Ollama conversation

Type: conversation.ollama

Status: alpha

Reference: https://docs.dapr.io/reference/components-reference/supported-conversation/ollama/

Example

apiVersion: cra.diagrid.io/v1beta1
kind: Component
metadata:
  name: <name>
spec:
  type: conversation.ollama
  version: v1
  metadata:
    # A time-to-live value for a prompt cache to expire. Uses Golang durations (Optional)
    #- name: cacheTTL
    #  value: "10m"
    # The URL of the Ollama server. (Optional)
    #- name: endpoint
    #  value: "http://localhost:11434/v1"
    # Default maximum number of tokens the model may generate per request. A request-level maxTokens value greater than zero overrides this default. When unset, no cap is sent and the provider's own default applies. (Optional)
    #- name: maxTokens
    #  value: "2048"
    # The Ollama LLM to use. Configurable via OLLAMA_MODEL environment variable. (Optional)
    #- name: model
    #  value: "llama3.2:latest"

Metadata

cacheTTL (string)

A time-to-live value for a prompt cache to expire. Uses Golang durations

Example value: 10m

endpoint (string)

The URL of the Ollama server.

Default value: http://localhost:11434/v1

Example value: http://10.20.23.21:11434/v1

maxTokens (number)

Default maximum number of tokens the model may generate per request. A request-level maxTokens value greater than zero overrides this default. When unset, no cap is sent and the provider's own default applies.

Example value: 2048

model (string)

The Ollama LLM to use. Configurable via OLLAMA_MODEL environment variable.

Default value: llama3.2:latest

Example value: llama3.2:latest