CfnKnowledgeBase
- class aws_cdk.aws_wisdom.CfnKnowledgeBase(scope, id, *, knowledge_base_type, name, description=None, rendering_configuration=None, server_side_encryption_configuration=None, source_configuration=None, tags=None, vector_ingestion_configuration=None)
Bases:
CfnResource
Specifies a knowledge base.
- See:
http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-wisdom-knowledgebase.html
- CloudformationResource:
AWS::Wisdom::KnowledgeBase
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom cfn_knowledge_base = wisdom.CfnKnowledgeBase(self, "MyCfnKnowledgeBase", knowledge_base_type="knowledgeBaseType", name="name", # the properties below are optional description="description", rendering_configuration=wisdom.CfnKnowledgeBase.RenderingConfigurationProperty( template_uri="templateUri" ), server_side_encryption_configuration=wisdom.CfnKnowledgeBase.ServerSideEncryptionConfigurationProperty( kms_key_id="kmsKeyId" ), source_configuration=wisdom.CfnKnowledgeBase.SourceConfigurationProperty( app_integrations=wisdom.CfnKnowledgeBase.AppIntegrationsConfigurationProperty( app_integration_arn="appIntegrationArn", # the properties below are optional object_fields=["objectFields"] ), managed_source_configuration=wisdom.CfnKnowledgeBase.ManagedSourceConfigurationProperty( web_crawler_configuration=wisdom.CfnKnowledgeBase.WebCrawlerConfigurationProperty( url_configuration=wisdom.CfnKnowledgeBase.UrlConfigurationProperty( seed_urls=[wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )] ), # the properties below are optional crawler_limits=wisdom.CfnKnowledgeBase.CrawlerLimitsProperty( rate_limit=123 ), exclusion_filters=["exclusionFilters"], inclusion_filters=["inclusionFilters"], scope="scope" ) ) ), tags=[CfnTag( key="key", value="value" )], vector_ingestion_configuration=wisdom.CfnKnowledgeBase.VectorIngestionConfigurationProperty( chunking_configuration=wisdom.CfnKnowledgeBase.ChunkingConfigurationProperty( chunking_strategy="chunkingStrategy", # the properties below are optional fixed_size_chunking_configuration=wisdom.CfnKnowledgeBase.FixedSizeChunkingConfigurationProperty( max_tokens=123, overlap_percentage=123 ), hierarchical_chunking_configuration=wisdom.CfnKnowledgeBase.HierarchicalChunkingConfigurationProperty( level_configurations=[wisdom.CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty( max_tokens=123 )], overlap_tokens=123 ), semantic_chunking_configuration=wisdom.CfnKnowledgeBase.SemanticChunkingConfigurationProperty( breakpoint_percentile_threshold=123, buffer_size=123, max_tokens=123 ) ), parsing_configuration=wisdom.CfnKnowledgeBase.ParsingConfigurationProperty( parsing_strategy="parsingStrategy", # the properties below are optional bedrock_foundation_model_configuration=wisdom.CfnKnowledgeBase.BedrockFoundationModelConfigurationProperty( model_arn="modelArn", # the properties below are optional parsing_prompt=wisdom.CfnKnowledgeBase.ParsingPromptProperty( parsing_prompt_text="parsingPromptText" ) ) ) ) )
- Parameters:
scope (
Construct
) – Scope in which this resource is defined.id (
str
) – Construct identifier for this resource (unique in its scope).knowledge_base_type (
str
) – The type of knowledge base. Only CUSTOM knowledge bases allow you to upload your own content. EXTERNAL knowledge bases support integrations with third-party systems whose content is synchronized automatically.name (
str
) – The name of the knowledge base.description (
Optional
[str
]) – The description.rendering_configuration (
Union
[IResolvable
,RenderingConfigurationProperty
,Dict
[str
,Any
],None
]) – Information about how to render the content.server_side_encryption_configuration (
Union
[IResolvable
,ServerSideEncryptionConfigurationProperty
,Dict
[str
,Any
],None
]) – This customer managed key must have a policy that allowskms:CreateGrant
andkms:DescribeKey
permissions to the IAM identity using the key to invoke Wisdom. For more information about setting up a customer managed key for Wisdom, see Enable Amazon Connect Wisdom for your instance . For information about valid ID values, see Key identifiers (KeyId) in the AWS Key Management Service Developer Guide .source_configuration (
Union
[IResolvable
,SourceConfigurationProperty
,Dict
[str
,Any
],None
]) – The source of the knowledge base content. Only set this argument for EXTERNAL or Managed knowledge bases.tags (
Optional
[Sequence
[Union
[CfnTag
,Dict
[str
,Any
]]]]) – The tags used to organize, track, or control access for this resource.vector_ingestion_configuration (
Union
[IResolvable
,VectorIngestionConfigurationProperty
,Dict
[str
,Any
],None
]) – Contains details about how to ingest the documents in a data source.
