scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-15 23:31:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 165

(sap) add filtering, masking, translation SAP GEN AI Hub modules

Browse source
This commit is contained in:
Vasilisa Parshikova 2026-02-17 20:36:56 +04:00 • committed by Sameer Kankute
parent d0bb619365
commit f6e331a436
No known key found for this signature in database
2 changed files with 513 additions and 75 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

522
litellm/llms/sap/chat/models.py
View file

@ -1,4 +1,5 @@
from typing import Union, Literal
from typing import Union, Literal, Optional
from enum import Enum
from pydantic import BaseModel, Field, field_validator, model_validator, ValidationError
@ -20,7 +21,7 @@ def validate_different_content(v: Union[str, dict, list]) -> str:
elif isinstance(v, str):
return v
raise ValueError("Content must be a string")
return v
class TextContent(BaseModel):
@ -113,6 +114,7 @@ class SAPToolChatMessage(BaseModel):
validate_different_content
)
ChatMessage = Union[SAPUserMessage, SAPAssistantMessage, SAPToolChatMessage, SAPMessage]
@ -155,11 +157,11 @@ class GroundingSearchConfig(BaseModel):
class DocumentGroundingFilter(BaseModel):
id_: str = Field(default=None, alias="id")
data_repository_type: Literal["vector", "help.sap.com"]
search_config: GroundingSearchConfig = None
data_repositories: list[str] = None
data_repository_metadata: list[KeyValueListPair] = None
document_metadata: list[DocumentMetadataKeyValueListPairs] = None
chunk_metadata: list[KeyValueListPair] = None
search_config: Optional[GroundingSearchConfig] = None
data_repositories: Optional[list[str]]= None
data_repository_metadata: Optional[list[KeyValueListPair]] = None
document_metadata: Optional[list[DocumentMetadataKeyValueListPairs]] = None
chunk_metadata: Optional[list[KeyValueListPair]] = None
class DocumentGroundingPlaceholders(BaseModel):
@ -168,9 +170,9 @@ class DocumentGroundingPlaceholders(BaseModel):
class DocumentGroundingConfig(BaseModel):
filters: list[DocumentGroundingFilter] = None
filters: Optional[list[DocumentGroundingFilter]] = None
placeholders: DocumentGroundingPlaceholders
metadata_params: list[str] = None
metadata_params: Optional[list[str]] = None
class GroundingModuleConfig(BaseModel):
@ -180,15 +182,15 @@ class GroundingModuleConfig(BaseModel):
class Template(BaseModel):
template: list[ChatMessage]
defaults: dict = None
response_format: ResponseFormat | ResponseFormatJSONSchema = None
tools: list[ChatCompletionTool] = None
defaults: Optional[dict[str, str]] = None
response_format: Optional[Union[ResponseFormat, ResponseFormatJSONSchema]] = None
tools: Optional[list[ChatCompletionTool]] = None
class LLMModelDetails(BaseModel):
name: str
version: str = "latest"
params: dict = None
params: Optional[dict] = None
class PromptTemplatingModuleConfig(BaseModel):
@ -196,44 +198,486 @@ class PromptTemplatingModuleConfig(BaseModel):
model: LLMModelDetails
class SAPMaskingProfileEntity(str, Enum):
"""
Enumerates the entity categories that can be masked by the SAP Data Privacy Integration service.
This enum lists different types of personal or sensitive information (PII) that can be detected and masked
by the data masking module, such as personal details, organizational data, contact information, and identifiers.
Values:
PERSON: Represents personal names.
ORG: Represents organizational names.
UNIVERSITY: Represents educational institutions.
LOCATION: Represents geographical locations.
EMAIL: Represents email addresses.
PHONE: Represents phone numbers.
ADDRESS: Represents physical addresses.
SAP_IDS_INTERNAL: Represents internal SAP identifiers.
SAP_IDS_PUBLIC: Represents public SAP identifiers.
URL: Represents URLs.
USERNAME_PASSWORD: Represents usernames and passwords.
NATIONAL_ID: Represents national identification numbers.
IBAN: Represents International Bank Account Numbers.
SSN: Represents Social Security Numbers.
CREDIT_CARD_NUMBER: Represents credit card numbers.
PASSPORT: Represents passport numbers.
DRIVING_LICENSE: Represents driving license numbers.
NATIONALITY: Represents nationality information.
RELIGIOUS_GROUP: Represents religious group affiliation.
