Create app.py

app.py

@@ -0,0 +1,59 @@
+import os
+from pathlib import Path
+import gradio as gr
+from huggingface_hub import CommitScheduler, hf_hub_download, login
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+login(HF_TOKEN)
+
+# Set up dataset storage
+dataset_folder = Path("dataset")
+dataset_folder.mkdir(exist_ok=True)
+
+# Function to get the latest dataset file
+def get_latest_dataset_file():
+    if files := glob.glob(str(dataset_folder / "data_*.jsonl")):
+        return max(files, key=os.path.getctime)
+    return None
+
+
+# Check for existing dataset and create or append to it
+if latest_file := get_latest_dataset_file():
+    dataset_file = Path(latest_file)
+    print(f"Appending to existing dataset file: {dataset_file}")
+else:
+    dataset_file = dataset_folder / f"data_{uuid.uuid4()}.jsonl"
+    print(f"Creating new dataset file: {dataset_file}")
+# Set up CommitScheduler for dataset uploads
+repo_id = "wannaphong/d1"  # Replace with your desired dataset repo
+scheduler = CommitScheduler(
+    repo_id=repo_id,
+    repo_type="dataset",
+    folder_path=dataset_folder,
+    path_in_repo="data",
+    every=1,  # Upload every 5 minutes
+)
+# Function to save feedback and generated data
+def save_data(name):
+    data = {
+        "name": name,
+    }
+    with scheduler.lock:
+        with dataset_file.open("a") as f:
+            f.write(json.dumps(data) + "\n")
+    # return "Data saved and will be uploaded to the dataset repository."
+
+
+
+def greet(name):
+    save_data(name)
+    return "Hello, " + name + "!"
+
+demo = gr.Interface(
+    fn=greet,
+    inputs=["text"],
+    outputs=["text"],
+)
+
+demo.launch()
+