Methods
- add_deletion_override(path)
Syntactic sugar for
addOverride(path, undefined)
.- Parameters:
path (
str
) – The path of the value to delete.- Return type:
None
- add_dependency(target)
Indicates that this resource depends on another resource and cannot be provisioned unless the other resource has been successfully provisioned.
This can be used for resources across stacks (or nested stack) boundaries and the dependency will automatically be transferred to the relevant scope.
- Parameters:
target (
CfnResource
) –- Return type:
None
- add_depends_on(target)
(deprecated) Indicates that this resource depends on another resource and cannot be provisioned unless the other resource has been successfully provisioned.
- Parameters:
target (
CfnResource
) –- Deprecated:
use addDependency
- Stability:
deprecated
- Return type:
None
- add_metadata(key, value)
Add a value to the CloudFormation Resource Metadata.
- Parameters:
key (
str
) –value (
Any
) –
- See:
- Return type:
None
https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/metadata-section-structure.html
Note that this is a different set of metadata from CDK node metadata; this metadata ends up in the stack template under the resource, whereas CDK node metadata ends up in the Cloud Assembly.
- add_override(path, value)
Adds an override to the synthesized CloudFormation resource.
To add a property override, either use
addPropertyOverride
or prefixpath
with “Properties.” (i.e.Properties.TopicName
).If the override is nested, separate each nested level using a dot (.) in the path parameter. If there is an array as part of the nesting, specify the index in the path.
To include a literal
.
in the property name, prefix with a\
. In most programming languages you will need to write this as"\\."
because the\
itself will need to be escaped.For example:
cfn_resource.add_override("Properties.GlobalSecondaryIndexes.0.Projection.NonKeyAttributes", ["myattribute"]) cfn_resource.add_override("Properties.GlobalSecondaryIndexes.1.ProjectionType", "INCLUDE")
would add the overrides Example:
"Properties": { "GlobalSecondaryIndexes": [ { "Projection": { "NonKeyAttributes": [ "myattribute" ] ... } ... }, { "ProjectionType": "INCLUDE" ... }, ] ... }
The
value
argument toaddOverride
will not be processed or translated in any way. Pass raw JSON values in here with the correct capitalization for CloudFormation. If you pass CDK classes or structs, they will be rendered with lowercased key names, and CloudFormation will reject the template.- Parameters:
path (
str
) –The path of the property, you can use dot notation to override values in complex types. Any intermediate keys will be created as needed.
value (
Any
) –The value. Could be primitive or complex.
- Return type:
None
- add_property_deletion_override(property_path)
Adds an override that deletes the value of a property from the resource definition.
- Parameters:
property_path (
str
) – The path to the property.- Return type:
None
- add_property_override(property_path, value)
Adds an override to a resource property.
Syntactic sugar for
addOverride("Properties.<...>", value)
.- Parameters:
property_path (
str
) – The path of the property.value (
Any
) – The value.
- Return type:
None
- apply_removal_policy(policy=None, *, apply_to_update_replace_policy=None, default=None)
Sets the deletion policy of the resource based on the removal policy specified.
The Removal Policy controls what happens to this resource when it stops being managed by CloudFormation, either because you’ve removed it from the CDK application or because you’ve made a change that requires the resource to be replaced.
The resource can be deleted (
RemovalPolicy.DESTROY
), or left in your AWS account for data recovery and cleanup later (RemovalPolicy.RETAIN
). In some cases, a snapshot can be taken of the resource prior to deletion (RemovalPolicy.SNAPSHOT
). A list of resources that support this policy can be found in the following link:- Parameters:
policy (
Optional
[RemovalPolicy
]) –apply_to_update_replace_policy (
Optional
[bool
]) – Apply the same deletion policy to the resource’s “UpdateReplacePolicy”. Default: truedefault (
Optional
[RemovalPolicy
]) – The default policy to apply in case the removal policy is not defined. Default: - Default value is resource specific. To determine the default value for a resource, please consult that specific resource’s documentation.
- See:
- Return type:
None
- get_att(attribute_name, type_hint=None)
Returns a token for an runtime attribute of this resource.