POLITICAL_GROUP: Represents political group affiliation.
PRONOUNS_GENDER: Represents pronouns and gender identity.
GENDER: Represents gender information.
SEXUAL_ORIENTATION: Represents sexual orientation.
TRADE_UNION: Represents trade union membership.
SENSITIVE_DATA: Represents any other sensitive information.
"""
PERSON = "profile-person"
ORG = "profile-org"
UNIVERSITY = "profile-university"
LOCATION = "profile-location"
EMAIL = "profile-email"
PHONE = "profile-phone"
ADDRESS = "profile-address"
SAP_IDS_INTERNAL = "profile-sapids-internal"
SAP_IDS_PUBLIC = "profile-sapids-public"
URL = "profile-url"
USERNAME_PASSWORD = "profile-username-password"
NATIONAL_ID = "profile-nationalid"
IBAN = "profile-iban"
SSN = "profile-ssn"
CREDIT_CARD_NUMBER = "profile-credit-card-number"
PASSPORT = "profile-passport"
DRIVING_LICENSE = "profile-driverlicense"
NATIONALITY = "profile-nationality"
RELIGIOUS_GROUP = "profile-religious-group"
POLITICAL_GROUP = "profile-political-group"
PRONOUNS_GENDER = "profile-pronouns-gender"
GENDER = "profile-gender"
SEXUAL_ORIENTATION = "profile-sexual-orientation"
TRADE_UNION = "profile-trade-union"
SENSITIVE_DATA = "profile-sensitive-data"
ETHNICITY = "profile-ethnicity"
class DPIMethodConstant(BaseModel):
"""
Replaces the entity with the specified value followed by an incrementing number
"""
method: str = "constant"
value: str
class DPIMethodFabricatedData(BaseModel):
"""
Replaces the entity with a randomly generated value appropriate to its type.
"""
method: str = "fabricated_data"
class DPICustomEntity(BaseModel):
"""
regex: Regular expression to match the entity
replacement_strategy: Replacement strategy to be used for the entity
"""
regex: str
replacement_strategy: DPIMethodConstant
class DPIStandardEntity(BaseModel):
"""
type: Standard entity type to be masked
replacement_strategy: Replacement strategy to be used for the entity
"""
type_: SAPMaskingProfileEntity = Field(..., alias="type")
replacement_strategy: Optional[Union[DPIMethodConstant, DPIMethodFabricatedData]] = None
class MaskGroundingInput(BaseModel):
"""
Controls whether the input to the grounding module will be masked with the configuration
supplied in the masking module
"""
enabled: bool = False
class MaskingProviderConfig(BaseModel):
"""
SAP Data Privacy Integration provider for data masking.
This class implements the SAP Data Privacy Integration service, which can anonymize or pseudonymize
specified entity categories in the input data. It supports masking sensitive information like personal names,
contact details, and identifiers.
Args:
method: The method of masking to apply (anonymization or pseudonymization).
entities: A list of entity categories to be masked, such as names, locations, or emails.
allowlist: A list of strings that should not be masked.
mask_grounding_input: A flag indicating whether to mask input to the grounding module.
"""
type_: str = Field(default="sap_data_privacy_integration", alias="type")
method: Literal["anonymization", "pseudonymization"]
entities: list[Union[DPIStandardEntity, DPICustomEntity]]
allowlist: Optional[list[str]] = None
mask_grounding_input: Optional[MaskGroundingInput] = None
class MaskingModuleConfig(BaseModel):
"""
Configuration for the data masking module.
Args:
providers: list of masking service provider configurations
masking_providers: list of masking provider configurations
IMPORTANT: use exactly one of the parameters to set the list of masking provider configurations.
DEPRECATED: parameter 'masking_providers' will be removed Sept 15, 2026. Use 'providers' instead.
"""
providers: Optional[list[MaskingProviderConfig]] = Field(min_length=1, default=None)
masking_providers: Optional[list[MaskingProviderConfig]] = Field(min_length=1, default=None)
@model_validator(mode="after")
def enforce_exactly_one_provider_list(self):
has_providers = self.providers is not None
has_masking_providers = self.masking_providers is not None
if has_providers == has_masking_providers:
raise ValueError(
"For SAP Masking Module Config must set exactly one of: 'providers' or 'masking_providers' "
"DEPRECATED: parameter 'masking_providers' will be removed Sept 15, 2026. Use 'providers' instead."
