scripts/debug_context_file.py


1
2
3
4
5
6
7
8
9
10
11
12
13
14

import json

path = "data/raw_datasets/personamem/shared_contexts_32k.jsonl"
with open(path, 'r') as f:
    line = f.readline()
    data = json.loads(line)
    print(f"Type: {type(data)}")
    if isinstance(data, dict):
        print(f"Keys: {list(data.keys())}")
        # Peek into values
        for k, v in data.items():
            print(f"Key '{k}' type: {type(v)}")
            if isinstance(v, list):
                print(f"  Length: {len(v)}")