Update

app.py

@@ -1,9 +1,135 @@
 import gradio as gr
+import os
+import json
 
-def greet(name):
-    return "Hello " + name + "!"
+from youtube_transcript_api import YouTubeTranscriptApi
 
-demo = gr.Interface(fn=greet, inputs="textbox", outputs="textbox")
+from openai import OpenAI
 
-if __name__ == "__main__":
-    demo.launch()
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+def gradio_video_id_to_transcript(video_id):
+
+    transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=["en"])
+    transcript_formatted = [{'start': entry['start'], 'text': entry['text']} for entry in transcript[0:10]]
+    transcript_formatted_str = json.dumps(transcript_formatted, indent=2)+'...'
+
+    return {output_transcript: transcript_formatted_str,
+            gv_transcript: transcript}
+
+def gradio_transcript_to_paragraphs(gv_transcript_value):
+
+    paragraphs, nb_input_tokens, nb_output_tokens, price = \
+        transcript_to_paragraphs(gv_transcript_value, openai_client, openai_model, chunk_size=5000)
+
+    paragraphs_formatted_str = json.dumps(paragraphs[0:4], indent=2)+'...'
+
+    return {output_paragraphs: paragraphs_formatted_str,
+            gv_paragraphs: paragraphs}
+
+def gradio_paragraphs_to_toc(gv_paragraphs_value):
+
+    paragraphs_dict = gv_paragraphs_value
+
+    json_toc, nb_input_tokens, nb_output_tokens, price = \
+      paragraphs_to_toc(paragraphs_dict, openai_client, openai_model, chunk_size=100)
+
+    json_toc_formatted_str = json.dumps(json_toc[0:4], indent=2)+'...'
+
+    return {output_toc: json_toc_formatted_str,
+            gv_toc: json_toc}
+
+
+def gradio_get_paragraphs_timestamps(gv_transcript_value, gv_paragraphs_value):
+
+    paragraphs = add_timestamps_to_paragraphs(gv_transcript_value, gv_paragraphs_value, num_words=50)
+
+    paragraphs_formatted_str = json.dumps(paragraphs[0:4], indent=2)+'...'
+
+    return {output_paragraphs_timestamps: paragraphs_formatted_str,
+            gv_paragraphs: paragraphs}
+
+
+def gradio_get_chapters(gv_paragraphs_value, gv_toc_value):
+
+    chapters = get_chapters(gv_paragraphs_value, gv_toc_value)
+
+    chapters_formatted_str = json.dumps(chapters[0:4], indent=2)+'...'
+
+    return {output_chapters: chapters_formatted_str,
+            gv_chapters: chapters}
+
+
+def gradio_get_markdown(gv_chapters_value):
+
+    markdown = chapters_to_markdown(gv_chapters_value)
+
+    return markdown
+
+with gr.Blocks() as app:
+
+    gr.Markdown("## Get transcript")
+
+    gv_transcript = gr.State()
+    video_id_input = gr.Textbox(label="Video ID", value = "ErnWZxJovaM")
+    get_transcript_button = gr.Button("Get transcript")
+    output_transcript = gr.Textbox(label = "Transcript (JSON format - start, text)")
+
+    get_transcript_button.click(gradio_video_id_to_transcript,
+                                inputs=[video_id_input],
+                                outputs=[output_transcript, gv_transcript])
+
+    gr.Markdown("## Transcript to paragraphs")
+
+    gv_paragraphs = gr.State()
+    get_paragraphs_button = gr.Button("Get paragraphs")
+    output_paragraphs = gr.Textbox(label = "Paragraphs (JSON format - paragraph_number, paragraph_text)")
+
+    get_paragraphs_button.click(gradio_transcript_to_paragraphs,
+                                inputs=[gv_transcript],
+                                outputs=[output_paragraphs, gv_paragraphs])
+
+    gr.Markdown("## Get table of content")
+
+    gv_toc = gr.State()
+    get_toc_button = gr.Button("Get table of contents")
+    output_toc = gr.Textbox(label = "Table of content (JSON format - paragraph_number, title)")
+
+    get_toc_button.click(gradio_paragraphs_to_toc,
+                         inputs=[gv_paragraphs],
+                         outputs=[output_toc, gv_toc])
+
+
+    gr.Markdown("## Infer paragraph timestamps with TF-IDF")
+
+    get_timestamps_button = gr.Button("Infer paragraph timestamps")
+    output_paragraphs_timestamps = gr.Textbox(label = "Paragraphs (JSON format - paragraph_number, paragraph_text, start)")
+
+    get_timestamps_button.click(gradio_get_paragraphs_timestamps,
+                                inputs=[gv_transcript, gv_paragraphs],
+                                outputs=[output_paragraphs_timestamps, gv_paragraphs])
+
+    gr.Markdown("## Get chapters")
+
+    gv_chapters = gr.State()
+    get_chapters_button = gr.Button("Get chapters")
+    output_chapters = gr.Textbox(label = "Chapters (JSON format)")
+
+    get_chapters_button.click(gradio_get_chapters,
+                              inputs=[gv_paragraphs, gv_toc],
+                              outputs=[output_chapters, gv_chapters])
+
+
+    gr.Markdown("## Markdown formatting")
+
+    get_markdown_button = gr.Button("Markdown formatting")
+    output_markdown = gr.Markdown(label = "Chapters (Markdown format)")
+
+    get_markdown_button.click(gradio_get_markdown,
+                              inputs=[gv_chapters],
+                              outputs=[output_markdown])
+
+
+app.launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+youtube-transcript-api
+openai
+gradio