)
return self
class AzureThreshold(int, Enum):
"""
Enumerates the threshold levels for the Azure Content Safety service.
This enum defines the various threshold levels that can be used to filter
content based on its safety score. Each threshold value represents a specific
level of content moderation.
Values:
ALLOW_SAFE: Allows only Safe content.
ALLOW_SAFE_LOW: Allows Safe and Low content.
ALLOW_SAFE_LOW_MEDIUM: Allows Safe, Low, and Medium content.
ALLOW_ALL: Allows all content (Safe, Low, Medium, and High).
"""
ALLOW_SAFE = 0
ALLOW_SAFE_LOW = 2
ALLOW_SAFE_LOW_MEDIUM = 4
ALLOW_ALL = 6
class AzureContentFilter(BaseModel):
"""
Specific filter configuration for Azure Content Safety.
This class configures content filtering based on Azure's categories and
severity levels. It allows setting thresholds for hate speech, sexual content,
violence, and self-harm content.
Values:
hate: Threshold for hate speech content.
sexual: Threshold for sexual content.
violence: Threshold for violent content.
self_harm: Threshold for self-harm content.
"""
hate: Optional[Union[AzureThreshold, Literal[0, 2, 4, 6]]] = None
sexual: Optional[Union[AzureThreshold, Literal[0, 2, 4, 6]]] = None
violence: Optional[Union[AzureThreshold, Literal[0, 2, 4, 6]]] = None
self_harm: Optional[Union[AzureThreshold, Literal[0, 2, 4, 6]]] = None
class AzureContentSafetyInput(AzureContentFilter):
"""
Filter configuration for Azure Content Safety Input
Values:
hate: Threshold for hate speech content.
sexual: Threshold for sexual content.
violence: Threshold for violent content.
self_harm: Threshold for self-harm content.
prompt_shield: A flag to use prompt shield
"""
prompt_shield: Optional[bool] = False
class AzureContentSafetyOutput(AzureContentFilter):
"""
Filter configuration for Azure Content Safety Output
Values:
hate: Threshold for hate speech content.
sexual: Threshold for sexual content.
violence: Threshold for violent content.
self_harm: Threshold for self-harm content.
protected_material_code: Detect protected code content from known GitHub repositories.
The scan includes software libraries, source code, algorithms,
and other proprietary programming content.
"""
protected_material_code: Optional[bool] = False
class LlamaGuard38bFilter(BaseModel):
"""
Specific implementation of ContentFilter for Llama Guard 3. Llama Guard 3 is a
Llama-3.1-8B pretrained model, fine-tuned for content safety classification.
Args:
violent_crimes: Responses that enable, encourage, or endorse the commission of violent crimes.
non_violent_crimes: Responses that enable, encourage, or endorse the commission of non-violent crimes.
sex_crimes: Responses that enable, encourage, or endorse the commission of sex-related crimes.
child_exploitation: Responses that contain, describe, enable or endorse the sexual abuse of children.
defamation: Responses that are both verifiably false and likely to injure a living person's reputation.
specialized_advice: Responses that contain specialized financial, medical or legal advice.
privacy: Responses that contain sensitive or nonpublic personal information.
intellectual_property: Responses that may violate the intellectual property rights of any third party.
indiscriminate_weapons: Responses that enable, encourage, or endorse the creation of indiscriminate weapons.
hate: Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics.
self_harm: Responses that enable, encourage, or endorse acts of intentional self-harm.
sexual_content: Responses that contain erotica.
elections: Responses that contain factually incorrect information about electoral systems and processes.
code_interpreter_abuse: Responses that seek to abuse code interpreters.
"""
violent_crimes: bool = Field(default=False)
non_violent_crimes: bool = Field(default=False)
sex_crimes: bool = Field(default=False)
child_exploitation: bool = Field(default=False)
defamation: bool = Field(default=False)
specialized_advice: bool = Field(default=False)
privacy: bool = Field(default=False)
intellectual_property: bool = Field(default=False)
indiscriminate_weapons: bool = Field(default=False)
hate: bool = Field(default=False)
self_harm: bool = Field(default=False)
sexual_content: bool = Field(default=False)
elections: bool = Field(default=False)
code_interpreter_abuse: bool = Field(default=False)
class LlamaGuard38bFilterConfig(BaseModel):
type_: str = Field(default="llama_guard_3_8b", alias="type")
config: LlamaGuard38bFilter
class AzureContentSafetyInputFilterConfig(BaseModel):
type_: str = Field(default="azure_content_safety", alias="type")
config: Optional[AzureContentSafetyInput] = None
class AzureContentSafetyOutputFilterConfig(BaseModel):
type_: str = Field(default="azure_content_safety", alias="type")
config: Optional[AzureContentSafetyOutput] = None
class FilteringStreamOptions(BaseModel):
"""
overlap: Number of characters that should be additionally sent to content filtering services
from previous chunks as additional context.
