i forgot to stage these for the last commit rip

app/main.py

@@ -1,83 +1,63 @@
-# To parse video ids
+import os
 import re
-
+import threading
-# Youtube Transcript stuff import
+import pytz
-import youtube_transcript_api._errors
+from datetime import datetime
-from youtube_transcript_api import YouTubeTranscriptApi
+from dotenv import load_dotenv
+from youtube_transcript_api import YouTubeTranscriptApi, _errors
 from youtube_transcript_api.formatters import TextFormatter
-
+from openai import AssistantEventHandler, OpenAI
-# OpenAI API stuff import
-from openai import AssistantEventHandler
-from openai import OpenAI
-
-### For streaming
 from typing_extensions import override
 import asyncio
-awaiter = asyncio.run
-
-# The StreamOutput class to handle streaming
-class StreamOutput:
-  
-  def __init__(self):
-    self.delta: str = ""
-    self.response: str = ""
-    self.done: bool = False
-    self.buffer: list = []
-  
-  def reset(self):
-    self.delta = ""
-    self.response = ""
-    self.done = False
-    self.buffer: list = []
-    
-  async def send_delta(self, delta):
-      self.delta = delta
-      self.response += delta
-      def get_index(list):
-        if len(list) == 0:  
-          return 0
-        else:
-          return len(list)-1
-      if self.buffer != []:
-        try:
-          if self.delta != self.buffer[get_index(self.buffer)]:
-            self.buffer.append(delta)
-        except IndexError as index_error:
-          log(f"\nCaught IndexError: {str(index_error)}")
-          self.buffer.append(delta)
-      else: self.buffer.append(delta)
-
-# To get the env var
-from dotenv import load_dotenv
-import os
 
+# Load environment variables
 load_dotenv()
 
 # For logging
-import pytz
+def log(message: str):
-from datetime import datetime
+    timestamp = datetime.now(pytz.timezone('America/New_York')).strftime('%Y-%m-%d %H:%M:%S')
+    with open("logs/log.md", "a") as file:
+        file.write(f"{timestamp} - {message}\n")
 
-def log(str):
+# StreamOutput class to handle streaming
-  with open("logs/log.md", "at") as file:
+class StreamOutput:
-    file.write(str)
+    def __init__(self):
+        self.response = ""
+        self.done = False
+        self.buffer = []
+        self.lock = threading.Lock()
 
-### OpenAI Config 
+    def reset(self):
+        with self.lock:
+            self.response = ""
+            self.done = False
+            self.buffer = []
 
-# Setting up OpenAI Client with API Key
+    def add_to_buffer(self, delta: str):
+        with self.lock:
+            self.response += delta
+            self.buffer.append(delta)
+
+output_stream = StreamOutput()
+
+# OpenAI Client Configuration
 client = OpenAI(
     organization='org-7ANUFsqOVIXLLNju8Rvmxu3h',
     project="proj_NGz8Kux8CSka7DRJucAlDCz6",
     api_key=os.getenv("OPENAI_API_KEY")
 )
 
-# screw bardo assistant that is configured to make notes and 5Q&A based on any given YouTube Transcript
 asst_screw_bardo_id = "asst_JGFaX6uOIotqy5mIJnu3Yyp7"
 
-# This is copy and pasted straight up from the quickstart guide, just appending to an output buffer instead of directly printing:
+# Async helper
+def awaiter(coro):
+    asyncio.run(coro)
+
+# EventHandler for OpenAI Assistant
 class EventHandler(AssistantEventHandler):
     @override
     def on_text_created(self, text) -> None:
-    awaiter(output_stream.send_delta("Response Recieved:\n\nScrew-Bardo:\n\n"))
+        awaiter(output_stream.send_delta("Response Received:\n\nScrew-Bardo:\n\n"))
 
     @override
     def on_text_delta(self, delta, snapshot):
@@ -86,7 +66,8 @@ class EventHandler(AssistantEventHandler):
     def on_tool_call_created(self, tool_call):
         raise Exception("Assistant shouldn't be calling tools.")
 
-def create_and_stream(transcript):
+def create_and_stream(transcript: str):
+    try:
         with client.beta.threads.create_and_run_stream(
             assistant_id=asst_screw_bardo_id,
             thread={
@@ -96,33 +77,26 @@ def create_and_stream(transcript):
         ) as stream:
             stream.until_done()
             output_stream.done = True
+    except Exception as e:
+        log(f"Error in create_and_stream: {e}")
+        output_stream.done = True
 
-def get_video_id(url):
+def get_video_id(url: str) -> str:
     youtu_be = r'(?<=youtu.be/)([A-Za-z0-9_-]{11})'
     youtube_com = r'(?<=youtube\.com\/watch\?v=)([A-Za-z0-9_-]{11})'
 
-  id = re.search(youtu_be, url)
+    match = re.search(youtu_be, url) or re.search(youtube_com, url)
-  if not id:
+    if match:
-      id = re.search(youtube_com, url)
+        return match.group(1)
-  
-  if not id:
-      # Couldn't parse video ID from URL
     return None
 
-  return id.group(1)
+def get_auto_transcript(video_id: str) -> str:
-
-# Takes the transcript and formats it in basic text before writing it to auto-transcript.txt
-def get_auto_transcript(video_id):
-  trans_api_errors = youtube_transcript_api._errors
     try:
-    transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=['en'], proxies=None, cookies=None, preserve_formatting=False)
+        transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=['en'])
-  except trans_api_errors.TranscriptsDisabled as e:
+        formatter = TextFormatter()
-    log(f'\n\n# Exception while fetching transcript:\n \n{e}\n')
+        return formatter.format_transcript(transcript)
+    except _errors.TranscriptsDisabled as e:
+        log(f'Exception while fetching transcript: {e}')
+    except Exception as e:
+        log(f'Unexpected error while fetching transcript: {e}')
     return None
-    
-  formatter = TextFormatter()  # Ensure that you create an instance of TextFormatter
-
-  txt_transcript = formatter.format_transcript(transcript)
-  return txt_transcript
-
-output_stream = StreamOutput()

docker-compose.yml

@@ -1,5 +1,3 @@
-version: '3.8'
-
 services:
   app:
     build: .