DocumentationWorkflowsAI and agents
Basic LLM Chain node
Connects a prompt to exactly one language model and returns its response. Use it for direct prompt-response flows without agents or tools. Learn how to configure it, map inputs and outputs, run a test and resolve common errors.
8 min readUpdated
What this node does
Connects a prompt to exactly one language model and returns its response. Use it for direct prompt-response flows without agents or tools.
Use Basic LLM Chain as a clearly defined step in an anymize workflow.
- Processes one input.
- Provides one output for following steps.
- Runs as a regular step in the flow.
Set up the node
- 01Open a workflow and add Basic LLM Chain 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
Basic LLM Chain has one focused purpose. Its available settings appear when you select the node.
Settings
| Field | Meaning | Area |
|---|---|---|
| Fallback model | Used only when no model node is connected to the Language model input. | Standard |
| System prompt | Configure this value in the node panel. | Standard |
| User prompt | Configure this value in the node panel. | Standard |
| Temperature | Lower values are more consistent; higher values create more variation. | Standard |
| Maximum output tokens | Limits the length of the model response. | Standard |
| Run once per item | Off (default): the node runs once for the whole input. On: if it receives several items (e.g. from Split Out), it runs once PER item, and {{ $json }} is that one item each time. This is how you work through a file list entry by entry. | Standard |
| If one item fails | "Skip" writes an `error` field for the failed item and keeps processing the rest, instead of losing the whole run to a single unreadable file. | Standard |
| Pause between items (milliseconds) | Wait before every run except the first. 1000 = 1 second per item. Useful when the other side would otherwise throttle you. Maximum 300000 (5 minutes). | Standard |
Inputs and outputs
| Input | Meaning | Type |
|---|---|---|
| Language model | Optional configuration from a model node such as Ollama. Without a connection, the Anymize model selected below is used. | json |
| User prompt | The message the model should answer. | text |
| System prompt | Optional role and rules for the model. | text |
| Output | Meaning | Type |
|---|---|---|
| Response | The text generated by the model. | text |
| Model | The model that was actually used. | text |
| Usage | Token counts when provided by the model service. | json |
| Raw response | The complete provider response for diagnostics. | json |
This node can process lists item by item. Error handling and the delay between items are available in advanced settings.
Example and test run
Answer a short question: begin with a small, recognizable record. Inspect the output and only map fields that are present there.
Test-run example
{
"message": "Erkläre semantische Suche in zwei Sätzen."
}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.
- List processed once: enable per-item execution in advanced settings.