Ideally, use generated attribute accessors (e.g.
resource.arn
), but this can be used for future compatibility in case there is no generated attribute.- Parameters:
attribute_name (
str
) – The name of the attribute.type_hint (
Optional
[ResolutionTypeHint
]) –
- Return type:
- get_metadata(key)
Retrieve a value value from the CloudFormation Resource Metadata.
- Parameters:
key (
str
) –- See:
- Return type:
Any
https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/metadata-section-structure.html
Note that this is a different set of metadata from CDK node metadata; this metadata ends up in the stack template under the resource, whereas CDK node metadata ends up in the Cloud Assembly.
- inspect(inspector)
Examines the CloudFormation resource and discloses attributes.
- Parameters:
inspector (
TreeInspector
) – tree inspector to collect and process attributes.- Return type:
None
- obtain_dependencies()
Retrieves an array of resources this resource depends on.
This assembles dependencies on resources across stacks (including nested stacks) automatically.
- Return type:
List
[Union
[Stack
,CfnResource
]]
- obtain_resource_dependencies()
Get a shallow copy of dependencies between this resource and other resources in the same stack.
- Return type:
List
[CfnResource
]
- override_logical_id(new_logical_id)
Overrides the auto-generated logical ID with a specific ID.
- Parameters:
new_logical_id (
str
) – The new logical ID to use for this stack element.- Return type:
None
- remove_dependency(target)
Indicates that this resource no longer depends on another resource.
This can be used for resources across stacks (including nested stacks) and the dependency will automatically be removed from the relevant scope.
- Parameters:
target (
CfnResource
) –- Return type:
None
- replace_dependency(target, new_target)
Replaces one dependency with another.
- Parameters:
target (
CfnResource
) – The dependency to replace.new_target (
CfnResource
) – The new dependency to add.
- Return type:
None
- to_string()
Returns a string representation of this construct.
- Return type:
str
- Returns:
a string representation of this resource
Attributes
- CFN_RESOURCE_TYPE_NAME = 'AWS::Wisdom::KnowledgeBase'
- attr_knowledge_base_arn
The Amazon Resource Name (ARN) of the knowledge base.
- CloudformationAttribute:
KnowledgeBaseArn
- attr_knowledge_base_id
The ID of the knowledge base.
- CloudformationAttribute:
KnowledgeBaseId
- cfn_options
Options for this resource, such as condition, update policy etc.
- cfn_resource_type
AWS resource type.
- creation_stack
return:
the stack trace of the point where this Resource was created from, sourced from the +metadata+ entry typed +aws:cdk:logicalId+, and with the bottom-most node +internal+ entries filtered.
- description
The description.
- knowledge_base_type
The type of knowledge base.
- logical_id
The logical ID for this CloudFormation stack element.
The logical ID of the element is calculated from the path of the resource node in the construct tree.
To override this value, use
overrideLogicalId(newLogicalId)
.- Returns:
the logical ID as a stringified token. This value will only get resolved during synthesis.
- name
The name of the knowledge base.
- node
The tree node.
- ref
Return a string that will be resolved to a CloudFormation
{ Ref }
for this element.If, by any chance, the intrinsic reference of a resource is not a string, you could coerce it to an IResolvable through
Lazy.any({ produce: resource.ref })
.
- rendering_configuration
Information about how to render the content.
- server_side_encryption_configuration
This customer managed key must have a policy that allows
kms:CreateGrant
andkms:DescribeKey
permissions to the IAM identity using the key to invoke Wisdom.
- source_configuration
The source of the knowledge base content.
- stack
The stack in which this element is defined.
CfnElements must be defined within a stack scope (directly or indirectly).
- tags
Tag Manager which manages the tags for this resource.
- tags_raw
The tags used to organize, track, or control access for this resource.
- vector_ingestion_configuration
Contains details about how to ingest the documents in a data source.
Static Methods
- classmethod is_cfn_element(x)
Returns
true
if a construct is a stack element (i.e. part of the synthesized cloudformation template).Uses duck-typing instead of
instanceof
to allow stack elements from different versions of this library to be included in the same stack.- Parameters:
x (
Any
) –- Return type:
bool
- Returns:
The construct as a stack element or undefined if it is not a stack element.
- classmethod is_cfn_resource(x)
Check whether the given object is a CfnResource.
