Ollama

Ollama connects your flows to the models installed on your own Ollama server. You can use it in two ways: as the model of an agent, by connecting its Model output to the agent’s Model input, or on its own, so that it answers the text that reaches its Input.

When to use it

Give an agent the model it uses to understand requests, decide which tools to use and answer.
Write, summarise or classify texts inside a flow, without an agent.
Work with models your company runs on its own machines.
Process a list of texts one by one with Batch Mode.

Configuration

In the Common tab:

Field	What it does
Base URL	The address of your Ollama server. NappAI must be able to reach it.
Model Name	The model that answers. After typing the server address, press the refresh button next to the field to load the models installed on it.
Temperature	How varied the answers are: low values give steadier, more predictable answers; high values, more creative ones. Default: 0.2.
Verbose	It does not change the answer; you can leave it off. Default: off.

Connection	What to connect
Input	The text the model must answer when it works on its own, for example the message of a Chat Input or the result of a Prompt.

Advanced options

In the Advanced tab:

Field	What it does
System Message	General instructions for the model when it works on its own: its role, the tone, what to avoid. You can type them or connect them from another component.
Stream	Shows the answer in the chat while it is being written, instead of waiting until it is finished. It only has an effect in the chat. Default: off.
Reasoning	How much the model thinks before answering, for models that think. Default keeps the model’s own behaviour; off and on turn it off or on; low, medium and high set how much it thinks. Default: Default.
Format	Type `json` so the answer arrives as structured data.
Context Window Size	How much text the model can take into account at once, in tokens.
Top K and Top P	Other ways to control how varied the answer is. Temperature is usually enough.
Repeat Penalty	How much repetition in the answer is penalised.
Stop Tokens	Words or symbols, separated by commas, at which the model stops writing.
Timeout	How long to wait for the server’s answer.
Other options	Mirostat, Mirostat Eta, Mirostat Tau, Number of GPUs, Number of Threads, Repeat Last N, TFS Z, Min p, Metadata, Tags, System, Template: fine-tuning settings for advanced users. Leave them as they are if you don’t need them.

Batch processing

With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.

Output

Output	What it contains
Model	The configured model. It sits at the top of the component. Connect it to the Model input of an agent or of any other component that asks for a model.
Text	The model’s answer to the text received in Input. Connect it, for example, to a Chat Output or to another component that works with text.

The two ways of using it exclude each other: when you connect the Model output, the component hides Input and Text, because the model now works inside the other component; and if you connect Input, Model is hidden.

Example

The Fiscal Sur consultancy has an Ollama server in its office so its clients’ data stays there. It types its address in Base URL, refreshes the Model Name list and chooses a model. Then it connects the Model output to an agent that sorts the incoming documents.

Good practices

Use a low Temperature when you need exact answers, such as classifying or extracting data, and raise it for more creative texts.
If you use the model with an agent, configure only the model here: the instructions and the tools are set in the agent.