Create app.py

app.py

@@ -0,0 +1,71 @@
+import gradio as gr
+import os
+from transformers import pipeline
+
+print("Booting up PredictiX Inference API...")
+
+# 1. Load Ticket Categorization Model (From local folder)
+try:
+    cat_path = "./distilbert_category_model"
+    model_id = cat_path if os.path.exists(cat_path) else "Dinusha-Ekanayake/predictix-ticket_categorization_model"
+    categorizer = pipeline("text-classification", model=model_id, top_k=None)
+except Exception as e:
+    categorizer = None
+    print(f"Failed to load categorizer: {e}")
+
+# 2. Load Ticket Summarization Model (From local folder)
+try:
+    sum_path = "./predictix-ticket_summarization_model"
+    model_id = sum_path if os.path.exists(sum_path) else "Dinusha-Ekanayake/predictix-ticket_summarization_model"
+    ticket_summarizer = pipeline("summarization", model=model_id)
+except Exception as e:
+    ticket_summarizer = None
+    print(f"Failed to load ticket summarizer: {e}")
+
+# 3. Load Asset Summarization Model (From Hub)
+try:
+    asset_summarizer = pipeline("summarization", model="Dinusha-Ekanayake/predictix-asset_summarization_model")
+except Exception as e:
+    asset_summarizer = None
+    print(f"Failed to load asset summarizer: {e}")
+
+# --- API Functions ---
+def categorize(text):
+    if not categorizer: return {"error": "Categorization model not loaded."}
+    return categorizer(text)
+
+def summarize_ticket(text):
+    if not ticket_summarizer: return {"error": "Ticket Summarization model not loaded."}
+    res = ticket_summarizer(text, min_length=15, max_length=150)
+    return {"summary": res[0]["summary_text"]}
+
+def summarize_asset(text):
+    if not asset_summarizer: return {"error": "Asset Summarization model not loaded."}
+    res = asset_summarizer(text, min_length=20, max_length=150)
+    return {"summary": res[0]["summary_text"]}
+
+# --- Server API Interface ---
+with gr.Blocks(title="PredictiX API") as demo:
+    gr.Markdown("# PredictiX Internal Inference Server 🚀")
+    gr.Markdown("This space holds the models in RAM and exposes them via REST API to the PredictiX backend.")
+    
+    with gr.Tab("Ticket Categorization"):
+        cat_in = gr.Textbox(label="Ticket Title & Description")
+        cat_out = gr.JSON(label="Categorization Result")
+        cat_btn = gr.Button("Categorize")
+        cat_btn.click(categorize, inputs=cat_in, outputs=cat_out, api_name="categorize")
+        
+    with gr.Tab("Ticket Summarization"):
+        ts_in = gr.Textbox(label="Ticket Details")
+        ts_out = gr.JSON(label="Summary")
+        ts_btn = gr.Button("Summarize Ticket")
+        ts_btn.click(summarize_ticket, inputs=ts_in, outputs=ts_out, api_name="summarize_ticket")
+        
+    with gr.Tab("Asset Summarization"):
+        as_in = gr.Textbox(label="Asset Details")
+        as_out = gr.JSON(label="Summary")
+        as_btn = gr.Button("Summarize Asset")
+        as_btn.click(summarize_asset, inputs=as_in, outputs=as_out, api_name="summarize_asset")
+
+if __name__ == "__main__":
+    demo.launch()