- Parameters:
x (
Any
) –- Return type:
bool
- classmethod is_construct(x)
Checks if
x
is a construct.Use this method instead of
instanceof
to properly detectConstruct
instances, even when the construct library is symlinked.Explanation: in JavaScript, multiple copies of the
constructs
library on disk are seen as independent, completely different libraries. As a consequence, the classConstruct
in each copy of theconstructs
library is seen as a different class, and an instance of one class will not test asinstanceof
the other class.npm install
will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of theconstructs
library can be accidentally installed, andinstanceof
will behave unpredictably. It is safest to avoid usinginstanceof
, and using this type-testing method instead.- Parameters:
x (
Any
) – Any object.- Return type:
bool
- Returns:
true if
x
is an object created from a class which extendsConstruct
.
AppIntegrationsConfigurationProperty
- class CfnKnowledgeBase.AppIntegrationsConfigurationProperty(*, app_integration_arn, object_fields=None)
Bases:
object
Configuration information for Amazon AppIntegrations to automatically ingest content.
- Parameters:
app_integration_arn (
str
) – The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content. - For Salesforce , your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at leastId
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, andIsDeleted
as source fields. - For ServiceNow , your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at leastnumber
,short_description
,sys_mod_count
,workflow_state
, andactive
as source fields. - For Zendesk , your AppIntegrations DataIntegration must have an ObjectConfiguration ifobjectFields
is not provided, including at leastid
,title
,updated_at
, anddraft
as source fields. - For SharePoint , your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are amongdocx
,pdf
,html
,htm
, andtxt
. - For Amazon S3 , the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. TheSourceURI
of your DataIntegration must use the following format:s3://your_s3_bucket_name
. .. epigraph:: The bucket policy of the corresponding S3 bucket must allow the AWS principalapp-integrations.amazonaws.com
to performs3:ListBucket
,s3:GetObject
, ands3:GetBucketLocation
against the bucket.object_fields (
Optional
[Sequence
[str
]]) –The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration. - For Salesforce , you must include at least
Id
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, andIsDeleted
. - For ServiceNow , you must include at leastnumber
,short_description
,sys_mod_count
,workflow_state
, andactive
. - For Zendesk , you must include at leastid
,title
,updated_at
, anddraft
. Make sure to include additional fields. These fields are indexed and used to source recommendations.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom app_integrations_configuration_property = wisdom.CfnKnowledgeBase.AppIntegrationsConfigurationProperty( app_integration_arn="appIntegrationArn", # the properties below are optional object_fields=["objectFields"] )
Attributes
- app_integration_arn
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce , your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least
Id
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, andIsDeleted
as source fields.For ServiceNow , your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least
number
,short_description
,sys_mod_count
,workflow_state
, andactive
as source fields.For Zendesk , your AppIntegrations DataIntegration must have an ObjectConfiguration if
objectFields
is not provided, including at leastid
,title
,updated_at
, anddraft
as source fields.For SharePoint , your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among
docx
,pdf
,html
,htm
, andtxt
.For Amazon S3 , the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The
SourceURI
of your DataIntegration must use the following format:s3://your_s3_bucket_name
.
The bucket policy of the corresponding S3 bucket must allow the AWS principal
app-integrations.amazonaws.com
to performs3:ListBucket
,s3:GetObject
, ands3:GetBucketLocation
against the bucket.
- object_fields
The fields from the source that are made available to your agents in Amazon Q in Connect.
Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce , you must include at least
Id
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, andIsDeleted
.For ServiceNow , you must include at least
number
,short_description
,sys_mod_count
,workflow_state
, andactive
.For Zendesk , you must include at least
id
,title
,updated_at
, anddraft
.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
BedrockFoundationModelConfigurationProperty
- class CfnKnowledgeBase.BedrockFoundationModelConfigurationProperty(*, model_arn, parsing_prompt=None)
Bases:
object
The configuration of the Bedrock foundation model.
- Parameters:
model_arn (
str
) – The model ARN of the Bedrock foundation model.parsing_prompt (
Union
[IResolvable
,ParsingPromptProperty
,Dict
[str
,Any
],None
]) – The parsing prompt of the Bedrock foundation model configuration.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom bedrock_foundation_model_configuration_property = wisdom.CfnKnowledgeBase.BedrockFoundationModelConfigurationProperty( model_arn="modelArn", # the properties below are optional parsing_prompt=wisdom.CfnKnowledgeBase.ParsingPromptProperty( parsing_prompt_text="parsingPromptText" ) )
Attributes
- model_arn
The model ARN of the Bedrock foundation model.
