Upload 5 files

app.py

@@ -0,0 +1,17 @@
+from typing import Union
+from fastapi import FastAPI
+from src.utils_youtube import get_youtube_transcript
+
+## create a new FASTAPI app instance
+app=FastAPI()
+
+
+@app.get("/")
+def home():
+    return {"message":"Hello World"}
+
+# Define a function to handle the GET request at `/generate`
+@app.get("/generate/")
+def generate(youtubeurl,src_lang,target_lang):
+    transript=get_youtube_transcript(youtubeurl,src_lang,target_lang)
+    return {"output":f"{transript}"}

dockerfile

@@ -0,0 +1,30 @@
+## Use the official Python 3.9 image
+FROM python:3.9
+
+## set the working directory to /code
+WORKDIR /code
+
+## Copy the current directory contents in the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+## Install the requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Set up a new user named "user" 
+RUN useradd user
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+## Start the FASTAPI App on port 7860
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.74.*
+requests==2.27.*
+uvicorn[standard]==0.17.*
+langchain-community
+typer
+youtube_transcript_api
+pytube

src/utils_youtube.py

@@ -0,0 +1,32 @@
+from langchain_community.document_loaders import YoutubeLoader
+from langchain_community.document_loaders.youtube import TranscriptFormat
+import os
+import json
+
+
+def get_youtube_transcript(video_url,src_language, target_language) -> None:
+    """get youtube transcript"""
+    try:
+
+        loader = YoutubeLoader.from_youtube_url(video_url,add_video_info=True,language=[src_language, "id"],translation=target_language, transcript_format=TranscriptFormat.TEXT)
+             
+        #docs = loader.load_and_split(text_splitter)
+        transcript = loader.load()
+        
+        #no transcript is found
+        if len(transcript) == 0:
+           return 'No transcript found', None, None
+        
+        #metadata = transcript[0].metadata
+        
+        #title = metadata.get('title')
+        #metadata['transcript'] = transcript[0].page_content
+        #metadata['youtubelink']=video_url
+        if not transcript:
+            raise ValueError(f"{src_language} transcript not available for this video.")
+        else:
+            return transcript[0].page_content
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return None
+