Add sample explorer app

README.md

@@ -1,13 +1,19 @@
 ---
-title: Suppdb Sample Explorer
-emoji: 🌍
-colorFrom: indigo
-colorTo: green
+title: SuppDB Supplements Sample Explorer
+emoji: 💊
+colorFrom: green
+colorTo: blue
 sdk: gradio
-sdk_version: 6.19.0
-python_version: '3.13'
+sdk_version: 5.9.0
 app_file: app.py
 pinned: false
+license: cc-by-nc-4.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 💊 SuppDB — Supplements & Nootropics Sample Explorer
+
+Interactively explore the free sample of [SuppDB](https://supplements-nootropics-suppdb.pages.dev): real supplement labels from the NIH DSLD, one row per active ingredient, with mg-normalized doses, proprietary-blend flags, and PubChem chemistry.
+
+Data: [free sample dataset](https://huggingface.co/datasets/Ichlibitiche/suppdb-supplements-sample) (2,249 ingredient records, 300 products, 218 brands). The full dataset (17,000+ products, 115,000+ ingredient records) is available at [suppdb.net](https://supplements-nootropics-suppdb.pages.dev).
+
+Sample data © SuppDB, CC BY-NC 4.0. Not medical advice.

app.py

@@ -0,0 +1,91 @@
+import gradio as gr
+import pandas as pd
+
+# Load the free sample directly from the public Hugging Face dataset
+DATA_URL = "hf://datasets/Ichlibitiche/suppdb-supplements-sample/suppdb_sample.csv"
+df = pd.read_csv(DATA_URL)
+
+DISPLAY_COLS = {
+    "brand": "Brand",
+    "product_name": "Product",
+    "form_type": "Form",
+    "ingredient": "Ingredient",
+    "ingredient_form": "Ingredient Form",
+    "ingredient_category": "Category",
+    "amount_per_serving_mg": "Dose (mg/serving)",
+    "is_proprietary_blend": "Hidden in Blend",
+    "recommended_daily_mg": "NIH RDA (mg)",
+    "upper_safety_limit_mg": "Upper Limit (mg)",
+    "molecular_formula": "Formula",
+    "source_url": "NIH DSLD Label",
+}
+
+BLEND_FILTERS = [
+    "All",
+    "Disclosed doses only",
+    "Proprietary-blend (hidden dose) only",
+]
+
+def choices(col):
+    vals = df[col].dropna().astype(str)
+    return ["All"] + sorted(v for v in vals.unique() if v.strip())
+
+def explore(ingredient_query, brand, category, form, blend_filter):
+    d = df
+    if ingredient_query and ingredient_query.strip():
+        q = ingredient_query.strip()
+        hit = (
+            d["ingredient"].fillna("").str.contains(q, case=False, regex=False)
+            | d["product_name"].fillna("").str.contains(q, case=False, regex=False)
+        )
+        d = d[hit]
+    if brand != "All":
+        d = d[d["brand"] == brand]
+    if category != "All":
+        d = d[d["ingredient_category"] == category]
+    if form != "All":
+        d = d[d["form_type"] == form]
+    if blend_filter == "Disclosed doses only":
+        d = d[d["is_proprietary_blend"] == 0]
+    elif blend_filter == "Proprietary-blend (hidden dose) only":
+        d = d[d["is_proprietary_blend"] == 1]
+
+    summary = (
+        f"**{len(d)} ingredient records** across **{d['product_id'].nunique()} products** "
+        f"from **{d['brand'].nunique()} brands** match — out of {len(df)} records in the free sample. "
+        f"The full SuppDB has **115,000+ ingredient records across 17,000+ products**."
+    )
+    return summary, d[list(DISPLAY_COLS)].rename(columns=DISPLAY_COLS)
+
+with gr.Blocks(title="SuppDB Sample Explorer") as demo:
+    gr.Markdown("# 💊 SuppDB: Supplements & Nootropics Sample Explorer")
+    gr.Markdown(f"""Explore **{len(df)} active-ingredient records from {df['product_id'].nunique()} real supplement products ({df['brand'].nunique()} brands)** — NIH DSLD labels with **mg-normalized doses**, **proprietary-blend transparency**, and **PubChem chemistry**.
+
+---
+### 🌐 This is the free sample. The full SuppDB has 17,000+ products and 115,000+ ingredient records.
+* **🔗 Official Portal (full dataset, $99 snapshot):** [suppdb.net](https://supplements-nootropics-suppdb.pages.dev)
+* **🤗 Free Sample Dataset (Download CSV):** [Ichlibitiche/suppdb-supplements-sample](https://huggingface.co/datasets/Ichlibitiche/suppdb-supplements-sample)
+* **🏆 Kaggle Dataset:** [SuppDB Supplements Sample](https://www.kaggle.com/datasets/ahtiticheamine/suppdb-supplements-sample)
+---""")
+
+    with gr.Row():
+        query_tb = gr.Textbox(label="Ingredient / Product Search", placeholder="e.g. Magnesium, Ashwagandha, Vitamin D...")
+        brand_dd = gr.Dropdown(choices=choices("brand"), value="All", label="Brand")
+    with gr.Row():
+        category_dd = gr.Dropdown(choices=choices("ingredient_category"), value="All", label="Ingredient Category")
+        form_dd = gr.Dropdown(choices=choices("form_type"), value="All", label="Product Form")
+        blend_dd = gr.Dropdown(choices=BLEND_FILTERS, value="All", label="Proprietary-Blend Transparency")
+
+    btn = gr.Button("Explore Supplements", variant="primary")
+
+    out_text = gr.Markdown()
+    out_table = gr.Dataframe(label="Matching Ingredient Records", wrap=True)
+
+    inputs = [query_tb, brand_dd, category_dd, form_dd, blend_dd]
+    btn.click(fn=explore, inputs=inputs, outputs=[out_text, out_table])
+    demo.load(fn=explore, inputs=inputs, outputs=[out_text, out_table])
+
+    gr.Markdown("""---
+*Sample data © SuppDB under CC BY-NC 4.0 — factual label data, not medical advice. Full dataset commercially licensed at [suppdb.net](https://supplements-nootropics-suppdb.pages.dev) · contact suppdb.doorframe589@simplelogin.com*""")
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+huggingface_hub