Upload 4 files

README.md

@@ -1,8 +1,8 @@
 ---
-title: Finance Commons
+title: Finance Commons Explorer
 emoji: 💻
-colorFrom: purple
-colorTo: green
+colorFrom: red
+colorTo: blue
 sdk: gradio
 sdk_version: 4.38.1
 app_file: app.py

app.py

@@ -0,0 +1,125 @@
+import os
+import re
+
+import gradio as gr
+from huggingface_hub import get_collection
+
+
+def extract_collection_id(input_text):
+    if url_match := re.match(r"https://huggingface\.co/collections/(.+)$", input_text):
+        return url_match[1]
+
+    # Check if input is already in the correct format
+    return input_text if re.match(r"^[\w-]+/[\w-]+", input_text) else None
+
+
+def load_collection():
+    collection_input = os.getenv("COLLECTION_SLUG_OR_URL")
+    if not collection_input:
+        raise ValueError("COLLECTION_SLUG_OR_URL environment variable is not set.")
+
+    collection_id = extract_collection_id(collection_input)
+    if not collection_id:
+        raise ValueError(
+            "Invalid collection ID or URL in COLLECTION_SLUG_OR_URL environment variable."
+        )
+
+    collection = get_collection(collection_id)
+    if dataset_ids := [
+        item.item_id for item in collection.items if item.item_type == "dataset"
+    ]:
+        return dataset_ids, collection_id
+    else:
+        raise ValueError("No datasets found in this collection.")
+
+
+def display_dataset(dataset_ids, index):
+    dataset_id = dataset_ids[index]
+    return gr.HTML(f"""<iframe
+    src="https://huggingface.co/datasets/{dataset_id}/embed/viewer"
+    frameborder="0"
+    width="100%"
+    height="560px"
+></iframe>""")
+
+
+def navigate_dataset(dataset_ids, index, direction):
+    new_index = (index + direction) % len(dataset_ids)
+    return (
+        new_index,
+        f"Dataset {new_index + 1} of {len(dataset_ids)}: {dataset_ids[new_index]}",
+    )
+
+
+def get_display_name(collection_id):
+    # Pattern to match username/repo-name with an optional ID of 16 or more hexadecimal characters
+    pattern = r"^(.+?)-([a-f0-9]{16,})$"
+    if match := re.match(pattern, collection_id):
+        return match[1]
+    else:
+        # If no match, return the original
+        return collection_id
+
+
+try:
+    dataset_ids, collection_id = load_collection()
+    display_name = get_display_name(collection_id)
+
+    with gr.Blocks() as demo:
+        gr.Markdown(f"<h1>Dataset Viewer for Collection: {display_name}</h1>")
+        gr.Markdown(
+            f"[View full collection on Hugging Face](https://huggingface.co/collections/{collection_id})"
+        )
+
+        gr.Markdown("""
+        This app allows you to browse and view datasets from a specific Hugging Face collection. 
+        Use the 'Previous' and 'Next' buttons to navigate through the datasets in the collection. 
+        See below for how to set up this app for a different collection.""")
+
+        index_state = gr.State(value=0)
+
+        with gr.Row():
+            left_btn = gr.Button("Previous")
+            right_btn = gr.Button("Next")
+
+        dataset_info = gr.Markdown(f"Dataset 1 of {len(dataset_ids)}: {dataset_ids[0]}")
+        iframe_output = gr.HTML()
+        gr.Markdown("""**Note**: This space is currently set up to display datasets from a specific collection. 
+        If you'd like to use it for a different collection:
+        1. Duplicate this space
+        2. In your duplicated space, set the `COLLECTION_SLUG_OR_URL` environment variable to your desired collection ID or URL
+        3. Your new space will then display datasets from your chosen collection!
+        Checkout the [docs](https://huggingface.co/docs/hub/datasets-viewer-embed) for other ways to use the iframe viewer.
+        """)
+        left_btn.click(
+            navigate_dataset,
+            inputs=[gr.State(dataset_ids), index_state, gr.Number(-1, visible=False)],
+            outputs=[index_state, dataset_info],
+        )
+        right_btn.click(
+            navigate_dataset,
+            inputs=[gr.State(dataset_ids), index_state, gr.Number(1, visible=False)],
+            outputs=[index_state, dataset_info],
+        )
+
+        index_state.change(
+            display_dataset,
+            inputs=[gr.State(dataset_ids), index_state],
+            outputs=[iframe_output],
+        )
+
+        # Initialize the display with the first dataset
+        demo.load(
+            fn=lambda: display_dataset(dataset_ids, 0),
+            inputs=None,
+            outputs=[iframe_output],
+        )
+
+    if __name__ == "__main__":
+        demo.launch()
+
+except Exception as e:
+    print(f"Error: {str(e)}")
+    print(
+        "Please set the COLLECTION_SLUG_OR_URL environment variable with a valid collection ID or URL."
+    )

