add basic querying with duckdb

app.py

@@ -1,14 +1,51 @@
+from gradio_huggingfacehub_search import HuggingfaceHubSearch
+from huggingface_hub import HfApi
+import pandas as pd
 import gradio as gr
-import spaces
-import torch
+import duckdb
+import requests
 
-zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+BASE_DATASETS_SERVER_URL = "https://datasets-server.huggingface.co"
 
-@spaces.GPU
-def greet(n):
-    print(zero.device) # <-- 'cuda:0' 🤗
-    return f"Hello {zero + n} Tensor"
+hf_api = HfApi()
+conn = duckdb.connect()
 
-demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
-demo.launch()
+
+def query_dataset(dataset_id: str, query: str) -> pd.DataFrame:
+    response = requests.get(f"{BASE_DATASETS_SERVER_URL}/parquet?dataset={dataset_id}")
+    response.raise_for_status()  # Check if the request was successful
+
+    first_parquet = response.json().get("parquet_files", [])[0]
+    first_parquet_url = first_parquet.get("url")
+
+    if not first_parquet_url:
+        raise ValueError("No valid URL found for the first parquet file.")
+
+    sql_query = f"SELECT * FROM read_parquet('{first_parquet_url}') limit 100;"
+
+    df = conn.execute(sql_query).fetchdf()
+    return df
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Query your HF Datasets with Natural Language 📈📊")
+    dataset_name = HuggingfaceHubSearch(
+        label="Hub Dataset ID",
+        placeholder="Find your favorite dataset...",
+        search_type="dataset",
+        value="jamescalam/world-cities-geo",
+    )
+    query_input = gr.Textbox("", label="Ask anything...")
+
+    btn = gr.Button("Ask 🪄")
+    df = gr.DataFrame(datatype="markdown")
+
+    btn.click(
+        query_dataset,
+        inputs=[dataset_name, query_input],
+        outputs=[df],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,83 @@
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+attrs==23.2.0
+certifi==2024.6.2
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+diskcache==5.6.3
+dnspython==2.6.1
+duckdb==1.0.0
+email_validator==2.1.1
+exceptiongroup==1.2.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.14.0
+fonttools==4.53.0
+fsspec==2024.6.0
+gradio==4.32.2
+gradio_client==0.17.0
+gradio_huggingfacehub_search==0.0.7
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.2
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+llama_cpp_python==0.2.77
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==1.26.4
+orjson==3.10.3
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+psutil==5.9.8
+pydantic==2.7.3
+pydantic_core==2.18.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+requests==2.32.3
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.7
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+spaces==0.28.3
+starlette==0.37.2
+sympy==1.12.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.3.0
+tqdm==4.66.4
+typer==0.12.3
+typing_extensions==4.12.1
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.1
+uvicorn==0.30.1
+uvloop==0.19.0
+watchfiles==0.22.0
+websockets==11.0.3