chore: added pre-commit-hooks and ruff formatting for commit-hooks

reproduce/Step_2.py

@@ -1,8 +1,8 @@
-import os
 import json
 from openai import OpenAI
 from transformers import GPT2Tokenizer
 
+
 def openai_complete_if_cache(
     model="gpt-4o", prompt=None, system_prompt=None, history_messages=[], **kwargs
 ) -> str:
@@ -19,24 +19,26 @@ def openai_complete_if_cache(
     )
     return response.choices[0].message.content
 
-tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+
 
 def get_summary(context, tot_tokens=2000):
     tokens = tokenizer.tokenize(context)
     half_tokens = tot_tokens // 2
 
-    start_tokens = tokens[1000:1000 + half_tokens]
-    end_tokens = tokens[-(1000 + half_tokens):1000]
+    start_tokens = tokens[1000 : 1000 + half_tokens]
+    end_tokens = tokens[-(1000 + half_tokens) : 1000]
 
     summary_tokens = start_tokens + end_tokens
     summary = tokenizer.convert_tokens_to_string(summary_tokens)
-    
+
     return summary
 
 
-clses = ['agriculture']
+clses = ["agriculture"]
 for cls in clses:
-    with open(f'../datasets/unique_contexts/{cls}_unique_contexts.json', mode='r') as f:
+    with open(f"../datasets/unique_contexts/{cls}_unique_contexts.json", mode="r") as f:
         unique_contexts = json.load(f)
 
     summaries = [get_summary(context) for context in unique_contexts]
@@ -67,10 +69,10 @@ for cls in clses:
         ...
     """
 
-    result = openai_complete_if_cache(model='gpt-4o', prompt=prompt)
+    result = openai_complete_if_cache(model="gpt-4o", prompt=prompt)
 
     file_path = f"../datasets/questions/{cls}_questions.txt"
     with open(file_path, "w") as file:
         file.write(result)
 
-    print(f"{cls}_questions written to {file_path}")
+    print(f"{cls}_questions written to {file_path}")