Commented th epipeline statement

app.py

@@ -1,150 +1,150 @@
-# ########## Overview ################################################################
-#  The application is divided into three main components:
-#  Extracts metadata, transcripts, and thumbnails from YouTube videos.
-#  Summarizes the extracted transcripts using the OpenAI API.
-#  Builds a Streamlit web interface that ties everything together.
-#
-#Step 1: Extracting YouTube Data
-#	The first step involves extracting the video ID, metadata (title and channel name), 
-# 	transcript, and thumbnail image from a YouTube URL. 
-#
-#Step 2: Summarizing the Transcript
-#	With the transcript in hand, the next step is to summarize it. This is done using 
-# 	the OpenAI API in summarize_text.py. Before running this script, make sure to set 
-# 	your OpenAI API key as an environment variable:
-#
-#Step 3: Building the Web Interface
-#	Finally, the web interface is created using Streamlit. Streamlit is a Python library 
-# 	that simplifies the process of creating web applications for data science and machine 
-#   learning projects. This file combines the functionality of the other two scripts and 
-# 	provides a user-friendly interface.
-#Bringing It All Together
-#	Extract Video ID and Metadata: When a user inputs a YouTube URL, the app extracts the 
-# 	video ID and retrieves the title and channel name using extract_metadata(url).
-#	Download Thumbnail: The app downloads the video’s thumbnail and displays it using 
-# 	get_thumbnail_from_url(url).
-#	Get and Summarize Transcript: The transcript is fetched using get_transcript_from_url(url) 
-# 	and summarized using summarize_transcript(transcript, language). The summary is displayed 
-# 	in the selected language.
-#################################################################################################
-# TO RUN, execute on the terminal:
-#streamlit run C:\projects\ewp\ai-projects\ewp-sales-bots-repo\ewp-sales-bots-program\notebooks\summarize_mp4_video.py
-#
-
-import os
-import subprocess
-from moviepy.video.io.VideoFileClip import VideoFileClip
-from moviepy.audio.io.AudioFileClip import AudioFileClip
-import whisper
-from openai import OpenAI
-from fastapi import FastAPI
-from transformers import pipeline
-
-#import os
-#os.system("apt-get update && apt-get install -y ffmpeg")
-
-#result = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True)
-#print(result.stdout)
-
-#input_file = "input.mp4"
-#output_file = "output.mp3"
-#subprocess.run(["ffmpeg", "-i", input_file, output_file])
-
-## create a new FASTAPI app instance
-app=FastAPI()
-
-# Initialize the text generation pipeline
-pipe = pipeline("text2text-generation", model="google/flan-t5-small")
-
-
-@app.get("/")
-def home():
-    return {"message":"Hello World"}
-
-# Define a function to handle the GET request at `/generate`
-
-
-@app.get("/generate")
-def generate(text:str):
-    ## use the pipeline to generate text from given input text
-    output=pipe(text)
-
-    ## return the generate text in Json reposne
-    return {"output":output[0]['generated_text']}
-
-@app.get("/transcribe")
-def get_transcript_mp4(self,mp4_path):
-    #path_to_check = r"C:\Program Files\ffmpeg\bin"
-    #if path_to_check in os.environ["PATH"]:
-        #print(f"{path_to_check} is in the PATH")
-    #else:
-        #print(f"{path_to_check} is NOT in the PATH")
-        #os.environ["PATH"] += os.pathsep + path_to_check
-    ffmpeg_version = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True)
-    print(ffmpeg_version.stdout)
-    # Assuming the mp4 file has a transcript available
-    # This is a placeholder function. You would need to implement actual transcript extraction from mp4.
-    # For now, we will return a dummy transcript.
