use ner and rel

app.py

@@ -1,19 +1,31 @@
 import re
 import gradio as gr
 
-# Your actual GLiNER predictions
-SIM_ENTITIES = {
-    "Home Visits Survey":                       "named dataset",
-    "Jordan":                                    "data geography",
-    "Round II":                                  "version",
-    "HV":                                        "acronym",
-    "UNHCR":                                     "author",
-    "World Food Programme":                      "author",
-    "2013":                                      "reference year",
-    "2014":                                      "publication year",
-    "detailed socio-economic, health, and protection data": "data description",
+# Your actual model outputs:
+ner = [
+    {
+        'start': 12,
+        'end': 30,
+        'text': 'Home Visits Survey',
+        'label': 'named dataset',
+        'score': 0.9947463870048523
+    }
+]
+
+relations = {
+    'Home Visits Survey': [
+        {'source': 'Home Visits Survey', 'relation': 'data geography',   'target': 'Jordan',                                        'score': 0.6180844902992249},
+        {'source': 'Home Visits Survey', 'relation': 'version',            'target': 'Round II',                                     'score': 0.9688164591789246},
+        {'source': 'Home Visits Survey', 'relation': 'acronym',            'target': 'HV',                                           'score': 0.9140607714653015},
+        {'source': 'Home Visits Survey', 'relation': 'author',             'target': 'UNHCR',                                       'score': 0.7762154340744019},
+        {'source': 'Home Visits Survey', 'relation': 'author',             'target': 'World Food Programme',                        'score': 0.6582539677619934},
+        {'source': 'Home Visits Survey', 'relation': 'reference year',     'target': '2013',                                        'score': 0.524115264415741},
+        {'source': 'Home Visits Survey', 'relation': 'publication year',   'target': '2014',                                        'score': 0.6853994131088257},
+        {'source': 'Home Visits Survey', 'relation': 'data description',   'target': 'detailed socio-economic, health, and protection data', 'score': 0.6544178128242493},
+    ]
 }
 
+# The sample sentence you want to highlight:
 SAMPLE_TEXT = (
     "The Jordan Home Visits Survey, Round II (HV), was carried out by UNHCR and the World Food "
     "Programme between November 2013 and September 2014. Through in-home visits to Syrian refugee "
@@ -23,29 +35,34 @@ SAMPLE_TEXT = (
 
 def highlight_text(text):
     entities = []
-    for phrase, label in SIM_ENTITIES.items():
-        for m in re.finditer(re.escape(phrase), text):
-            entities.append({
-                "entity": label,
-                "start":  m.start(),
-                "end":    m.end(),
-            })
+    # 1) NER spans
+    for ent in ner:
+        entities.append({
+            "entity": ent["label"],
+            "start":  ent["start"],
+            "end":    ent["end"],
+        })
+    # 2) RE spans: annotate each target with its relation label
+    for src, rels in relations.items():
+        for r in rels:
+            label = r["relation"]
+            target = r["target"]
+            for m in re.finditer(re.escape(target), text):
+                entities.append({
+                    "entity": label,
+                    "start":  m.start(),
+                    "end":    m.end(),
+                })
     return {"text": text, "entities": entities}
 
 with gr.Blocks() as demo:
-    gr.Markdown("## GLiNER NER + RE Highlighting\n"
-                "This demo uses your model’s actual predictions to annotate the sample sentence.\n\n"
-                "**Labels & spans** matching your `ner` and `relations` outputs will be colored below.")
+    gr.Markdown("## Data Use Detector\n"
+                "Input text and the model will highlight the entities it detects.")
     
-    txt_in = gr.Textbox(
-        label="Input Text",
-        lines=4,
-        value=SAMPLE_TEXT
-    )
-    btn = gr.Button("Highlight Entities")
+    txt_in  = gr.Textbox(label="Input Text", lines=4, value=SAMPLE_TEXT)
+    btn     = gr.Button("Highlight Entities")
     txt_out = gr.HighlightedText(label="Annotated Entities")
     
-    # wire up
     btn.click(fn=highlight_text, inputs=txt_in, outputs=txt_out)
     txt_in.submit(fn=highlight_text, inputs=txt_in, outputs=txt_out)
     demo.load(fn=highlight_text, inputs=txt_in, outputs=txt_out)
@@ -63,4 +80,4 @@ with gr.Blocks() as demo:
 """)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()