This is the multi-page printable view of this section. Click here to print.

Return to the regular view of this page.

Conversation component specs

The supported conversation components that interface with Dapr

1: Anthropic
2: AWS Bedrock
3: DeepSeek
4: Local Testing
5: GoogleAI
6: Huggingface
7: Mistral
8: Ollama
9: OpenAI

Table headers to note:

Header	Description	Example
Status	Component certification status	Alpha Beta Stable
Component version	The version of the component	v1
Since runtime version	The version of the Dapr runtime when the component status was set or updated	1.11

Amazon Web Services (AWS)

Component	Status	Component version	Since runtime version
AWS Bedrock	Alpha	v1	1.15

Generic

Component	Status	Component version	Since runtime version
Anthropic	Alpha	v1	1.15
DeepSeek	Alpha	v1	1.15
GoogleAI	Alpha	v1	1.16
Huggingface	Alpha	v1	1.15
Local echo	Stable	v1	1.15
Mistral	Alpha	v1	1.15
Ollama	Alpha	v1	1.16
OpenAI	Alpha	v1	1.15

1 - Anthropic

Detailed information on the Anthropic conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: anthropic
spec:
  type: conversation.anthropic
  metadata:
  - name: key
    value: "mykey"
  - name: model
    value: claude-3-5-sonnet-20240620
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for Anthropic.	`"mykey"`
`model`	N	The Anthropic LLM to use. Defaults to `claude-3-5-sonnet-20240620`	`claude-3-5-sonnet-20240620`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

Conversation API overview

2 - AWS Bedrock

Detailed information on the AWS Bedrock conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: awsbedrock
spec:
  type: conversation.aws.bedrock
  metadata:
  - name: endpoint
    value: "http://localhost:4566"
  - name: model
    value: amazon.titan-text-express-v1
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`endpoint`	N	AWS endpoint for the component to use and connect to emulators. Not recommended for production AWS use.	`http://localhost:4566`
`model`	N	The LLM to use. Defaults to Bedrock’s default provider model from Amazon.	`amazon.titan-text-express-v1`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

Authenticating AWS

Instead of using a key parameter, AWS Bedrock authenticates using Dapr’s standard method of IAM or static credentials. Learn more about authenticating with AWS.

Conversation API overview

3 - DeepSeek

Detailed information on the DeepSeek conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: deepseek
spec:
  type: conversation.deepseek
  metadata:
  - name: key
    value: mykey
  - name: maxTokens
    value: 2048

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for DeepSeek.	`mykey`
`maxTokens`	N	The max amount of tokens for each request.	`2048`

Conversation API overview

4 - Local Testing

Detailed information on the echo conversation component used for local testing

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: echo
spec:
  type: conversation.echo
  version: v1

Information

This component is only meant for local validation and testing of a Conversation component implementation. It does not actually send the data to any LLM but rather echos the input back directly.

Conversation API overview

5 - GoogleAI

Detailed information on the GoogleAI conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: googleai
spec:
  type: conversation.googleai
  metadata:
  - name: key
    value: mykey
  - name: model
    value: gemini-1.5-flash
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for GoogleAI.	`mykey`
`model`	N	The GoogleAI LLM to use. Defaults to `gemini-1.5-flash`.	`gemini-2.0-flash`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

Conversation API overview

6 - Huggingface

Detailed information on the Huggingface conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: huggingface
spec:
  type: conversation.huggingface
  metadata:
  - name: key
    value: mykey
  - name: model
    value: meta-llama/Meta-Llama-3-8B
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for Huggingface.	`mykey`
`model`	N	The Huggingface LLM to use. Defaults to `meta-llama/Meta-Llama-3-8B`.	`meta-llama/Meta-Llama-3-8B`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

Conversation API overview

7 - Mistral

Detailed information on the Mistral conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: mistral
spec:
  type: conversation.mistral
  metadata:
  - name: key
    value: mykey
  - name: model
    value: open-mistral-7b
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for Mistral.	`mykey`
`model`	N	The Mistral LLM to use. Defaults to `open-mistral-7b`.	`open-mistral-7b`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

