Add files

app.py

@@ -57,57 +57,53 @@ def search_datasets_fn(query: str) -> List[str]:
         return []
 
 
-def download_and_list_episodes(repo_id: str, progress=gr.Progress()):
+def load_episodes_for_dataset(repo_id: str):
     """Download dataset and list available episodes"""
     if not repo_id:
-        return "Please provide a dataset repo ID.", []
+        return ""
     
     token = os.environ.get("HF_TOKEN")
     temp_dir = tempfile.mkdtemp(prefix="episode_delete_")
     
     try:
-        progress(0.3, desc="Downloading dataset...")
         download_dataset(repo_id, temp_dir, hf_token=token)
-        
-        progress(0.7, desc="Listing episodes...")
         episodes = list_episodes(temp_dir)
         
-        if not episodes:
-            return f"No episodes found in {repo_id}", []
+        # Cleanup temp directory
+        shutil.rmtree(temp_dir, ignore_errors=True)
         
-        # Format episodes as choices
-        episode_choices = [f"Episode {ep}" for ep in episodes]
+        if not episodes:
+            return "No episodes found"
         
-        return (
-            f"Downloaded {repo_id}. Found {len(episodes)} episodes.",
-            gr.update(choices=episode_choices, value=[]),
-        )
+        # Return info about available episodes
+        return f"Found {len(episodes)} episodes: {', '.join(map(str, episodes))}"
     except Exception as e:
-        return f"Error: {str(e)}", gr.update(choices=[], value=[])
+        print(f"Error loading episodes: {e}")
+        return f"Error: {e}"
 
 
-def delete_episodes_stream(repo_id: str, selected_episodes: List[str], dest_repo_id: str):
+def delete_episodes_stream(repo_id: str, episode_indexes_str: str, dest_repo_id: str):
     """Delete selected episodes and upload to destination repo"""
     if not repo_id:
         yield "Please provide a source dataset repo ID."
         return
     
-    if not selected_episodes:
-        yield "Please select at least one episode to delete."
+    if not episode_indexes_str or not episode_indexes_str.strip():
+        yield "Please provide at least one episode index to delete."
         return
     
-    if not dest_repo_id:
-        yield "Please provide a destination repo ID."
-        return
+    # If no destination provided, use the same repo name
+    if not dest_repo_id or not dest_repo_id.strip():
+        dest_repo_id = repo_id
     
-    # Parse episode numbers from selection (format: "Episode 0", "Episode 1", etc.)
+    # Parse comma-separated episode indexes
     episode_indexes = []
-    for ep_str in selected_episodes:
+    for ep_str in episode_indexes_str.split(","):
         try:
-            ep_num = int(ep_str.replace("Episode ", ""))
+            ep_num = int(ep_str.strip())
             episode_indexes.append(ep_num)
         except ValueError:
-            yield f"Invalid episode format: {ep_str}"
+            yield f"Invalid episode index: {ep_str.strip()}"
             return
     
     token = os.environ.get("HF_TOKEN")
@@ -182,105 +178,48 @@ def delete_episodes_stream(repo_id: str, selected_episodes: List[str], dest_repo
 
 
 # Build the Gradio interface
-with gr.Blocks(title="LeRobot Episode Deleter", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🗑️ LeRobot Dataset Episode Deleter")
-    gr.Markdown(
-        "Delete specific episodes from a HuggingFace LeRobot dataset and upload the cleaned version."
-    )
+with gr.Blocks(title="LeRobot Episode Deleter") as demo:
+    gr.Markdown("**Delete specific episodes from a Hugging Face dataset (LeRobot format).**")
     
     # Load initial datasets
     _initial_choices = search_datasets_fn("griffinlabs-cortex")
     
-    with gr.Row():
-        search_box = gr.Textbox(
-            label="Search Datasets (optional)",
-            placeholder="Enter keyword or organization name (e.g., 'lerobot', 'griffinlabs-cortex')",
-            value="griffinlabs-cortex"
-        )
-        search_btn = gr.Button("🔍 Search")
-    
-    with gr.Row():
-        dataset_dropdown = gr.Dropdown(
-            label="Select Dataset",
-            choices=_initial_choices,
-            interactive=True,
-            allow_custom_value=True,
-        )
-    
-    with gr.Row():
-        download_btn = gr.Button("📥 Download & List Episodes", variant="secondary", size="lg")
+    dataset_dropdown = gr.Dropdown(
+        label="Select dataset",
+        choices=_initial_choices,
+        interactive=True,
+    )
     
-    download_status = gr.Textbox(
-        label="Status",
-        lines=2,
+    episodes_info = gr.Textbox(
+        label="Available episodes",
         interactive=False,
+        lines=2
     )
     
-    gr.Markdown("---")
-    gr.Markdown("### Select Episodes to Delete")
-    
-    episodes_selector = gr.CheckboxGroup(
-        label="Episodes (select to delete)",
-        choices=[],
-        interactive=True,
+    episodes_input = gr.Textbox(
+        label="Episode indexes to delete (comma-separated)",
+        placeholder="0, 1, 2"
     )
     
-    selected_count = gr.Markdown("*No episodes selected*")
-    
-    gr.Markdown("---")
-    gr.Markdown("### Configure Destination & Execute")
-    
     dest_repo_input = gr.Textbox(
-        label="Destination Repository ID",
-        placeholder="your-org/cleaned-dataset",
-        info="The HuggingFace repo where the cleaned dataset will be uploaded"
+        label="Destination repo id (leave empty to use same repo)",
+        placeholder="org/cleaned_dataset"
     )
     
-    with gr.Row():
-        execute_btn = gr.Button(
-            "🚀 Delete Episodes & Upload",
-            variant="primary",
-            size="lg",
-        )
+    execute_btn = gr.Button("Delete Episodes and Upload")
     
-    progress_log = gr.Textbox(
-        label="Progress Log",
-        lines=20,
-        interactive=False,
-        max_lines=25,
-    )
+    progress_log = gr.Textbox(label="Progress log", lines=20)
     
     # Event handlers
-    def update_search_results(query):
-        results = search_datasets_fn(query)
-        return gr.update(choices=results, value=None)
-    
-    search_btn.click(
-        update_search_results,
-        inputs=search_box,
-        outputs=dataset_dropdown,
-    )
-    
-    download_btn.click(
-        download_and_list_episodes,
+    dataset_dropdown.change(
+        load_episodes_for_dataset,
         inputs=dataset_dropdown,
-        outputs=[download_status, episodes_selector],
-    )
-    
-    def update_selected_count(selected):
-        if not selected:
-            return "*No episodes selected*"
-        return f"**{len(selected)} episode(s) selected for deletion**"
-    
-    episodes_selector.change(
-        update_selected_count,
-        inputs=episodes_selector,
-        outputs=selected_count,
+        outputs=episodes_info,
     )
     
     execute_btn.click(
         delete_episodes_stream,
-        inputs=[dataset_dropdown, episodes_selector, dest_repo_input],
+        inputs=[dataset_dropdown, episodes_input, dest_repo_input],
         outputs=progress_log,
     )