Linting

* validate python formatting on every build with Ruff
* fix lint warnings

scripts/old/ingest_rst.py

@@ -1,38 +1,42 @@
-from pathlib import Path
-from langchain.text_splitter import CharacterTextSplitter
-import faiss
-from langchain.vectorstores import FAISS
-from langchain.embeddings import OpenAIEmbeddings
 import pickle
-import dotenv
-import tiktoken
 import sys
 from argparse import ArgumentParser
+from pathlib import Path
+
+import dotenv
+import faiss
+import tiktoken
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+
 
 def num_tokens_from_string(string: str, encoding_name: str) -> int:
-# Function to convert string to tokens and estimate user cost.
+    # Function to convert string to tokens and estimate user cost.
     encoding = tiktoken.get_encoding(encoding_name)
     num_tokens = len(encoding.encode(string))
-    total_price = ((num_tokens/1000) * 0.0004)
+    total_price = ((num_tokens / 1000) * 0.0004)
     return num_tokens, total_price
 
+
 def call_openai_api():
-# Function to create a vector store from the documents and save it to disk.
+    # Function to create a vector store from the documents and save it to disk.
     store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
     faiss.write_index(store.index, "docs.index")
     store.index = None
     with open("faiss_store.pkl", "wb") as f:
         pickle.dump(store, f)
 
+
 def get_user_permission():
-# Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
+    # Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
     # Here we convert the docs list to a string and calculate the number of OpenAI tokens the string represents.
     docs_content = (" ".join(docs))
     tokens, total_price = num_tokens_from_string(string=docs_content, encoding_name="cl100k_base")
     # Here we print the number of tokens and the approx user cost with some visually appealing formatting.
     print(f"Number of Tokens = {format(tokens, ',d')}")
     print(f"Approx Cost = ${format(total_price, ',.2f')}")
-    #Here we check for user permission before calling the API.
+    # Here we check for user permission before calling the API.
     user_input = input("Price Okay? (Y/N) \n").lower()
     if user_input == "y":
         call_openai_api()
@@ -41,7 +45,8 @@ def get_user_permission():
     else:
         print("The API was not called. No money was spent.")
 
-#Load .env file
+
+# Load .env file
 dotenv.load_dotenv()
 
 ap = ArgumentParser("Script for training DocsGPT on .rst documentation files.")