temp fix for app.py

.gitignore

@@ -0,0 +1,3 @@
+.venv/
+log.csv
+python.version

.python-version

@@ -0,0 +1 @@
+3.10.11

app.py

@@ -1,59 +1,22 @@
+# import examples object from examples.json file
 import json
-from typing import Dict, Union, List
-from gliner import GLiNER
-import gradio as gr
-import os
-
-# Load available models
-MODELS = {
-    "GLiNER Medium v2.1": "urchade/gliner_medium-v2.1",
-    "NuNER Zero": "numind/NuZero_token",
-    "GLiNER Multi PII": "urchade/gliner_multi_pii-v1"
-}
-
-# Example datasets with descriptions
-EXAMPLE_SETS = {
-    "General NER": "examples.json",
-    "NuNER Zero": "examples-nuner.json",
-    "PII Detection": "examples-pii.json"
-}
 
-# Initialize models (will be loaded on demand)
-loaded_models = {}
+with open("examples.json", "r") as f:
+    examples = json.load(f)
 
-# Current examples
-current_examples = []
-
-def load_example_set(example_set_name):
-    """Load a set of examples from the specified file"""
-    try:
-        file_path = EXAMPLE_SETS[example_set_name]
-        with open(file_path, "r", encoding="utf-8") as f:
-            examples = json.load(f)
-        return examples
-    except (KeyError, FileNotFoundError, json.JSONDecodeError) as e:
-        print(f"Error loading example set {example_set_name}: {e}")
-        return []
-
-# Load default example set
-current_examples = load_example_set("General NER")
+from typing import Dict, Union
+from gliner import GLiNER
+import gradio as gr
 
-def get_model(model_name):
-    """Load model if not already loaded"""
-    if model_name not in loaded_models:
-        model_path = MODELS[model_name]
-        loaded_models[model_name] = GLiNER.from_pretrained(model_path)
-    return loaded_models[model_name]
+model = GLiNER.from_pretrained("urchade/gliner_medium-v2.1")
 
 def merge_entities(entities):
-    """Merge adjacent entities of the same type"""
     if not entities:
         return []
     merged = []
     current = entities[0]
     for next_entity in entities[1:]:
-        if (next_entity['entity'] == current['entity'] and 
-            (next_entity['start'] == current['end'] + 1 or next_entity['start'] == current['end'])):
+        if next_entity['entity'] == current['entity'] and (next_entity['start'] == current['end'] + 1 or next_entity['start'] == current['end']):
             current['word'] += ' ' + next_entity['word']
             current['end'] = next_entity['end']
         else:
@@ -63,217 +26,102 @@ def merge_entities(entities):
     return merged
 
 def ner(
-    text: str, 
-    labels: str, 
-    model_name: str,
-    threshold: float, 
-    nested_ner: bool,
-    merge_entities_toggle: bool
-) -> Dict[str, Union[str, List]]:
-    """Run named entity recognition with selected model and parameters"""
-    
-    # Get the selected model
-    model = get_model(model_name)
-    
-    # Split labels
-    label_list = [label.strip() for label in labels.split(",")]
-    
-    # Predict entities
-    entities = [
-        {
-            "entity": entity["label"],
-            "word": entity["text"],
-            "start": entity["start"],
-            "end": entity["end"],
-            "score": entity.get("score", 0),
-        }
-        for entity in model.predict_entities(
-            text, label_list, flat_ner=not nested_ner, threshold=threshold
-        )
-    ]
-    
-    # Merge entities if enabled
-    if merge_entities_toggle:
-        entities = merge_entities(entities)
-    
-    # Return results
-    return {
+    text, labels: str, threshold: float, nested_ner: bool
+) -> Dict[str, Union[str, int, float]]:
+    labels = labels.split(",")
+    r = {
         "text": text,
-        "entities": entities,
+        "entities": [
+            {
+                "entity": entity["label"],
+                "word": entity["text"],
+                "start": entity["start"],
+                "end": entity["end"],
+                "score": 0,
+            }
+            for entity in model.predict_entities(
+                text, labels, flat_ner=not nested_ner, threshold=threshold
+            )
+        ],
     }
+    # r["entities"] =  merge_entities(r["entities"])
+    return r
 
