = r"C:\Users\Naresh Kumar Lahajal\Desktop\FINAL\media\recorded.mp3"
-output_audio = r"C:\Users\Naresh Kumar Lahajal\Desktop\FINAL\media\ouput_file.mp3"
-
-def autoplay_audio(file_path: str):
-    with open(file_path, "rb") as f:
-        data = f.read()
-    b64 = base64.b64encode(data).decode("utf-8")
-    md = f"""
-    <audio autoplay>
-    <source src="data:audio/mp3;base64,{b64}" type="audio/mp3">
-    </audio>
-    """
-    st.markdown(md, unsafe_allow_html=True)
-
-def get_answer(query):
-    response = chain.invoke(query)
-    return response['result']
-
-def audio_d():
-    float_init()
-
-    st.title("Ai Doubt resolver")
-
-    # Initialize session state
-    if "messages" not in st.session_state:
-        st.session_state.messages = [
-            {"role": "assistant", "content": "Hi! How may I assist you today?"}
-        ]
-
-    footer_container = st.container()
-
-    with footer_container:
-        audio_bytes = audio_recorder()
-
-    for message in st.session_state.messages:
-        with st.chat_message(message["role"]):
-            st.write(message["content"])
-
-    if audio_bytes:
-        with st.spinner("Transcribing..."):
-            webm_file_path = recorded_audio
-            with open(webm_file_path, "wb") as f:
-                f.write(audio_bytes)
-
-            transcript = speech_to_text()
-            if transcript:
-                st.session_state.messages.append({"role": "user", "content": transcript})
-                with st.chat_message("user"):
-                    st.write(transcript)
-
-    if st.session_state.messages[-1]["role"] != "assistant":
-        with st.chat_message("assistant"):
-            with st.spinner("Thinking🤔..."):
-                final_response = get_answer(str(st.session_state.messages))
-            with st.spinner("Generating audio response..."):    
-                text_to_speech(final_response)
-                audio_file = output_audio
-                autoplay_audio(audio_file)
-            st.write(final_response)
-            st.session_state.messages.append({"role": "assistant", "content": final_response})
-            #os.remove(audio_file)
-
-    # Float the footer container and provide CSS to target it with
-    footer_container.float("bottom: 0rem;")

src/chainlit.md

@@ -1,27 +0,0 @@
-# Virtual Tutor Project
-
-Welcome to the Virtual Tutor Project! Our mission is to revolutionize education through personalized and interactive virtual tutoring experiences.
-
-## Introduction
-The Virtual Tutor Project utilizes cutting-edge technology, including Large Language Models (LLMs), to create a dynamic learning environment tailored to each student's needs.
-
-## Key Features
-- **Personalized Learning:** Our virtual tutor adapts to the individual learning pace and style of each student, providing customized learning experiences.
-- **Interactive Sessions:** Engaging lessons with interactive elements such as quizzes, games, and simulations enhance learning retention.
-- **Real-time Feedback:** Immediate feedback on assignments and assessments helps students track their progress and identify areas for improvement.
-- **24/7 Availability:** Accessible anytime, anywhere, our virtual tutor ensures learning continuity and flexibility.
-- **Comprehensive Subjects:** Covering a wide range of subjects and topics, from mathematics and science to languages and humanities, catering to diverse educational needs.
-- **OCR for Questionnaires:** Utilize Optical Character Recognition (OCR) technology to facilitate the processing of questionnaires for improved assessment and feedback.
-- **Audio-to-Audio Query Window:** Incorporate an audio-to-audio query window feature, enabling students to ask questions verbally and receive audio responses from the virtual tutor.
-
-## Benefits
-- **Enhanced Learning Outcomes:** Personalized learning experiences foster deeper understanding and improved academic performance.
-- **Convenience and Flexibility:** Students can learn at their own pace and schedule, eliminating barriers to education.
-- **Engagement and Motivation:** Interactive lessons and real-time feedback keep students engaged and motivated to learn.
-- **Accessibility:** The virtual tutor provides access to quality education to students worldwide, regardless of geographical location or socioeconomic background.
-
-## Get in Touch
-Have questions or feedback? Feel free to contact us at [naresh.is21@bmsce.ac.in](mailto:naresh.is21@bmsce.ac.in).
-
-## Join the Virtual Tutor Revolution!
-Experience the future of education with our Virtual Tutor Project. Start your journey to academic success today!

