Description:
This step fetches responses from an Ollama (language) local model.
Inputs
- actAs – act as user persona
- model – model to use
- prompt – text prompt
- varGlobalStoreResult – variable/global to store the response
Returns
- True – step executed successfully
- False – step failed to execute
Usage:
Example:
Let’s build and execute the “OllamaAIDef” example.
- Create a new definition called “OllamaAIDef”
- Select the definition and click the “design” button
- Drag an “OllamaAI” step from the toolbox
- Connect the dots between the Start and “OllamaAI” step
- Define a variable/global to store the result after execution
- Click the "OllamaAI" step to configure its "Required" properties. Provide a name to the step. Select the language model from the drop-down list. Provide the text context prompt. Provide the variable/global reference to store the result. Click the Save button to confirm.
- Click the "OllamaAI" step to configure its "Required" properties. Provide the user persona description as below. Click the Save button.
- The “Logging” setting configuration is necessary for documentation and also measures the workflow progress and the percent complete. This is achieved by configuring the step state and percent fields individually, as shown in the images below. Configure the “Logging” using the following properties.
- Save the process definition, create a new instance, and execute. Render the process instance. Click on the process step to view its properties. The “OllamaAI” step should generate and store the prompt response in the variable/global as configured.
Definition Sample:
You may download the sample definition(s) from the link here and later import it (drag-drop) to your FlowWright Process Definition (XML file) or Form Definition (HTML file) page.
NOTE: Please verify and complete the process steps for any missing configurations, such as file path references and database connections after import. Then, save the definition to confirm the changes.