add-hub-search

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from datasets import load_dataset, Dataset
 from difflib import ndiff
 import pandas as pd
+from gradio_huggingfacehub_search import HuggingfaceHubSearch
 
 from semhash import SemHash
 from semhash.datamodels import DeduplicationResult
@@ -323,7 +324,12 @@ with gr.Blocks(
     )
 
     with gr.Row():
-        dataset1_name = gr.Textbox(value=default_dataset_name, label="Dataset 1 Name")
+        dataset1_name = HuggingfaceHubSearch(
+            label="Dataset 1 Name",
+            placeholder="Search for datasets on HuggingFace Hub",
+            search_type="dataset",
+            value=default_dataset_name,
+        )
         dataset1_split = gr.Textbox(
             value=default_dataset1_split, label="Dataset 1 Split"
         )
@@ -334,8 +340,11 @@ with gr.Blocks(
     dataset2_inputs = gr.Column(visible=True)
     with dataset2_inputs:
         with gr.Row():
-            dataset2_name = gr.Textbox(
-                value=default_dataset_name, label="Dataset 2 Name"
+            dataset2_name = HuggingfaceHubSearch(
+                label="Dataset 2 Name",
+                placeholder="Search for datasets on HuggingFace Hub",
+                search_type="dataset",
+                value=default_dataset_name,
             )
             dataset2_split = gr.Textbox(
                 value=default_dataset2_split, label="Dataset 2 Split"

pyproject.toml

@@ -6,6 +6,7 @@ readme = "README.md"
 requires-python = ">=3.11"
 dependencies = [
     "datasets>=3.6.0",
+    "gradio-huggingfacehub-search>=0.0.12",
     "gradio[oauth]>=5.32.1",
     "huggingface-hub>=0.32.3",
     "model2vec>=0.5.0",

requirements.txt

@@ -1,8 +1,87 @@
-gradio
-datasets
-semhash
-model2vec
-huggingface_hub
-numpy
-tqdm
-
+# This file was autogenerated by uv via the following command:
+#    uv export --format requirements-txt --no-hashes
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.7
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+attrs==25.3.0
+audioop-lts==0.2.1 ; python_full_version >= '3.13'
+authlib==1.6.0
+certifi==2025.4.26
+cffi==1.17.1 ; platform_python_implementation != 'PyPy'
+charset-normalizer==3.4.2
+click==8.2.1 ; sys_platform != 'emscripten'
+colorama==0.4.6 ; platform_system == 'Windows'
+cryptography==45.0.3
+datasets==3.6.0
+dill==0.3.8
+fastapi==0.115.12
+ffmpy==0.6.0
+filelock==3.18.0
+frozendict==2.4.6
+frozenlist==1.6.0
+fsspec==2025.3.0
+gradio==5.32.1
+gradio-client==1.10.2
+gradio-huggingfacehub-search==0.0.12
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.2 ; platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.32.3
+idna==3.10
+itsdangerous==2.2.0
+jinja2==3.1.6
+joblib==1.5.1
+markdown-it-py==3.0.0
+markupsafe==3.0.2
+mdurl==0.1.2
+model2vec==0.5.0
+multidict==6.4.4
+multiprocess==0.70.16
+numpy==2.2.6
+orjson==3.10.18
+packaging==25.0
+pandas==2.2.3
+pillow==11.2.1
+propcache==0.3.1
+pyarrow==20.0.0
+pycparser==2.22 ; platform_python_implementation != 'PyPy'
+pydantic==2.11.5
+pydantic-core==2.33.2
+pydub==0.25.1
+pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+pyyaml==6.0.2
+requests==2.32.3
+rich==14.0.0
+ruff==0.11.12 ; sys_platform != 'emscripten'
+safehttpx==0.1.6
+safetensors==0.5.3
+semantic-version==2.10.0
+semhash==0.3.0
+setuptools==80.9.0
+shellingham==1.5.4 ; sys_platform != 'emscripten'
+simsimd==6.4.7
+six==1.17.0
+sniffio==1.3.1
+starlette==0.46.2
+tokenizers==0.21.1
+tomlkit==0.13.2
+tqdm==4.67.1
+typer==0.16.0 ; sys_platform != 'emscripten'
+typing-extensions==4.14.0
+typing-inspection==0.4.1
+tzdata==2025.2
+urllib3==2.4.0
+usearch==2.17.8
+uvicorn==0.34.3 ; sys_platform != 'emscripten'
+vicinity==0.4.1
+websockets==15.0.1
+xxhash==3.5.0
+yarl==1.20.0

uv.lock

@@ -582,6 +582,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/9b/1b/b372308c263379ae3ebc440512432979458330113bdee26cef86c89bf48e/gradio_client-1.10.2-py3-none-any.whl", hash = "sha256:6de67b6224123d264c7887caa0586b2a9e2c369ec32ca38927cf8a841694edcd", size = 323311 },
 ]
 
+[[package]]
+name = "gradio-huggingfacehub-search"
+version = "0.0.12"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "gradio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c2/aa/dbe96e59a31fbeacce39eb0a7828109dc3b8d0005a967f30acb48f3395b2/gradio_huggingfacehub_search-0.0.12.tar.gz", hash = "sha256:9da6b7b7c97f2ff8fcfad8d5789a68c79e995e0d39163bccfded422135df7288", size = 1199884 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fc/f6/5aeb2b22a28e7961c2b396e4847c82c634cf139c1a80be697b824ec5e525/gradio_huggingfacehub_search-0.0.12-py3-none-any.whl", hash = "sha256:41d8870fa6b2b715848fcadb5e773eab4da0b9fe431c463a7cce2d616ad8f743", size = 1128435 },
+]
+
 [[package]]
 name = "groovy"
 version = "0.1.2"
@@ -1475,6 +1487,7 @@ source = { virtual = "." }
 dependencies = [
     { name = "datasets" },
     { name = "gradio", extra = ["oauth"] },
+    { name = "gradio-huggingfacehub-search" },
     { name = "huggingface-hub" },
     { name = "model2vec" },
     { name = "numpy" },
@@ -1486,6 +1499,7 @@ dependencies = [
 requires-dist = [
     { name = "datasets", specifier = ">=3.6.0" },
     { name = "gradio", extras = ["oauth"], specifier = ">=5.32.1" },
+    { name = "gradio-huggingfacehub-search", specifier = ">=0.0.12" },
     { name = "huggingface-hub", specifier = ">=0.32.3" },
     { name = "model2vec", specifier = ">=0.5.0" },
     { name = "numpy", specifier = ">=2.2.6" },