Conversation API overview

8 - Ollama

Detailed information on the Ollama conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: ollama
spec:
  type: conversation.ollama
  metadata:
  - name: model
    value: llama3.2:latest
  - name: cacheTTL
    value: 10m

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`model`	N	The Ollama LLM to use. Defaults to `llama3.2:latest`.	`phi4:latest`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`

OpenAI Compatibility

Ollama is compatible with OpenAI’s API. You can use the OpenAI component with Ollama models with the following changes:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: ollama-openai
spec:
  type: conversation.openai # use the openai component type
  metadata:
  - name: key
    value: 'ollama' # just any non-empty string
  - name: model
    value: gpt-oss:20b  # an ollama model (https://ollama.com/search) in this case openai open source model. See https://ollama.com/library/gpt-oss
  - name: endpoint
    value: 'http://localhost:11434/v1' # ollama endpoint

Conversation API overview

9 - OpenAI

Detailed information on the OpenAI conversation component

Component format

A Dapr conversation.yaml component file has the following structure:

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: openai
spec:
  type: conversation.openai
  metadata:
  - name: key
    value: mykey
  - name: model
    value: gpt-4-turbo
  - name: endpoint
    value: 'https://api.openai.com/v1'
  - name: cacheTTL
    value: 10m
  # - name: apiType # Optional
  #   value: 'azure'
  # - name: apiVersion # Optional
  #   value: '2025-01-01-preview'

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`key`	Y	API key for OpenAI.	`mykey`
`model`	N	The OpenAI LLM to use. Defaults to `gpt-4-turbo`.	`gpt-4-turbo`
`endpoint`	N	Custom API endpoint URL for OpenAI API-compatible services. If not specified, the default OpenAI API endpoint is used. Required when `apiType` is set to `azure`.	`https://api.openai.com/v1`, `https://example.openai.azure.com/`
`cacheTTL`	N	A time-to-live value for a prompt cache to expire. Uses Golang duration format.	`10m`
`apiType`	N	Specifies the API provider type. Required when using a provider that does not follow the default OpenAI API endpoint conventions.	`azure`
`apiVersion`	N	The API version to use. Required when the `apiType` is set to `azure`.	`2025-04-01-preview`

Azure OpenAI Configuration

To configure the OpenAI component to connect to Azure OpenAI, you need to set the following metadata fields which are required for Azure’s API format.

Required fields for Azure OpenAI

When connecting to Azure OpenAI, the following fields are required:

apiType: Must be set to azure to enable Azure OpenAI compatibility
endpoint: Your Azure OpenAI resource endpoint URL (e.g., https://your-resource.openai.azure.com/)
apiVersion: The API version for your Azure OpenAI deployment (e.g., 2025-01-01-preview)
key: Your Azure OpenAI API key

Get your configuration values from: https://ai.azure.com/

Azure OpenAI component example

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
  name: azure-openai
spec:
  type: conversation.openai
  metadata:
  - name: key
    value: "your-azure-openai-api-key"
  - name: model
    value: "gpt-4.1-nano"  # Default: gpt-4.1-nano
  - name: endpoint
    value: "https://your-resource.openai.azure.com/"
  - name: apiType
    value: "azure"
  - name: apiVersion
    value: "2025-01-01-preview"

Note

When using Azure OpenAI, both endpoint and apiVersion are mandatory fields. The component returns an error if either field is missing when apiType is set to azure.

Conversation component specs

Amazon Web Services (AWS)

Generic

1 - Anthropic

Component format

Warning

Spec metadata fields

Related links

2 - AWS Bedrock

Component format

Warning

Spec metadata fields

Authenticating AWS

Related links

3 - DeepSeek

Component format

Warning

Spec metadata fields

Related links

4 - Local Testing

Component format

Information

Related links

5 - GoogleAI

Component format

Warning

Spec metadata fields

Related links

6 - Huggingface

Component format

Warning

Spec metadata fields

Related links

7 - Mistral

Component format

Warning

Spec metadata fields

Related links

8 - Ollama

Component format

Warning

Spec metadata fields

OpenAI Compatibility

Related links

9 - OpenAI

Component format

Warning

Spec metadata fields

Azure OpenAI Configuration

Required fields for Azure OpenAI

Azure OpenAI component example

Note

Related links