-    if os.path.exists(mp4_path):
-        print("File exists!: ", mp4_path)
-        # construct mp3 path 
-        # Replace the .mp4 extension with .mp3
-        # Get the file name without extension
-        base_name = os.path.splitext(mp4_path)[0]
-        mp3_path = f"{base_name}.mp3"  # Append .mp3 extension
-        #construct wav file path
-        wav_path = f"{base_name}.wav"  # Append .mp3 extension
-        # construct the file to store the transcript
-        transcript_path = f"{base_name}_transcript.txt"
-        video = VideoFileClip(mp4_path)
-        video.audio.write_audiofile(mp3_path)
-        print("Conversion to mp3 complete!")
-        audio = AudioFileClip(mp3_path)
-        audio.write_audiofile(wav_path)
-        print("Conversion to wav complete!")
-        # Initialize the Whisper model (small model is a good balance for speed and accuracy)
-        print("Transcribing audio...")
-        model = whisper.load_model("tiny.en")  # Options: "tiny", "base", "small", "medium", "large"
-        # Transcribe the audio
-            
-        result = model.transcribe(wav_path)
-        print("Transcription completed!")
-        meet_data=result["text"]
-        with open(transcript_path, "w") as file:
-            file.write(meet_data)
-            print("Txt written to file: ", transcript_path)
-        return meet_data
-    else:
-        print("File NOT found! Check the path for: ", mp4_path)       
-        return "Test summary"
-    
-@app.get("/summarize")
-def summarize_text(self,text, lang='en'):
-    OpenAI.api_key = os.getenv("OPENAI_API_KEY")
-    client = OpenAI(api_key=OpenAI.api_key)
-
-    prompt = f"""
-    The following text is in its original language. Provide the output in this language: {lang}. 
-    Format the output as follows:
-    
-    Summary:
-    short summary of the video
-    
-    Key Takeaways:
-    succinct bullet point list of key takeaways
-    
-    Detailed important points:
-    succinct bullet point list of feature details
-    
-    input text: {text}
-    """
-    
-    response = client.chat.completions.create(
-        messages=[{"role": "user", "content": prompt}],
-        model="gpt-4o",
-        temperature=0,
-        #model="gpt-4-turbo", # better performance, slower inference
-    )
-    
-    summary_text = response.to_dict()['choices'][0]['message']['content']
-    return summary_text
+# ########## Overview ################################################################
+#  The application is divided into three main components:
+#  Extracts metadata, transcripts, and thumbnails from YouTube videos.
+#  Summarizes the extracted transcripts using the OpenAI API.
+#  Builds a Streamlit web interface that ties everything together.
+#
+#Step 1: Extracting YouTube Data
+#	The first step involves extracting the video ID, metadata (title and channel name), 
+# 	transcript, and thumbnail image from a YouTube URL. 
+#
+#Step 2: Summarizing the Transcript
+#	With the transcript in hand, the next step is to summarize it. This is done using 
+# 	the OpenAI API in summarize_text.py. Before running this script, make sure to set 
+# 	your OpenAI API key as an environment variable:
+#
+#Step 3: Building the Web Interface
+#	Finally, the web interface is created using Streamlit. Streamlit is a Python library 
+# 	that simplifies the process of creating web applications for data science and machine 
+#   learning projects. This file combines the functionality of the other two scripts and 
+# 	provides a user-friendly interface.
+#Bringing It All Together
+#	Extract Video ID and Metadata: When a user inputs a YouTube URL, the app extracts the 
+# 	video ID and retrieves the title and channel name using extract_metadata(url).
+#	Download Thumbnail: The app downloads the video’s thumbnail and displays it using 
+# 	get_thumbnail_from_url(url).
+#	Get and Summarize Transcript: The transcript is fetched using get_transcript_from_url(url) 
+# 	and summarized using summarize_transcript(transcript, language). The summary is displayed 
+# 	in the selected language.
