Clean up trunk check recommendation

ai_ta_backend/beam/ingest.py

@@ -22,7 +22,7 @@
 import pytesseract
 import sentry_sdk
 import supabase
-from beam import App, QueueDepthAutoscaler, RequestLatencyAutoscaler, Runtime
+from beam import App, QueueDepthAutoscaler, Runtime  # RequestLatencyAutoscaler,
 from bs4 import BeautifulSoup
 from git.repo import Repo
 from langchain.document_loaders import (

ai_ta_backend/executors/process_pool_executor.py

@@ -1,7 +1,5 @@
 from concurrent.futures import ProcessPoolExecutor
 
-from injector import inject
-
 
 class ProcessPoolExecutorInterface:
 

ai_ta_backend/executors/thread_pool_executor.py

@@ -1,7 +1,5 @@
 from concurrent.futures import ThreadPoolExecutor
 
-from injector import inject
-
 
 class ThreadPoolExecutorInterface:
 

ai_ta_backend/public_api/uiuc_chat_api.py

@@ -1,5 +1,6 @@
-import requests
 import json
+
+import requests
 """
 # Example usage
 

ai_ta_backend/service/export_service.py

@@ -1,4 +1,3 @@
-import io
 import json
 import os
 import uuid
@@ -40,7 +39,7 @@ def export_documents_json(self, course_name: str, from_date='', to_date=''):
       # call background task to upload to s3
 
       filename = course_name + '_' + str(uuid.uuid4()) + '_documents.zip'
-      s3_filepath = s3_file = f"courses/{course_name}/{filename}"
+      s3_filepath = f"courses/{course_name}/{filename}"
       # background task of downloading data - map it with above ID
       executor = ProcessPoolExecutor()
       executor.submit(self.export_data_in_bg, response, "documents", course_name, s3_filepath)
@@ -214,7 +213,7 @@ def export_convo_history_json(self, course_name: str, from_date='', to_date=''):
     if response.count > 1000:
       # call background task to upload to s3
       filename = course_name + '_' + str(uuid.uuid4()) + '_convo_history.zip'
-      s3_filepath = s3_file = f"courses/{course_name}/{filename}"
+      s3_filepath = f"courses/{course_name}/{filename}"
       # background task of downloading data - map it with above ID
       executor = ProcessPoolExecutor()
       executor.submit(self.export_data_in_bg, response, "conversations", course_name, s3_filepath)

ai_ta_backend/service/nomic_service.py

@@ -677,10 +677,10 @@ def data_prep_for_doc_map(self, df: pd.DataFrame):
     embeddings = []
     texts = []
 
-    for index, row in df.iterrows():
+    for _index, row in df.iterrows():
 
       current_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-      if row['url'] == None:
+      if row['url'] is None:
         row['url'] = ""
       # iterate through all contexts and create separate entries for each
       context_count = 0

ai_ta_backend/service/retrieval_service.py

@@ -6,10 +6,8 @@
 
 import openai
 from injector import inject
-from langchain import hub
 from langchain.chat_models import AzureChatOpenAI
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.load import dumps, loads
 from langchain.schema import Document
 
 from ai_ta_backend.database.aws import AWSStorage
@@ -326,7 +324,7 @@ def delete_from_nomic_and_supabase(self, course_name: str, identifier_key: str,
         project_id = response.data[0]['doc_map_id']
       else:
         return "No document map found for this course"
-      res = self.nomicService.delete_from_document_map(project_id, nomic_ids_to_delete)
+      self.nomicService.delete_from_document_map(project_id, nomic_ids_to_delete)
 
       # delete from Supabase
       self.sqlDb.deleteMaterialsForCourseAndKeyAndValue(course_name, identifier_key, identifier_value)

ai_ta_backend/utils/context_parent_doc_padding.py

@@ -4,8 +4,6 @@
 from functools import partial
 from multiprocessing import Manager
 
-import supabase
-
 DOCUMENTS_TABLE = os.environ['SUPABASE_DOCUMENTS_TABLE']
 # SUPABASE_CLIENT = supabase.create_client(supabase_url=os.environ['SUPABASE_URL'],
 #  supabase_key=os.environ['SUPABASE_API_KEY'])  # type: ignore