Glov Marketplace IQ

Boost Shopping Experience with Enriched Accurate Complete Content

Turn your disorganized and inaccurately mapped catalogue data into pristine, structured content.

Product tagger

Simplify catalog management with Glov. No more manual tagging!

Our AI uses multimodal (visual and textual) data to extract features and generate detailed product tags. Enhance your online store’s product discoverability and make it easier for customers to find what they want.

Copy Rewriter

Revamp your product titles, labels and descriptions for higher conversions. Tailored alternatives for specific audiences.

Similarity Shopper

Drive conversions with personalized product recommendations powered by our MultiModal AI (visual+textual) technology.

With 300+ features, suggest closely matched items from your catalog. Never miss a sale due to out-of-stock items. Improve visibility, relevancy, and customer discovery.

Connect, enrich & sit back

Effortlessly set up your product index using a few API calls. Leverage the endpoints to quickly assure quality and enrich your content using the latest AI models.

Upload Products
Extract Features
Fix Records
Group Products

				
					import glov
glov.init(api_token="YOUR_API_TOKEN")

# create a catalog
cat = "my_awesome_shop"
glov.create_catalog(catalog_name=cat)
    
#create a product instance
my_product = {
    "id": "unique_product_id",
    "schema_group": "product_category", # feature set group
    "text_data": {
        "name": "Product Name",
        "description": "<div> Product Description as displayed on site </div>",
        "user_reviews": [ ... ],
    },
    "image_urls": [ ... ] # multi-modal content
}

# upload product data to catalog
glov.upsert_to_catalog(cat, my_product)

				
					import glov
glov.init(api_token="YOUR_API_TOKEN")

# When no prior schema is defined, infer a schema first, thena apply the schema
glov.apply_schema(
    catalog_name=cat,
    schema_group= "product_category",
    product_id="my_product",
    schema=None
)

# OUTPUT:
{
    "productID": "unique_product_id",
    "labels": "Sofa",
    "fabricColor": "Cream",
    "typesOfFabrics": "boucle fabric",
    "function": "Non-extendible",
    "seatingComfort": "Soft",
    "frameMaterial": "Plywood",
    "fillingMaterial": "32 kg/m3 sponge",
    "backCushion": "Sponge",
    "legMaterial": "Wood",
    "legColor": "Gold",
    "dimensions": "70 cm H x 380 cm W x 110 cm D",
    "seatDepth": "70 cm"
}

				
					import glov
glov.init(api_token="YOUR_API_TOKEN")

glov.get_schema_value_suggestions(
    catalog_name=cat,
    schema_group= "product_category"
)

# OUTPUT:
[
    {
        "current_value": "Ivory",
        "suggested_value": "Cream",
        "schema_path": ["fabric", "color"],
        "reason": "Distinct Value Reduction"
    },
    {
        "current_value": "Soft-Medium",
        "suggested_value": "Soft",
        "schema_path": ["seating", "comfort"],
        "reason": "Distinct Value Reduction"
    },
    {
        "current_value": "Wood",
        "suggested_value": "Plywood",
        "schema_path": ["frame", "material"],
        "reason": "Normalization"
    }
]

				
					import glov
glov.init(api_token="YOUR_API_TOKEN")

glov.create_grouping_rule(
    catalog_name=cat,
    schema_group= "product_category",
    rule_id="sofa_similarity_by_look",
    rule={
        "type": "similarity",
        "schema_paths": [
            ["fabric", "color"],
            ["fabric", "material"],
            ["style"],
            ["leg", "material"],
            ["leg", "color"]
        ],
        "algorithm": "skyline",
        "metric": "cosine",
    }
)

glov.get_item_in_group(
    catalog_name=cat,
    schema_group= "product_category",
    rule_id="sofa_similarity_by_look",
    product_id="my_product"
)

# OUTPUT:
[
    {
        "id": "unique_product_id_1",
        "score": 0.98
    },
    {
        "id": "unique_product_id_2",
        "score": 0.95
    },
]