first commit

.env.example

@@ -0,0 +1 @@
+HF_TOKEN=your_hugging_face_token_here 

.gitignore

@@ -0,0 +1,11 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+.env

.python-version

@@ -0,0 +1 @@
+3.11

app.py

@@ -0,0 +1,172 @@
+import requests
+import gradio as gr
+from urllib.parse import urlencode
+from dotenv import load_dotenv
+import os
+
+# Load environment variables
+load_dotenv()
+
+
+def create_image(stats, username):
+    url = "https://argilla.imglab-cdn.net/dibt/dibt_v2.png"
+
+    total_stats = stats["Total Statistics"]
+    top_items = stats["Most Popular Items"]
+
+    text = f"""<span size="12pt" weight="bold">Hugging Face  ❤️ {username} in 2024</span>
+
+<span weight="bold">{total_stats['Model Downloads']:,}</span> model downloads
+<span weight="bold">{total_stats['Model Likes']:,}</span> model likes
+<span weight="bold">{total_stats['Dataset Downloads']:,}</span> dataset downloads
+<span weight="bold">{total_stats['Dataset Likes']:,}</span> dataset likes
+
+<span size="10pt">Most Popular Contributions:</span>
+Model: <span weight="bold">{top_items['Top Model']['name']}</span>
+  ({top_items['Top Model']['downloads']:,} downloads, {top_items['Top Model']['likes']} likes)
+Dataset: <span weight="bold">{top_items['Top Dataset']['name']}</span>
+  ({top_items['Top Dataset']['downloads']:,} downloads, {top_items['Top Dataset']['likes']} likes)
+Space: <span weight="bold">{top_items['Top Space']['name']}</span>
+  ({top_items['Top Space']['likes']} likes)"""
+
+    params = {
+        "width": "1200",
+        "text": text,
+        "text-width": "800",
+        "text-height": "600",
+        "text-padding": "60",
+        "text-color": "39,71,111",
+        "text-x": "460",
+        "text-y": "40",
+        "format": "png",
+        "dpr": "2",
+    }
+
+    return f"{url}?{urlencode(params)}"
+
+
+def get_user_stats(username):
+    headers = {"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"}
+
+    # Get models stats
+    models_response = requests.get(
+        "https://huggingface.co/api/models",
+        params={"author": username, "full": "True"},
+        headers=headers,
+    )
+    models = models_response.json()
+
+    # Get datasets stats
+    datasets_response = requests.get(
+        "https://huggingface.co/api/datasets",
+        params={"author": username, "full": "True"},
+        headers=headers,
+    )
+    datasets = datasets_response.json()
+
+    # Get spaces stats
+    spaces_response = requests.get(
+        "https://huggingface.co/api/spaces",
+        params={"author": username, "full": "True"},
+        headers=headers,
+    )
+    spaces = spaces_response.json()
+
+    # Calculate totals
+    total_model_downloads = sum(model.get("downloads", 0) for model in models)
+    total_model_likes = sum(model.get("likes", 0) for model in models)
+    total_dataset_downloads = sum(dataset.get("downloads", 0) for dataset in datasets)
+    total_dataset_likes = sum(dataset.get("likes", 0) for dataset in datasets)
+    total_space_likes = sum(space.get("likes", 0) for space in spaces)
+
+    # Find most liked items
+    most_liked_model = max(models, key=lambda x: x.get("likes", 0), default=None)
+    most_liked_dataset = max(datasets, key=lambda x: x.get("likes", 0), default=None)
+    most_liked_space = max(spaces, key=lambda x: x.get("likes", 0), default=None)
+
+    stats = {
+        "Total Statistics": {
+            "Model Downloads": total_model_downloads,
+            "Model Likes": total_model_likes,
+            "Dataset Downloads": total_dataset_downloads,
+            "Dataset Likes": total_dataset_likes,
+            "Space Likes": total_space_likes,
+        },
+        "Most Popular Items": {
+            "Top Model": {
+                "name": most_liked_model.get("modelId", "None")
+                if most_liked_model
+                else "None",
+                "likes": most_liked_model.get("likes", 0) if most_liked_model else 0,
+                "downloads": most_liked_model.get("downloads", 0)
+                if most_liked_model
+                else 0,
+            },
+            "Top Dataset": {
+                "name": most_liked_dataset.get("id", "None")
+                if most_liked_dataset
+                else "None",
+                "likes": most_liked_dataset.get("likes", 0)
+                if most_liked_dataset
+                else 0,
+                "downloads": most_liked_dataset.get("downloads", 0)
+                if most_liked_dataset
+                else 0,
+            },
+            "Top Space": {
+                "name": most_liked_space.get("id", "None")
+                if most_liked_space
+                else "None",
+                "likes": most_liked_space.get("likes", 0) if most_liked_space else 0,
+            },
+        },
+    }
+
+    # Generate image URL
+    image_url = create_image(stats, username)
+
+    return image_url
+
+
+with gr.Blocks(title="Hugging Face Community Stats") as demo:
+    gr.Markdown("# Hugging Face Community Recap")
+    gr.Markdown(
+        "Enter a username to see their impact and top contributions across the Hugging Face Hub"
+    )
+
+    with gr.Row():
+        username_input = gr.Textbox(
+            label="Username", placeholder="Enter Hugging Face username...", scale=4
+        )
+        submit_btn = gr.Button("Get Stats", scale=1)
+
+    with gr.Row():
+        with gr.Column():
+            stats_image = gr.Markdown()
+
+    # Add example usernames
+    gr.Examples(
+        examples=[["merve"], ["mlabonne"], ["bartowski"]],
+        inputs=username_input,
+        label="Try these examples",
+    )
+
+    def format_markdown(image_url):
+        return f"![Hugging Face Stats]({image_url})"
+
+    # Handle submission
+    submit_btn.click(
+        fn=lambda x: format_markdown(get_user_stats(x)),
+        inputs=username_input,
+        outputs=stats_image,
+        api_name="get_stats",
+    )
+    # Also trigger on enter key
+    username_input.submit(
+        fn=lambda x: format_markdown(get_user_stats(x)),
+        inputs=username_input,
+        outputs=stats_image,
+    )
+
+if __name__ == "__main__":
+    demo.launch()

