initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+src/full_screenshot.png filter=lfs diff=lfs merge=lfs -text

src/Home.py

@@ -0,0 +1,112 @@
+import streamlit as st
+from pathlib import Path
+import json
+import urllib.parse as ul
+
+st.set_page_config(page_title="AutoTA | Pause. Ask. Progress.",
+                   page_icon="🎓",
+                   layout="centered",
+                   initial_sidebar_state="collapsed",
+                   )
+
+# --------------  Dummy catalogue  --------------
+# Replace with your DB / API
+videos = [
+    {
+        "id": "intro_algo",
+        "title": "Introduction to Algorithms and Analysis – Lec 1: Insertion Sort",
+        "summary": "An introduction to the Insertion Sort algorithm and its complexity.",
+        "url": "https://www.youtube.com/watch?v=oZgbwa8lvDE", # Corrected YouTube URL
+        "thumbnail": "https://i.ytimg.com/vi/oZgbwa8lvDE/hqdefault.jpg",
+        "video_file": "videos/oZgbwa8lvDE.mp4",
+        "transcript_file": "transcripts/oZgbwa8lvDE.csv"
+    },
+    {
+        "id": "dl_basics",
+        "title": "Deep Learning(CS7015): Lec 2.5 Perceptron Learning Algorithm",
+        "summary": "An introduction to the perceptron learning algorithm with an example.",
+        "url": "https://www.youtube.com/watch?v=VRcixOuG-TU", # Corrected YouTube URL
+        "thumbnail": "https://i.ytimg.com/vi/VRcixOuG-TU/hqdefault.jpg",
+        "video_file": "videos/VRcixOuG-TU.mp4",
+        "transcript_file": "transcripts/VRcixOuG-TU.csv"
+    },
+    {
+        "id": "python_intro",
+        "title": "Unit testing | Intro to CS - Python | Khan Academy",
+        "summary": "How do teams of programmers continuously write and revise code without breaking things? Unit tests define a function's expected behavior and then enforce that those requirements are met.",
+        "url": "https://www.youtube.com/watch?v=3OmfTIf-SOU", # Corrected YouTube URL
+        "thumbnail": "https://i.ytimg.com/vi/3OmfTIf-SOU/hqdefault.jpg",
+        "video_file": "videos/3OmfTIf-SOU.mp4",
+        "transcript_file": "transcripts/3OmfTIf-SOU.csv"
+    },
+]
+# Persists last timestamp per-user per-video
+progress_store = Path(".progress.json")
+if progress_store.exists():
+    last_pos = json.loads(progress_store.read_text())
+else:
+    last_pos = {}
+
+st.markdown(
+    """
+    <style>
+    .autota-style {
+        font-family: 'Montserrat', sans-serif; /* Define Montserrat */
+        text-align: center; /* Centers the text horizontally */
+        font-size: 100px;    /* Adjust the font size as desired */
+        font-weight: bold;  /* Optional: make it bold */
+        color: white;        /* Optional: change text color */
+        padding: 10px;      /* Optional: Add some padding around the text */
+    }
+    </style>
+    <div class="autota-style">AutoTA</div>
+    """,
+    unsafe_allow_html=True
+)
+st.markdown(
+    """
+    <style>
+    .center-desc {
+        font-family: 'Montserrat', sans-serif; /* Define Montserrat */
+        text-align: center; /* Centers the text horizontally */
+        font-size: 30px;    /* Adjust the font size as desired */
+        font-weight: bold;  /* Optional: make it bold */
+        color: #555;        /* Optional: change text color */
+        padding: 10px;      /* Optional: Add some padding around the text */
+    }
+    </style>
+    <div class="center-desc">A Virtual TA to interact with lecture videos</div>
+    """,
+    unsafe_allow_html=True
+)
+st.divider()
+
+st.title("Video Gallery")
+
+st.markdown("---") # Separator
+
+for video in videos:
+    with st.container(border=True):
+        col1, col2 = st.columns([1, 3]) # Column for thumbnail, column for text
+
+        with col1:
+            # Use Streamlit's markdown to embed HTML for a clickable image link.
+            # The 'href' should point to the page name (from the 'pages' folder, without '.py').
+            # Query parameters are used to pass data (like video_id).
+            st.markdown(
+                f"""
+                <a href="/VideoViewer?video_id={video['id']}" target="_self">
+                    <img src="{video['thumbnail']}" width="160" style="border-radius: 8px; box-shadow: 0 4px 8px rgba(0,0,0,0.1); display: block; margin: auto;">
+                </a>
+                """,
+                unsafe_allow_html=True
+            )
+
+        with col2:
+            st.subheader(video['title'])
+            st.write(video['summary'])
+            # You can also add a direct Streamlit link button for clarity
+            # This is an alternative or supplementary way to navigate
+
+    st.markdown("---") # Separator between video entries
+            

src/README.md

@@ -0,0 +1,20 @@
+# AutoTA
+
+AutoTA is an interface for interacting with educational lecture videos.
+
+## Installation
+
+Install the required dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+## To run locally
+
+To run the demo locally:
+```bash
+streamlit run Home.py
+```
+## Some Additional Information
+
+Please add your own API key to chatbot/llm_answer.py.

src/get_transcripts.py

@@ -0,0 +1,25 @@
+import pandas as pd 
+from youtube_transcript_api import YouTubeTranscriptApi
+from pytube import extract
+
+ids = ['oZgbwa8lvDE', 'VRcixOuG-TU']  # Example video IDs
+count = 0
+for i in range(len(ids)):
+    #url = df['video_url'][0]
+    try:
+        id = ids[i]
+
+        transcript = YouTubeTranscriptApi.get_transcript(id)
+        #print(transcript[0])
+        file_df = pd.DataFrame()
+        for j in range(len(transcript)):
+            file_df = file_df._append([dict(transcript[j])])
+        file_df.reset_index()
+        transcript_filename = str(id)+".csv"
+        file_path = "/Users/sourjyadip/Desktop/autota/transcripts/" + transcript_filename
+        file_df.to_csv(file_path)
+        print(i, " done")
+    except:
+        count += 1
+
+print("number of skipped videos: ", count)

src/requirements.txt

@@ -0,0 +1,49 @@
+altair==5.5.0
+attrs==25.3.0
+blinker==1.9.0
+cachetools==6.1.0
+certifi==2025.7.9
+charset-normalizer==3.4.2
+click==8.2.1
+gitdb==4.0.12
+GitPython==3.1.44
+idna==3.10
+Jinja2==3.1.6
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+MarkupSafe==3.0.2
+MouseInfo==0.1.3
+narwhals==1.46.0
+numpy==2.2.6
+opencv-python==4.12.0.88
+packaging==25.0
+pandas==2.3.1
+pillow==11.3.0
+protobuf==6.31.1
+pyarrow==20.0.0
+PyAutoGUI==0.9.54
+pydeck==0.9.1
+PyGetWindow==0.0.9
+PyMsgBox==1.0.9
+pyobjc-core==11.1
+pyobjc-framework-Cocoa==11.1
+pyobjc-framework-Quartz==11.1
+pyperclip==1.9.0
+PyRect==0.2.0
+PyScreeze==1.0.1
+python-dateutil==2.9.0.post0
+pytweening==1.2.0
+pytz==2025.2
+referencing==0.36.2
+requests==2.32.4
+rpds-py==0.26.0
+rubicon-objc==0.5.1
+six==1.17.0
+smmap==5.0.2
+streamlit==1.46.1
+tenacity==9.1.2
+toml==0.10.2
+tornado==6.5.1
+typing_extensions==4.14.1
+tzdata==2025.2
+urllib3==2.5.0