File size: 3,829 Bytes
96a57ab
83365c5
96a57ab
 
83365c5
 
 
 
 
 
 
88af0ff
83365c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7599b35
 
 
 
 
 
 
 
 
 
83365c5
 
 
 
d1a4bde
51ca89b
d1a4bde
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51ca89b
d1a4bde
 
83365c5
 
 
 
 
 
 
 
 
 
 
 
 
51ca89b
83365c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96a57ab
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
import gradio as gr
from transformers import pipeline


# Model names (keeping it programmatic)
model_names = [
    "c-ho/2026-04-24-crf-classweights-clean",
    "c-ho/2026-04-23-crf-classweights-clean"
]

example_sent = (
    "As a result, Indo-European developed a minimal vowel system combined with a very large consonant inventory including glottalized stops, also grammatical gender and adjectival agreement."
)

# -----------------------
# UI helpers
# -----------------------

# Programmatically build the model info dict
model_info = {
    model_name: {
        "link": f"https://huggingface.co/{model_name}",
        "usage": f"""from transformers import pipeline
ner = pipeline("ner", model="{model_name}", grouped_entities=True)
result = ner("{example_sent}")
print(result)""",
    }
    for model_name in model_names
}

# Load models into a dictionary programmatically for the analyze function
models = {
    model_name: pipeline("ner", model=model_name) #, grouped_entities=True)
    for model_name in model_names
}

def display_model_info(model_name):
    info = model_info[model_name]
    usage_code = info["usage"]
    link = f"[Open model page]({info['link']})"
    return usage_code, link

model_cache = {}
def get_model(model_name):
    if model_name not in model_cache:
        model_cache[model_name] = pipeline(
            "ner",
            model=model_name,
            aggregation_strategy="simple"  # safer for display
        )
    return model_cache[model_name]


# -----------------------
# NER function (SAFE OUTPUT)
# -----------------------

'''
# Function to run NER on input text
def analyze_text(text, model_name):
    ner = models[model_name]
    ner_results = ner(text)
    highlighted_text = []
    last_idx = 0
    for entity in ner_results:
        start = entity["start"]
        end = entity["end"]
        label = entity["entity_group"]
        # Add non-entity text
        if start > last_idx:
            highlighted_text.append((text[last_idx:start], None))
        # Add entity text
        highlighted_text.append((text[start:end], label))
        last_idx = end
    # Add any remaining text after the last entity
    if last_idx < len(text):
        highlighted_text.append((text[last_idx:], None))
    return highlighted_text
'''


def analyze_text(text, model_name):
    ner = get_model(model_name)
    results = ner(text)
    # Convert to safe string output (avoids HighlightedText SSR issues)
    if not results:
        return "No entities found."
    lines = []
    for ent in results:
        word = ent.get("word", "")
        label = ent.get("entity_group", ent.get("entity", "UNK"))
        score = ent.get("score", 0.0)
        lines.append(f"{word} -> {label} ({score:.2f})")
    return "\n".join(lines)

# -----------------------
# UI
# -----------------------
with gr.Blocks() as demo:
    gr.Markdown("# Named Entity Recognition (NER) Demo")
    model_selector = gr.Dropdown(
        choices=model_names,
        value=model_names[0],
        label="Select Model"
    )
    text_input = gr.Textbox(
        label="Input Text",
        lines=5,
        value=example_sent
    )
    btn = gr.Button("Run NER")
    output = gr.Textbox(label="Entities")
    code_output = gr.Code(label="Usage Example")
    link_output = gr.Markdown()
    btn.click(
        analyze_text,
        inputs=[text_input, model_selector],
        outputs=output
    )
    model_selector.change(
        display_model_info,
        inputs=model_selector,
        outputs=[code_output, link_output]
    )
    # Initialize UI on load
    demo.load(
        display_model_info,
        inputs=model_selector,
        outputs=[code_output, link_output]
    )

    
#def greet(name):
#    return "Hello " + name + "!!"

#demo = gr.Interface(fn=greet, inputs="text", outputs="text")
demo.launch()