Hugging Face's logo

Spaces:
ramitha2002
/
product-reranker-model-api
Running on Zero

App Files Community
product-reranker-model-api
File size: 3,166 Bytes
6e15691
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from typing import Any

import gradio as gr
import spaces
from sentence_transformers import CrossEncoder


MODEL_ID = "ramitha2002/genieai-product-reranker"

# ZeroGPU requires CUDA placement at module level.
model = CrossEncoder(
    MODEL_ID,
    device="cuda",
    max_length=384,
)


def format_value(value: Any) -> str:
    if isinstance(value, list):
        return ", ".join(str(item) for item in value)
    return str(value)


def build_product_text(product: dict[str, Any]) -> str:
    fields = [
        ("Title", product.get("title") or product.get("name")),
        ("Description", product.get("description") or product.get("summary")),
        ("Features", product.get("features")),
        ("Brand", product.get("brand")),
        ("Color", product.get("color")),
        ("Category", product.get("category")),
    ]

    return "\n".join(
        f"{label}: {format_value(value)}"
        for label, value in fields
        if value is not None and value != ""
    )


@spaces.GPU(duration=30)
def rerank(
    query: str,
    products: list[dict[str, Any]],
    top_n: int,
) -> dict[str, Any]:
    query = query.strip()

    if not query:
        raise gr.Error("Query is required.")

    if not isinstance(products, list) or not products:
        raise gr.Error("Products must be a non-empty JSON array.")

    if len(products) > 30:
        raise gr.Error("Maximum 30 products per request.")

    pairs = [
        (query, build_product_text(product))
        for product in products
    ]

    scores = model.predict(
        pairs,
        batch_size=min(16, len(pairs)),
        show_progress_bar=False,
    )

    ranked = sorted(
        [
            {
                **product,
                "rerankerScore": float(score),
            }
            for product, score in zip(products, scores)
        ],
        key=lambda product: product["rerankerScore"],
        reverse=True,
    )

    return {
        "results": ranked[:max(1, min(int(top_n), len(ranked)))]
    }


sample_products = [
    {
        "id": "flowers-1",
        "name": "Pink Rose Bouquet",
        "description": "Fresh roses arranged for birthdays",
        "brand": "Bloom House",
        "color": "Pink"
    },
    {
        "id": "mouse-1",
        "name": "Wireless Gaming Mouse",
        "description": "RGB computer mouse",
        "brand": "GamePoint",
        "color": "Black"
    }
]


with gr.Blocks(title="GenieAI Product Reranker") as demo:
    gr.Markdown("# GenieAI Product Reranker")

    query_input = gr.Textbox(
        label="Search query",
        value="birthday flowers for mother",
    )

    products_input = gr.JSON(
        label="Products",
        value=sample_products,
    )

    top_n_input = gr.Slider(
        minimum=1,
        maximum=30,
        value=4,
        step=1,
        label="Number of results",
    )

    rerank_button = gr.Button("Rerank", variant="primary")
    output = gr.JSON(label="Ranked products")

    rerank_button.click(
        fn=rerank,
        inputs=[query_input, products_input, top_n_input],
        outputs=output,
        api_name="rerank",
    )

demo.queue(default_concurrency_limit=2).launch()