Create app.py

app.py

@@ -0,0 +1,89 @@
+import torch
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
+import os
+
+# Load the tokenizer and models for the first pipeline
+tokenizer_ext = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_token")
+model_ext = AutoModelForTokenClassification.from_pretrained("AlGe/deberta-v3-large_token")
+tokenizer_ext.model_max_length = 512
+pipe_ext = gr.pipeline("ner", model=model_ext, tokenizer=tokenizer_ext)
+
+# Load the tokenizer and models for the second pipeline
+tokenizer_ais = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_AIS-token")
+model_ais = AutoModelForTokenClassification.from_pretrained("AlGe/deberta-v3-large_AIS-token")
+tokenizer_ais.model_max_length = 512
+pipe_ais = gr.pipeline("ner", model=model_ais, tokenizer=tokenizer_ais)
+
+# Load the tokenizer and models for the third pipeline
+auth_token = os.environ['HF_TOKEN']
+model1 = AutoModelForSequenceClassification.from_pretrained("AlGe/deberta-v3-large_Int_segment", num_labels=1, use_auth_token=auth_token)
+tokenizer1 = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_Int_segment", use_auth_token=auth_token)
+
+model2 = AutoModelForSequenceClassification.from_pretrained("AlGe/deberta-v3-large_seq_ext", num_labels=1, use_auth_token=auth_token)
+
+# Define functions to process inputs
+def process_ner(text, pipeline):
+    output = pipeline(text)
+    entities = []
+    current_entity = None
+
+    for token in output:
+        entity_type = token['entity'][2:]
+        entity_prefix = token['entity'][:1]
+
+        if current_entity is None or entity_type != current_entity['entity'] or (entity_prefix == 'B' and entity_type == current_entity['entity']):
+            if current_entity is not None:
+                entities.append(current_entity)
+            current_entity = {
+                "entity": entity_type,
+                "start": token['start'],
+                "end": token['end'],
+                "score": token['score']
+            }
+        else:
+            current_entity['end'] = token['end']
+            current_entity['score'] = max(current_entity['score'], token['score'])
+
+    if current_entity is not None:
+        entities.append(current_entity)
+
+    return {"text": text, "entities": entities}
+
+def process_classification(text, model1, model2, tokenizer1):
+    inputs1 = tokenizer1(text, max_length=512, return_tensors='pt', truncation=True, padding=True)
+    
+    with torch.no_grad():
+        outputs1 = model1(**inputs1)
+        outputs2 = model2(**inputs1)
+    
+    prediction1 = outputs1[0].item()
+    prediction2 = outputs2[0].item()
+    score = prediction1 / (prediction2 + prediction1)
+
+    return f"{round(prediction1, 1)}", f"{round(prediction2, 1)}", f"{round(score, 2)}"
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn={
+        "NER - Extended Sequence Classification": lambda text: process_ner(text, pipe_ext),
+        "NER - Autobiographical Interview Scoring": lambda text: process_ner(text, pipe_ais),
+        "Internal Detail Count": lambda text: process_classification(text, model1, model2, tokenizer1)[0],
+        "External Detail Count": lambda text: process_classification(text, model1, model2, tokenizer1)[1],
+        "Approximated Internal Detail Ratio": lambda text: process_classification(text, model1, model2, tokenizer1)[2]
+    },
+    inputs=gr.Textbox(placeholder="Enter sentence here..."),
+    outputs=[
+        gr.HighlightedText(label="NER - Extended Sequence Classification"),
+        gr.HighlightedText(label="NER - Autobiographical Interview Scoring"),
+        gr.Label(label="Internal Detail Count"),
+        gr.Label(label="External Detail Count"),
+        gr.Label(label="Approximated Internal Detail Ratio")
+    ],
+    title="Combined Demo",
+    description="This demo combines two different NER models and two different sequence classification models. Enter a sentence to see the results.",
+    theme="monochrome"
+)
+
+# Launch the combined interface
+iface.launch()