Spaces:

pujithapsx
/

Finetuned_crossencoder_test

Sleeping

Update app.py

602ebb2 verified 8 months ago

9.73 kB

import gradio as gr
from sentence_transformers import CrossEncoder
import torch

# Load fine-tuned model from Hub
MODEL_NAME = "pujithapsx/address-crossencoder-bge-reranker-v2-m3-finetuned"

print("Loading model...")
# Use CrossEncoder directly - it handles the model format correctly
model = CrossEncoder(
    MODEL_NAME,
    trust_remote_code=True,
    device="cpu"  # Use "cuda" if GPU is available in your HF Space
)
print("Model loaded successfully!")

# STATIC THRESHOLD
THRESHOLD = 0.75


def predict_similarity(input1, input2):
    """
    Predict similarity between two addresses using static threshold.
    Returns: Similarity %, Match/No Match result, and confidence bar value.
    """
    if not input1.strip() or not input2.strip():
        return "—", "⚠️ Please provide both addresses", 0

    score = model.predict([[input1, input2]])[0]
    similarity_pct = score * 100

    if score >= THRESHOLD:
        result = "✅ MATCH"
        confidence_label = "High" if score > 0.85 else "Medium"
    else:
        result = "❌ NO MATCH"
        confidence_label = "High" if score < 0.40 else "Medium"

    similarity_str = f"{similarity_pct:.2f}%"
    result_str = f"{result}  •  Confidence: {confidence_label}"

    return similarity_str, result_str, float(similarity_pct)