pyproject.toml

@@ -0,0 +1,10 @@
+[project]
+name = "hub-recap"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "gradio>=5.9.1",
+    "requests>=2.32.3",
+]

requirements.txt

@@ -0,0 +1,55 @@
+# This file was autogenerated by uv via the following command:
+#    uv export --format requirements-txt --no-hashes
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.7.0
+audioop-lts==0.2.1 ; python_full_version >= '3.13'
+certifi==2024.12.14
+charset-normalizer==3.4.0
+click==8.1.7 ; sys_platform != 'emscripten'
+colorama==0.4.6 ; platform_system == 'Windows'
+fastapi==0.115.6
+ffmpy==0.4.0
+filelock==3.16.1
+fsspec==2024.10.0
+gradio==5.9.1
+gradio-client==1.5.2
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub==0.27.0
+idna==3.10
+jinja2==3.1.4
+markdown-it-py==3.0.0 ; sys_platform != 'emscripten'
+markupsafe==2.1.5
+mdurl==0.1.2 ; sys_platform != 'emscripten'
+numpy==2.2.0
+orjson==3.10.12
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+pydantic==2.10.4
+pydantic-core==2.27.2
+pydub==0.25.1
+pygments==2.18.0 ; sys_platform != 'emscripten'
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2024.2
+pyyaml==6.0.2
+requests==2.32.3
+rich==13.9.4 ; sys_platform != 'emscripten'
+ruff==0.8.3 ; sys_platform != 'emscripten'
+safehttpx==0.1.6
+semantic-version==2.10.0
+shellingham==1.5.4 ; sys_platform != 'emscripten'
+six==1.17.0
+sniffio==1.3.1
+starlette==0.41.3
+tomlkit==0.13.2
+tqdm==4.67.1
+typer==0.15.1 ; sys_platform != 'emscripten'
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.34.0 ; sys_platform != 'emscripten'
+websockets==14.1