- parsing_prompt
The parsing prompt of the Bedrock foundation model configuration.
ChunkingConfigurationProperty
- class CfnKnowledgeBase.ChunkingConfigurationProperty(*, chunking_strategy, fixed_size_chunking_configuration=None, hierarchical_chunking_configuration=None, semantic_chunking_configuration=None)
Bases:
object
Details about how to chunk the documents in the data source.
A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
- Parameters:
chunking_strategy (
str
) – Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt forNONE
, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.fixed_size_chunking_configuration (
Union
[IResolvable
,FixedSizeChunkingConfigurationProperty
,Dict
[str
,Any
],None
]) – Configurations for when you choose fixed-size chunking. If you set thechunkingStrategy
asNONE
, exclude this field.hierarchical_chunking_configuration (
Union
[IResolvable
,HierarchicalChunkingConfigurationProperty
,Dict
[str
,Any
],None
]) – Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.semantic_chunking_configuration (
Union
[IResolvable
,SemanticChunkingConfigurationProperty
,Dict
[str
,Any
],None
]) – Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom chunking_configuration_property = wisdom.CfnKnowledgeBase.ChunkingConfigurationProperty( chunking_strategy="chunkingStrategy", # the properties below are optional fixed_size_chunking_configuration=wisdom.CfnKnowledgeBase.FixedSizeChunkingConfigurationProperty( max_tokens=123, overlap_percentage=123 ), hierarchical_chunking_configuration=wisdom.CfnKnowledgeBase.HierarchicalChunkingConfigurationProperty( level_configurations=[wisdom.CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty( max_tokens=123 )], overlap_tokens=123 ), semantic_chunking_configuration=wisdom.CfnKnowledgeBase.SemanticChunkingConfigurationProperty( breakpoint_percentile_threshold=123, buffer_size=123, max_tokens=123 ) )
Attributes
- chunking_strategy
Knowledge base can split your source data into chunks.
A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for
NONE
, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
- fixed_size_chunking_configuration
Configurations for when you choose fixed-size chunking.
If you set the
chunkingStrategy
asNONE
, exclude this field.
- hierarchical_chunking_configuration
Settings for hierarchical document chunking for a data source.
Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
- semantic_chunking_configuration
Settings for semantic document chunking for a data source.
Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
CrawlerLimitsProperty
- class CfnKnowledgeBase.CrawlerLimitsProperty(*, rate_limit=None)
Bases:
object
The limits of the crawler.
- Parameters:
rate_limit (
Union
[int
,float
,None
]) – The limit rate at which the crawler is configured.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom crawler_limits_property = wisdom.CfnKnowledgeBase.CrawlerLimitsProperty( rate_limit=123 )
Attributes
- rate_limit
The limit rate at which the crawler is configured.
FixedSizeChunkingConfigurationProperty
- class CfnKnowledgeBase.FixedSizeChunkingConfigurationProperty(*, max_tokens, overlap_percentage)
Bases:
object
Configurations for when you choose fixed-size chunking.
If you set the
chunkingStrategy
asNONE
, exclude this field.- Parameters:
max_tokens (
Union
[int
,float
]) – The maximum number of tokens to include in a chunk.overlap_percentage (
Union
[int
,float
]) – The percentage of overlap between adjacent chunks of a data source.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom fixed_size_chunking_configuration_property = wisdom.CfnKnowledgeBase.FixedSizeChunkingConfigurationProperty( max_tokens=123, overlap_percentage=123 )
Attributes
- max_tokens
The maximum number of tokens to include in a chunk.
- overlap_percentage
The percentage of overlap between adjacent chunks of a data source.
HierarchicalChunkingConfigurationProperty
- class CfnKnowledgeBase.HierarchicalChunkingConfigurationProperty(*, level_configurations, overlap_tokens)
Bases:
object
Settings for hierarchical document chunking for a data source.
Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
- Parameters:
level_configurations (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,HierarchicalChunkingLevelConfigurationProperty
,Dict
[str
,Any
]]]]) – Token settings for each layer.overlap_tokens (
Union
[int
,float
]) – The number of tokens to repeat across chunks in the same layer.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom hierarchical_chunking_configuration_property = wisdom.CfnKnowledgeBase.HierarchicalChunkingConfigurationProperty( level_configurations=[wisdom.CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty( max_tokens=123 )], overlap_tokens=123 )
Attributes
- level_configurations
Token settings for each layer.
- overlap_tokens
The number of tokens to repeat across chunks in the same layer.