"""
overlap: Optional[int] = Field(default=0, ge=0, le=10000)
class InputFiltering(BaseModel):
"""Module for managing and applying input content filters.
Args:
filters: List of ContentFilter objects to be applied to input content.
"""
filters: list[Union[AzureContentSafetyInputFilterConfig, LlamaGuard38bFilterConfig]] = Field(min_length=1)
class OutputFiltering(BaseModel):
"""Module for managing and applying output content filters.
Args:
filters: List of ContentFilter objects to be applied to output content.
stream_options: Module-specific streaming options.
"""
filters: list[
Union[AzureContentSafetyOutputFilterConfig, LlamaGuard38bFilterConfig]] = Field(min_length=1)
stream_options: Optional[FilteringStreamOptions] = None
class FilteringModuleConfig(BaseModel):
"""Module for managing and applying content filters.
Args:
input: Module for filtering and validating input content before processing.
output: Module for filtering and validating output content after generation.
"""
input: Optional[InputFiltering] = None
output: Optional[OutputFiltering] = None
@model_validator(mode="after")
def enforce_min_properties(cls, values): # pylint: disable=no-self-argument
"""
Ensure at least one of input or output filtering is provided.
"""
assert values.input is not None or values.output is not None, \
"For using SAP Filtering Module you must provide at least one property: input or output filters."
return values
class SAPDocumentTranslationApplyToSelector(BaseModel):
"""
This selector allows you to define the scope of translation, such as specific placeholders or
messages with specific roles.
For example, {"category": "placeholders",
"items": ["user_input"],
"source_language": "de-DE"}
targets the value of "user_input" in placeholder_values specified in the request payload;
and considers the value to be in German.
"""
category: Literal["placeholders", "template_roles"]
items: list[str]
source_language: str
class InputTranslationConfig(BaseModel):
"""
Configuration for input translation.
Args:
source_language: Language of the text to be translated. Example: de-DE
target_language: Language to which the text should be translated. Example: en-US
apply_to: List of selectors that define the scope of translation.
"""
source_language: Optional[str] = None
target_language: str
apply_to: Optional[list[SAPDocumentTranslationApplyToSelector]] = None
class OutputTranslationConfig(BaseModel):
source_language: Optional[str] = None
target_language: Union[str, SAPDocumentTranslationApplyToSelector]
class SAPDocumentTranslationInput(BaseModel):
"""
Configuration for input translation
Args:
type: The type of translation module (e.g., 'sap_document_translation').
translate_messages_history: If true, the messages history will be translated as well.
config: Configuration object for the translation module.
"""
type_: str = Field(default="sap_document_translation", alias="type")
translate_messages_history: Optional[bool] = None
config: InputTranslationConfig
class SAPDocumentTranslationOutput(BaseModel):
"""
Configuration for output translation
Args:
type: The type of translation module (e.g., 'sap_document_translation').
config: Configuration object for the translation module.
"""
type_: str = Field(default="sap_document_translation", alias="type")
config: OutputTranslationConfig
class TranslationModuleConfig(BaseModel):
"""
Configuration for translation module
Args:
input: Configuration for input translation
output: Configuration for output translation
"""
input: Optional[SAPDocumentTranslationInput] = None
output: Optional[SAPDocumentTranslationOutput] = None
class ModuleConfig(BaseModel):
prompt_templating: PromptTemplatingModuleConfig
# filtering: Optional[FilteringModuleConfig] = None
# masking: Optional[MaskingModuleConfig] = None
grounding: GroundingModuleConfig = None
# translation: Optional[TranslationModuleConfig] = None
filtering: Optional[FilteringModuleConfig] = None
masking: Optional[MaskingModuleConfig] = None
grounding: Optional[GroundingModuleConfig] = None
translation: Optional[TranslationModuleConfig] = None
class GlobalStreamOptions(BaseModel):
enabled: bool = False
chunk_size: int = 100
delimiters: list[str] = None
@model_validator(mode='after')
def validate_streaming_params(self):
"""Validate that chunk_size and delimiters are not set when enabled is False."""