# ── Custom CSS ──────────────────────────────────────────────────────────────
custom_css = """
@import url('https://fonts.googleapis.com/css2?family=Space+Mono:wght@400;700&family=DM+Sans:wght@300;400;500;600&display=swap');
:root {
    --bg:        #0b0f1a;
    --surface:   #111827;
    --border:    #1f2d45;
    --accent:    #38bdf8;
    --accent2:   #818cf8;
    --green:     #34d399;
    --red:       #f87171;
    --yellow:    #fbbf24;
    --text:      #e2e8f0;
    --muted:     #64748b;
    --radius:    12px;
}
body, .gradio-container {
    background: var(--bg) !important;
    font-family: 'DM Sans', sans-serif !important;
    color: var(--text) !important;
}
/* ── header ── */
#header-box {
    background: linear-gradient(135deg, #0f172a 0%, #1e293b 100%);
    border: 1px solid var(--border);
    border-radius: var(--radius);
    padding: 36px 40px 28px;
    margin-bottom: 24px;
    position: relative;
    overflow: hidden;
}
#header-box::before {
    content: '';
    position: absolute;
    top: -60px; right: -60px;
    width: 200px; height: 200px;
    background: radial-gradient(circle, rgba(56,189,248,0.12) 0%, transparent 70%);
    pointer-events: none;
}
#header-box h1 {
    font-family: 'Space Mono', monospace !important;
    font-size: 1.9rem !important;
    font-weight: 700 !important;
    color: var(--accent) !important;
    margin: 0 0 8px !important;
    letter-spacing: -0.5px;
}
#header-box p {
    color: var(--muted) !important;
    font-size: 0.95rem !important;
    margin: 0 !important;
    line-height: 1.6;
}
.badge {
    display: inline-block;
    background: rgba(56,189,248,0.12);
    border: 1px solid rgba(56,189,248,0.3);
    color: var(--accent);
    font-family: 'Space Mono', monospace;
    font-size: 0.7rem;
    padding: 3px 10px;
    border-radius: 20px;
    margin-right: 8px;
    margin-top: 12px;
}
/* ── input cards ── */
.input-card textarea,
.input-card input {
    background: var(--surface) !important;
    border: 1px solid var(--border) !important;
    border-radius: var(--radius) !important;
    color: var(--text) !important;
    font-family: 'DM Sans', sans-serif !important;
    font-size: 0.95rem !important;
    padding: 14px 16px !important;
    transition: border-color 0.2s;
}
.input-card textarea:focus,
.input-card input:focus {
    border-color: var(--accent) !important;
    box-shadow: 0 0 0 3px rgba(56,189,248,0.1) !important;
}
label span {
    font-family: 'Space Mono', monospace !important;
    font-size: 0.75rem !important;
    color: var(--accent2) !important;
    letter-spacing: 0.5px;
    text-transform: uppercase;
}
/* ── button ── */
#run-btn {
    background: linear-gradient(135deg, var(--accent) 0%, var(--accent2) 100%) !important;
    border: none !important;
    border-radius: var(--radius) !important;
    color: #0b0f1a !important;
    font-family: 'Space Mono', monospace !important;
    font-size: 0.9rem !important;
    font-weight: 700 !important;
    letter-spacing: 0.5px;
    padding: 14px 32px !important;
    cursor: pointer;
    transition: opacity 0.2s, transform 0.15s;
    width: 100%;
    margin-top: 8px;
}
#run-btn:hover { opacity: 0.9; transform: translateY(-1px); }
#run-btn:active { transform: translateY(0); }
/* ── output cards ── */
.output-card textarea,
.output-card input {
    background: #0d1424 !important;
    border: 1px solid var(--border) !important;
    border-radius: var(--radius) !important;
    color: var(--text) !important;
    font-family: 'Space Mono', monospace !important;
    font-size: 1.1rem !important;
    font-weight: 700 !important;
    text-align: center;
}
/* ── slider (score bar) ── */
.score-slider input[type=range] {
    accent-color: var(--accent);
}
/* ── examples table ── */
.gr-samples-table {
    background: var(--surface) !important;
    border: 1px solid var(--border) !important;
    border-radius: var(--radius) !important;
}
.gr-samples-table th {
    font-family: 'Space Mono', monospace !important;
    font-size: 0.72rem !important;
    color: var(--muted) !important;
    text-transform: uppercase;
    letter-spacing: 0.5px;
    background: #0d1424 !important;
}
.gr-samples-table td {
    color: var(--text) !important;
    font-size: 0.88rem !important;
}
.gr-samples-table tr:hover td {
    background: rgba(56,189,248,0.04) !important;
}
/* ── info footer ── */
#footer-info {
    background: var(--surface);
    border: 1px solid var(--border);
    border-radius: var(--radius);
    padding: 20px 24px;
    margin-top: 20px;
}
#footer-info p {
    color: var(--muted) !important;
    font-family: 'Space Mono', monospace !important;
    font-size: 0.78rem !important;
    margin: 4px 0 !important;
    line-height: 1.7;
}
#footer-info span { color: var(--accent) !important; }
"""

# ── Gradio UI ────────────────────────────────────────────────────────────────
with gr.Blocks(css=custom_css, title="Address Entity Matcher") as demo:

    # Header
    gr.HTML("""
    <div id="header-box">
        <h1>Address Entity Matcher</h1>
        <p>
            Enter two addresses to determine whether they refer to the same location.<br>
            Powered by a fine-tuned <strong>BGE-Reranker-v2-m3</strong> cross-encoder model.
        </p>
        <span class="badge">CrossEncoder</span>
        <span class="badge">BGE-Reranker-v2-m3</span>
        <span class="badge">Threshold: 0.75</span>
    </div>
    """)

    # Inputs
    with gr.Row(equal_height=True):
        with gr.Column(elem_classes="input-card"):
            input1 = gr.Textbox(
                label="Address 1",
                placeholder="e.g., Flat 12-B Sector 5 Noida",
                lines=3,
            )
        with gr.Column(elem_classes="input-card"):
            input2 = gr.Textbox(
                label="Address 2",
                placeholder="e.g., Flat 23-B Sector 5 Noida",
                lines=3,
            )

    btn = gr.Button(" Check Match", elem_id="run-btn", variant="primary")

