Add Gradio interfaces for dataset search, file listing, and file download in app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
-import os, json, pathlib
+import os, json, pathlib, tempfile
 import pandas as pd
-import tempfile, pathlib
 from typing import List, Dict
 from kaggle.api.kaggle_api_extended import KaggleApi
 
@@ -13,23 +12,23 @@ 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, page_size=max_results)
+    results = api.dataset_list(search=query, max_size= None)
     out = []
-    for ds in results:
+    for ds in results[:max_results]:
         out.append({
             "title": ds.title,
             "slug": ds.ref,
-            "size_mb": round(ds.size/1e6, 2),
-            "downloads": ds.downloadCount,
-            "votes": ds.totalVotes,
+            "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.totalBytes / 1e6, 2)} for f in files]
+    return [{"name": f.name, "size_mb": round(f.total_bytes / 1e6, 2)} for f in files]
 
-def downlaod_file(dataset_slug: str, file_name: str):
+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}"
@@ -38,6 +37,41 @@ def downlaod_file(dataset_slug: str, file_name: str):
         zip_path = pathlib.Path(tmp_dir) / f"{file_name}.zip"
     return str(zip_path)
 
+search_iface = gr.Interface(
+    fn=search_datasets,
+    inputs=[
+        gr.Textbox(label="Search term", placeholder="e.g. titanic"),
+        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="zynicide/wine-reviews"),
+    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="zynicide/wine-reviews"),
+        gr.Textbox(label="File name", placeholder="winemag-data_first150k.csv")
+    ],
+    outputs=gr.File(label="Download file"),
+    title="Download a File",
+    description="Downloads one file from the dataset and returns it."
+)
+
+demo = gr.TabbedInterface(
+    [search_iface, list_files_iface, download_file_iface],
+    tab_names=["Search", "Files", "Download"]
+)
+
 def _bootstrap_kaggle_credentials():
     user = os.getenv("KAGGLE_USERNAME")
     key = os.getenv("KAGGLE_KEY")
@@ -55,4 +89,7 @@ def _bootstrap_kaggle_credentials():
 _bootstrap_kaggle_credentials()    
 
 api = KaggleApi()
-api.authenticate()
+api.authenticate()
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860, mcp_server=True)