Upload 2 files

app.py

@@ -0,0 +1,157 @@
+from llama_index import Document, GPTListIndex, GPTSimpleVectorIndex
+import gradio as gr
+import openai
+import os
+from pytube import YouTube
+
+
+def download_yt_video(ytlink):
+
+    try:
+
+        yt = YouTube(ytlink)
+
+        video = yt.streams.filter(only_audio=True).first()
+
+        out_file = video.download(output_path="./")
+
+        base, ext = os.path.splitext(out_file)
+        new_file = base + '.mp3'
+
+        os.rename(out_file, new_file)
+
+        return new_file
+    except Exception as e:
+        return e
+
+
+def get_transcript(filename):
+    import requests
+    import json
+
+    headers = {
+        'accept': 'application/json',
+        'x-gladia-key': '70ad5f6e-31e6-4acf-8a15-89c166c4cc9f',
+        # requests won't add a boundary if this header is set when you pass files=
+        # 'Content-Type': 'multipart/form-data',
+    }
+
+    files = {
+        'audio': (filename, open(filename, 'rb'), 'audio/mpeg'),
+        'audio_url': (None, 'http://files.gladia.io/example/audio-transcription/split_infinity.wav'),
+        'language': (None, 'english'),
+        'language_behaviour': (None, 'manual'),
+        'output_format': (None, 'json'),
+    }
+
+    response = requests.post(
+        'https://api.gladia.io/audio/text/audio-transcription/', headers=headers, files=files)
+
+    data = json.loads(response.text)
+
+    result = ""
+    for dict_ in data['prediction']:
+        result = result + dict_['transcription'] + " "
+
+    result = ' '.join(result.strip().split())
+
+    with open(f"{filename[:-4]}.txt", "w") as f:
+        f.write(result)
+
+    return result
+
+
+def createindex(url, openaikey):
+
+    try:
+        filename = download_yt_video(url)
+
+        transcript = get_transcript(filename)
+
+        os.remove(filename)
+
+        # Store openai key in environment
+        os.environ['OPENAI_API_KEY'] = openaikey
+
+        # Create index
+        index = GPTListIndex([Document(transcript)], chunk_size_limit=2500)
+
+        index_filename = filename[:-4] + ".json"
+        index.save_to_disk(index_filename)
+
+        return "Video processed. Now you can start querying."
+    except Exception as e:
+        return e
+
+
+def videoques(query, openaikey):
+
+    # Basic Checks
+    if not query:
+        return "Please enter your query."
+
+    # Basic Checks
+    if not openaikey:
+        return "Please enter openaikey."
+
+    # Store openai key in environment
+    os.environ['OPENAI_API_KEY'] = openaikey
+
+    index_name = "index.json"
+
+    index = GPTListIndex.load_from_disk(index_name)
+
+    # Query based on index
+    response = index.query(query, mode="embedding", similarity_top_k=4)
+
+    return response
+
+
+def cleartext(query, output):
+    """
+    Function to clear text
+    """
+    return ["", ""]
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+    <h1><center><b>Portuguese VideoQues</center></h1>
+    
+    """)
+    gr.Markdown(
+        """
+    Portuguese VideoQues answers your queries on any Portuguese video.
+    
+    """)
+    with gr.Row():
+        with gr.Column():
+            url = gr.Textbox(lines=2, label="Enter Youtube Video link.")
+            openaikey = gr.Textbox(lines=2, label="Enter Your OpenAI key.")
+            submit1_button = gr.Button("Submit")
+            ans1_output = gr.Textbox(label="Status.")
+            clear1_button = gr.Button("Clear")
+        with gr.Column():
+            query = gr.Textbox(lines=2, label="Enter Your Query.")
+            submit2_button = gr.Button("Submit")
+            ans2_output = gr.Textbox(label="Answer.")
+            clear2_button = gr.Button("Clear")
+
+    # Submit button for showing YT Video thumbnail.
+    submit1_button.click(createindex, inputs=[
+                         url, openaikey], outputs=[ans1_output])
+
+    # Submit button for submitting query.
+    submit2_button.click(videoques, inputs=[
+                         query, openaikey], outputs=[ans2_output])
+
+    # Clear button for clearing query and answer.
+    clear1_button.click(cleartext, inputs=[
+                        url, ans1_output], outputs=[url, ans1_output])
+
+    # Clear button for clearing query and answer.
+    clear2_button.click(cleartext, inputs=[query, ans2_output], outputs=[
+                        query, ans2_output])
+
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+llama-index
+pytube
+pydub
+openai