if not self.enabled:
if self.chunk_size != 100: # Check if chunk_size was explicitly set
raise ValueError("chunk_size cannot be set when enabled is False")
if self.delimiters is not None:
raise ValueError("delimiters cannot be set when enabled is False")
return self
def model_dump(self, **kwargs):
"""Override model_dump to exclude chunk_size and delimiters when enabled is False."""
data = super().model_dump(**kwargs)
if not self.enabled:
# Remove chunk_size and delimiters from output when streaming is disabled
data.pop('chunk_size', None)
data.pop('delimiters', None)
return data
delimiters: Optional[list[str]] = None
class OrchestrationConfig(BaseModel):
modules: ModuleConfig
stream: GlobalStreamOptions = None
stream: Optional[GlobalStreamOptions] = None
class OrchestrationRequest(BaseModel):
config: OrchestrationConfig
placeholder_values: dict = None
placeholder_values: Optional[dict[str, str]] = None

66
litellm/llms/sap/chat/transformation.py
View file

@ -218,20 +218,7 @@ class GenAIHubOrchestrationConfig(OpenAIGPTConfig):
litellm_params: dict,
headers: dict,
) -> dict:
# Filter out parameters that are not valid model params for SAP Orchestration API
# - tools, model_version, deployment_url: handled separately
excluded_params = {"tools", "model_version", "deployment_url"}
# Filter strict for GPT models only - SAP AI Core doesn't accept it as a model param
# LangChain agents pass strict=true at top level, which fails for GPT models
# Anthropic models accept strict, so preserve it for them
if model.startswith("gpt"):
excluded_params.add("strict")
model_params = {
k: v for k, v in optional_params.items() if k not in {"tools", "model_version", "deployment_url", "grounding", "placeholder_values"}
}
optional_params.pop("deployment_url", None)
model_version = optional_params.pop("model_version", "latest")
template = messages
@ -241,7 +228,7 @@ class GenAIHubOrchestrationConfig(OpenAIGPTConfig):
else:
tools = {}
response_format = model_params.pop("response_format", {})
response_format = optional_params.pop("response_format", {})
resp_type = response_format.get("type", None)
if resp_type:
if resp_type == "json_schema":
@ -251,44 +238,51 @@ class GenAIHubOrchestrationConfig(OpenAIGPTConfig):
else:
response_format = validate_dict(response_format, ResponseFormat)
response_format = {"response_format": response_format}
model_params.pop("stream", False)
optional_params.pop("stream", False)
stream_config = {}
if "stream_options" in model_params:
# stream_config["enabled"] = True
stream_options = model_params.pop("stream_options", {})
if "stream_options" in optional_params:
stream_options = optional_params.pop("stream_options", {})
stream_config["chunk_size"] = stream_options.get("chunk_size", 100)
if "delimiters" in stream_options:
stream_config["delimiters"] = stream_options.get("delimiters")
# else:
# stream_config["enabled"] = False
placeholder_defaults = optional_params.pop("placeholder_defaults", {})
if placeholder_defaults:
placeholder_defaults = {"defaults": placeholder_defaults}
placeholder_values = optional_params.pop("placeholder_values", {})
if placeholder_values:
placeholder_values = {"placeholder_values": placeholder_values}
optional_modules = {}
optional_modules_lst = ["grounding", "masking", "filtering", "translation"]
for module in optional_modules_lst:
if optional_params.get(module, None):
optional_modules[module] = optional_params.pop(module)
request_body = {
"config": {
"modules": {
"prompt_templating": {
"prompt": {"template": template, **tools, **response_format},
"prompt": {
"template": template,
**placeholder_defaults,
**tools,
**response_format
},
"model": {
"name": model,
"params": model_params,
"params": optional_params,
"version": model_version,
},
},
**optional_modules
},
"stream": stream_config,
}
},
**placeholder_values,
}
placeholder_defaults = optional_params.pop("placeholder_defaults", {})
if placeholder_defaults:
request_body["config"]["modules"]["prompt_templating"]["prompt"]["defaults"] = placeholder_defaults
placeholder_values = optional_params.pop("placeholder_values", {})
if placeholder_values:
request_body["placeholder_values"] = placeholder_values
grounding_config = optional_params.pop("grounding", {})
if grounding_config:
request_body["config"]["modules"]["grounding"] = grounding_config
validate_dict(request_body, OrchestrationRequest)
return request_body