Update app.py

app.py

@@ -469,6 +469,14 @@ with gr.Blocks(css=css) as demo:
                 current_item_idx += 1
 
 
+    def upload_file(file):
+        # Upload file to Hugging Face Hub
+        # Replace with your own file upload logic
+        # For example, you can use the `huggingface_hub` library to upload the file
+        # See: https://huggingface.co/docs/hub/uploading
+        pass
+
+
     @search_button.click(inputs=search_bar, outputs=button_groups + buttons + [generated_texts_state])
     def search_dataset_from_search_button(search_query):
         yield from _search_datasets(search_query)
@@ -538,7 +546,7 @@ with gr.Blocks(css=css) as demo:
     def show_dataset_from_button(search_query, *buttons_values, i):
         dataset_name, tags = buttons_values[2 * i : 2 * i + 2]
         yield from _show_dataset(search_query, dataset_name, tags)
-    
+
     for i, (dataset_name_button, tags_button) in enumerate(batched(buttons, 2)):
         dataset_name_button.click(partial(show_dataset_from_button, i=i), inputs=show_dataset_inputs, outputs=show_dataset_outputs, js=scroll_to_top_js)
         tags_button.click(partial(show_dataset_from_button, i=i), inputs=show_dataset_inputs, outputs=show_dataset_outputs, js=scroll_to_top_js)
@@ -642,5 +650,37 @@ with gr.Blocks(css=css) as demo:
             yield {search_page: gr.Column(visible=True)}
 
 
-demo.launch()
+    @demo.upload(inputs=[search_bar, dataset_title, dataset_content, dataset_dataframe, select_namespace_dropdown, visibility_radio], outputs=[save_dataset_button, open_dataset_message])
+    def upload_dataset(search_query, dataset_name, dataset_content, df, namespace, visability):
+        dataset_name, tags = dataset_name.strip("# ").split("\ntags:", 1)
+        dataset_name, tags = dataset_name.strip(), tags.strip()
+        csv_header, preview_df = parse_preview_df(dataset_content)
+        # Remove dummy "id" columns
+        for column_name, values in preview_df.to_dict(orient="series").items():
+            try:
+                if [int(v) for v in values] == list(range(len(preview_df))):
+                    preview_df = preview_df.drop(columns=column_name)
+                if [int(v) for v in values] == list(range(1, len(preview_df) + 1)):
+                    preview_df = preview_df.drop(columns=column_name)
+            except Exception:
+                pass
+        columns = list(preview_df)
+        output: list[Optional[dict]] = [None] * NUM_ROWS
+        output[:len(preview_df)] = [{"idx": i, **x} for i, x in enumerate(preview_df.to_dict(orient="records"))]
+        yield {
+            save_dataset_button: gr.Button(f"💾 Save Dataset {namespace}/{dataset_name}" + (" (private)" if visability != "public" else ""), interactive=False),
+            open_dataset_message: gr.Markdown(f"Uploading dataset {dataset_name}...")
+        }
+        token = oauth_token.token if oauth_token else save_dataset_hf_token
+        repo_id = f"{namespace}/{dataset_name}"
+        dataset_url = f"{URL}?q={search_query.replace(' ', '+')}&dataset={dataset_name.replace(' ', '+')}&tags={tags.replace(' ', '+')}"
+        create_repo(repo_id=repo_id, repo_type="dataset", private=visability!="public", exist_ok=True, token=token)
+        df.to_csv(f"hf://datasets/{repo_id}/data.csv", storage_options={"token": token}, index=False)
+        DatasetCard(DATASET_CARD_CONTENT.format(title=title, content=content, url=URL, dataset_url=dataset_url, model_id=model_id, search_query=search_query)).push_to_hub(repo_id=repo_id, repo_type="dataset", token=token)
+        gr.Info(f"✅ Dataset saved at {repo_id}")
+        additional_message = "PS: You can also save datasets under your account in the Settings ;)"
+        yield {open_dataset_message: gr.Markdown(f"# 🎉 Yay ! Your dataset has been saved to [{repo_id}](https://huggingface.co/datasets/{repo_id}) !\n\nDataset link: [https://huggingface.co/datasets/{repo_id}](https://huggingface.co/datasets/{repo_id})\n\n{additional_message}", visible=True)}
+        print(f"Saved {dataset_name}!")
+
 
+demo.launch()