konnect 2.7.1, May 1 25

konnect 2.7.1 published on Thursday, May 1, 2025 by kong

konnect.getGatewayPluginAiProxyAdvanced

Explore with Pulumi AI

konnect 2.7.1 published on Thursday, May 1, 2025 by kong

Using getGatewayPluginAiProxyAdvanced

Two invocation forms are available. The direct form accepts plain arguments and either blocks until the result value is available, or returns a Promise-wrapped result. The output form accepts Input-wrapped arguments and returns an Output-wrapped result.

function getGatewayPluginAiProxyAdvanced(args: GetGatewayPluginAiProxyAdvancedArgs, opts?: InvokeOptions): Promise<GetGatewayPluginAiProxyAdvancedResult>
function getGatewayPluginAiProxyAdvancedOutput(args: GetGatewayPluginAiProxyAdvancedOutputArgs, opts?: InvokeOptions): Output<GetGatewayPluginAiProxyAdvancedResult>

def get_gateway_plugin_ai_proxy_advanced(control_plane_id: Optional[str] = None,
                                         opts: Optional[InvokeOptions] = None) -> GetGatewayPluginAiProxyAdvancedResult
def get_gateway_plugin_ai_proxy_advanced_output(control_plane_id: Optional[pulumi.Input[str]] = None,
                                         opts: Optional[InvokeOptions] = None) -> Output[GetGatewayPluginAiProxyAdvancedResult]

func LookupGatewayPluginAiProxyAdvanced(ctx *Context, args *LookupGatewayPluginAiProxyAdvancedArgs, opts ...InvokeOption) (*LookupGatewayPluginAiProxyAdvancedResult, error)
func LookupGatewayPluginAiProxyAdvancedOutput(ctx *Context, args *LookupGatewayPluginAiProxyAdvancedOutputArgs, opts ...InvokeOption) LookupGatewayPluginAiProxyAdvancedResultOutput

> Note: This function is named LookupGatewayPluginAiProxyAdvanced in the Go SDK.

public static class GetGatewayPluginAiProxyAdvanced 
{
    public static Task<GetGatewayPluginAiProxyAdvancedResult> InvokeAsync(GetGatewayPluginAiProxyAdvancedArgs args, InvokeOptions? opts = null)
    public static Output<GetGatewayPluginAiProxyAdvancedResult> Invoke(GetGatewayPluginAiProxyAdvancedInvokeArgs args, InvokeOptions? opts = null)
}

public static CompletableFuture<GetGatewayPluginAiProxyAdvancedResult> getGatewayPluginAiProxyAdvanced(GetGatewayPluginAiProxyAdvancedArgs args, InvokeOptions options)
public static Output<GetGatewayPluginAiProxyAdvancedResult> getGatewayPluginAiProxyAdvanced(GetGatewayPluginAiProxyAdvancedArgs args, InvokeOptions options)

fn::invoke:
  function: konnect:index/getGatewayPluginAiProxyAdvanced:getGatewayPluginAiProxyAdvanced
  arguments:
    # arguments dictionary

The following arguments are supported:

ControlPlaneId string

ControlPlaneId string

controlPlaneId String

controlPlaneId string

control_plane_id str

controlPlaneId String

getGatewayPluginAiProxyAdvanced Result

The following output properties are available:

config GetGatewayPluginAiProxyAdvancedConfig
consumer GetGatewayPluginAiProxyAdvancedConsumer
consumerGroup GetGatewayPluginAiProxyAdvancedConsumerGroup
controlPlaneId String
createdAt Double
enabled Boolean
id String
instanceName String
ordering GetGatewayPluginAiProxyAdvancedOrdering
protocols List<String>
route GetGatewayPluginAiProxyAdvancedRoute
service GetGatewayPluginAiProxyAdvancedService
tags List<String>
updatedAt Double

config Property Map
consumer Property Map
consumerGroup Property Map
controlPlaneId String
createdAt Number
enabled Boolean
id String
instanceName String
ordering Property Map
protocols List<String>
route Property Map
service Property Map
tags List<String>
updatedAt Number

Supporting Types

GetGatewayPluginAiProxyAdvancedConfig

Balancer GetGatewayPluginAiProxyAdvancedConfigBalancer
Embeddings GetGatewayPluginAiProxyAdvancedConfigEmbeddings
LlmFormat string: LLM input and output format and schema to use
MaxRequestBodySize double: max allowed body size allowed to be introspected
ModelNameHeader bool: Display the model name selected in the X-Kong-LLM-Model response header
ResponseStreaming string: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
Targets List<GetGatewayPluginAiProxyAdvancedConfigTarget>
Vectordb GetGatewayPluginAiProxyAdvancedConfigVectordb

Balancer GetGatewayPluginAiProxyAdvancedConfigBalancer
Embeddings GetGatewayPluginAiProxyAdvancedConfigEmbeddings
LlmFormat string: LLM input and output format and schema to use
MaxRequestBodySize float64: max allowed body size allowed to be introspected
ModelNameHeader bool: Display the model name selected in the X-Kong-LLM-Model response header
ResponseStreaming string: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
Targets []GetGatewayPluginAiProxyAdvancedConfigTarget
Vectordb GetGatewayPluginAiProxyAdvancedConfigVectordb

balancer GetGatewayPluginAiProxyAdvancedConfigBalancer
embeddings GetGatewayPluginAiProxyAdvancedConfigEmbeddings
llmFormat String: LLM input and output format and schema to use
maxRequestBodySize Double: max allowed body size allowed to be introspected
modelNameHeader Boolean: Display the model name selected in the X-Kong-LLM-Model response header
responseStreaming String: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
targets List<GetGatewayPluginAiProxyAdvancedConfigTarget>
vectordb GetGatewayPluginAiProxyAdvancedConfigVectordb

balancer GetGatewayPluginAiProxyAdvancedConfigBalancer
embeddings GetGatewayPluginAiProxyAdvancedConfigEmbeddings
llmFormat string: LLM input and output format and schema to use
maxRequestBodySize number: max allowed body size allowed to be introspected
modelNameHeader boolean: Display the model name selected in the X-Kong-LLM-Model response header
responseStreaming string: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
targets GetGatewayPluginAiProxyAdvancedConfigTarget[]
vectordb GetGatewayPluginAiProxyAdvancedConfigVectordb