-def load_example(example_idx):
-    """Load a specific example by index from the current example set"""
-    if not current_examples or example_idx >= len(current_examples):
-        return "", "", 0.3, False, False
-    
-    example = current_examples[example_idx]
-    return example[0], example[1], example[2], example[3], False
-
-def switch_example_set(example_set_name):
-    """Switch to a different example set and update the interface"""
-    global current_examples
-    current_examples = load_example_set(example_set_name)
-    
-    # Return the first example from the new set
-    if current_examples:
-        example = current_examples[0]
-        # Return example text, labels, threshold, nested_ner, merge status, example names for dropdown
-        example_names = [f"Example {i+1}" for i in range(len(current_examples))]
-        return example[0], example[1], example[2], example[3], False, gr.Dropdown.update(choices=example_names, value="Example 1")
-    else:
-        return "", "", 0.3, False, False, gr.Dropdown.update(choices=[], value=None)
-
-with gr.Blocks(title="Unified NER Interface") as demo:
+with gr.Blocks(title="GLiNER-medium-v2.1") as demo:
     gr.Markdown(
         """
-        # Unified Zero-shot Named Entity Recognition Interface
-        
-        This interface allows you to compare different zero-shot Named Entity Recognition models.
-        
-        ## Models Available:
-        - **GLiNER Medium v2.1**: The original GLiNER medium model
-        - **NuNER Zero**: A specialized token-based NER model
-        - **GLiNER Multi PII**: Fine-tuned for detecting personally identifiable information across multiple languages
-        
-        ## Features:
-        - Select different models
-        - Switch between example sets for different use cases
-        - Toggle nested entity recognition
-        - Toggle entity merging (combining adjacent entities of the same type)
-        - Select from various examples within each set
+        # GLiNER Testbed
+
+        GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios. This model has the commercially permissive Apache 2.0 license.
+
+        ## Links
+
+        * Model: https://huggingface.co/urchade/gliner_medium-v2.1
+        * All GLiNER models: https://huggingface.co/models?library=gliner
+        * Paper: https://arxiv.org/abs/2311.08526
+        * Repository: https://github.com/urchade/GLiNER
         """
     )
-    
-    with gr.Row():
-        model_dropdown = gr.Dropdown(
-            choices=list(MODELS.keys()),
-            value=list(MODELS.keys())[0],
-            label="Model",
-            info="Select the NER model to use"
-        )
-        example_set_dropdown = gr.Dropdown(
-            choices=list(EXAMPLE_SETS.keys()),
-            value="General NER",
-            label="Example Set",
-            info="Select a set of example texts"
-        )
-        
-    with gr.Row():
-        example_dropdown = gr.Dropdown(
-            choices=[f"Example {i+1}" for i in range(len(current_examples))],
-            value="Example 1",
-            label="Example",
-            info="Select a specific example text"
-        )
-    
+
     input_text = gr.Textbox(
-        value=current_examples[0][0] if current_examples else "", 
-        label="Text input", 
-        placeholder="Enter your text here",
-        lines=5
+        value=examples[0][0], label="Text input", placeholder="Enter your text here"
     )
-    
-    with gr.Row():
+    with gr.Row() as row:
         labels = gr.Textbox(
-            value=current_examples[0][1] if current_examples else "",
-            label="Entity Labels",
+            value=examples[0][1],
+            label="Labels",
             placeholder="Enter your labels here (comma separated)",
             scale=2,
         )
         threshold = gr.Slider(
