Package io.quarkiverse.langchain4j.ollama.runtime.config

Interface ChatModelConfig

public interface ChatModelConfig

Method Summary

Modifier and Type	Method	Description
String	modelId()	Model to use.
Integer	numPredict()	Maximum number of tokens to predict when generating text
Optional<Integer>	seed()	With a static number the result is always the same.
Optional<String>	stop()	Sets the stop sequences to use.
Double	temperature()	The temperature of the model.
Integer	topK()	Reduces the probability of generating nonsense.
Double	topP()	Works together with top-k.

Method Details

modelId

@WithDefault("latest")
String modelId()

Model to use. According to Ollama docs, the default value is latest

temperature

@WithDefault("0.8")
Double temperature()

The temperature of the model. Increasing the temperature will make the model answer with more variability. A lower temperature will make the model answer more conservatively.

numPredict

@WithDefault("128")
Integer numPredict()

Maximum number of tokens to predict when generating text

stop

Optional<String> stop()

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return

topP

@WithDefault("0.9")
Double topP()

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text

topK

@WithDefault("40")
Integer topK()

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

seed

Optional<Integer> seed()

With a static number the result is always the same. With a random number the result varies Example: Random random = new Random(); int x = random.nextInt(Integer.MAX_VALUE);