    # Outputs
    with gr.Row(equal_height=True):
        with gr.Column(elem_classes="output-card"):
            similarity_output = gr.Textbox(
                label="Similarity Score",
                interactive=False,
                placeholder="—",
            )
        with gr.Column(elem_classes="output-card"):
            result_output = gr.Textbox(
                label="Match Result",
                interactive=False,
                placeholder="—",
            )

    score_bar = gr.Slider(
        minimum=0,
        maximum=100,
        value=0,
        step=0.01,
        label="Score Visualisation  (threshold line: 75%)",
        interactive=False,
        elem_classes="score-slider",
    )

    # Examples
    gr.Examples(
        examples=[
            ["Flat 12-B Sector 5 Noida",                          "Flat 23-B Sector 5 Noida"],
            ["Phase 4 Whitefield Bangalore",                       "Whitefield Phase V Bangalore"],
            ["Thirteen I 7th Avenue Adyar Chennai",                "13 Seventh Avenue Adyar Chennai"],
            ["Twenty Nine A Second Cross Koramangala Bengaluru",   "47 Forty Seven B Third Street Indiranagar Bengaluru"],
            ["Plot 8 Banjara Hills Hyderabad",                     "Plot 8 Banjara Hills Hyderabad"],
            ["House No 4 Lane 2 DLF Phase 1 Gurugram",            "H.No 4/2 DLF Phase One Gurgaon"],
        ],
        inputs=[input1, input2],
        label="Examples",
    )

    # Footer info
    gr.HTML(f"""
    <div id="footer-info">
        <p> <strong>Model:</strong> <span>pujithapsx/address-crossencoder-bge-reranker-v2-m3-finetuned</span></p>
        <p><strong>Threshold:</strong> <span>{THRESHOLD}</span> — Score ≥ {THRESHOLD} → MATCH &nbsp;|&nbsp; Score &lt; {THRESHOLD} → NO MATCH</p>
        <p> <strong>Confidence:</strong> High (score &gt; 0.85 or &lt; 0.40) &nbsp;|&nbsp; Medium (otherwise)</p>
    </div>
    """)

    # Wiring
    btn.click(
        fn=predict_similarity,
        inputs=[input1, input2],
        outputs=[similarity_output, result_output, score_bar],
    )

if __name__ == "__main__":
    demo.launch()

	import gradio as gr
	from sentence_transformers import CrossEncoder
	import torch

	# Load fine-tuned model from Hub
	MODEL_NAME = "pujithapsx/address-crossencoder-bge-reranker-v2-m3-finetuned"

	print("Loading model...")
	# Use CrossEncoder directly - it handles the model format correctly
	model = CrossEncoder(
	MODEL_NAME,
	trust_remote_code=True,
	device="cpu" # Use "cuda" if GPU is available in your HF Space
	)
	print("Model loaded successfully!")

	# STATIC THRESHOLD
	THRESHOLD = 0.75


	def predict_similarity(input1, input2):
	"""
	Predict similarity between two addresses using static threshold.
	Returns: Similarity %, Match/No Match result, and confidence bar value.
	"""
	if not input1.strip() or not input2.strip():
	return "—", "⚠️ Please provide both addresses", 0

	score = model.predict([[input1, input2]])[0]
	similarity_pct = score * 100

	if score >= THRESHOLD:
	result = "✅ MATCH"
	confidence_label = "High" if score > 0.85 else "Medium"
	else:
	result = "❌ NO MATCH"
	confidence_label = "High" if score < 0.40 else "Medium"

	similarity_str = f"{similarity_pct:.2f}%"
	result_str = f"{result} • Confidence: {confidence_label}"

	return similarity_str, result_str, float(similarity_pct)


	# ── Custom CSS ──────────────────────────────────────────────────────────────
	custom_css = """
	@import url('https://fonts.googleapis.com/css2?family=Space+Mono:wght@400;700&family=DM+Sans:wght@300;400;500;600&display=swap');

	:root {
	--bg: #0b0f1a;
	--surface: #111827;
	--border: #1f2d45;
	--accent: #38bdf8;
	--accent2: #818cf8;
	--green: #34d399;
	--red: #f87171;
	--yellow: #fbbf24;
	--text: #e2e8f0;
	--muted: #64748b;
	--radius: 12px;
	}

	body, .gradio-container {
	background: var(--bg) !important;
	font-family: 'DM Sans', sans-serif !important;
	color: var(--text) !important;
	}

