Fix all lint errors (#2627)

evaluation/evals.py

@@ -1,11 +1,12 @@
-import json
 import argparse
-from metrics.utils import calculate_metrics, calculate_bleu_scores
-from metrics.llm_judge import evaluate_llm_judge
-from collections import defaultdict
-from tqdm import tqdm
 import concurrent.futures
+import json
 import threading
+from collections import defaultdict
+
+from metrics.llm_judge import evaluate_llm_judge
+from metrics.utils import calculate_bleu_scores, calculate_metrics
+from tqdm import tqdm
 
 
 def process_item(item_data):

evaluation/generate_scores.py

@@ -1,6 +1,7 @@
-import pandas as pd
 import json
 
+import pandas as pd
+
 # Load the evaluation metrics data
 with open('evaluation_metrics.json', 'r') as f:
     data = json.load(f)

evaluation/metrics/llm_judge.py

@@ -1,8 +1,9 @@
-from openai import OpenAI
+import argparse
 import json
 from collections import defaultdict
+
 import numpy as np
-import argparse
+from openai import OpenAI
 
 client = OpenAI()
 

evaluation/metrics/utils.py

@@ -10,22 +10,17 @@ Borrowed from https://github.com/WujiangXu/AgenticMemory/blob/main/utils.py
 }
 """
 
-import re
-import string
-import numpy as np
-from typing import List, Dict, Union
 import statistics
 from collections import defaultdict
-from rouge_score import rouge_scorer
-from nltk.translate.bleu_score import sentence_bleu, SmoothingFunction
-from bert_score import score as bert_score
+from typing import Dict, List, Union
+
 import nltk
+from bert_score import score as bert_score
+from nltk.translate.bleu_score import SmoothingFunction, sentence_bleu
 from nltk.translate.meteor_score import meteor_score
+from rouge_score import rouge_scorer
 from sentence_transformers import SentenceTransformer
-import logging
-from dataclasses import dataclass
-from pathlib import Path
-from openai import OpenAI
+
 # from load_dataset import load_locomo_dataset, QA, Turn, Session, Conversation
 from sentence_transformers.util import pytorch_cos_sim
 
@@ -71,7 +66,7 @@ def calculate_bleu_scores(prediction: str, reference: str) -> Dict[str, float]:
     for n, weights in enumerate(weights_list, start=1):
         try:
             score = sentence_bleu(ref_tokens, pred_tokens, weights=weights, smoothing_function=smooth)
-        except Exception:
+        except Exception as e:
             print(f"Error calculating BLEU score: {e}")
             score = 0.0
         scores[f'bleu{n}'] = score
@@ -158,21 +153,13 @@ def calculate_metrics(prediction: str, reference: str) -> Dict[str, float]:
         f1 = 2 * precision * recall / (precision + recall) if (precision + recall) > 0 else 0.0
     
     # Calculate all scores
-    rouge_scores = 0 #calculate_rouge_scores(prediction, reference)
     bleu_scores = calculate_bleu_scores(prediction, reference)
-    bert_scores = 0 # calculate_bert_scores(prediction, reference)
-    meteor = 0 # calculate_meteor_score(prediction, reference)
-    sbert_similarity = 0 # calculate_sentence_similarity(prediction, reference)
     
     # Combine all metrics
     metrics = {
         "exact_match": exact_match,
         "f1": f1,
-        # **rouge_scores,
         **bleu_scores,
-        # **bert_scores,
-        # "meteor": meteor,
-        # "sbert_similarity": sbert_similarity
     }
 
     return metrics

evaluation/run_experiments.py

@@ -1,14 +1,14 @@
+import argparse
 import os
-import json
+
+from src.langmem import LangMemManager
 from src.memzero.add import MemoryADD
 from src.memzero.search import MemorySearch
-from src.utils import TECHNIQUES, METHODS
-import argparse
-from src.rag import RAGManager
-from src.langmem import LangMemManager
-from src.zep.search import ZepSearch
-from src.zep.add import ZepAdd
 from src.openai.predict import OpenAIPredict
+from src.rag import RAGManager
+from src.utils import METHODS, TECHNIQUES
+from src.zep.add import ZepAdd
+from src.zep.search import ZepSearch
 
 
 class Experiment:

