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: responseCacheTTL
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 |
maxTokens | N | Default maximum number of tokens the model may generate per request. A request-level maxTokens value overrides this default. When unset, no cap is sent and the provider’s own default applies. | 2048 |
responseCacheTTL | N | Time-to-live for the in-memory response cache. When set, identical requests are served from cache until they expire. | 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