	/* ── header ── */
	#header-box {
	background: linear-gradient(135deg, #0f172a 0%, #1e293b 100%);
	border: 1px solid var(--border);
	border-radius: var(--radius);
	padding: 36px 40px 28px;
	margin-bottom: 24px;
	position: relative;
	overflow: hidden;
	}
	#header-box::before {
	content: '';
	position: absolute;
	top: -60px; right: -60px;
	width: 200px; height: 200px;
	background: radial-gradient(circle, rgba(56,189,248,0.12) 0%, transparent 70%);
	pointer-events: none;
	}
	#header-box h1 {
	font-family: 'Space Mono', monospace !important;
	font-size: 1.9rem !important;
	font-weight: 700 !important;
	color: var(--accent) !important;
	margin: 0 0 8px !important;
	letter-spacing: -0.5px;
	}
	#header-box p {
	color: var(--muted) !important;
	font-size: 0.95rem !important;
	margin: 0 !important;
	line-height: 1.6;
	}
	.badge {
	display: inline-block;
	background: rgba(56,189,248,0.12);
	border: 1px solid rgba(56,189,248,0.3);
	color: var(--accent);
	font-family: 'Space Mono', monospace;
	font-size: 0.7rem;
	padding: 3px 10px;
	border-radius: 20px;
	margin-right: 8px;
	margin-top: 12px;
	}

	/* ── input cards ── */
	.input-card textarea,
	.input-card input {
	background: var(--surface) !important;
	border: 1px solid var(--border) !important;
	border-radius: var(--radius) !important;
	color: var(--text) !important;
	font-family: 'DM Sans', sans-serif !important;
	font-size: 0.95rem !important;
	padding: 14px 16px !important;
	transition: border-color 0.2s;
	}
	.input-card textarea:focus,
	.input-card input:focus {
	border-color: var(--accent) !important;
	box-shadow: 0 0 0 3px rgba(56,189,248,0.1) !important;
	}
	label span {
	font-family: 'Space Mono', monospace !important;
	font-size: 0.75rem !important;
	color: var(--accent2) !important;
	letter-spacing: 0.5px;
	text-transform: uppercase;
	}

	/* ── button ── */
	#run-btn {
	background: linear-gradient(135deg, var(--accent) 0%, var(--accent2) 100%) !important;
	border: none !important;
	border-radius: var(--radius) !important;
	color: #0b0f1a !important;
	font-family: 'Space Mono', monospace !important;
	font-size: 0.9rem !important;
	font-weight: 700 !important;
	letter-spacing: 0.5px;
	padding: 14px 32px !important;
	cursor: pointer;
	transition: opacity 0.2s, transform 0.15s;
	width: 100%;
	margin-top: 8px;
	}
	#run-btn:hover { opacity: 0.9; transform: translateY(-1px); }
	#run-btn:active { transform: translateY(0); }

	/* ── output cards ── */
	.output-card textarea,
	.output-card input {
	background: #0d1424 !important;
	border: 1px solid var(--border) !important;
	border-radius: var(--radius) !important;
	color: var(--text) !important;
	font-family: 'Space Mono', monospace !important;
	font-size: 1.1rem !important;
	font-weight: 700 !important;
	text-align: center;
	}

	/* ── slider (score bar) ── */
	.score-slider input[type=range] {
	accent-color: var(--accent);
	}

	/* ── examples table ── */
	.gr-samples-table {
	background: var(--surface) !important;
	border: 1px solid var(--border) !important;
	border-radius: var(--radius) !important;
	}
	.gr-samples-table th {
	font-family: 'Space Mono', monospace !important;
	font-size: 0.72rem !important;
	color: var(--muted) !important;
	text-transform: uppercase;
	letter-spacing: 0.5px;
	background: #0d1424 !important;
	}
	.gr-samples-table td {
	color: var(--text) !important;
	font-size: 0.88rem !important;
	}
	.gr-samples-table tr:hover td {
	background: rgba(56,189,248,0.04) !important;
	}