HierarchicalChunkingLevelConfigurationProperty
- class CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty(*, max_tokens)
Bases:
object
Token settings for each layer.
- Parameters:
max_tokens (
Union
[int
,float
]) – The maximum number of tokens that a chunk can contain in this layer.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom hierarchical_chunking_level_configuration_property = wisdom.CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty( max_tokens=123 )
Attributes
- max_tokens
The maximum number of tokens that a chunk can contain in this layer.
ManagedSourceConfigurationProperty
- class CfnKnowledgeBase.ManagedSourceConfigurationProperty(*, web_crawler_configuration)
Bases:
object
Source configuration for managed resources.
- Parameters:
web_crawler_configuration (
Union
[IResolvable
,WebCrawlerConfigurationProperty
,Dict
[str
,Any
]]) – Configuration data for web crawler data source.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom managed_source_configuration_property = wisdom.CfnKnowledgeBase.ManagedSourceConfigurationProperty( web_crawler_configuration=wisdom.CfnKnowledgeBase.WebCrawlerConfigurationProperty( url_configuration=wisdom.CfnKnowledgeBase.UrlConfigurationProperty( seed_urls=[wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )] ), # the properties below are optional crawler_limits=wisdom.CfnKnowledgeBase.CrawlerLimitsProperty( rate_limit=123 ), exclusion_filters=["exclusionFilters"], inclusion_filters=["inclusionFilters"], scope="scope" ) )
Attributes
- web_crawler_configuration
Configuration data for web crawler data source.
ParsingConfigurationProperty
- class CfnKnowledgeBase.ParsingConfigurationProperty(*, parsing_strategy, bedrock_foundation_model_configuration=None)
Bases:
object
Settings for parsing document contents.
By default, the service converts the contents of each document into text before splitting it into chunks. To improve processing of PDF files with tables and images, you can configure the data source to convert the pages of text into images and use a model to describe the contents of each page.
- Parameters:
parsing_strategy (
str
) – The parsing strategy for the data source.bedrock_foundation_model_configuration (
Union
[IResolvable
,BedrockFoundationModelConfigurationProperty
,Dict
[str
,Any
],None
]) – Settings for a foundation model used to parse documents for a data source.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom parsing_configuration_property = wisdom.CfnKnowledgeBase.ParsingConfigurationProperty( parsing_strategy="parsingStrategy", # the properties below are optional bedrock_foundation_model_configuration=wisdom.CfnKnowledgeBase.BedrockFoundationModelConfigurationProperty( model_arn="modelArn", # the properties below are optional parsing_prompt=wisdom.CfnKnowledgeBase.ParsingPromptProperty( parsing_prompt_text="parsingPromptText" ) ) )
Attributes
- bedrock_foundation_model_configuration
Settings for a foundation model used to parse documents for a data source.
- parsing_strategy
The parsing strategy for the data source.
ParsingPromptProperty
- class CfnKnowledgeBase.ParsingPromptProperty(*, parsing_prompt_text)
Bases:
object
Instructions for interpreting the contents of a document.
- Parameters:
parsing_prompt_text (
str
) – Instructions for interpreting the contents of a document.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom parsing_prompt_property = wisdom.CfnKnowledgeBase.ParsingPromptProperty( parsing_prompt_text="parsingPromptText" )
Attributes
- parsing_prompt_text
Instructions for interpreting the contents of a document.
RenderingConfigurationProperty
- class CfnKnowledgeBase.RenderingConfigurationProperty(*, template_uri=None)
Bases:
object
Information about how to render the content.
- Parameters:
template_uri (
Optional
[str
]) – A URI template containing exactly one variable in${variableName}
format. This can only be set forEXTERNAL
knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following: - Salesforce:Id
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, orIsDeleted
- ServiceNow:number
,short_description
,sys_mod_count
,workflow_state
, oractive
- Zendesk:id
,title
,updated_at
, ordraft
The variable is replaced with the actual value for a piece of content when calling GetContent .- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom rendering_configuration_property = wisdom.CfnKnowledgeBase.RenderingConfigurationProperty( template_uri="templateUri" )
Attributes
- template_uri
A URI template containing exactly one variable in
${variableName}
format.This can only be set for
EXTERNAL
knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:Salesforce:
Id
,ArticleNumber
,VersionNumber
,Title
,PublishStatus
, orIsDeleted
ServiceNow:
number
,short_description
,sys_mod_count
,workflow_state
, oractive
Zendesk:
id
,title
,updated_at
, ordraft
The variable is replaced with the actual value for a piece of content when calling GetContent .