balancer GetGatewayPluginAiProxyAdvancedConfigBalancer
embeddings GetGatewayPluginAiProxyAdvancedConfigEmbeddings
llm_format str: LLM input and output format and schema to use
max_request_body_size float: max allowed body size allowed to be introspected
model_name_header bool: Display the model name selected in the X-Kong-LLM-Model response header
response_streaming str: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
targets Sequence[GetGatewayPluginAiProxyAdvancedConfigTarget]
vectordb GetGatewayPluginAiProxyAdvancedConfigVectordb

balancer Property Map
embeddings Property Map
llmFormat String: LLM input and output format and schema to use
maxRequestBodySize Number: max allowed body size allowed to be introspected
modelNameHeader Boolean: Display the model name selected in the X-Kong-LLM-Model response header
responseStreaming String: Whether to 'optionally allow', 'deny', or 'always' (force) the streaming of answers via server sent events.
targets List<Property Map>
vectordb Property Map

GetGatewayPluginAiProxyAdvancedConfigBalancer

Algorithm string: Which load balancing algorithm to use.
ConnectTimeout double
FailoverCriterias List<string>: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
HashOnHeader string: The header to use for consistent-hashing.
LatencyStrategy string: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
ReadTimeout double
Retries double: The number of retries to execute upon failure to proxy.
Slots double: The number of slots in the load balancer algorithm.
TokensCountStrategy string: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
WriteTimeout double

Algorithm string: Which load balancing algorithm to use.
ConnectTimeout float64
FailoverCriterias []string: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
HashOnHeader string: The header to use for consistent-hashing.
LatencyStrategy string: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
ReadTimeout float64
Retries float64: The number of retries to execute upon failure to proxy.
Slots float64: The number of slots in the load balancer algorithm.
TokensCountStrategy string: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
WriteTimeout float64

algorithm String: Which load balancing algorithm to use.
connectTimeout Double
failoverCriterias List<String>: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
hashOnHeader String: The header to use for consistent-hashing.
latencyStrategy String: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
readTimeout Double
retries Double: The number of retries to execute upon failure to proxy.
slots Double: The number of slots in the load balancer algorithm.
tokensCountStrategy String: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
writeTimeout Double

algorithm string: Which load balancing algorithm to use.
connectTimeout number
failoverCriterias string[]: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
hashOnHeader string: The header to use for consistent-hashing.
latencyStrategy string: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
readTimeout number
retries number: The number of retries to execute upon failure to proxy.
slots number: The number of slots in the load balancer algorithm.
tokensCountStrategy string: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
writeTimeout number

algorithm str: Which load balancing algorithm to use.
connect_timeout float
failover_criterias Sequence[str]: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
hash_on_header str: The header to use for consistent-hashing.
latency_strategy str: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
read_timeout float
retries float: The number of retries to execute upon failure to proxy.
slots float: The number of slots in the load balancer algorithm.
tokens_count_strategy str: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
write_timeout float

algorithm String: Which load balancing algorithm to use.
connectTimeout Number
failoverCriterias List<String>: Specifies in which cases an upstream response should be failover to the next target. Each option in the array is equivalent to the function of http://nginx.org/en/docs/http/ngx_http_proxy_module.html#proxy_next_upstream
hashOnHeader String: The header to use for consistent-hashing.
latencyStrategy String: What metrics to use for latency. Available values are: tpot (time-per-output-token) and e2e.
readTimeout Number
retries Number: The number of retries to execute upon failure to proxy.
slots Number: The number of slots in the load balancer algorithm.
tokensCountStrategy String: What tokens to use for usage calculation. Available values are: total_tokens prompt_tokens, completion_tokens and cost.
writeTimeout Number

GetGatewayPluginAiProxyAdvancedConfigEmbeddings

Auth GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth
Model GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

Auth GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth
Model GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

auth GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth
model GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

auth GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth
model GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

auth GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth
model GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

auth Property Map
model Property Map

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth

AllowOverride bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
AwsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
AwsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
AzureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
AzureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
AzureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
AzureUseManagedIdentity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
GcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
GcpUseServiceAccount bool: Use service account auth for GCP-based providers and models.
HeaderName string: If AI model requires authentication via Authorization or API key header, specify its name here.
HeaderValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
ParamLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
ParamName string: If AI model requires authentication via query parameter, specify its name here.
ParamValue string: Specify the full parameter value for 'param_name'.

AllowOverride bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
AwsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
AwsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
AzureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
AzureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
AzureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
AzureUseManagedIdentity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
GcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
GcpUseServiceAccount bool: Use service account auth for GCP-based providers and models.
HeaderName string: If AI model requires authentication via Authorization or API key header, specify its name here.
HeaderValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
ParamLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
ParamName string: If AI model requires authentication via query parameter, specify its name here.
ParamValue string: Specify the full parameter value for 'param_name'.

allowOverride Boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity Boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson String: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount Boolean: Use service account auth for GCP-based providers and models.
headerName String: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue String: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation String: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName String: If AI model requires authentication via query parameter, specify its name here.
paramValue String: Specify the full parameter value for 'param_name'.

allowOverride boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount boolean: Use service account auth for GCP-based providers and models.
headerName string: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName string: If AI model requires authentication via query parameter, specify its name here.
paramValue string: Specify the full parameter value for 'param_name'.

allow_override bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
aws_access_key_id str: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
aws_secret_access_key str: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azure_client_id str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azure_client_secret str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azure_tenant_id str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azure_use_managed_identity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcp_service_account_json str: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcp_use_service_account bool: Use service account auth for GCP-based providers and models.
header_name str: If AI model requires authentication via Authorization or API key header, specify its name here.
header_value str: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
param_location str: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
param_name str: If AI model requires authentication via query parameter, specify its name here.
param_value str: Specify the full parameter value for 'param_name'.

allowOverride Boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity Boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson String: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount Boolean: Use service account auth for GCP-based providers and models.
headerName String: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue String: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation String: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName String: If AI model requires authentication via query parameter, specify its name here.
paramValue String: Specify the full parameter value for 'param_name'.

