adqwe

app.py

@@ -1,66 +1,50 @@
+import re
 import gradio as gr
-from typing import Union, Dict, Any, List
 
-# Sample pre-calculated entities
-sample_text = (
-    "Recent studies on ocean currents from the Global Ocean Temperature Dataset "
-    "(GOTD) indicate significant shifts in marine biodiversity."
-)
-sample_entities = [
-    {"label": "named dataset", "text": "Global Ocean Temperature Dataset", "start": 29, "end": 62, "score": 0.99},
-    {"label": "acronym", "text": "GOTD", "start": 64, "end": 68, "score": 0.98},
-]
-rels = [
-    'acronym', 'author', 'data description',
-    'data geography', 'data source', 'data type',
-    'publication year', 'publisher', 'reference year', 'version'
-]
-MODELS = ["demo-model-1", "demo-model-2"]
+# A simulated GLiNER output mapping for demonstration:
+SIMULATED_ENTITIES = {
+    "Household Survey Data": "named dataset",
+    "Ethiopia": "data geography",
+    "2020": "reference year",
+    "World Bank": "publisher"
+}
 
-# Annotate_query simulation
+def highlight_text(text):
+    """
+    Simulate GLiNER entity extraction by looking for a few known phrases
+    and returning start/end spans + labels.
+    """
+    entities = []
+    for phrase, label in SIMULATED_ENTITIES.items():
+        for match in re.finditer(re.escape(phrase), text):
+            entities.append({
+                "start": match.start(),
+                "end": match.end(),
+                "label": label
+            })
+    # Return in the format gr.HighlightedText expects:
+    return {"text": text, "entities": entities}
 
-def annotate_query(
-    query: str,
-    labels: Union[str, List[str]],
-    threshold: float = 0.3,
-    nested_ner: bool = False,
-    model_name: str = None
-) -> Dict[str, Any]:
-    # In a real app, you'd call parse_query/inference_pipeline here.
-    # For simulation, reuse sample_entities.
-    return {
-        "text": query,
-        "entities": [
-            {"start": ent["start"], "end": ent["end"], "label": ent["label"]}
-            for ent in sample_entities
-        ]
-    }
-
-# Build Gradio UI
-demo = gr.Blocks()
-with demo:
-    gr.Markdown(
-        """
-        ## Step: Annotate Query Simulation
-        Enter text (prepopulated) and click **Annotate** to see how entities are highlighted.
-        """
-    )
-    # Inputs
-    query = gr.Textbox(lines=3, value=sample_text, label="Input Text")
-    entities = gr.Textbox(value=", ".join(rels), label="Relations (unused in simulation)")
-    threshold = gr.Slider(0, 1, value=0.3, step=0.01, label="Threshold")
-    nested = gr.Checkbox(value=False, label="Nested NER")
-    model = gr.Radio(choices=MODELS, value=MODELS[0], label="Model")
-
-    # Outputs
-    output_hl = gr.HighlightedText(label="Annotated Entities")
-
-    # Button
-    annotate_btn = gr.Button("Annotate")
-    annotate_btn.click(
-        fn=annotate_query,
-        inputs=[query, entities, threshold, nested, model],
-        outputs=[output_hl]
+# Build the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("## Simulated GLiNER Entity Highlighter\n"
+                "Enter any sentence (or use the default) and see simulated entity highlights.")
+    text_input = gr.Textbox(
+        label="Input Text",
+        lines=3,
+        value="The Household Survey Data for Ethiopia in 2020 was published by the World Bank."
     )
+    highlighted = gr.HighlightedText(label="Highlighted Entities")
+    # Trigger highlighting whenever the text changes
+    text_input.change(fn=highlight_text, inputs=text_input, outputs=highlighted)
+    
+    gr.Markdown("""
+**Entity legend**  
+- **named dataset**: Household Survey Data  
+- **data geography**: Ethiopia  
+- **reference year**: 2020  
+- **publisher**: World Bank
+""")
 
-demo.launch(debug=True)
+if __name__ == "__main__":
+    demo.launch()