+#################################################################################################
+# TO RUN, execute on the terminal:
+#streamlit run C:\projects\ewp\ai-projects\ewp-sales-bots-repo\ewp-sales-bots-program\notebooks\summarize_mp4_video.py
+#
+
+import os
+import subprocess
+from moviepy.video.io.VideoFileClip import VideoFileClip
+from moviepy.audio.io.AudioFileClip import AudioFileClip
+import whisper
+from openai import OpenAI
+from fastapi import FastAPI
+from transformers import pipeline
+
+#import os
+#os.system("apt-get update && apt-get install -y ffmpeg")
+
+#result = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True)
+#print(result.stdout)
+
+#input_file = "input.mp4"
+#output_file = "output.mp3"
+#subprocess.run(["ffmpeg", "-i", input_file, output_file])
+
+## create a new FASTAPI app instance
+app=FastAPI()
+
+# Initialize the text generation pipeline
+#pipe = pipeline("text2text-generation", model="google/flan-t5-small")
+
+
+@app.get("/")
+def home():
+    return {"message":"Hello World"}
+
+# Define a function to handle the GET request at `/generate`
+
+
+@app.get("/generate")
+def generate(text:str):
+    ## use the pipeline to generate text from given input text
+    output=pipe(text)
+
+    ## return the generate text in Json reposne
+    return {"output":output[0]['generated_text']}
+
+@app.get("/transcribe")
+def get_transcript_mp4(self,mp4_path):
+    #path_to_check = r"C:\Program Files\ffmpeg\bin"
+    #if path_to_check in os.environ["PATH"]:
+        #print(f"{path_to_check} is in the PATH")
+    #else:
+        #print(f"{path_to_check} is NOT in the PATH")
+        #os.environ["PATH"] += os.pathsep + path_to_check
+    ffmpeg_version = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True)
+    print(ffmpeg_version.stdout)
+    # Assuming the mp4 file has a transcript available
+    # This is a placeholder function. You would need to implement actual transcript extraction from mp4.
+    # For now, we will return a dummy transcript.
+    if os.path.exists(mp4_path):
+        print("File exists!: ", mp4_path)
+        # construct mp3 path 
+        # Replace the .mp4 extension with .mp3
+        # Get the file name without extension
+        base_name = os.path.splitext(mp4_path)[0]
+        mp3_path = f"{base_name}.mp3"  # Append .mp3 extension
+        #construct wav file path
+        wav_path = f"{base_name}.wav"  # Append .mp3 extension
+        # construct the file to store the transcript
+        transcript_path = f"{base_name}_transcript.txt"
+        video = VideoFileClip(mp4_path)
+        video.audio.write_audiofile(mp3_path)
+        print("Conversion to mp3 complete!")
+        audio = AudioFileClip(mp3_path)
+        audio.write_audiofile(wav_path)
+        print("Conversion to wav complete!")
+        # Initialize the Whisper model (small model is a good balance for speed and accuracy)
+        print("Transcribing audio...")
+        model = whisper.load_model("tiny.en")  # Options: "tiny", "base", "small", "medium", "large"
+        # Transcribe the audio
+            
+        result = model.transcribe(wav_path)
+        print("Transcription completed!")
+        meet_data=result["text"]
+        with open(transcript_path, "w") as file:
+            file.write(meet_data)
+            print("Txt written to file: ", transcript_path)
+        return meet_data
+    else:
+        print("File NOT found! Check the path for: ", mp4_path)       
+        return "Test summary"
+    
+@app.get("/summarize")
+def summarize_text(self,text, lang='en'):
+    OpenAI.api_key = os.getenv("OPENAI_API_KEY")
+    client = OpenAI(api_key=OpenAI.api_key)
+
+    prompt = f"""
+    The following text is in its original language. Provide the output in this language: {lang}. 
+    Format the output as follows:
+    
+    Summary:
+    short summary of the video
+    
+    Key Takeaways:
+    succinct bullet point list of key takeaways
+    
+    Detailed important points:
+    succinct bullet point list of feature details
+    
+    input text: {text}
+    """
+    
+    response = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="gpt-4o",
+        temperature=0,
+        #model="gpt-4-turbo", # better performance, slower inference
+    )
+    
+    summary_text = response.to_dict()['choices'][0]['message']['content']
+    return summary_text