requirements.in

@@ -0,0 +1,2 @@
+huggingface_hub
+gradio==4.38.1

requirements.txt

@@ -0,0 +1,217 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile requirements.in -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+altair==5.3.0
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.4.0
+    # via
+    #   httpx
+    #   starlette
+    #   watchfiles
+attrs==23.2.0
+    # via
+    #   jsonschema
+    #   referencing
+certifi==2024.7.4
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via
+    #   typer
+    #   uvicorn
+contourpy==1.2.1
+    # via matplotlib
+cycler==0.12.1
+    # via matplotlib
+dnspython==2.6.1
+    # via email-validator
+email-validator==2.2.0
+    # via fastapi
+fastapi==0.111.1
+    # via gradio
+fastapi-cli==0.0.4
+    # via fastapi
+ffmpy==0.3.2
+    # via gradio
+filelock==3.15.4
+    # via huggingface-hub
+fonttools==4.53.1
+    # via matplotlib
+fsspec==2024.6.1
+    # via
+    #   gradio-client
+    #   huggingface-hub
+gradio==4.38.1
+    # via -r requirements.in
+gradio-client==1.1.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.5
+    # via httpx
+httptools==0.6.1
+    # via uvicorn
+httpx==0.27.0
+    # via
+    #   fastapi
+    #   gradio
+    #   gradio-client
+huggingface-hub==0.23.5
+    # via
+    #   -r requirements.in
+    #   gradio
+    #   gradio-client
+idna==3.7
+    # via
+    #   anyio
+    #   email-validator
+    #   httpx
+    #   requests
+importlib-resources==6.4.0
+    # via gradio
+jinja2==3.1.4
+    # via
+    #   altair
+    #   fastapi
+    #   gradio
+jsonschema==4.23.0
+    # via altair
+jsonschema-specifications==2023.12.1
+    # via jsonschema
+kiwisolver==1.4.5
+    # via matplotlib
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.9.1
+    # via gradio
+mdurl==0.1.2
+    # via markdown-it-py
+numpy==2.0.0
+    # via
+    #   altair
+    #   contourpy
+    #   gradio
+    #   matplotlib
+    #   pandas
+orjson==3.10.6
+    # via gradio
+packaging==24.1
+    # via
+    #   altair
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+pandas==2.2.2
+    # via
+    #   altair
+    #   gradio
+pillow==10.4.0
+    # via
+    #   gradio
+    #   matplotlib
+pydantic==2.8.2
+    # via
+    #   fastapi
+    #   gradio
+pydantic-core==2.20.1
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+pyparsing==3.1.2
+    # via matplotlib
+python-dateutil==2.9.0.post0
+    # via
+    #   matplotlib
+    #   pandas
+python-dotenv==1.0.1
+    # via uvicorn
+python-multipart==0.0.9
+    # via
+    #   fastapi
+    #   gradio
+pytz==2024.1
+    # via pandas
+pyyaml==6.0.1
+    # via
+    #   gradio
+    #   huggingface-hub
+    #   uvicorn
+referencing==0.35.1
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+requests==2.32.3
+    # via huggingface-hub
+rich==13.7.1
+    # via typer
+rpds-py==0.19.0
+    # via
+    #   jsonschema
+    #   referencing
+ruff==0.5.2
+    # via gradio
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+starlette==0.37.2
+    # via fastapi
+tomlkit==0.12.0
+    # via gradio
+toolz==0.12.1
+    # via altair
+tqdm==4.66.4
+    # via huggingface-hub
+typer==0.12.3
+    # via
+    #   fastapi-cli
+    #   gradio
+typing-extensions==4.12.2
+    # via
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   typer
+tzdata==2024.1
+    # via pandas
+urllib3==2.2.2
+    # via
+    #   gradio
+    #   requests
+uvicorn==0.30.1
+    # via
+    #   fastapi
+    #   gradio
+uvloop==0.19.0
+    # via uvicorn
+watchfiles==0.22.0
+    # via uvicorn
+websockets==11.0.3
+    # via
+    #   gradio-client
+    #   uvicorn