             0,
             1,
-            value=current_examples[0][2] if current_examples else 0.3,
+            value=0.3,
             step=0.01,
-            label="Confidence Threshold",
+            label="Threshold",
             info="Lower the threshold to increase how many entities get predicted.",
             scale=1,
         )
-    
-    with gr.Row():
-        nested_ner = gr.Checkbox(
-            value=current_examples[0][3] if current_examples else False,
-            label="Nested NER",
-            info="Allow entities to be contained within other entities",
-        )
-        merge_entities_toggle = gr.Checkbox(
-            value=False,
-            label="Merge Adjacent Entities",
-            info="Combine adjacent entities of the same type into a single entity",
-        )
-    
+        with gr.Column() as col:
+            nested_ner = gr.Checkbox(
+                value=examples[0][2],
+                label="Nested NER",
+                info="Allow for nested NER?",
+                scale=0,
+            )
+            merged_ent = gr.Checkbox(
+                #value=examples[0][3],
+                value=False,
+                label="Merged Entities",
+                info="Merge adjacent entities?",
+                scale=0,
+            )
     output = gr.HighlightedText(label="Predicted Entities")
     submit_btn = gr.Button("Submit")
-    
-    # Handling example set selection
-    example_set_dropdown.change(
-        fn=switch_example_set,
-        inputs=[example_set_dropdown],
-        outputs=[input_text, labels, threshold, nested_ner, merge_entities_toggle, example_dropdown]
+    examples = gr.Examples(
+        examples,
+        fn=ner,
+        inputs=[input_text, labels, threshold, nested_ner],
+        outputs=output,
+        cache_examples=True,
     )
-    
-    # Handling example selection within a set
-    example_dropdown.change(
-        fn=lambda idx: load_example(int(idx.split()[1]) - 1),
-        inputs=[example_dropdown],
-        outputs=[input_text, labels, threshold, nested_ner, merge_entities_toggle]
-    )
-    
-    # Add a model recommendation for the example set
-    def recommend_model(example_set_name):
-        """Recommend appropriate model based on example set"""
-        if example_set_name == "PII Detection":
-            return gr.Dropdown.update(value="GLiNER Multi PII")
-        elif example_set_name == "NuNER Zero":
-            return gr.Dropdown.update(value="NuNER Zero")
-        else:
-            return gr.Dropdown.update(value="GLiNER Medium v2.1")
-    
-    # Auto-suggest model when changing example set
-    example_set_dropdown.change(
-        fn=recommend_model,
-        inputs=[example_set_dropdown],
-        outputs=[model_dropdown]
-    )
-    
+
     # Submitting
-    submit_btn.click(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
-    )
     input_text.submit(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
+        fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output
     )
-    
-    # Other interactions
-    model_dropdown.change(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
+    labels.submit(
+        fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output
     )
-    
     threshold.release(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
+        fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output
     )
-    
-    nested_ner.change(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
+    submit_btn.click(
+        fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output
     )
-    
-    merge_entities_toggle.change(
-        fn=ner, 
-        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
-        outputs=output
+    nested_ner.change(
+        fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output
     )
 