evaluation/src/langmem.py

@@ -1,28 +1,24 @@
+import json
+import multiprocessing as mp
+import os
+import time
+from collections import defaultdict
+
+from dotenv import load_dotenv
+from jinja2 import Template
 from langgraph.checkpoint.memory import MemorySaver
 from langgraph.prebuilt import create_react_agent
 from langgraph.store.memory import InMemoryStore
 from langgraph.utils.config import get_store
-from langmem import (
-    create_manage_memory_tool,
-    create_search_memory_tool
-)
-import time
-import multiprocessing as mp
-import json
-from functools import partial
-import os
-from tqdm import tqdm
+from langmem import create_manage_memory_tool, create_search_memory_tool
 from openai import OpenAI
-from collections import defaultdict
-from dotenv import load_dotenv
 from prompts import ANSWER_PROMPT
+from tqdm import tqdm
 
 load_dotenv()
 
 client = OpenAI()
 
-from jinja2 import Template
-
 ANSWER_PROMPT_TEMPLATE = Template(ANSWER_PROMPT)
 
 

evaluation/src/memzero/add.py

@@ -1,11 +1,13 @@
-from mem0 import MemoryClient
 import json
-import time
 import os
 import threading
-from tqdm import tqdm
+import time
 from concurrent.futures import ThreadPoolExecutor
+
 from dotenv import load_dotenv
+from tqdm import tqdm
+
+from mem0 import MemoryClient
 
 load_dotenv()
 

evaluation/src/memzero/search.py

@@ -1,14 +1,16 @@
+import json
+import os
+import time
 from collections import defaultdict
 from concurrent.futures import ThreadPoolExecutor
-from tqdm import tqdm
-from mem0 import MemoryClient
-import json
-import time
+
+from dotenv import load_dotenv
 from jinja2 import Template
 from openai import OpenAI
-from prompts import ANSWER_PROMPT_GRAPH, ANSWER_PROMPT
-import os
-from dotenv import load_dotenv
+from prompts import ANSWER_PROMPT, ANSWER_PROMPT_GRAPH
+from tqdm import tqdm
+
+from mem0 import MemoryClient
 
 load_dotenv()
 

evaluation/src/openai/predict.py

@@ -1,12 +1,13 @@
-from openai import OpenAI
-import os
+import argparse
 import json
-from jinja2 import Template
-from tqdm import tqdm
+import os
 import time
 from collections import defaultdict
+
 from dotenv import load_dotenv
-import argparse
+from jinja2 import Template
+from openai import OpenAI
+from tqdm import tqdm
 
 load_dotenv()
 

evaluation/src/rag.py

@@ -1,13 +1,14 @@
-from openai import OpenAI
 import json
-import numpy as np
-from tqdm import tqdm
-from jinja2 import Template
-import tiktoken
+import os
 import time
 from collections import defaultdict
-import os
+
+import numpy as np
+import tiktoken
 from dotenv import load_dotenv
+from jinja2 import Template
+from openai import OpenAI
+from tqdm import tqdm
 
 load_dotenv()
 

evaluation/src/zep/add.py

@@ -1,6 +1,7 @@
 import argparse
 import json
 import os
+
 from dotenv import load_dotenv
 from tqdm import tqdm
 from zep_cloud import Message

evaluation/src/zep/search.py

@@ -1,16 +1,16 @@
 import argparse
+import json
+import os
+import time
 from collections import defaultdict
+
 from dotenv import load_dotenv
 from jinja2 import Template
 from openai import OpenAI
+from prompts import ANSWER_PROMPT_ZEP
 from tqdm import tqdm
 from zep_cloud import EntityEdge, EntityNode
 from zep_cloud.client import Zep
-import json
-import os
-import pandas as pd
-import time
-from prompts import ANSWER_PROMPT_ZEP
 
 load_dotenv()
 
@@ -52,7 +52,6 @@ class ZepSearch:
         while retries < max_retries:
             try:
                 user_id = f"run_id_{run_id}_experiment_user_{idx}"
-                session_id = f"run_id_{run_id}_experiment_session_{idx}"
                 edges_results = (self.zep_client.graph.search(user_id=user_id, reranker='cross_encoder', query=query, scope='edges', limit=20)).edges
                 node_results = (self.zep_client.graph.search(user_id=user_id, reranker='rrf', query=query, scope='nodes', limit=20)).nodes
                 context = self.compose_search_context(edges_results, node_results)