content_quality_tool/attr_extraction/serializers.py

# from rest_framework import serializers

# class ProductInputSerializer(serializers.Serializer):
#     """Serializer for individual product input."""
#     product_id = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     title = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     short_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     long_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)


# class SingleProductRequestSerializer(serializers.Serializer):
#     """Serializer for single product extraction request."""
#     title = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     short_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     long_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
#     mandatory_attrs = serializers.DictField(
#         child=serializers.ListField(child=serializers.CharField()),
#         required=True
#     )
#     model = serializers.CharField(required=False, default="llama-3.1-8b-instant")
#     extract_additional = serializers.BooleanField(required=False, default=True)

#     def validate_model(self, value):
#         from django.conf import settings
#         if value not in settings.SUPPORTED_MODELS:
#             raise serializers.ValidationError(
#                 f"Model must be one of {settings.SUPPORTED_MODELS}"
#             )
#         return value


# class BatchProductRequestSerializer(serializers.Serializer):
#     """Serializer for batch product extraction request."""
#     products = serializers.ListField(
#         child=ProductInputSerializer(),
#         required=True,
#         min_length=1
#     )
#     mandatory_attrs = serializers.DictField(
#         child=serializers.ListField(child=serializers.CharField()),
#         required=True
#     )
#     model = serializers.CharField(required=False, default="llama-3.1-8b-instant")
#     extract_additional = serializers.BooleanField(required=False, default=True)

#     def validate_model(self, value):
#         from django.conf import settings
#         if value not in settings.SUPPORTED_MODELS:
#             raise serializers.ValidationError(
#                 f"Model must be one of {settings.SUPPORTED_MODELS}"
#             )
#         return value

#     def validate_products(self, value):
#         from django.conf import settings
#         max_size = getattr(settings, 'MAX_BATCH_SIZE', 100)
#         if len(value) > max_size:
#             raise serializers.ValidationError(
#                 f"Batch size cannot exceed {max_size} products"
#             )
#         return value


# class ProductAttributeResultSerializer(serializers.Serializer):
#     """Serializer for individual product extraction result."""
#     product_id = serializers.CharField(required=False)
#     mandatory = serializers.DictField()
#     additional = serializers.DictField(required=False)
#     error = serializers.CharField(required=False)
#     raw_output = serializers.CharField(required=False)


# class BatchProductResponseSerializer(serializers.Serializer):
#     """Serializer for batch extraction response."""
#     results = serializers.ListField(child=ProductAttributeResultSerializer())
#     total_products = serializers.IntegerField()
#     successful = serializers.IntegerField()
#     failed = serializers.IntegerField()








# ==================== serializers.py ====================
from rest_framework import serializers

class ProductInputSerializer(serializers.Serializer):
    """Serializer for individual product input."""
    product_id = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    title = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    short_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    long_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    image_url = serializers.URLField(required=False, allow_blank=True, allow_null=True)


class SingleProductRequestSerializer(serializers.Serializer):
    """Serializer for single product extraction request."""
    # title = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    # short_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    # long_desc = serializers.CharField(required=False, allow_blank=True, allow_null=True)
    # image_url = serializers.URLField(required=False, allow_blank=True, allow_null=True)
    item_id = serializers.CharField(required=True)
    mandatory_attrs = serializers.DictField(
        child=serializers.ListField(child=serializers.CharField()),
        required=True
    )
    model = serializers.CharField(required=False, default="llama-3.1-8b-instant")
    extract_additional = serializers.BooleanField(required=False, default=True)
    process_image = serializers.BooleanField(required=False, default=True)

    def validate_model(self, value):
        from django.conf import settings
        if value not in settings.SUPPORTED_MODELS:
            raise serializers.ValidationError(
                f"Model must be one of {settings.SUPPORTED_MODELS}"
            )
        return value


# class BatchProductRequestSerializer(serializers.Serializer):
#     """Serializer for batch product extraction request."""
#     products = serializers.ListField(
#         child=ProductInputSerializer(),
#         required=True,
#         min_length=1
#     )
#     mandatory_attrs = serializers.DictField(
#         child=serializers.ListField(child=serializers.CharField()),
#         required=True
#     )
#     model = serializers.CharField(required=False, default="llama-3.1-8b-instant")
#     extract_additional = serializers.BooleanField(required=False, default=True)
#     process_image = serializers.BooleanField(required=False, default=True)

#     def validate_model(self, value):
#         from django.conf import settings
#         if value not in settings.SUPPORTED_MODELS:
#             raise serializers.ValidationError(
#                 f"Model must be one of {settings.SUPPORTED_MODELS}"
#             )
#         return value

#     def validate_products(self, value):
#         from django.conf import settings
#         max_size = getattr(settings, 'MAX_BATCH_SIZE', 100)
#         if len(value) > max_size:
#             raise serializers.ValidationError(
#                 f"Batch size cannot exceed {max_size} products"
#             )
#         return value


class BatchProductRequestSerializer(serializers.Serializer):
    """Serializer for batch product extraction request (by item_id)."""
    item_ids = serializers.ListField(
        child=serializers.CharField(),
        required=True,
        min_length=1
    )
    mandatory_attrs = serializers.DictField(
        child=serializers.ListField(child=serializers.CharField()),
        required=True
    )
    model = serializers.CharField(required=False, default="llama-3.1-8b-instant")
    extract_additional = serializers.BooleanField(required=False, default=True)
    process_image = serializers.BooleanField(required=False, default=True)

    def validate_model(self, value):
        from django.conf import settings
        if value not in settings.SUPPORTED_MODELS:
            raise serializers.ValidationError(
                f"Model must be one of {settings.SUPPORTED_MODELS}"
            )
        return value

    def validate_item_ids(self, value):
        from django.conf import settings
        max_size = getattr(settings, 'MAX_BATCH_SIZE', 100)
        if len(value) > max_size:
            raise serializers.ValidationError(
                f"Batch size cannot exceed {max_size} products"
            )
        return value



class OCRResultSerializer(serializers.Serializer):
    """Serializer for OCR results."""
    detected_text = serializers.ListField(child=serializers.DictField())
    extracted_attributes = serializers.DictField()


class ProductAttributeResultSerializer(serializers.Serializer):
    """Serializer for individual product extraction result."""
    product_id = serializers.CharField(required=False)
    mandatory = serializers.DictField()
    additional = serializers.DictField(required=False)
    ocr_results = OCRResultSerializer(required=False)
    error = serializers.CharField(required=False)
    raw_output = serializers.CharField(required=False)


class BatchProductResponseSerializer(serializers.Serializer):
    """Serializer for batch extraction response."""
    results = serializers.ListField(child=ProductAttributeResultSerializer())
    total_products = serializers.IntegerField()
    successful = serializers.IntegerField()
    failed = serializers.IntegerField()




from rest_framework import serializers
from .models import Product

class ProductSerializer(serializers.ModelSerializer):
    class Meta:
        model = Product
        fields = [
            'id',
            'item_id',
            'product_name',
            'product_long_description',
            'product_short_description',
            'product_type',
            'image_path',
            'image',
        ]