Create app-backup.py

app-backup.py

@@ -0,0 +1,280 @@
+import spaces
+import gradio as gr
+from phi3_instruct_graph import MODEL_LIST, Phi3InstructGraph
+import rapidjson
+from pyvis.network import Network
+import networkx as nx
+import spacy
+from spacy import displacy
+from spacy.tokens import Span
+import random
+from tqdm import tqdm
+
+# Constants
+TITLE = "🌐 GraphMind: Phi-3 Instruct Graph Explorer"
+SUBTITLE = "✨ Extract and visualize knowledge graphs from any text in multiple languages"
+
+# Custom CSS for styling
+CUSTOM_CSS = """
+.gradio-container {
+    font-family: 'Inter', 'Segoe UI', Roboto, sans-serif;
+}
+.gr-button-primary {
+    background-color: #6366f1 !important;
+}
+.gr-button-secondary {
+    border-color: #6366f1 !important;
+    color: #6366f1 !important;
+}
+"""
+
+# Color utilities
+def get_random_light_color():
+    r = random.randint(140, 255)
+    g = random.randint(140, 255)
+    b = random.randint(140, 255)
+    return f"#{r:02x}{g:02x}{b:02x}"
+
+# Text preprocessing
+def handle_text(text):
+    return " ".join(text.split())
+
+# Main processing functions
+@spaces.GPU
+def extract(text, model):
+    try:
+        model = Phi3InstructGraph(model=model)    
+        result = model.extract(text)
+        return rapidjson.loads(result)
+    except Exception as e:
+        raise gr.Error(f"Extraction error: {str(e)}")
+
+def find_token_indices(doc, substring, text):
+    result = []
+    start_index = text.find(substring)
+    
+    while start_index != -1:
+        end_index = start_index + len(substring)
+        start_token = None
+        end_token = None
+
+        for token in doc:
+            if token.idx == start_index:
+                start_token = token.i
+            if token.idx + len(token) == end_index:
+                end_token = token.i + 1
+
+        if start_token is not None and end_token is not None:
+            result.append({
+                "start": start_token,
+                "end": end_token
+            })
+        
+        # Search for next occurrence
+        start_index = text.find(substring, end_index)
+
+    return result
+
+def create_custom_entity_viz(data, full_text):
+    nlp = spacy.blank("xx")
+    doc = nlp(full_text)
+
+    spans = []
+    colors = {}
+    for node in data["nodes"]:
+        entity_spans = find_token_indices(doc, node["id"], full_text)
+        for dataentity in entity_spans:
+            start = dataentity["start"]
+            end = dataentity["end"]
+            
+            if start < len(doc) and end <= len(doc):
+                # Check for overlapping spans
+                overlapping = any(s.start < end and start < s.end for s in spans)
+                if not overlapping:                
+                    span = Span(doc, start, end, label=node["type"])
+                    spans.append(span)
+                    if node["type"] not in colors:
+                        colors[node["type"]] = get_random_light_color()
+
+    doc.set_ents(spans, default="unmodified")
+    doc.spans["sc"] = spans
+
+    options = {
+        "colors": colors,
+        "ents": list(colors.keys()),
+        "style": "ent",
+        "manual": True
+    }
+
+    html = displacy.render(doc, style="span", options=options)
+    return html
+
+def create_graph(json_data):
+    G = nx.Graph()
+
+    # Add nodes with tooltips
+    for node in json_data['nodes']:
+        G.add_node(node['id'], title=f"{node['type']}: {node['detailed_type']}")
+
+    # Add edges with labels
+    for edge in json_data['edges']:
+        G.add_edge(edge['from'], edge['to'], title=edge['label'], label=edge['label'])
+
+    # Create network visualization
+    nt = Network(
+        width="720px",
+        height="600px",
+        directed=True,
+        notebook=False,
+        bgcolor="#f8fafc", 
+        font_color="#1e293b"
+    )
+    
+    # Configure network display
+    nt.from_nx(G)
+    nt.barnes_hut(
+        gravity=-3000,
+        central_gravity=0.3,
+        spring_length=50,
+        spring_strength=0.001,
+        damping=0.09,
+        overlap=0,
+    )
+    
+    # Customize edge appearance
+    for edge in nt.edges:
+        edge['width'] = 2
+        edge['arrows'] = {'to': {'enabled': True, 'type': 'arrow'}}
+        edge['color'] = {'color': '#6366f1', 'highlight': '#4f46e5'}
+        edge['font'] = {'size': 12, 'color': '#4b5563', 'face': 'Arial'}
+
+    # Customize node appearance
+    for node in nt.nodes:
+        node['color'] = {'background': '#e0e7ff', 'border': '#6366f1', 'highlight': {'background': '#c7d2fe', 'border': '#4f46e5'}}
+        node['font'] = {'size': 14, 'color': '#1e293b'}
+        node['shape'] = 'dot'
+        node['size'] = 25
+
+    # Generate HTML with iframe to isolate styles
+    html = nt.generate_html()
+    html = html.replace("'", '"')
+
+    return f"""<iframe style="width: 100%; height: 620px; margin: 0 auto; border-radius: 8px; box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1), 0 2px 4px -1px rgba(0, 0, 0, 0.06);" 
+        name="result" allow="midi; geolocation; microphone; camera; display-capture; encrypted-media;" 
+        sandbox="allow-modals allow-forms allow-scripts allow-same-origin allow-popups 
+        allow-top-navigation-by-user-activation allow-downloads" allowfullscreen="" 
+        allowpaymentrequest="" frameborder="0" srcdoc='{html}'></iframe>"""
+
+def process_and_visualize(text, model, progress=gr.Progress()):
+    if not text or not model:
+        raise gr.Error("⚠️ Both text and model must be provided.")