src/chat.py

@@ -1,76 +0,0 @@
-import streamlit as st
-import base64
-from utils.qa import chain
-from langchain.memory import ConversationBufferWindowMemory
-from langchain_community.chat_message_histories import StreamlitChatMessageHistory
-
-def virtual_tutor():
-    #st.set_page_config(layout='wide')
-    #st.set_page_config(page_title="Virtual Tutor")
-
-    st.markdown("""
-        <svg width="600" height="100">
-            <text x="50%" y="50%" font-family="San serif" font-size="42px" fill="Black" text-anchor="middle" stroke="white"
-             stroke-width="0.3" stroke-linejoin="round">Virtual Tutor - CHAT
-            </text>
-        </svg>
-    """, unsafe_allow_html=True)
-
-    def add_bg_from_local(image_file):
-        with open(image_file, "rb") as image_file:
-            encoded_string = base64.b64encode(image_file.read())
-        st.markdown(
-            f"""<style>.stApp {{background-image: url(data:image/{"png"};base64,{encoded_string.decode()});
-            background-size: cover}}</style>""",
-            unsafe_allow_html=True)
-
-    #add_bg_from_local(r'C:\Users\Naresh Kumar Lahajal\Desktop\Capstone-streamlit\STREAMCHAT\freepik-export-20240425023906eVmL.jpeg')
-
-    def initialize_session_state():
-        if "messages" not in st.session_state:
-            st.session_state.messages = [
-                {"role": "assistant", "content": "Hi! How may I assist you today?"}
-            ]
-
-    initialize_session_state()
-
-    m = st.markdown("""
-        <style> 
-        .stChatInputContainer > div {
-        background-color: #000000;
-        }
-        </style>
-        """, unsafe_allow_html=True)
-
-    def get_answer(query):
-        response = chain.invoke(query)
-        return response
-
-    memory_storage = StreamlitChatMessageHistory(key="chat_messages")
-    memory = ConversationBufferWindowMemory(memory_key="chat_history", human_prefix="User", chat_memory=memory_storage, k=3)
-
-    for message in st.session_state.messages:  # Display the prior chat messages
-        with st.chat_message(message["role"]):
-            st.write(message["content"])
-
-    for i, msg in enumerate(memory_storage.messages):
-        name = "user" if i % 2 == 0 else "assistant"
-        st.chat_message(name).markdown(msg.content)
-
-    if user_input := st.chat_input("User Input"):
-        with st.chat_message("user"):
-            st.markdown(user_input)
-
-        with st.spinner("Generating Response..."):
-
-            with st.chat_message("assistant"):
-                response = get_answer(user_input)
-                answer = response['result']
-                st.markdown(answer)
-                message = {"role": "assistant", "content": answer}
-                message_u = {"role": "user", "content": user_input}
-                st.session_state.messages.append(message_u)
-                st.session_state.messages.append(message)
-
-
-#virtual_tutor()

src/pdf.py

@@ -1,43 +0,0 @@
-import streamlit as st
-from streamlit import session_state as ss
-from langchain.memory import ConversationBufferWindowMemory, StreamlitChatMessageHistory
-from streamlit_pdf_viewer import pdf_viewer
-from utils.qa import chain
-
-def get_answer(query):
-    response = chain.invoke(query)
-    return response['result']
-
-def pdf_v():
-    # Declare variable.
-    if 'pdf_ref' not in ss:
-        ss.pdf_ref = None
-
-    # Access the uploaded ref via a key.
-    st.file_uploader("Upload PDF file", type=('pdf'), key='pdf')
-
-    if ss.pdf:
-        ss.pdf_ref = ss.pdf  # backup
-
-    # Now you can access "pdf_ref" anywhere in your app.
-    if ss.pdf_ref:
-        binary_data = ss.pdf_ref.getvalue()
-        pdf_viewer(input=binary_data, width=700)
-
-    memory_storage = StreamlitChatMessageHistory(key="chat_messages")
-    memory = ConversationBufferWindowMemory(memory_key="chat_history", human_prefix="User", chat_memory=memory_storage, k=3)
-
-    for i, msg in enumerate(memory_storage.messages):
-        name = "user" if i % 2 == 0 else "assistant"
-        st.chat_message(name).markdown(msg.content)
-
-    if user_input := st.chat_input("User Input"):
-        with st.chat_message("user"):
-            st.markdown(user_input)
-
-        with st.spinner("Generating Response..."):
-            with st.chat_message("assistant"):
-                response = get_answer(user_input)
-                answer = response
-                st.markdown(answer)
-

src/pdf_up.py

@@ -1,41 +0,0 @@
-import tempfile
-import streamlit as st
-from PIL import Image
-import os
-from utils.ingest1 import create_vector_database
-
-def process_uploaded_file():
-    st.title("Upload File to Chat")
-    uploaded_file = st.file_uploader("File upload", type="pdf")
-    if uploaded_file:
-        temp_dir = tempfile.mkdtemp()
-        path = os.path.join(temp_dir, uploaded_file.name)
-    #with open(path, "wb") as f:
-    #    f.write(uploaded_file.getvalue())
-        print(path)    
-        st.write("Document uploaded successfully!")
-        # Display the uploaded document
-        st.write("Preview of the document:")
-        st.write(uploaded_file)
-
-        # Button to start parsing and vector database creation
-        if st.button("Start Processing"):
-            # Placeholder for processing logic
-            st.write("Processing...")
-
-            # Placeholder for progress bar
-            with st.spinner('Processing...'):
-                # Call your function to parse data and create vector database
-                create_vector_database(path)
-
-            st.success("Processing completed!")
-
-            # Display success message
-            st.write("Vector database created successfully!")
-
-            # Show success image
-            success_image = Image.open("success_image.jpg")
-            st.image(success_image, caption="Success!", use_column_width=True)
-
-    # Add a footer
-    #st.text("Built with Streamlit")