SeedUrlProperty
- class CfnKnowledgeBase.SeedUrlProperty(*, url=None)
Bases:
object
A URL for crawling.
- Parameters:
url (
Optional
[str
]) – URL for crawling.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom seed_url_property = wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )
Attributes
SemanticChunkingConfigurationProperty
- class CfnKnowledgeBase.SemanticChunkingConfigurationProperty(*, breakpoint_percentile_threshold, buffer_size, max_tokens)
Bases:
object
Settings for semantic document chunking for a data source.
Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
- Parameters:
breakpoint_percentile_threshold (
Union
[int
,float
]) – The dissimilarity threshold for splitting chunks.buffer_size (
Union
[int
,float
]) – The buffer size.max_tokens (
Union
[int
,float
]) – The maximum number of tokens that a chunk can contain.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom semantic_chunking_configuration_property = wisdom.CfnKnowledgeBase.SemanticChunkingConfigurationProperty( breakpoint_percentile_threshold=123, buffer_size=123, max_tokens=123 )
Attributes
- breakpoint_percentile_threshold
The dissimilarity threshold for splitting chunks.
- buffer_size
The buffer size.
- max_tokens
The maximum number of tokens that a chunk can contain.
ServerSideEncryptionConfigurationProperty
- class CfnKnowledgeBase.ServerSideEncryptionConfigurationProperty(*, kms_key_id=None)
Bases:
object
The configuration information for the customer managed key used for encryption.
- Parameters:
kms_key_id (
Optional
[str
]) –The customer managed key used for encryption. This customer managed key must have a policy that allows
kms:CreateGrant
andkms:DescribeKey
permissions to the IAM identity using the key to invoke Wisdom. For more information about setting up a customer managed key for Wisdom, see Enable Amazon Connect Wisdom for your instance . For information about valid ID values, see Key identifiers (KeyId) .- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom server_side_encryption_configuration_property = wisdom.CfnKnowledgeBase.ServerSideEncryptionConfigurationProperty( kms_key_id="kmsKeyId" )
Attributes
- kms_key_id
The customer managed key used for encryption.
This customer managed key must have a policy that allows
kms:CreateGrant
andkms:DescribeKey
permissions to the IAM identity using the key to invoke Wisdom.For more information about setting up a customer managed key for Wisdom, see Enable Amazon Connect Wisdom for your instance . For information about valid ID values, see Key identifiers (KeyId) .
SourceConfigurationProperty
- class CfnKnowledgeBase.SourceConfigurationProperty(*, app_integrations=None, managed_source_configuration=None)
Bases:
object
Configuration information about the external data source.
- Parameters:
app_integrations (
Union
[IResolvable
,AppIntegrationsConfigurationProperty
,Dict
[str
,Any
],None
]) – Configuration information for Amazon AppIntegrations to automatically ingest content.managed_source_configuration (
Union
[IResolvable
,ManagedSourceConfigurationProperty
,Dict
[str
,Any
],None
]) – Source configuration for managed resources.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom source_configuration_property = wisdom.CfnKnowledgeBase.SourceConfigurationProperty( app_integrations=wisdom.CfnKnowledgeBase.AppIntegrationsConfigurationProperty( app_integration_arn="appIntegrationArn", # the properties below are optional object_fields=["objectFields"] ), managed_source_configuration=wisdom.CfnKnowledgeBase.ManagedSourceConfigurationProperty( web_crawler_configuration=wisdom.CfnKnowledgeBase.WebCrawlerConfigurationProperty( url_configuration=wisdom.CfnKnowledgeBase.UrlConfigurationProperty( seed_urls=[wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )] ), # the properties below are optional crawler_limits=wisdom.CfnKnowledgeBase.CrawlerLimitsProperty( rate_limit=123 ), exclusion_filters=["exclusionFilters"], inclusion_filters=["inclusionFilters"], scope="scope" ) ) )
Attributes
- app_integrations
Configuration information for Amazon AppIntegrations to automatically ingest content.
- managed_source_configuration
Source configuration for managed resources.
UrlConfigurationProperty
- class CfnKnowledgeBase.UrlConfigurationProperty(*, seed_urls=None)
Bases:
object
The configuration of the URL/URLs for the web content that you want to crawl.
You should be authorized to crawl the URLs.
