Save workflow

save_workflow makes it possible to save your workflow settings for later re-use.

Usage

save_workflow(workflow_obj, filepath)

Arguments

workflow_obj

A workflow object containing all parameters describing the workflow required

filepath

filepath to a JSON file that will capture your workflow configuration.

Value

the workflow itself after saving it, so that it can be included inside a series of pipes.

Details

A function to save your workflow settings to a specific JSON file. To reload the settings use the load_workflow() function.

Examples

my_workflow <- ai_workflow() |> set_connector("ollama")  |>
 set_model(model_name= "llama3:8b-instruct-q5_K_S") |>
 set_n_predict(500) |>
 set_temperature(0.8) |> 
 set_default_missing_parameters_in_workflow() |> 
 set_system_prompt("You are a computer hardware and software specialist.") |>
 save_workflow(filepath="myworkflow.json")
#> → Default IP address has been set to 127.0.0.1.
#> → Default port has been set to 11434.
#> → Frequency Penalty was not specified and given a default value of 1.
#> → Presence Penalty was not specified and given a default value of 1.5.
#> → Repeat Penalty was not specified and given a default value of 1.2.
#> → Mode was not specified and 'chat' was selected by default.
#> → System Prompt was not specified and given a default value of 'You are a helpful AI assistant.'.
#> → The workflow has been saved to myworkflow.json.