Update app.py

app.py

@@ -1,54 +1,107 @@
-from gpt_index import GPTListIndex
+from llama_index import Document, GPTListIndex, GPTSimpleVectorIndex
 import gradio as gr
 import openai
 import os
+from pytube import YouTube
 
 
-def openaiapikeyvaliditycheck(openaikey):
-    """
-    Function to check validity of openai key
-    """
-    # Set the API key
-    openai.api_key = openaikey
-    # Test the API key by making a request to the OpenAI API
+def download_yt_video(ytlink):
+
     try:
-        response = openai.Model.list()
-        return "Valid OpenAI API key"
-    except openai.OpenAIError:
-        apikeylink = "https://beta.openai.com/account/api-keys"
-        return f"Incorrect OpenAI API key provided: {openaikey}. You can find your OpenAI API key here - {apikeylink}"
 
+        yt = YouTube(ytlink)
 
-def docques(index_type, query, apikey):
-    """
-    Function to create index and query
-    """
+        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'),
+        '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 = "index.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 index_type:
-        return "Please Select source type"
     if not query:
         return "Please enter your query."
-    if not apikey:
-        return "Please enter your openai apikey."
-
-    openaiapikeyvality = openaiapikeyvaliditycheck(apikey)
 
-    if openaiapikeyvality != "Valid OpenAI API key":
-        return openaiapikeyvality
+    # Basic Checks
+    if not openaikey:
+        return "Please enter openaikey."
 
     # Store openai key in environment
-    os.environ['OPENAI_API_KEY'] = apikey
+    os.environ['OPENAI_API_KEY'] = openaikey
 
-    index = ""
+    index_name = "index.json"
 
-    if index_type == "Como validar seu produto antes mesmo de criá-lo":
-        index = GPTListIndex.load_from_disk('index_audiolong.json')
-    elif index_type == "Conheça a Robotizia - Criação de conteúdos com Inteligência Artificial, uma startup da ReportFlex":
-        index = GPTListIndex.load_from_disk('index_audioshort.json')
+    index = GPTListIndex.load_from_disk(index_name)
 
     # Query based on index
-    response = index.query(query, response_mode="tree_summarize")
+    response = index.query(query, mode="embedding", similarity_top_k=4)
 
     return response
 
@@ -65,24 +118,39 @@ with gr.Blocks() as demo:
         """
     <h1><center><b>VideoQues</center></h1>
     
+    """)
+    gr.Markdown(
+        """
+    VideoQues answers your queries on any youtube video.
+    
     """)
     with gr.Row():
         with gr.Column():
-            index_type = gr.Dropdown(["Como validar seu produto antes mesmo de criá-lo",
-                                      "Conheça a Robotizia - Criação de conteúdos com Inteligência Artificial, uma startup da ReportFlex"], label="Select source type")
-            apikey = gr.Textbox(lines=2, label="Enter Your OpenAI API Key.")
-            query = gr.Textbox(lines=2, label="Enter Your Query.")
-            submit_button = gr.Button("Submit")
+            url = gr.Textbox(lines=1, label="Enter Youtube Video link.")
+            openaikey = gr.Textbox(lines=1, label="Enter Your OpenAI key.")
+            submit1_button = gr.Button("Submit")
+            ans1_output = gr.Textbox(label="Status.")
+            clear1_button = gr.Button("Clear")
         with gr.Column():
-            ans_output = gr.Textbox(label="Answer.")
-            clear_button = gr.Button("Clear")
+            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.
-    submit_button.click(
-        docques, inputs=[index_type, query, apikey], outputs=[ans_output])
+    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.
-    clear_button.click(cleartext, inputs=[
-                       query, ans_output], outputs=[query, ans_output])
+    clear2_button.click(cleartext, inputs=[query, ans2_output], outputs=[
+                        query, ans2_output])
 
-demo.launch(debug=True)
+demo.launch(debug=True)