Description:

This step sends a prompt to a locally hosted Ollama AI model and retrieves an AI-generated response.

The Ask Question from Ollama Local Model workflow step connects to an Ollama server running on your local network or server, submits a user-defined prompt along with optional system instructions and image files, receives the generated response from the selected AI model, and stores the result in a FlowWright Variable or Global Variable.

The step supports both text-only prompts and multimodal prompts that include image files, allowing workflows to perform document understanding, image analysis, content generation, summarization, classification, question answering, and intelligent business process automation without requiring a cloud-based AI service.

By executing AI models locally, organizations can maintain control over sensitive data while integrating advanced AI capabilities into FlowWright workflows.

The step supports:

• Local Ollama AI integration
• Selection of installed Ollama models
• System ("Act As") instructions
• Text prompt processing
• Optional image analysis
• Storage of AI-generated responses
• Integration with FlowWright Variables and Global Variables
• Offline AI processing

This step can be used for:

• Intelligent document processing
• Local AI automation
• Content generation
• Document summarization
• Image analysis
• Question answering
• Business process automation

Usage:

The Ask Question from Ollama Local Model step is typically placed after document retrieval, OCR processing, form submission, image acquisition, or data collection activities where AI-generated insights or content are required.

The workflow submits the configured prompt, optional system instructions, and optional image files to the selected Ollama model, stores the generated response, and makes it available for downstream workflow processing.

A typical workflow might look like this:

Once the AI response has been generated, later workflow steps can:

• Summarize documents
• Classify records
• Extract key information
• Make workflow decisions
• Populate workflow variables
• Generate reports
• Continue workflow execution

The selected Ollama model must already be installed and available before this step is executed.

Example:

Let’s build and execute the “OllamaAIDef” example.          

• Create a new process definition called “OllamaAIDef” and open it in Designer mode.
• Drag an “OllamaAI” step to the canvas. 
• Connect the dots between the “Start” and “OllamaAI” steps, as shown above. 
• Define a variable or a global to store the result.
• Click the "OllamaAI" step to configure its "Required" properties. Provide a name for the step. Select the language model from the drop-down list. Enter the text context prompt. Specify the variable or global reference to store the result. Click the Save button. Note: Click the "AI Predict" button for the Copilot to add new process steps that match your process description. 

• Click the "OllamaAI" step to configure its "Optional" properties. Enter the user persona description. Click the Save button. 

• The “Logging” configuration is necessary for documentation and also measures workflow progress and 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 Process Instance and execute it. When the workflow reaches the Ask Question from Ollama Local Model step, FlowWright connects to the configured Ollama service and submits the prompt, optional system instructions, and any specified image files to the selected model. If the request completes successfully, the generated response is stored in the configured Variable or Global Variable, and the workflow follows the True return path. If the Ollama service is unavailable, the selected model is not installed, the prompt cannot be processed, or an internal processing error occurs, the workflow follows the False return path. Click the process step to view its properties. The step should successfully generate an AI response, populate the configured Variable or Global Variable, and return True upon completion.

Tips:

• Verify that the Ollama service is running before executing the workflow.
• Ensure the selected AI model has been downloaded and is available in the local Ollama installation.
• Use the Act As property to provide clear system instructions and improve response consistency.
• Include image files when using vision-capable Ollama models to analyze scanned documents, invoices, screenshots, or photographs.
• Store the AI response in a Global Variable when multiple workflow steps require access to the generated content.
• Use workflow variables to dynamically construct prompts based on workflow data.
• Use the True and False return paths to implement appropriate success and exception handling.
• Combine this step with OCR, Convert Word to Text, PDF to HTML, JSON to XML, Update Variables, Send Email, or Conditional Routing workflow steps to automate AI-powered document processing and business workflows.

Notes:

• The Ollama service must be installed, running, and accessible from the FlowWright server.
• The selected model must already be installed within Ollama.
• The Act As property provides system-level instructions that influence the AI model's behavior.
• Image analysis is available only when the selected Ollama model supports it.
• The generated AI response is stored in the configured Variable or Global Variable.
• Service connectivity issues, unavailable models, invalid prompts, unsupported image formats, or internal processing errors may cause the step to return False.
• This step retrieves AI-generated responses only and does not modify the source documents or images.
• The workflow should include appropriate handling for both True and False return paths.
• Running AI models locally helps organizations maintain data privacy, reduce dependency on cloud services, and process sensitive information entirely within their own infrastructure.

Definition Sample:

You may download the sample definition(s) from the link provided and later import them (drag-and-drop) into your FlowWright Process Definition page.

Note: Verify and complete any missing configuration after importing the sample, including:

• Ollama model selection
• Prompt text
• System instructions
• Image file paths (if applicable)
• Variable or Global Variable mapping
• Ollama server availability
• Environment-specific settings

After verifying the configuration, save the Process Definition before execution.

Click here to download the sample file.