Upload 3 files

README.md

@@ -25,7 +25,7 @@ Zero-shot image classification for medical imagery powered by **google/medsiglip
 - Smart Modality Router v2 blends filename heuristics, simple color statistics, and a lightweight fallback classifier to choose the best label bank.
 - CT, Ultrasound, Musculoskeletal, chest X-ray, brain MRI, fundus, histopathology, skin, cardiovascular, and general label libraries curated from MedSigLIP prompts and clinical references.
 - CPU-optimized inference with single model load, float32 execution on CPU, capped torch threads, cached results, and batched label scoring.
-- Gradio interface ready for local execution or deployment to Hugging Face Spaces (verified on Gradio 4.44.1+).
+- Gradio interface ready for local execution or deployment to Hugging Face Spaces (verified on Gradio 4.44.1+, API disabled by default to avoid schema bugs).
 
 
 ## Project Structure
@@ -115,7 +115,7 @@ Each label file contains 100-200 modality-specific diagnostic phrases reflecting
 1. Create a new Space (Gradio template) named `medsiglip-smart-filter`.
 2. Push the project files to the Space repository (via `git` or the web UI).
 3. In **Settings -> Repository Secrets**, add `HF_TOKEN` with your Hugging Face access token so the model and auxiliary router weights can be downloaded during build.
-4. The default `python app.py` launch serves the Gradio interface at `https://<space-name>.hf.space`.
+4. The default `python app.py` launch honors `SERVER_PORT`, `SERVER_NAME`, and `GRADIO_SHARE` if set by the Space runner.
 
 
 ## Model Reference Update

app.py

@@ -81,8 +81,18 @@ demo = gr.Interface(
     outputs=gr.Label(num_top_classes=5, label="🧠 Top Predictions"),
     title="🩻 MedSigLIP Smart Medical Classifier",
     description="Zero-shot model with automatic label filtering for different modalities.",
+    allow_api=False,
 )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    server_name = os.getenv("SERVER_NAME", "0.0.0.0")
+    port_env = os.getenv("SERVER_PORT") or os.getenv("PORT") or "7860"
+    share_env = os.getenv("GRADIO_SHARE", "false").lower()
+
+    demo.launch(
+        server_name=server_name,
+        server_port=int(port_env),
+        share=share_env in {"1", "true", "yes"},
+        show_api=False,
+    )