Remove datasets

.gitignore

@@ -0,0 +1,3 @@
+scripts/__pycache__
+.env
+.gradio

app.py

@@ -33,7 +33,7 @@ from scripts.visual_qa import visualizer
 from tqdm import tqdm
 
 from smolagents import (
-    MANAGED_AGENT_PROMPT,
+    # MANAGED_AGENT_PROMPT,
     CodeAgent,
     HfApiModel,
     LiteLLMModel,
@@ -79,6 +79,8 @@ SET = "validation"
 
 custom_role_conversions = {"tool-call": "assistant", "tool-response": "user"}
 
+# skip
+_ = """
 ### LOAD EVALUATION DATASET
 
 eval_ds = datasets.load_dataset("gaia-benchmark/GAIA", "2023_all")[SET]
@@ -95,6 +97,7 @@ eval_ds = eval_ds.map(preprocess_file_paths)
 eval_df = pd.DataFrame(eval_ds)
 print("Loaded evaluation dataset:")
 print(eval_df["task"].value_counts())
+# """
 
 user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
 

requirements.txt

@@ -12,7 +12,8 @@ openai>=1.52.2
 openpyxl
 pandas>=2.2.3
 pathvalidate>=3.2.1
-pdfminer>=20191125
+
+# pdfminer>=20191125
 pdfminer.six>=20240706
 Pillow>=11.0.0
 puremagic>=1.28
@@ -20,7 +21,10 @@ pypdf>=5.1.0
 python-dotenv>=1.0.1
 python_pptx>=1.0.2
 Requests>=2.32.3
-serpapi>=0.1.5
+# serpapi>=0.1.5
+serpapi
+
+google-search-results
 tqdm>=4.66.4
 torch>=2.2.2
 torchvision>=0.17.2

scripts/text_web_browser.py

@@ -11,7 +11,8 @@ from urllib.parse import unquote, urljoin, urlparse
 
 import pathvalidate
 import requests
-from serpapi import GoogleSearch
+# from serpapi import GoogleSearch
+from serpapi.google_search import GoogleSearch
 
 from smolagents import Tool