# TeleportRetrievalModelV1 This guide is a comprehensive reference to the fields in the `TeleportRetrievalModelV1` resource, which you can apply after installing the Teleport Kubernetes operator. ## resources.teleport.dev/v1 **apiVersion:** resources.teleport.dev/v1 | Field | Type | Description | | ---------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | apiVersion | string | APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: | | kind | string | Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: | | metadata | object | | | spec | [object](#spec) | RetrievalModel resource definition v1 from Teleport | ### spec | Field | Type | Description | | ---------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | bedrock | [object](#specbedrock) | Bedrock indicates that this model uses Amazon Bedrock as the embeddings provider and specifies Bedrock-specific parameters. | | inference\_model\_name | string | inference\_model\_name is the name of the model used to convert natural language search queries into API requests and generate prose from a session summary. | | openai | [object](#specopenai) | Openai indicates that this model uses OpenAI as the embeddings provider and specifies OpenAI-specific parameters. | ### spec.bedrock | Field | Type | Description | | ------------------ | ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | bedrock\_model\_id | string | BedrockModelId specifies a model ID or an inference profile as understood by the Bedrock API. | | integration | string | Integration is the AWS OIDC Integration name. If unset, Teleport will use AWS credentials available on the Auth Service machine; otherwise, it will use the specified OIDC integration for assuming appropriate role. | | region | string | Region is the AWS region which will be used for inference. | | temperature | number | Temperature controls the randomness of the model's output. | ### spec.openai | Field | Type | Description | | --------------------- | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | api\_key\_secret\_ref | string | ApiKeySecretRef is a reference to an InferenceSecret that contains the OpenAI API key. | | base\_url | string | BaseUrl is the OpenAI API base URL. Optional, defaults to the public OpenAI API URL. May be used to point to a custom OpenAI-compatible API, such as LiteLLM. In such case, the `api_key_secret_ref` must point to a secret that contains the API key for that custom API. | | openai\_model\_id | string | OpenaiModelId specifies the model ID, as understood by the OpenAI API. | | temperature | number | Temperature controls the randomness of the model's output. |