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

Name string: Model name to execute.
Options GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions: Key/value settings for the model
Provider string: AI provider format to use for embeddings API

Name string: Model name to execute.
Options GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions: Key/value settings for the model
Provider string: AI provider format to use for embeddings API

name String: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions: Key/value settings for the model
provider String: AI provider format to use for embeddings API

name string: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions: Key/value settings for the model
provider string: AI provider format to use for embeddings API

name str: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions: Key/value settings for the model
provider str: AI provider format to use for embeddings API

name String: Model name to execute.
options Property Map: Key/value settings for the model
provider String: AI provider format to use for embeddings API

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions

Azure GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure
Bedrock GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock
Gemini GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini
Huggingface GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface
UpstreamUrl string: upstream url for the embeddings

Azure GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure
Bedrock GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock
Gemini GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini
Huggingface GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface
UpstreamUrl string: upstream url for the embeddings

azure GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure
bedrock GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface
upstreamUrl String: upstream url for the embeddings

azure GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure
bedrock GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface
upstreamUrl string: upstream url for the embeddings

azure GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure
bedrock GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface
upstream_url str: upstream url for the embeddings

azure Property Map
bedrock Property Map
gemini Property Map
huggingface Property Map
upstreamUrl String: upstream url for the embeddings

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure

ApiVersion string: 'api-version' for Azure OpenAI instances.
DeploymentId string: Deployment ID for Azure OpenAI instances.
Instance string: Instance name for Azure OpenAI hosted models.

ApiVersion string: 'api-version' for Azure OpenAI instances.
DeploymentId string: Deployment ID for Azure OpenAI instances.
Instance string: Instance name for Azure OpenAI hosted models.

apiVersion String: 'api-version' for Azure OpenAI instances.
deploymentId String: Deployment ID for Azure OpenAI instances.
instance String: Instance name for Azure OpenAI hosted models.

apiVersion string: 'api-version' for Azure OpenAI instances.
deploymentId string: Deployment ID for Azure OpenAI instances.
instance string: Instance name for Azure OpenAI hosted models.

api_version str: 'api-version' for Azure OpenAI instances.
deployment_id str: Deployment ID for Azure OpenAI instances.
instance str: Instance name for Azure OpenAI hosted models.

apiVersion String: 'api-version' for Azure OpenAI instances.
deploymentId String: Deployment ID for Azure OpenAI instances.
instance String: Instance name for Azure OpenAI hosted models.

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock

AwsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
AwsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
AwsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
AwsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

AwsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
AwsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
AwsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
AwsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn String: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion String: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName String: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl String: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

aws_assume_role_arn str: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
aws_region str: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
aws_role_session_name str: If using AWS providers (Bedrock), set the identifier of the assumed role session.
aws_sts_endpoint_url str: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn String: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion String: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName String: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl String: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini

ApiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
LocationId string: If running Gemini on Vertex, specify the location ID.
ProjectId string: If running Gemini on Vertex, specify the project ID.

ApiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
LocationId string: If running Gemini on Vertex, specify the location ID.
ProjectId string: If running Gemini on Vertex, specify the project ID.

apiEndpoint String: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId String: If running Gemini on Vertex, specify the location ID.
projectId String: If running Gemini on Vertex, specify the project ID.

apiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId string: If running Gemini on Vertex, specify the location ID.
projectId string: If running Gemini on Vertex, specify the project ID.

api_endpoint str: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
location_id str: If running Gemini on Vertex, specify the location ID.
project_id str: If running Gemini on Vertex, specify the project ID.

apiEndpoint String: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId String: If running Gemini on Vertex, specify the location ID.
projectId String: If running Gemini on Vertex, specify the project ID.

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface

UseCache bool: Use the cache layer on the inference API
WaitForModel bool: Wait for the model if it is not ready

UseCache bool: Use the cache layer on the inference API
WaitForModel bool: Wait for the model if it is not ready

useCache Boolean: Use the cache layer on the inference API
waitForModel Boolean: Wait for the model if it is not ready

useCache boolean: Use the cache layer on the inference API
waitForModel boolean: Wait for the model if it is not ready

use_cache bool: Use the cache layer on the inference API
wait_for_model bool: Wait for the model if it is not ready

useCache Boolean: Use the cache layer on the inference API
waitForModel Boolean: Wait for the model if it is not ready

GetGatewayPluginAiProxyAdvancedConfigTarget

Auth GetGatewayPluginAiProxyAdvancedConfigTargetAuth
Description string: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
Logging GetGatewayPluginAiProxyAdvancedConfigTargetLogging
Model GetGatewayPluginAiProxyAdvancedConfigTargetModel
RouteType string: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
Weight double: The weight this target gets within the upstream loadbalancer (1-65535).

Auth GetGatewayPluginAiProxyAdvancedConfigTargetAuth
Description string: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
Logging GetGatewayPluginAiProxyAdvancedConfigTargetLogging
Model GetGatewayPluginAiProxyAdvancedConfigTargetModel
RouteType string: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
Weight float64: The weight this target gets within the upstream loadbalancer (1-65535).

auth GetGatewayPluginAiProxyAdvancedConfigTargetAuth
description String: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
logging GetGatewayPluginAiProxyAdvancedConfigTargetLogging
model GetGatewayPluginAiProxyAdvancedConfigTargetModel
routeType String: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
weight Double: The weight this target gets within the upstream loadbalancer (1-65535).

auth GetGatewayPluginAiProxyAdvancedConfigTargetAuth
description string: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
logging GetGatewayPluginAiProxyAdvancedConfigTargetLogging
model GetGatewayPluginAiProxyAdvancedConfigTargetModel
routeType string: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
weight number: The weight this target gets within the upstream loadbalancer (1-65535).

auth GetGatewayPluginAiProxyAdvancedConfigTargetAuth
description str: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
logging GetGatewayPluginAiProxyAdvancedConfigTargetLogging
model GetGatewayPluginAiProxyAdvancedConfigTargetModel
route_type str: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
weight float: The weight this target gets within the upstream loadbalancer (1-65535).

auth Property Map
description String: The semantic description of the target, required if using semantic load balancing. Specially, setting this to 'CATCHALL' will indicate such target to be used when no other targets match the semantic threshold.
logging Property Map
model Property Map
routeType String: The model's operation implementation, for this provider. Set to preserve to pass through without transformation.
weight Number: The weight this target gets within the upstream loadbalancer (1-65535).

