Upload 34 files

app.py

@@ -427,10 +427,17 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), css=CUSTOM_CSS, title="
 
     with gr.Tab("💬 AI Assistant"):
         gr.HTML(data_badge(
-            "🧪 <b>You are testing:</b> an LLM chatbot grounded in a 10-article synthetic "
-            "warehouse-ops knowledge base (RAG), routed by an intent classifier trained on "
-            "~480 synthetic queries. <b>Data type:</b> hand-written knowledge articles + "
-            "template-generated questions — not real Daifuku data."
+            "🧪 <b>Source:</b> hand-written by the developer — 10 original knowledge-base "
+            "articles on warehouse operations (AS/RS, AGV/AMR, WMS, sortation, picking, "
+            "maintenance, safety) plus ~480 template-generated example queries. Not scraped "
+            "or sourced from Daifuku or any real company.<br>"
+            "<b>What it describes:</b> generic intralogistics/automation concepts and "
+            "operational scenarios (equipment faults, safety incidents, order/inventory "
+            "questions) — general domain knowledge, not any specific facility's live data.<br>"
+            "<b>Function:</b> answers free-text warehouse-ops questions by first classifying "
+            "the query's intent, retrieving the most relevant knowledge-base passage(s) "
+            "(RAG), then generating a grounded answer with a hosted LLM — falling back to "
+            "showing the retrieved passages directly if no LLM is available."
         ))
         gr.ChatInterface(
             fn=chat_fn,
@@ -451,10 +458,18 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), css=CUSTOM_CSS, title="
 
     with gr.Tab("📦 Inventory & Order Query"):
         gr.HTML(data_badge(
-            f"🧪 <b>You are testing:</b> NL→structured-query search over "
-            f"{len(inventory_df)} synthetic SKUs and {len(orders_df)} synthetic orders. "
-            "<b>Data type:</b> randomly generated inventory/order records (fixed seed, "
-            "reproducible) — a stand-in for a live WMS, not real warehouse data."
+            f"🧪 <b>Source:</b> randomly generated by the developer's code "
+            f"(`src/data_generation.py`, fixed seed) — {len(inventory_df)} synthetic SKU "
+            f"records and {len(orders_df)} synthetic orders. Not exported from Daifuku or "
+            "any real WMS.<br>"
+            "<b>What it describes:</b> a stand-in inventory table (SKU, category, zone, "
+            "on-hand units, reorder point, unit cost) and orders table (order ID, status, "
+            "line count, priority, zone) — realistic in shape and ranges, but fictional "
+            "records, not live warehouse data.<br>"
+            "<b>Function:</b> classifies whether a query is about inventory or order status, "
+            "extracts SKU/order-ID/zone identifiers with regex, and filters the "
+            "corresponding table — a lightweight stand-in for a natural-language WMS query "
+            "tool."
         ))
         with gr.Row():
             inv_input = gr.Textbox(label="Query", placeholder="How many units of SKU-1042 are in Zone B?", scale=4)
@@ -481,10 +496,17 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), css=CUSTOM_CSS, title="
 
     with gr.Tab("⚠️ Predictive Maintenance"):
         gr.HTML(data_badge(
-            "🧪 <b>You are testing:</b> an Isolation Forest anomaly detector for conveyor/"
-            "crane motor sensors. <b>Data type:</b> 1,000 synthetic sensor readings (900 "
-            "normal + 100 simulated-fault) across temperature, vibration, current, and belt "
-            "speed — trained unsupervised, not on real Daifuku equipment telemetry."
+            "🧪 <b>Source:</b> randomly generated by the developer's code "
+            "(`src/data_generation.py`, fixed seed) — 1,000 synthetic sensor readings "
+            "(900 normal + 100 simulated-fault). Not logged from real Daifuku equipment.<br>"
+            "<b>What it describes:</b> conveyor/crane motor sensor readings — temperature, "
+            "vibration, current draw, and belt speed — with the 'anomaly' readings modelled "
+            "on realistic failure signatures (elevated temp/vibration/current with reduced "
+            "belt speed, as seen with bearing wear or motor overload).<br>"
+            "<b>Function:</b> an Isolation Forest model trained unsupervised (it never sees "
+            "an anomaly label) learns what 'normal' sensor behaviour looks like, then flags "
+            "any new reading — like the ones you enter below — that deviates from it, as an "
+            "early-warning signal before an unplanned equipment stoppage."
         ))
         preset_dropdown = gr.Dropdown(
             choices=list(ANOMALY_PRESETS.keys()), label="Load a preset reading", value="Normal reading"
@@ -552,4 +574,4 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), css=CUSTOM_CSS, title="
 
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860)))
+    demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860)))