File size: 4,504 Bytes
b99c98e
7b0d4d1
 
b99c98e
25ba008
 
b99c98e
25ba008
 
 
 
 
569b533
25ba008
569b533
25ba008
 
 
569b533
 
 
25ba008
 
 
 
 
569b533
25ba008
569b533
25ba008
 
 
 
 
 
 
 
d855e11
 
7b0d4d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d855e11
 
 
7b0d4d1
 
 
 
 
 
569b533
 
 
d855e11
569b533
 
 
 
 
 
 
 
 
d855e11
569b533
 
 
 
 
 
 
 
d855e11
 
569b533
 
 
 
 
 
7b0d4d1
d855e11
 
7b0d4d1
 
 
 
 
d855e11
7b0d4d1
 
569b533
7b0d4d1
 
569b533
 
a678f86
 
 
 
 
 
 
 
 
 
 
 
 
25ba008
e9d2479
25ba008
e9d2479
25ba008
569b533
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
import gradio as gr
import os, json, pathlib, tempfile, datetime
from typing import List, Dict, Optional

from dotenv import load_dotenv
load_dotenv()

def search_datasets(query: str, max_results: int = 20) -> List[Dict]:
    """
    Return brief metadata for up to `max_results` public datasets
    whose title or description matches `query`.
    """
    results = api.dataset_list(search=query, max_size= None)
    out = []
    for ds in results[:max_results]:
        out.append({
            "title": ds.title,
            "slug": ds.ref,
            "size_mb": round(ds.total_bytes/1e6, 2),
            "downloads": ds.download_count,
            "votes": ds.vote_count,
        })
    return out

def list_files(dataset_slug: str) -> List[Dict]:
    files = api.dataset_list_files(dataset_slug).files
    return [{"name": f.name, "size_mb": round(f.total_bytes / 1e6, 2)} for f in files]

def download_file(dataset_slug: str, file_name: str):
    tmp_dir = tempfile.mkdtemp()
    api.dataset_download_file(dataset_slug, file_name, path=tmp_dir, quiet=False)
    zip_path = pathlib.Path(tmp_dir) / f"{file_name}"

    if not zip_path.exists():
        zip_path = pathlib.Path(tmp_dir) / f"{file_name}.zip"
    return str(zip_path)

def search_kernels(query: str, max_results: int = 20) -> List[Dict]:
    
    kernels = api.kernels_list(
        search=query,
        page_size=min(max_results, 20),
        sort_by="voteCount",
    )

    out = []
    for k in kernels[:max_results]:
        last_run_raw = getattr(k, "lastRunTime", None) or getattr(k, "updated", None)
        try:
            last_run = (
                datetime.datetime.fromisoformat(last_run_raw.rstrip("z"))
                .strftime("%Y-%m-%d %H:%M") if last_run_raw else None
            )
        except Exception:
            last_run = last_run_raw
        out.append(
            {
                "title": k.title,
                "ref": k.ref,
                "language": getattr(k, "language", None),
                "kernel_type": getattr(k, "kernelType", None),
                "votes": k.total_votes,
                "last_run": last_run,
            }
        )
    return out
    

search_iface = gr.Interface(
    fn=search_datasets,
    inputs=[
        gr.Textbox(label="Search term", placeholder="e.g. fashion mnist"),
        gr.Slider(1, 50, step=1, value=20, label="Max results")
    ],
    outputs=gr.JSON(label="Datasets"),
    title="Search kaggle Datasets",
    description="Resturns a JSON array of dataset metadata."
)

list_files_iface = gr.Interface(
    fn=list_files,
    inputs=gr.Textbox(label="Dataset slug", placeholder="zalando-research/fashionmnist"),
    outputs=gr.JSON(label="Files"),
    title="List Dataset Files",
    description="Given a dataset slug, returns its file list."
)

download_file_iface = gr.Interface(
    fn=download_file,
    inputs=[
        gr.Textbox(label="Dataset slug", placeholder="zalando-research/fashionmnist"),
        gr.Textbox(label="File name", placeholder="fashion-mnist_test.csv")
    ],
    outputs=gr.File(label="Download file"),
    title="Download a File",
    description="Downloads one file from the dataset and returns it."
)

search_kernels_iface = gr.Interface(
    fn=search_kernels,
    inputs=[
        gr.Textbox(label="search term", placeholder="e.g. computer vision"),
        gr.Slider(1, 50, step=1, value=20, label="Max results"),
    ],
    outputs=gr.JSON(label="kernels"),
    title="Search kaggle kernels",
    description="Find notebook or script kernels by keyword."
)

demo = gr.TabbedInterface(
    [search_iface, list_files_iface, download_file_iface, search_kernels_iface],
    tab_names=["Search Datasets", "Files", "Download File", "Search Kernels"],
)

def _bootstrap_kaggle_credentials():
    user = os.getenv("KAGGLE_USERNAME")
    key = os.getenv("KAGGLE_KEY")
    if not (user and key):
        raise RuntimeError(
            "Kaggle credentials not found."
            "Set KAGGLE_USERNAME and KAGGLE_KEY as env vars or in .env"
        )
    cred_path = pathlib.Path.home() / ".kaggle" / "kaggle.json"
    if not cred_path.exists():
        cred_path.parent.mkdir(exist_ok=True)
        cred_path.write_text(json.dumps({"username": user, "key": key}))
        cred_path.chmod(0o600)

_bootstrap_kaggle_credentials()  

from kaggle.api.kaggle_api_extended import KaggleApi
api = KaggleApi()
api.authenticate()

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0", server_port=7860, mcp_server=True)