GetGatewayPluginAiProxyAdvancedConfigTargetAuth

AllowOverride bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
AwsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
AwsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
AzureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
AzureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
AzureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
AzureUseManagedIdentity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
GcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
GcpUseServiceAccount bool: Use service account auth for GCP-based providers and models.
HeaderName string: If AI model requires authentication via Authorization or API key header, specify its name here.
HeaderValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
ParamLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
ParamName string: If AI model requires authentication via query parameter, specify its name here.
ParamValue string: Specify the full parameter value for 'param_name'.

AllowOverride bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
AwsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
AwsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
AzureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
AzureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
AzureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
AzureUseManagedIdentity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
GcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
GcpUseServiceAccount bool: Use service account auth for GCP-based providers and models.
HeaderName string: If AI model requires authentication via Authorization or API key header, specify its name here.
HeaderValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
ParamLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
ParamName string: If AI model requires authentication via query parameter, specify its name here.
ParamValue string: Specify the full parameter value for 'param_name'.

allowOverride Boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity Boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson String: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount Boolean: Use service account auth for GCP-based providers and models.
headerName String: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue String: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation String: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName String: If AI model requires authentication via query parameter, specify its name here.
paramValue String: Specify the full parameter value for 'param_name'.

allowOverride boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey string: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId string: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson string: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount boolean: Use service account auth for GCP-based providers and models.
headerName string: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue string: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation string: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName string: If AI model requires authentication via query parameter, specify its name here.
paramValue string: Specify the full parameter value for 'param_name'.

allow_override bool: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
aws_access_key_id str: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
aws_secret_access_key str: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azure_client_id str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azure_client_secret str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azure_tenant_id str: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azure_use_managed_identity bool: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcp_service_account_json str: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcp_use_service_account bool: Use service account auth for GCP-based providers and models.
header_name str: If AI model requires authentication via Authorization or API key header, specify its name here.
header_value str: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
param_location str: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
param_name str: If AI model requires authentication via query parameter, specify its name here.
param_value str: Specify the full parameter value for 'param_name'.

allowOverride Boolean: If enabled, the authorization header or parameter can be overridden in the request by the value configured in the plugin.
awsAccessKeyId String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_ACCESS_KEY_ID environment variable for this plugin instance.
awsSecretAccessKey String: Set this if you are using an AWS provider (Bedrock) and you are authenticating using static IAM User credentials. Setting this will override the AWS_SECRET_ACCESS_KEY environment variable for this plugin instance.
azureClientId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client ID.
azureClientSecret String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the client secret.
azureTenantId String: If azure_use_managed_identity is set to true, and you need to use a different user-assigned identity for this LLM instance, set the tenant ID.
azureUseManagedIdentity Boolean: Set true to use the Azure Cloud Managed Identity (or user-assigned identity) to authenticate with Azure-provider models.
gcpServiceAccountJson String: Set this field to the full JSON of the GCP service account to authenticate, if required. If null (and gcp_use_service_account is true), Kong will attempt to read from environment variable GCP_SERVICE_ACCOUNT.
gcpUseServiceAccount Boolean: Use service account auth for GCP-based providers and models.
headerName String: If AI model requires authentication via Authorization or API key header, specify its name here.
headerValue String: Specify the full auth header value for 'header_name', for example 'Bearer key' or just 'key'.
paramLocation String: Specify whether the 'param_name' and 'param_value' options go in a query string, or the POST form/JSON body.
paramName String: If AI model requires authentication via query parameter, specify its name here.
paramValue String: Specify the full parameter value for 'param_name'.

GetGatewayPluginAiProxyAdvancedConfigTargetLogging

LogPayloads bool: If enabled, will log the request and response body into the Kong log plugin(s) output.
LogStatistics bool: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

LogPayloads bool: If enabled, will log the request and response body into the Kong log plugin(s) output.
LogStatistics bool: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

logPayloads Boolean: If enabled, will log the request and response body into the Kong log plugin(s) output.
logStatistics Boolean: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

logPayloads boolean: If enabled, will log the request and response body into the Kong log plugin(s) output.
logStatistics boolean: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

log_payloads bool: If enabled, will log the request and response body into the Kong log plugin(s) output.
log_statistics bool: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

logPayloads Boolean: If enabled, will log the request and response body into the Kong log plugin(s) output.
logStatistics Boolean: If enabled and supported by the driver, will add model usage and token metrics into the Kong log plugin(s) output.

GetGatewayPluginAiProxyAdvancedConfigTargetModel

Name string: Model name to execute.
Options GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions: Key/value settings for the model
Provider string: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

Name string: Model name to execute.
Options GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions: Key/value settings for the model
Provider string: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

name String: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions: Key/value settings for the model
provider String: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

name string: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions: Key/value settings for the model
provider string: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

name str: Model name to execute.
options GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions: Key/value settings for the model
provider str: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

name String: Model name to execute.
options Property Map: Key/value settings for the model
provider String: AI provider request format - Kong translates requests to and from the specified backend compatible formats.