- Parameters:
seed_urls (
Union
[IResolvable
,Sequence
[Union
[IResolvable
,SeedUrlProperty
,Dict
[str
,Any
]]],None
]) – List of URLs for crawling.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom url_configuration_property = wisdom.CfnKnowledgeBase.UrlConfigurationProperty( seed_urls=[wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )] )
Attributes
VectorIngestionConfigurationProperty
- class CfnKnowledgeBase.VectorIngestionConfigurationProperty(*, chunking_configuration=None, parsing_configuration=None)
Bases:
object
Contains details about how to ingest the documents in a data source.
- Parameters:
chunking_configuration (
Union
[IResolvable
,ChunkingConfigurationProperty
,Dict
[str
,Any
],None
]) – Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.parsing_configuration (
Union
[IResolvable
,ParsingConfigurationProperty
,Dict
[str
,Any
],None
]) – A custom parser for data source documents.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom vector_ingestion_configuration_property = wisdom.CfnKnowledgeBase.VectorIngestionConfigurationProperty( chunking_configuration=wisdom.CfnKnowledgeBase.ChunkingConfigurationProperty( chunking_strategy="chunkingStrategy", # the properties below are optional fixed_size_chunking_configuration=wisdom.CfnKnowledgeBase.FixedSizeChunkingConfigurationProperty( max_tokens=123, overlap_percentage=123 ), hierarchical_chunking_configuration=wisdom.CfnKnowledgeBase.HierarchicalChunkingConfigurationProperty( level_configurations=[wisdom.CfnKnowledgeBase.HierarchicalChunkingLevelConfigurationProperty( max_tokens=123 )], overlap_tokens=123 ), semantic_chunking_configuration=wisdom.CfnKnowledgeBase.SemanticChunkingConfigurationProperty( breakpoint_percentile_threshold=123, buffer_size=123, max_tokens=123 ) ), parsing_configuration=wisdom.CfnKnowledgeBase.ParsingConfigurationProperty( parsing_strategy="parsingStrategy", # the properties below are optional bedrock_foundation_model_configuration=wisdom.CfnKnowledgeBase.BedrockFoundationModelConfigurationProperty( model_arn="modelArn", # the properties below are optional parsing_prompt=wisdom.CfnKnowledgeBase.ParsingPromptProperty( parsing_prompt_text="parsingPromptText" ) ) ) )
Attributes
- chunking_configuration
Details about how to chunk the documents in the data source.
A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
- parsing_configuration
A custom parser for data source documents.
WebCrawlerConfigurationProperty
- class CfnKnowledgeBase.WebCrawlerConfigurationProperty(*, url_configuration, crawler_limits=None, exclusion_filters=None, inclusion_filters=None, scope=None)
Bases:
object
The configuration details for the web data source.
- Parameters:
url_configuration (
Union
[IResolvable
,UrlConfigurationProperty
,Dict
[str
,Any
]]) – The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.crawler_limits (
Union
[IResolvable
,CrawlerLimitsProperty
,Dict
[str
,Any
],None
]) – The configuration of crawl limits for the web URLs.exclusion_filters (
Optional
[Sequence
[str
]]) – A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.inclusion_filters (
Optional
[Sequence
[str
]]) – A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.scope (
Optional
[str
]) – The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URLhttps://docs.aws.amazon.com/bedrock/latest/userguide/
and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that containaws.amazon.com
can also include sub domaindocs.aws.amazon.com
.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_wisdom as wisdom web_crawler_configuration_property = wisdom.CfnKnowledgeBase.WebCrawlerConfigurationProperty( url_configuration=wisdom.CfnKnowledgeBase.UrlConfigurationProperty( seed_urls=[wisdom.CfnKnowledgeBase.SeedUrlProperty( url="url" )] ), # the properties below are optional crawler_limits=wisdom.CfnKnowledgeBase.CrawlerLimitsProperty( rate_limit=123 ), exclusion_filters=["exclusionFilters"], inclusion_filters=["inclusionFilters"], scope="scope" )
Attributes
- crawler_limits
The configuration of crawl limits for the web URLs.
- exclusion_filters
A list of one or more exclusion regular expression patterns to exclude certain URLs.
If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
- inclusion_filters
A list of one or more inclusion regular expression patterns to include certain URLs.
If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
- scope
The scope of what is crawled for your URLs.
You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL
https://docs.aws.amazon.com/bedrock/latest/userguide/
and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that containaws.amazon.com
can also include sub domaindocs.aws.amazon.com
.
- url_configuration
The configuration of the URL/URLs for the web content that you want to crawl.
You should be authorized to crawl the URLs.