-if __name__ == "__main__":
-    demo.queue()
-    demo.launch(debug=True)
+demo.queue()
+demo.launch(debug=True)

app2.py

@@ -0,0 +1,279 @@
+import json
+from typing import Dict, Union, List
+from gliner import GLiNER
+import gradio as gr
+import os
+
+# Load available models
+MODELS = {
+    "GLiNER Medium v2.1": "urchade/gliner_medium-v2.1",
+    "NuNER Zero": "numind/NuZero_token",
+    "GLiNER Multi PII": "urchade/gliner_multi_pii-v1"
+}
+
+# Example datasets with descriptions
+EXAMPLE_SETS = {
+    "General NER": "examples.json",
+    "NuNER Zero": "examples-nuner.json",
+    "PII Detection": "examples-pii.json"
+}
+
+# Initialize models (will be loaded on demand)
+loaded_models = {}
+
+# Current examples
+current_examples = []
+
+def load_example_set(example_set_name):
+    """Load a set of examples from the specified file"""
+    try:
+        file_path = EXAMPLE_SETS[example_set_name]
+        with open(file_path, "r", encoding="utf-8") as f:
+            examples = json.load(f)
+        return examples
+    except (KeyError, FileNotFoundError, json.JSONDecodeError) as e:
+        print(f"Error loading example set {example_set_name}: {e}")
+        return []
+
+# Load default example set
+current_examples = load_example_set("General NER")
+
+def get_model(model_name):
+    """Load model if not already loaded"""
+    if model_name not in loaded_models:
+        model_path = MODELS[model_name]
+        loaded_models[model_name] = GLiNER.from_pretrained(model_path)
+    return loaded_models[model_name]
+
+def merge_entities(entities):
+    """Merge adjacent entities of the same type"""
+    if not entities:
+        return []
+    merged = []
+    current = entities[0]
+    for next_entity in entities[1:]:
+        if (next_entity['entity'] == current['entity'] and 
+            (next_entity['start'] == current['end'] + 1 or next_entity['start'] == current['end'])):
+            current['word'] += ' ' + next_entity['word']
+            current['end'] = next_entity['end']
+        else:
+            merged.append(current)
+            current = next_entity
+    merged.append(current)
+    return merged
+
+def ner(
+    text: str, 
+    labels: str, 
+    model_name: str,
+    threshold: float, 
+    nested_ner: bool,
+    merge_entities_toggle: bool
+) -> Dict[str, Union[str, List]]:
+    """Run named entity recognition with selected model and parameters"""
+    
+    # Get the selected model
+    model = get_model(model_name)
+    
+    # Split labels
+    label_list = [label.strip() for label in labels.split(",")]
+    
+    # Predict entities
+    entities = [
+        {
+            "entity": entity["label"],
+            "word": entity["text"],
+            "start": entity["start"],
+            "end": entity["end"],
+            "score": entity.get("score", 0),
+        }
+        for entity in model.predict_entities(
+            text, label_list, flat_ner=not nested_ner, threshold=threshold
+        )
+    ]
+    
+    # Merge entities if enabled
+    if merge_entities_toggle:
+        entities = merge_entities(entities)
+    
+    # Return results
+    return {
+        "text": text,
+        "entities": entities,
+    }
+
+def load_example(example_idx):
+    """Load a specific example by index from the current example set"""
+    if not current_examples or example_idx >= len(current_examples):
+        return "", "", 0.3, False, False
+    
+    example = current_examples[example_idx]
+    return example[0], example[1], example[2], example[3], False
+
+def switch_example_set(example_set_name):
+    """Switch to a different example set and update the interface"""
+    global current_examples
+    current_examples = load_example_set(example_set_name)
+    
+    # Return the first example from the new set
+    if current_examples:
+        example = current_examples[0]
+        # Return example text, labels, threshold, nested_ner, merge status, example names for dropdown
+        example_names = [f"Example {i+1}" for i in range(len(current_examples))]
+        return example[0], example[1], example[2], example[3], False, gr.Dropdown.update(choices=example_names, value="Example 1")
+    else:
+        return "", "", 0.3, False, False, gr.Dropdown.update(choices=[], value=None)
+
+with gr.Blocks(title="Unified NER Interface") as demo:
+    gr.Markdown(
+        """
+        # Unified Zero-shot Named Entity Recognition Interface
+        
+        This interface allows you to compare different zero-shot Named Entity Recognition models.
+        
+        ## Models Available:
+        - **GLiNER Medium v2.1**: The original GLiNER medium model