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions

AnthropicVersion string: Defines the schema/API version, if using Anthropic provider.
AzureApiVersion string: 'api-version' for Azure OpenAI instances.
AzureDeploymentId string: Deployment ID for Azure OpenAI instances.
AzureInstance string: Instance name for Azure OpenAI hosted models.
Bedrock GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock
Gemini GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini
Huggingface GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface
InputCost double: Defines the cost per 1M tokens in your prompt.
Llama2Format string: If using llama2 provider, select the upstream message format.
MaxTokens double: Defines the max_tokens, if using chat or completion models.
MistralFormat string: If using mistral provider, select the upstream message format.
OutputCost double: Defines the cost per 1M tokens in the output of the AI.
Temperature double: Defines the matching temperature, if using chat or completion models.
TopK double: Defines the top-k most likely tokens, if supported.
TopP double: Defines the top-p probability mass, if supported.
UpstreamPath string: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
UpstreamUrl string: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

AnthropicVersion string: Defines the schema/API version, if using Anthropic provider.
AzureApiVersion string: 'api-version' for Azure OpenAI instances.
AzureDeploymentId string: Deployment ID for Azure OpenAI instances.
AzureInstance string: Instance name for Azure OpenAI hosted models.
Bedrock GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock
Gemini GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini
Huggingface GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface
InputCost float64: Defines the cost per 1M tokens in your prompt.
Llama2Format string: If using llama2 provider, select the upstream message format.
MaxTokens float64: Defines the max_tokens, if using chat or completion models.
MistralFormat string: If using mistral provider, select the upstream message format.
OutputCost float64: Defines the cost per 1M tokens in the output of the AI.
Temperature float64: Defines the matching temperature, if using chat or completion models.
TopK float64: Defines the top-k most likely tokens, if supported.
TopP float64: Defines the top-p probability mass, if supported.
UpstreamPath string: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
UpstreamUrl string: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

anthropicVersion String: Defines the schema/API version, if using Anthropic provider.
azureApiVersion String: 'api-version' for Azure OpenAI instances.
azureDeploymentId String: Deployment ID for Azure OpenAI instances.
azureInstance String: Instance name for Azure OpenAI hosted models.
bedrock GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface
inputCost Double: Defines the cost per 1M tokens in your prompt.
llama2Format String: If using llama2 provider, select the upstream message format.
maxTokens Double: Defines the max_tokens, if using chat or completion models.
mistralFormat String: If using mistral provider, select the upstream message format.
outputCost Double: Defines the cost per 1M tokens in the output of the AI.
temperature Double: Defines the matching temperature, if using chat or completion models.
topK Double: Defines the top-k most likely tokens, if supported.
topP Double: Defines the top-p probability mass, if supported.
upstreamPath String: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
upstreamUrl String: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

anthropicVersion string: Defines the schema/API version, if using Anthropic provider.
azureApiVersion string: 'api-version' for Azure OpenAI instances.
azureDeploymentId string: Deployment ID for Azure OpenAI instances.
azureInstance string: Instance name for Azure OpenAI hosted models.
bedrock GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface
inputCost number: Defines the cost per 1M tokens in your prompt.
llama2Format string: If using llama2 provider, select the upstream message format.
maxTokens number: Defines the max_tokens, if using chat or completion models.
mistralFormat string: If using mistral provider, select the upstream message format.
outputCost number: Defines the cost per 1M tokens in the output of the AI.
temperature number: Defines the matching temperature, if using chat or completion models.
topK number: Defines the top-k most likely tokens, if supported.
topP number: Defines the top-p probability mass, if supported.
upstreamPath string: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
upstreamUrl string: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

anthropic_version str: Defines the schema/API version, if using Anthropic provider.
azure_api_version str: 'api-version' for Azure OpenAI instances.
azure_deployment_id str: Deployment ID for Azure OpenAI instances.
azure_instance str: Instance name for Azure OpenAI hosted models.
bedrock GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock
gemini GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini
huggingface GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface
input_cost float: Defines the cost per 1M tokens in your prompt.
llama2_format str: If using llama2 provider, select the upstream message format.
max_tokens float: Defines the max_tokens, if using chat or completion models.
mistral_format str: If using mistral provider, select the upstream message format.
output_cost float: Defines the cost per 1M tokens in the output of the AI.
temperature float: Defines the matching temperature, if using chat or completion models.
top_k float: Defines the top-k most likely tokens, if supported.
top_p float: Defines the top-p probability mass, if supported.
upstream_path str: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
upstream_url str: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

anthropicVersion String: Defines the schema/API version, if using Anthropic provider.
azureApiVersion String: 'api-version' for Azure OpenAI instances.
azureDeploymentId String: Deployment ID for Azure OpenAI instances.
azureInstance String: Instance name for Azure OpenAI hosted models.
bedrock Property Map
gemini Property Map
huggingface Property Map
inputCost Number: Defines the cost per 1M tokens in your prompt.
llama2Format String: If using llama2 provider, select the upstream message format.
maxTokens Number: Defines the max_tokens, if using chat or completion models.
mistralFormat String: If using mistral provider, select the upstream message format.
outputCost Number: Defines the cost per 1M tokens in the output of the AI.
temperature Number: Defines the matching temperature, if using chat or completion models.
topK Number: Defines the top-k most likely tokens, if supported.
topP Number: Defines the top-p probability mass, if supported.
upstreamPath String: Manually specify or override the AI operation path, used when e.g. using the 'preserve' route_type.
upstreamUrl String: Manually specify or override the full URL to the AI operation endpoints, when calling (self-)hosted models, or for running via a private endpoint.

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock

AwsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
AwsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
AwsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
AwsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

AwsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
AwsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
AwsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
AwsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn String: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion String: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName String: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl String: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn string: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion string: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName string: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl string: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

aws_assume_role_arn str: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
aws_region str: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
aws_role_session_name str: If using AWS providers (Bedrock), set the identifier of the assumed role session.
aws_sts_endpoint_url str: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

awsAssumeRoleArn String: If using AWS providers (Bedrock) you can assume a different role after authentication with the current IAM context is successful.
awsRegion String: If using AWS providers (Bedrock) you can override the AWS_REGION environment variable by setting this option.
awsRoleSessionName String: If using AWS providers (Bedrock), set the identifier of the assumed role session.
awsStsEndpointUrl String: If using AWS providers (Bedrock), override the STS endpoint URL when assuming a different role.

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini

ApiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
LocationId string: If running Gemini on Vertex, specify the location ID.
ProjectId string: If running Gemini on Vertex, specify the project ID.

ApiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
LocationId string: If running Gemini on Vertex, specify the location ID.
ProjectId string: If running Gemini on Vertex, specify the project ID.

apiEndpoint String: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId String: If running Gemini on Vertex, specify the location ID.
projectId String: If running Gemini on Vertex, specify the project ID.

apiEndpoint string: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId string: If running Gemini on Vertex, specify the location ID.
projectId string: If running Gemini on Vertex, specify the project ID.

api_endpoint str: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
location_id str: If running Gemini on Vertex, specify the location ID.
project_id str: If running Gemini on Vertex, specify the project ID.

apiEndpoint String: If running Gemini on Vertex, specify the regional API endpoint (hostname only).
locationId String: If running Gemini on Vertex, specify the location ID.
projectId String: If running Gemini on Vertex, specify the project ID.

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface

UseCache bool: Use the cache layer on the inference API
WaitForModel bool: Wait for the model if it is not ready

UseCache bool: Use the cache layer on the inference API
WaitForModel bool: Wait for the model if it is not ready

useCache Boolean: Use the cache layer on the inference API
waitForModel Boolean: Wait for the model if it is not ready

useCache boolean: Use the cache layer on the inference API
waitForModel boolean: Wait for the model if it is not ready

use_cache bool: Use the cache layer on the inference API
wait_for_model bool: Wait for the model if it is not ready

useCache Boolean: Use the cache layer on the inference API
waitForModel Boolean: Wait for the model if it is not ready

GetGatewayPluginAiProxyAdvancedConfigVectordb

Dimensions double: the desired dimensionality for the vectors
DistanceMetric string: the distance metric to use for vector searches
Pgvector GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector
Redis GetGatewayPluginAiProxyAdvancedConfigVectordbRedis
Strategy string: which vector database driver to use
Threshold double: the default similarity threshold for accepting semantic search results (float)

Dimensions float64: the desired dimensionality for the vectors
DistanceMetric string: the distance metric to use for vector searches
Pgvector GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector
Redis GetGatewayPluginAiProxyAdvancedConfigVectordbRedis
Strategy string: which vector database driver to use
Threshold float64: the default similarity threshold for accepting semantic search results (float)

dimensions Double: the desired dimensionality for the vectors
distanceMetric String: the distance metric to use for vector searches
pgvector GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector
redis GetGatewayPluginAiProxyAdvancedConfigVectordbRedis
strategy String: which vector database driver to use
threshold Double: the default similarity threshold for accepting semantic search results (float)

dimensions number: the desired dimensionality for the vectors
distanceMetric string: the distance metric to use for vector searches
pgvector GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector
redis GetGatewayPluginAiProxyAdvancedConfigVectordbRedis
strategy string: which vector database driver to use
threshold number: the default similarity threshold for accepting semantic search results (float)

dimensions float: the desired dimensionality for the vectors
distance_metric str: the distance metric to use for vector searches
pgvector GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector
redis GetGatewayPluginAiProxyAdvancedConfigVectordbRedis
strategy str: which vector database driver to use
threshold float: the default similarity threshold for accepting semantic search results (float)

dimensions Number: the desired dimensionality for the vectors
distanceMetric String: the distance metric to use for vector searches
pgvector Property Map
redis Property Map
strategy String: which vector database driver to use
threshold Number: the default similarity threshold for accepting semantic search results (float)

GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector

Database string: the database of the pgvector database
Host string: the host of the pgvector database
Password string: the password of the pgvector database
Port double: the port of the pgvector database
Ssl bool: whether to use ssl for the pgvector database
SslCert string: the path of ssl cert to use for the pgvector database
SslCertKey string: the path of ssl cert key to use for the pgvector database
SslRequired bool: whether ssl is required for the pgvector database
SslVerify bool: whether to verify ssl for the pgvector database
SslVersion string: the ssl version to use for the pgvector database
Timeout double: the timeout of the pgvector database
User string: the user of the pgvector database

Database string: the database of the pgvector database
Host string: the host of the pgvector database
Password string: the password of the pgvector database
Port float64: the port of the pgvector database
Ssl bool: whether to use ssl for the pgvector database
SslCert string: the path of ssl cert to use for the pgvector database
SslCertKey string: the path of ssl cert key to use for the pgvector database
SslRequired bool: whether ssl is required for the pgvector database
SslVerify bool: whether to verify ssl for the pgvector database
SslVersion string: the ssl version to use for the pgvector database
Timeout float64: the timeout of the pgvector database
User string: the user of the pgvector database

database String: the database of the pgvector database
host String: the host of the pgvector database
password String: the password of the pgvector database
port Double: the port of the pgvector database
ssl Boolean: whether to use ssl for the pgvector database
sslCert String: the path of ssl cert to use for the pgvector database
sslCertKey String: the path of ssl cert key to use for the pgvector database
sslRequired Boolean: whether ssl is required for the pgvector database
sslVerify Boolean: whether to verify ssl for the pgvector database
sslVersion String: the ssl version to use for the pgvector database
timeout Double: the timeout of the pgvector database
user String: the user of the pgvector database

database string: the database of the pgvector database
host string: the host of the pgvector database
password string: the password of the pgvector database
port number: the port of the pgvector database
ssl boolean: whether to use ssl for the pgvector database
sslCert string: the path of ssl cert to use for the pgvector database
sslCertKey string: the path of ssl cert key to use for the pgvector database
sslRequired boolean: whether ssl is required for the pgvector database
sslVerify boolean: whether to verify ssl for the pgvector database
sslVersion string: the ssl version to use for the pgvector database
timeout number: the timeout of the pgvector database
user string: the user of the pgvector database

database str: the database of the pgvector database
host str: the host of the pgvector database
password str: the password of the pgvector database
port float: the port of the pgvector database
ssl bool: whether to use ssl for the pgvector database
ssl_cert str: the path of ssl cert to use for the pgvector database
ssl_cert_key str: the path of ssl cert key to use for the pgvector database
ssl_required bool: whether ssl is required for the pgvector database
ssl_verify bool: whether to verify ssl for the pgvector database
ssl_version str: the ssl version to use for the pgvector database
timeout float: the timeout of the pgvector database
user str: the user of the pgvector database

database String: the database of the pgvector database
host String: the host of the pgvector database
password String: the password of the pgvector database
port Number: the port of the pgvector database
ssl Boolean: whether to use ssl for the pgvector database
sslCert String: the path of ssl cert to use for the pgvector database
sslCertKey String: the path of ssl cert key to use for the pgvector database
sslRequired Boolean: whether ssl is required for the pgvector database
sslVerify Boolean: whether to verify ssl for the pgvector database
sslVersion String: the ssl version to use for the pgvector database
timeout Number: the timeout of the pgvector database
user String: the user of the pgvector database