	/* ── info footer ── */
	#footer-info {
	background: var(--surface);
	border: 1px solid var(--border);
	border-radius: var(--radius);
	padding: 20px 24px;
	margin-top: 20px;
	}
	#footer-info p {
	color: var(--muted) !important;
	font-family: 'Space Mono', monospace !important;
	font-size: 0.78rem !important;
	margin: 4px 0 !important;
	line-height: 1.7;
	}
	#footer-info span { color: var(--accent) !important; }
	"""

	# ── Gradio UI ────────────────────────────────────────────────────────────────
	with gr.Blocks(css=custom_css, title="Address Entity Matcher") as demo:

	# Header
	gr.HTML("""
	<div id="header-box">
	<h1>Address Entity Matcher</h1>
	<p>
	Enter two addresses to determine whether they refer to the same location.<br>
	Powered by a fine-tuned <strong>BGE-Reranker-v2-m3</strong> cross-encoder model.
	</p>
	<span class="badge">CrossEncoder</span>
	<span class="badge">BGE-Reranker-v2-m3</span>
	<span class="badge">Threshold: 0.75</span>
	</div>
	""")

	# Inputs
	with gr.Row(equal_height=True):
	with gr.Column(elem_classes="input-card"):
	input1 = gr.Textbox(
	label="Address 1",
	placeholder="e.g., Flat 12-B Sector 5 Noida",
	lines=3,
	)
	with gr.Column(elem_classes="input-card"):
	input2 = gr.Textbox(
	label="Address 2",
	placeholder="e.g., Flat 23-B Sector 5 Noida",
	lines=3,
	)

	btn = gr.Button(" Check Match", elem_id="run-btn", variant="primary")

	# Outputs
	with gr.Row(equal_height=True):
	with gr.Column(elem_classes="output-card"):
	similarity_output = gr.Textbox(
	label="Similarity Score",
	interactive=False,
	placeholder="—",
	)
	with gr.Column(elem_classes="output-card"):
	result_output = gr.Textbox(
	label="Match Result",
	interactive=False,
	placeholder="—",
	)

	score_bar = gr.Slider(
	minimum=0,
	maximum=100,
	value=0,
	step=0.01,
	label="Score Visualisation (threshold line: 75%)",
	interactive=False,
	elem_classes="score-slider",
	)

	# Examples
	gr.Examples(
	examples=[
	["Flat 12-B Sector 5 Noida", "Flat 23-B Sector 5 Noida"],
	["Phase 4 Whitefield Bangalore", "Whitefield Phase V Bangalore"],
	["Thirteen I 7th Avenue Adyar Chennai", "13 Seventh Avenue Adyar Chennai"],
	["Twenty Nine A Second Cross Koramangala Bengaluru", "47 Forty Seven B Third Street Indiranagar Bengaluru"],
	["Plot 8 Banjara Hills Hyderabad", "Plot 8 Banjara Hills Hyderabad"],
	["House No 4 Lane 2 DLF Phase 1 Gurugram", "H.No 4/2 DLF Phase One Gurgaon"],
	],
	inputs=[input1, input2],
	label="Examples",
	)

	# Footer info
	gr.HTML(f"""
	<div id="footer-info">
	<p> <strong>Model:</strong> <span>pujithapsx/address-crossencoder-bge-reranker-v2-m3-finetuned</span></p>
	<p><strong>Threshold:</strong> <span>{THRESHOLD}</span> — Score ≥ {THRESHOLD} → MATCH  \|  Score < {THRESHOLD} → NO MATCH</p>
	<p> <strong>Confidence:</strong> High (score > 0.85 or < 0.40)  \|  Medium (otherwise)</p>
	</div>
	""")

	# Wiring
	btn.click(
	fn=predict_similarity,
	inputs=[input1, input2],
	outputs=[similarity_output, result_output, score_bar],
	)

	if __name__ == "__main__":
	demo.launch()