+        - **NuNER Zero**: A specialized token-based NER model
+        - **GLiNER Multi PII**: Fine-tuned for detecting personally identifiable information across multiple languages
+        
+        ## Features:
+        - Select different models
+        - Switch between example sets for different use cases
+        - Toggle nested entity recognition
+        - Toggle entity merging (combining adjacent entities of the same type)
+        - Select from various examples within each set
+        """
+    )
+    
+    with gr.Row():
+        model_dropdown = gr.Dropdown(
+            choices=list(MODELS.keys()),
+            value=list(MODELS.keys())[0],
+            label="Model",
+            info="Select the NER model to use"
+        )
+        example_set_dropdown = gr.Dropdown(
+            choices=list(EXAMPLE_SETS.keys()),
+            value="General NER",
+            label="Example Set",
+            info="Select a set of example texts"
+        )
+        
+    with gr.Row():
+        example_dropdown = gr.Dropdown(
+            choices=[f"Example {i+1}" for i in range(len(current_examples))],
+            value="Example 1",
+            label="Example",
+            info="Select a specific example text"
+        )
+    
+    input_text = gr.Textbox(
+        value=current_examples[0][0] if current_examples else "", 
+        label="Text input", 
+        placeholder="Enter your text here",
+        lines=5
+    )
+    
+    with gr.Row():
+        labels = gr.Textbox(
+            value=current_examples[0][1] if current_examples else "",
+            label="Entity Labels",
+            placeholder="Enter your labels here (comma separated)",
+            scale=2,
+        )
+        threshold = gr.Slider(
+            0,
+            1,
+            value=current_examples[0][2] if current_examples else 0.3,
+            step=0.01,
+            label="Confidence Threshold",
+            info="Lower the threshold to increase how many entities get predicted.",
+            scale=1,
+        )
+    
+    with gr.Row():
+        nested_ner = gr.Checkbox(
+            value=current_examples[0][3] if current_examples else False,
+            label="Nested NER",
+            info="Allow entities to be contained within other entities",
+        )
+        merge_entities_toggle = gr.Checkbox(
+            value=False,
+            label="Merge Adjacent Entities",
+            info="Combine adjacent entities of the same type into a single entity",
+        )
+    
+    output = gr.HighlightedText(label="Predicted Entities")
+    submit_btn = gr.Button("Submit")
+    
+    # Handling example set selection
+    example_set_dropdown.change(
+        fn=switch_example_set,
+        inputs=[example_set_dropdown],
+        outputs=[input_text, labels, threshold, nested_ner, merge_entities_toggle, example_dropdown]
+    )
+    
+    # Handling example selection within a set
+    example_dropdown.change(
+        fn=lambda idx: load_example(int(idx.split()[1]) - 1),
+        inputs=[example_dropdown],
+        outputs=[input_text, labels, threshold, nested_ner, merge_entities_toggle]
+    )
+    
+    # Add a model recommendation for the example set
+    def recommend_model(example_set_name):
+        """Recommend appropriate model based on example set"""
+        if example_set_name == "PII Detection":
+            return gr.Dropdown.update(value="GLiNER Multi PII")
+        elif example_set_name == "NuNER Zero":
+            return gr.Dropdown.update(value="NuNER Zero")
+        else:
+            return gr.Dropdown.update(value="GLiNER Medium v2.1")
+    
+    # Auto-suggest model when changing example set
+    example_set_dropdown.change(
+        fn=recommend_model,
+        inputs=[example_set_dropdown],
+        outputs=[model_dropdown]
+    )
+    
+    # Submitting
+    submit_btn.click(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+    input_text.submit(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+    
+    # Other interactions
+    model_dropdown.change(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+    
+    threshold.release(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+    
+    nested_ner.change(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+    
+    merge_entities_toggle.change(
+        fn=ner, 
+        inputs=[input_text, labels, model_dropdown, threshold, nested_ner, merge_entities_toggle], 
+        outputs=output
+    )
+
+if __name__ == "__main__":
+    demo.queue()
+    demo.launch(debug=True)

requirements.txt

@@ -1,2 +1,3 @@
+gradio
 gliner
 scipy==1.12