GetGatewayPluginAiProxyAdvancedConfigVectordbRedis

ClusterMaxRedirections double: Maximum retry attempts for redirection.
ClusterNodes List<GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode>: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
ConnectTimeout double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
ConnectionIsProxied bool: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
Database double: Database to use for the Redis connection when using the redis strategy
Host string: A string representing a host name, such as example.com.
KeepaliveBacklog double: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
KeepalivePoolSize double: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
Password string: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
Port double: An integer representing a port number between 0 and 65535, inclusive.
ReadTimeout double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
SendTimeout double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
SentinelMaster string: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
SentinelNodes List<GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode>: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
SentinelPassword string: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
SentinelRole string: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
SentinelUsername string: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
ServerName string: A string representing an SNI (server name indication) value for TLS.
Ssl bool: If set to true, uses SSL to connect to Redis.
SslVerify bool: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
Username string: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

ClusterMaxRedirections float64: Maximum retry attempts for redirection.
ClusterNodes []GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
ConnectTimeout float64: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
ConnectionIsProxied bool: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
Database float64: Database to use for the Redis connection when using the redis strategy
Host string: A string representing a host name, such as example.com.
KeepaliveBacklog float64: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
KeepalivePoolSize float64: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
Password string: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
Port float64: An integer representing a port number between 0 and 65535, inclusive.
ReadTimeout float64: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
SendTimeout float64: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
SentinelMaster string: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
SentinelNodes []GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
SentinelPassword string: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
SentinelRole string: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
SentinelUsername string: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
ServerName string: A string representing an SNI (server name indication) value for TLS.
Ssl bool: If set to true, uses SSL to connect to Redis.
SslVerify bool: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
Username string: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

clusterMaxRedirections Double: Maximum retry attempts for redirection.
clusterNodes List<GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode>: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
connectTimeout Double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
connectionIsProxied Boolean: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
database Double: Database to use for the Redis connection when using the redis strategy
host String: A string representing a host name, such as example.com.
keepaliveBacklog Double: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
keepalivePoolSize Double: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
password String: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
port Double: An integer representing a port number between 0 and 65535, inclusive.
readTimeout Double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sendTimeout Double: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sentinelMaster String: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
sentinelNodes List<GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode>: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
sentinelPassword String: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
sentinelRole String: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
sentinelUsername String: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
serverName String: A string representing an SNI (server name indication) value for TLS.
ssl Boolean: If set to true, uses SSL to connect to Redis.
sslVerify Boolean: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
username String: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

clusterMaxRedirections number: Maximum retry attempts for redirection.
clusterNodes GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode[]: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
connectTimeout number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
connectionIsProxied boolean: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
database number: Database to use for the Redis connection when using the redis strategy
host string: A string representing a host name, such as example.com.
keepaliveBacklog number: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
keepalivePoolSize number: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
password string: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
port number: An integer representing a port number between 0 and 65535, inclusive.
readTimeout number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sendTimeout number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sentinelMaster string: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
sentinelNodes GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode[]: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
sentinelPassword string: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
sentinelRole string: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
sentinelUsername string: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
serverName string: A string representing an SNI (server name indication) value for TLS.
ssl boolean: If set to true, uses SSL to connect to Redis.
sslVerify boolean: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
username string: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

cluster_max_redirections float: Maximum retry attempts for redirection.
cluster_nodes Sequence[GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode]: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
connect_timeout float: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
connection_is_proxied bool: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
database float: Database to use for the Redis connection when using the redis strategy
host str: A string representing a host name, such as example.com.
keepalive_backlog float: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
keepalive_pool_size float: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
password str: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
port float: An integer representing a port number between 0 and 65535, inclusive.
read_timeout float: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
send_timeout float: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sentinel_master str: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
sentinel_nodes Sequence[GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode]: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
sentinel_password str: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
sentinel_role str: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
sentinel_username str: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
server_name str: A string representing an SNI (server name indication) value for TLS.
ssl bool: If set to true, uses SSL to connect to Redis.
ssl_verify bool: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
username str: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

clusterMaxRedirections Number: Maximum retry attempts for redirection.
clusterNodes List<Property Map>: Cluster addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Cluster. The minimum length of the array is 1 element.
connectTimeout Number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
connectionIsProxied Boolean: If the connection to Redis is proxied (e.g. Envoy), set it true. Set the host and port to point to the proxy address.
database Number: Database to use for the Redis connection when using the redis strategy
host String: A string representing a host name, such as example.com.
keepaliveBacklog Number: Limits the total number of opened connections for a pool. If the connection pool is full, connection queues above the limit go into the backlog queue. If the backlog queue is full, subsequent connect operations fail and return nil. Queued operations (subject to set timeouts) resume once the number of connections in the pool is less than keepalive_pool_size. If latency is high or throughput is low, try increasing this value. Empirically, this value is larger than keepalive_pool_size.
keepalivePoolSize Number: The size limit for every cosocket connection pool associated with every remote server, per worker process. If neither keepalive_pool_size nor keepalive_backlog is specified, no pool is created. If keepalive_pool_size isn't specified but keepalive_backlog is specified, then the pool uses the default value. Try to increase (e.g. 512) this value if latency is high or throughput is low.
password String: Password to use for Redis connections. If undefined, no AUTH commands are sent to Redis.
port Number: An integer representing a port number between 0 and 65535, inclusive.
readTimeout Number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sendTimeout Number: An integer representing a timeout in milliseconds. Must be between 0 and 2^31-2.
sentinelMaster String: Sentinel master to use for Redis connections. Defining this value implies using Redis Sentinel.
sentinelNodes List<Property Map>: Sentinel node addresses to use for Redis connections when the redis strategy is defined. Defining this field implies using a Redis Sentinel. The minimum length of the array is 1 element.
sentinelPassword String: Sentinel password to authenticate with a Redis Sentinel instance. If undefined, no AUTH commands are sent to Redis Sentinels.
sentinelRole String: Sentinel role to use for Redis connections when the redis strategy is defined. Defining this value implies using Redis Sentinel.
sentinelUsername String: Sentinel username to authenticate with a Redis Sentinel instance. If undefined, ACL authentication won't be performed. This requires Redis v6.2.0+.
serverName String: A string representing an SNI (server name indication) value for TLS.
ssl Boolean: If set to true, uses SSL to connect to Redis.
sslVerify Boolean: If set to true, verifies the validity of the server SSL certificate. If setting this parameter, also configure lua_ssl_trusted_certificate in kong.conf to specify the CA (or server) certificate used by your Redis server. You may also need to configure lua_ssl_verify_depth accordingly.
username String: Username to use for Redis connections. If undefined, ACL authentication won't be performed. This requires Redis v6.0.0+. To be compatible with Redis v5.x.y, you can set it to default.

GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode

Ip string: A string representing a host name, such as example.com.
Port double: An integer representing a port number between 0 and 65535, inclusive.

Ip string: A string representing a host name, such as example.com.
Port float64: An integer representing a port number between 0 and 65535, inclusive.

ip String: A string representing a host name, such as example.com.
port Double: An integer representing a port number between 0 and 65535, inclusive.

ip string: A string representing a host name, such as example.com.
port number: An integer representing a port number between 0 and 65535, inclusive.

ip str: A string representing a host name, such as example.com.
port float: An integer representing a port number between 0 and 65535, inclusive.

ip String: A string representing a host name, such as example.com.
port Number: An integer representing a port number between 0 and 65535, inclusive.

GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode

Host string: A string representing a host name, such as example.com.
Port double: An integer representing a port number between 0 and 65535, inclusive.

Host string: A string representing a host name, such as example.com.
Port float64: An integer representing a port number between 0 and 65535, inclusive.

host String: A string representing a host name, such as example.com.
port Double: An integer representing a port number between 0 and 65535, inclusive.

host string: A string representing a host name, such as example.com.
port number: An integer representing a port number between 0 and 65535, inclusive.

host str: A string representing a host name, such as example.com.
port float: An integer representing a port number between 0 and 65535, inclusive.

host String: A string representing a host name, such as example.com.
port Number: An integer representing a port number between 0 and 65535, inclusive.

GetGatewayPluginAiProxyAdvancedConsumer

Id string

Id string

id String

id string

id str

id String

GetGatewayPluginAiProxyAdvancedConsumerGroup

Id string

Id string

id String

id string

id str

id String

GetGatewayPluginAiProxyAdvancedOrdering

After GetGatewayPluginAiProxyAdvancedOrderingAfter
Before GetGatewayPluginAiProxyAdvancedOrderingBefore

After GetGatewayPluginAiProxyAdvancedOrderingAfter
Before GetGatewayPluginAiProxyAdvancedOrderingBefore

after GetGatewayPluginAiProxyAdvancedOrderingAfter
before GetGatewayPluginAiProxyAdvancedOrderingBefore

after GetGatewayPluginAiProxyAdvancedOrderingAfter
before GetGatewayPluginAiProxyAdvancedOrderingBefore

after GetGatewayPluginAiProxyAdvancedOrderingAfter
before GetGatewayPluginAiProxyAdvancedOrderingBefore

after Property Map
before Property Map

GetGatewayPluginAiProxyAdvancedOrderingAfter

Accesses List<string>

Accesses []string

accesses List<String>

accesses string[]

accesses Sequence[str]

accesses List<String>

GetGatewayPluginAiProxyAdvancedOrderingBefore

Accesses List<string>

Accesses []string

accesses List<String>

accesses string[]

accesses Sequence[str]

accesses List<String>

GetGatewayPluginAiProxyAdvancedRoute

Id string

Id string

id String

id string

id str

id String

GetGatewayPluginAiProxyAdvancedService

Id string

Id string

id String

id string

id str

id String

Package Details

Repository: konnect kong/terraform-provider-konnect
License
Notes: This Pulumi package is based on the konnect Terraform Provider.

konnect 2.7.1 published on Thursday, May 1, 2025 by kong

kong/terraform-provider-konnect

konnect.getGatewayPluginAiProxyAdvanced

On this page

On this page

Using getGatewayPluginAiProxyAdvanced

getGatewayPluginAiProxyAdvanced Result

Supporting Types

GetGatewayPluginAiProxyAdvancedConfig

GetGatewayPluginAiProxyAdvancedConfigBalancer

GetGatewayPluginAiProxyAdvancedConfigEmbeddings

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsAuth

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModel

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptions

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsAzure

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsBedrock

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsGemini

GetGatewayPluginAiProxyAdvancedConfigEmbeddingsModelOptionsHuggingface

GetGatewayPluginAiProxyAdvancedConfigTarget

GetGatewayPluginAiProxyAdvancedConfigTargetAuth

GetGatewayPluginAiProxyAdvancedConfigTargetLogging

GetGatewayPluginAiProxyAdvancedConfigTargetModel

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptions

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsBedrock

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsGemini

GetGatewayPluginAiProxyAdvancedConfigTargetModelOptionsHuggingface

GetGatewayPluginAiProxyAdvancedConfigVectordb

GetGatewayPluginAiProxyAdvancedConfigVectordbPgvector

GetGatewayPluginAiProxyAdvancedConfigVectordbRedis

GetGatewayPluginAiProxyAdvancedConfigVectordbRedisClusterNode

GetGatewayPluginAiProxyAdvancedConfigVectordbRedisSentinelNode

GetGatewayPluginAiProxyAdvancedConsumer

GetGatewayPluginAiProxyAdvancedConsumerGroup

GetGatewayPluginAiProxyAdvancedOrdering

GetGatewayPluginAiProxyAdvancedOrderingAfter

GetGatewayPluginAiProxyAdvancedOrderingBefore

GetGatewayPluginAiProxyAdvancedRoute

GetGatewayPluginAiProxyAdvancedService

Package Details

On this page

On this page