+    
+    progress(0, desc="Starting extraction...")
+    json_data = extract(text, model)
+    
+    progress(0.5, desc="Creating entity visualization...")
+    entities_viz = create_custom_entity_viz(json_data, text)
+    
+    progress(0.8, desc="Building knowledge graph...")
+    graph_html = create_graph(json_data)
+    
+    node_count = len(json_data["nodes"])
+    edge_count = len(json_data["edges"])
+    stats = f"📊 Extracted {node_count} entities and {edge_count} relationships"
+    
+    progress(1.0, desc="Complete!")
+    return graph_html, entities_viz, json_data, stats
+
+# Example texts in different languages
+EXAMPLES = [
+    [handle_text("""Legendary rock band Aerosmith has officially announced their retirement from touring after 54 years, citing 
+    lead singer Steven Tyler's unrecoverable vocal cord injury. 
+    The decision comes after months of unsuccessful treatment for Tyler's fractured larynx, 
+    which he suffered in September 2023.""")],
+    
+    [handle_text("""Pop star Justin Timberlake, 43, had his driver's license suspended by a New York judge during a virtual 
+    court hearing on August 2, 2024. The suspension follows Timberlake's arrest for driving while intoxicated (DWI) 
+    in Sag Harbor on June 18. Timberlake, who is currently on tour in Europe, 
+    pleaded not guilty to the charges.""")],
+    
+    [handle_text("""세계적인 기술 기업 삼성전자는 새로운 인공지능 기반 스마트폰을 올해 하반기에 출시할 예정이라고 발표했다. 
+    이 스마트폰은 현재 개발 중인 갤럭시 시리즈의 최신작으로, 강력한 AI 기능과 혁신적인 카메라 시스템을 탑재할 것으로 알려졌다. 
+    삼성전자의 CEO는 이번 신제품이 스마트폰 시장에 새로운 혁신을 가져올 것이라고 전망했다.""")],
+    
+    [handle_text("""한국 영화 '기생충'은 2020년 아카데미 시상식에서 작품상, 감독상, 각본상, 국제영화상 등 4개 부문을 수상하며 역사를 새로 썼다. 
+    봉준호 감독이 연출한 이 영화는 한국 영화 최초로 칸 영화제 황금종려상도 수상했으며, 전 세계적으로 엄청난 흥행과 
+    평단의 호평을 받았다.""")]
+]
+
+def create_ui():
+    with gr.Blocks(css=CUSTOM_CSS, title=TITLE) as demo:
+        # Header
+        gr.Markdown(f"# {TITLE}")
+        gr.Markdown(f"{SUBTITLE}")
+        
+        with gr.Row():
+            gr.Markdown("🌍 **Multilingual Support Available** 🔤")
+            
+        # Main interface
+        with gr.Row():
+            # Input column
+            with gr.Column(scale=1):
+                input_model = gr.Dropdown(
+                    MODEL_LIST, 
+                    label="🤖 Select Model",
+                    info="Choose a model to process your text",
+                    value=MODEL_LIST[0] if MODEL_LIST else None
+                )
+                
+                input_text = gr.TextArea(
+                    label="📝 Input Text", 
+                    info="Enter text in any language to extract a knowledge graph",
+                    placeholder="Enter text here...",
+                    lines=10
+                )
+                
+                with gr.Row():
+                    submit_button = gr.Button("🚀 Extract & Visualize", variant="primary", scale=2)
+                    clear_button = gr.Button("🔄 Clear", variant="secondary", scale=1)
+                
+                gr.Examples(
+                    examples=EXAMPLES,
+                    inputs=input_text,
+                    label="📚 Example Texts (English & Korean)"
+                )
+                
+                stats_output = gr.Markdown("", label="🔍 Analysis Results")
+                
+            # Output column
+            with gr.Column(scale=1):
+                with gr.Tab("🧩 Knowledge Graph"):
+                    output_graph = gr.HTML(label="")
+                
+                with gr.Tab("🏷️ Entities"):
+                    output_entity_viz = gr.HTML(label="")
+                    
+                with gr.Tab("📊 JSON Data"):
+                    output_json = gr.JSON(label="")
+                    
+        # Functionality
+        submit_button.click(
+            fn=process_and_visualize, 
+            inputs=[input_text, input_model],
+            outputs=[output_graph, output_entity_viz, output_json, stats_output]
+        )
+        
+        clear_button.click(
+            fn=lambda: [None, None, None, ""],
+            inputs=[],
+            outputs=[output_graph, output_entity_viz, output_json, stats_output]
+        )
+        
+        # Footer
+        gr.Markdown("---")
+        gr.Markdown("📋 **Instructions:** Enter text in any language, select a model, and click 'Extract & Visualize' to generate a knowledge graph.")
+        gr.Markdown("🛠️ Powered by Phi-3 Instruct Graph | Emergent Methods")
+        
+    return demo
+
+demo = create_ui()
+demo.launch(share=False)