Configuration property fixed at build time - All other configuration properties are overridable at runtime

Configuration property

Type

Default

quarkus.langchain4j.devservices.enabled

If DevServices has been explicitly enabled or disabled. DevServices is generally enabled by default, unless there is an existing configuration present.

When DevServices is enabled Quarkus will attempt to automatically serve a model if there are any matching ones.

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_ENABLED

boolean

true

quarkus.langchain4j.devservices.port

The default port where the inference server listens for requests

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_PORT

int

11434

quarkus.langchain4j.devservices.preload

Instructs Ollama to preload a model in order to get faster response times

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_PRELOAD

boolean

true

quarkus.langchain4j.response-schema

Configuration property to enable or disable the use of the {response schema} placeholder in the @SystemMessage/@UserMessage.

Environment variable: QUARKUS_LANGCHAIN4J_RESPONSE_SCHEMA

boolean

true

quarkus.langchain4j.log-requests

Whether clients should log requests

Environment variable: QUARKUS_LANGCHAIN4J_LOG_REQUESTS

boolean

false

quarkus.langchain4j.log-responses

Whether clients should log responses

Environment variable: QUARKUS_LANGCHAIN4J_LOG_RESPONSES

boolean

false

quarkus.langchain4j.timeout

Global timeout for requests to LLM APIs

Environment variable: QUARKUS_LANGCHAIN4J_TIMEOUT

Duration

10s

quarkus.langchain4j.guardrails.max-retries

Configures the maximum number of retries for the guardrail. Sets it to 0 to disable retries.

Environment variable: QUARKUS_LANGCHAIN4J_GUARDRAILS_MAX_RETRIES

int

3

Default model config

Type

Default

quarkus.langchain4j.chat-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_CHAT_MODEL_PROVIDER

string

quarkus.langchain4j.embedding-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_EMBEDDING_MODEL_PROVIDER

string

quarkus.langchain4j.moderation-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_MODERATION_MODEL_PROVIDER

string

quarkus.langchain4j.image-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_IMAGE_MODEL_PROVIDER

string

Named model config

Type

Default

quarkus.langchain4j."model-name".chat-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__CHAT_MODEL_PROVIDER

string

quarkus.langchain4j."model-name".embedding-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__EMBEDDING_MODEL_PROVIDER

string

quarkus.langchain4j."model-name".moderation-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__MODERATION_MODEL_PROVIDER

string

quarkus.langchain4j."model-name".image-model.provider

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__IMAGE_MODEL_PROVIDER

string
About the Duration format

To write duration values, use the standard java.time.Duration format. See the Duration#parse() Java API documentation for more information.

You can also use a simplified format, starting with a number:

  • If the value is only a number, it represents time in seconds.

  • If the value is a number followed by ms, it represents time in milliseconds.

In other cases, the simplified format is translated to the java.time.Duration format for parsing:

  • If the value is a number followed by h, m, or s, it is prefixed with PT.

  • If the value is a number followed by d, it is prefixed with P.