View GAIA Val Cases

requirements.txt

@@ -1,2 +1,15 @@
 gradio
-requests
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+arxiv
+pymupdf
+wikipedia

view_GAIA.py

@@ -0,0 +1,38 @@
+import json
+import random
+import argparse
+
+def main(nums=1):
+    with open('metadata.jsonl', 'r') as jsonl_file:
+        json_list = list(jsonl_file)
+
+    json_QA = []
+    for json_str in json_list:
+        json_data = json.loads(json_str)
+        json_QA.append(json_data)
+
+    random_samples = random.sample(json_QA, nums)
+    for sample in random_samples:
+        print("=" * 50)
+        print(f"Task ID: {sample['task_id']}")
+        print(f"Question: {sample['Question']}")
+        print(f"Level: {sample['Level']}")
+        print(f"Final Answer: {sample['Final answer']}")
+        print(f"Annotator Metadata: ")
+        print(f"  ├── Steps: ")
+        for step in sample['Annotator Metadata']['Steps'].split('\n'):
+            print(f"  │      ├── {step}")
+        print(f"  ├── Number of steps: {sample['Annotator Metadata']['Number of steps']}")
+        print(f"  ├── How long did this take?: {sample['Annotator Metadata']['How long did this take?']}")
+        print(f"  ├── Tools:")
+        for tool in sample['Annotator Metadata']['Tools'].split('\n'):
+            print(f"  │      ├── {tool}")
+        print(f"  └── Number of tools: {sample['Annotator Metadata']['Number of tools']}")
+    print("=" * 50)
+
+if __name__=='__main__':
+    parser = argparse.ArgumentParser(description="number of GAIA examples")
+    parser.add_argument('--nums', type=int, required=True, 
+                       help="number of GAIA examples")
+    args = parser.parse_args()
+    main(nums=args.nums)