Solving issue of loading transcirpt

Data/get_video_link.py

@@ -1,17 +1,28 @@
 import os
 import requests
 from dotenv import load_dotenv
-from new_video_added import get_new_video_url
+from Data.new_video_added import get_new_video_url
 from datetime import datetime
 import json
 
 load_dotenv()
 
 api_key = os.getenv('API_KEY')
+CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 BASE_URL = "https://www.googleapis.com/youtube/v3"
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 channel = "https://www.youtube.com/@hubermanlab/videos"
 new_video_added = False
-video_links_folder_name = "videolinks"
+# video_links_folder_name = os.path.join(BASE_DIR, "videolinks")
+print("THIS IS BASE DIR:", BASE_DIR)
+print("THIS is current dir:", CURRENT_DIR)
+video_links_folder_name = os.path.join(CURRENT_DIR, "videolinks")
+
+
+def ensure_directories():
+    if not os.path.exists(video_links_folder_name):
+        os.makedirs(video_links_folder_name)
+        print(f"Directory {video_links_folder_name} created")
 
 
 def get_chanel_id(chanel_name):
@@ -104,6 +115,7 @@ def load_video_links():
 
 
 def video_links_main():
+    ensure_directories()
     video_links = load_video_links()
     if video_links:
         print(f"Using {len(video_links)} saved video links")

Data/yt_transcript.py

@@ -1,5 +1,6 @@
 from youtube_transcript_api import YouTubeTranscriptApi
-from get_video_link import video_links_main
+# from get_video_link import video_links_main
+from Data.get_video_link import video_links_main
 import os
 from datetime import datetime
 

Rag/rag.py

@@ -0,0 +1,28 @@
+from langchain_google_genai import GoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain.chains import ConversationalRetrievalChain
+from langchain_community.document_loaders import TextLoader
+from langchain.memory import ConversationBufferMemory
+import google.generativeai as genai
+import os
+from typing import Dict, List
+import os
+import sys
+from Data.yt_transcript import all_video_transcript_pipeline
+import google.generativeai as genai
+
+PROJECT_ROOT = os.path.abspath(os.path.dirname(os.path.abspath(__file__)))
+sys.path.append(PROJECT_ROOT)
+print("THIS IS PROJECT ROOT")
+print(PROJECT_ROOT)
+API_KEY = os.getenv("GOOGLE_API_KEY")
+if API_KEY:
+    genai.configure(api_key=API_KEY)
+print(API_KEY)
+
+full_transcripts = all_video_transcript_pipeline()
+print("this is full transcripts of all the youtube videos")
+print(full_transcripts)
+
+# loader = TextLoader()

requirements.txt

@@ -1,2 +1,12 @@
-requests~=2.32.3
-python-dotenv~=1.0.1
+pyarrow
+pandas[performance, parquet, aws]
+pendulum
+google.generativeai
+langchain
+langchain_openai
+langchain_chroma
+langchain_community
+chromadb
+pypdf
+flask
+flask_cors