DocumentationWorkflowsAI and agents
Ollama Chat Model node
Provides a local or self-hosted Ollama model to an LLM chain. The server address comes exclusively from server configuration. Learn how to configure it, map inputs and outputs, run a test and resolve common errors.
7 min readUpdated
What this node does
Provides a local or self-hosted Ollama model to an LLM chain. The server address comes exclusively from server configuration.
Use Ollama Chat Model as a clearly defined step in an anymize workflow.
- Starts a new workflow run.
- Provides one output for following steps.
- Runs as a regular step in the flow.
Set up the node
- 01Open a workflow and add Ollama Chat Model from the node catalog.
- 02Complete the required fields and map values from previous steps.
- 03Run the node with a small test record and inspect its output.
- 04Connect the successful output and activate the workflow after an end-to-end test.
Operations and modes
Ollama Chat Model has one focused purpose. Its available settings appear when you select the node.
Settings
| Field | Meaning | Area |
|---|---|---|
| Model | The model must already be available on the connected Ollama server. | Standard |
| Response format | Choices: Text, JSON | Standard |
| Temperature | Lower values are more consistent; higher values create more variation. | Standard |
| Top P | Limits selection to the most likely tokens. | Standard |
| Maximum output tokens | Configure this value in the node panel. | Standard |
| Seed | Optional integer seed for reproducible responses. | Standard |
| Keep model loaded | How long Ollama keeps the model in memory after the response. | Standard |
Inputs and outputs
| Input | Meaning | Type |
|---|---|---|
| Standard | This trigger does not require an input. | JSON |
| Output | Meaning | Type |
|---|---|---|
| Model configuration | Safe model and generation settings for a connected LLM chain node. | json |
| Model | The configured Ollama model name. | text |
Example and test run
Local Llama 3.2: begin with a small, recognizable record. Inspect the output and only map fields that are present there.
Test-run example
{}Access and security
Before activation, review which data enters this step and what its output contains.
Store keys and credentials in the protected connection manager. Never paste them into normal workflow fields, test data or descriptions.
Troubleshooting
- No output: inspect the latest run and confirm that the previous node returned the expected fields.
- Empty variable: open the previous step output and use a field name from the real test data.