Add organic reactions search app with Gradio interface

README.md

@@ -10,4 +10,32 @@ pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Organic Reactions Search
+
+This is a Gradio-based web app for searching the organic reactions dataset from Hugging Face.
+
+## Dataset
+
+The dataset used is `smitathkr1/organic_reactions_enhanced`, which contains information about various organic reactions including names, reactants, products, conditions, mechanisms, and descriptions.
+
+## Features
+
+- **Search by Reaction Name**: Enter a reaction name to get details
+- **Search by Reactant**: Find reactions that use a specific reactant
+- **Search by Product**: Find reactions that produce a specific product
+- **Autocomplete**: Get suggestions for reaction names, reactants, and products
+
+## Performance
+
+The dataset is loaded into memory using pandas for fast searches. With only 828 entries, all operations are sub-second.
+
+## Local Development
+
+To run locally:
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+The app will launch in your browser.

app.py

@@ -0,0 +1,118 @@
+import gradio as gr
+import pandas as pd
+from datasets import load_dataset
+from fuzzywuzzy import process
+
+# Load dataset
+ds = load_dataset("smitathkr1/organic_reactions_enhanced")
+df = ds['train'].to_pandas()
+
+# Precompute unique values for autocomplete
+reaction_names = df['name'].unique().tolist()
+all_reactants = []
+all_products = []
+
+for _, row in df.iterrows():
+    all_reactants.extend(row['reactants'])
+    all_products.extend(row['products'])
+
+unique_reactants = list(set(all_reactants))
+unique_products = list(set(all_products))
+
+def search_by_reaction_name(query):
+    if not query:
+        return "Please enter a reaction name."
+    # Exact match first
+    result = df[df['name'].str.lower() == query.lower()]
+    if not result.empty:
+        row = result.iloc[0]
+        return f"**{row['name']}**\n\n**Reactants:** {', '.join(row['reactants'])}\n\n**Products:** {', '.join(row['products'])}\n\n**Description:** {row['description'][:500]}..."
+    # Fuzzy match
+    matches = process.extract(query, reaction_names, limit=1)
+    if matches and matches[0][1] > 80:
+        best_match = matches[0][0]
+        result = df[df['name'] == best_match]
+        row = result.iloc[0]
+        return f"**{row['name']}** (closest match)\n\n**Reactants:** {', '.join(row['reactants'])}\n\n**Products:** {', '.join(row['products'])}\n\n**Description:** {row['description'][:500]}..."
+    return "No matching reaction found."
+
+def search_by_reactant(reactant):
+    if not reactant:
+        return "Please enter a reactant."
+    matches = df[df['reactants'].apply(lambda x: reactant.lower() in [r.lower() for r in x])]
+    if not matches.empty:
+        results = []
+        for _, row in matches.head(5).iterrows():
+            results.append(f"**{row['name']}**: {', '.join(row['reactants'])} → {', '.join(row['products'])}")
+        return "\n\n".join(results)
+    return "No reactions found with that reactant."
+
+def search_by_product(product):
+    if not product:
+        return "Please enter a product."
+    matches = df[df['products'].apply(lambda x: product.lower() in [p.lower() for p in x])]
+    if not matches.empty:
+        results = []
+        for _, row in matches.head(5).iterrows():
+            results.append(f"**{row['name']}**: {', '.join(row['reactants'])} → {', '.join(row['products'])}")
+        return "\n\n".join(results)
+    return "No reactions found with that product."
+
+def get_autocomplete_reactions(query):
+    if not query:
+        return reaction_names[:10]
+    matches = process.extract(query, reaction_names, limit=10)
+    return [m[0] for m in matches if m[1] > 60]
+
+def get_autocomplete_reactants(query):
+    if not query:
+        return unique_reactants[:10]
+    matches = process.extract(query, unique_reactants, limit=10)
+    return [m[0] for m in matches if m[1] > 60]
+
+def get_autocomplete_products(query):
+    if not query:
+        return unique_products[:10]
+    matches = process.extract(query, unique_products, limit=10)
+    return [m[0] for m in matches if m[1] > 60]
+
+with gr.Blocks(title="Organic Reactions Search") as demo:
+    gr.Markdown("# Organic Reactions Search API")
+    gr.Markdown("Search through the organic reactions dataset by name, reactant, or product.")
+
+    with gr.Tab("Search by Reaction Name"):
+        reaction_input = gr.Textbox(label="Reaction Name", placeholder="e.g., appel-reaction")
+        reaction_output = gr.Markdown(label="Result")
+        reaction_btn = gr.Button("Search")
+        reaction_btn.click(search_by_reaction_name, inputs=reaction_input, outputs=reaction_output)
+
+    with gr.Tab("Search by Reactant"):
+        reactant_input = gr.Textbox(label="Reactant", placeholder="e.g., alcohol")
+        reactant_output = gr.Markdown(label="Results")
+        reactant_btn = gr.Button("Search")
+        reactant_btn.click(search_by_reactant, inputs=reactant_input, outputs=reactant_output)
+
+    with gr.Tab("Search by Product"):
+        product_input = gr.Textbox(label="Product", placeholder="e.g., ester")
+        product_output = gr.Markdown(label="Results")
+        product_btn = gr.Button("Search")
+        product_btn.click(search_by_product, inputs=product_input, outputs=product_output)
+
+    with gr.Tab("Autocomplete"):
+        gr.Markdown("### Reaction Names")
+        reaction_query = gr.Textbox(label="Query")
+        reaction_suggestions = gr.Textbox(label="Suggestions", lines=5, interactive=False)
+        reaction_query.change(get_autocomplete_reactions, inputs=reaction_query, outputs=reaction_suggestions)
+
+        gr.Markdown("### Reactants")
+        reactant_query = gr.Textbox(label="Query")
+        reactant_suggestions = gr.Textbox(label="Suggestions", lines=5, interactive=False)
+        reactant_query.change(get_autocomplete_reactants, inputs=reactant_query, outputs=reactant_suggestions)
+
+        gr.Markdown("### Products")
+        product_query = gr.Textbox(label="Query")
+        product_suggestions = gr.Textbox(label="Suggestions", lines=5, interactive=False)
+        product_query.change(get_autocomplete_products, inputs=product_query, outputs=product_suggestions)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+datasets
+pandas
+gradio
+fuzzywuzzy
+python-levenshtein