or run

tessl search

tessl/maven-io-quarkiverse-langchain4j--quarkus-langchain4j-core

tessl install tessl/maven-io-quarkiverse-langchain4j--quarkus-langchain4j-core@1.5.0

Quarkus LangChain4j Core provides runtime integration for LangChain4j with the Quarkus framework, enabling declarative AI service creation through CDI annotations.

Configuration

Configuration capabilities enable customization of LangChain4j behavior through Microprofile Config, including logging, timeouts, temperature, guardrails, and tracing settings.

Capabilities

LangChain4jConfig Interface

Main configuration interface for LangChain4j settings.

// Package: io.quarkiverse.langchain4j.runtime.config
/**
 * Main configuration interface for Quarkus LangChain4j.
 * Mapped to properties under quarkus.langchain4j prefix.
 */
@ConfigMapping(prefix = "quarkus.langchain4j")
public interface LangChain4jConfig {

    /**
     * Enable/disable request logging.
     */
    Optional<Boolean> logRequests();

    /**
     * Enable/disable response logging.
     */
    Optional<Boolean> logResponses();

    /**
     * Global timeout for model requests.
     */
    Optional<Duration> timeout();

    /**
     * Global temperature setting for model requests.
     * Typically ranges from 0.0 (deterministic) to 2.0 (creative).
     */
    OptionalDouble temperature();

    /**
     * Guardrails configuration.
     */
    GuardrailsConfig guardrails();

    /**
     * Tracing configuration.
     */
    TracingConfig tracing();
}

GuardrailsConfig Interface

Configuration for guardrail behavior.

// Package: io.quarkiverse.langchain4j.runtime.config
/**
 * Configuration for guardrails.
 */
public interface GuardrailsConfig {

    /**
     * Maximum retry attempts for guardrail failures.
     * Default: 3
     */
    int maxRetries();
}

TracingConfig Interface

Configuration for OpenTelemetry tracing.

// Package: io.quarkiverse.langchain4j.runtime.config
/**
 * Configuration for OpenTelemetry tracing.
 */
public interface TracingConfig {

    /**
     * Include prompt text in OpenTelemetry spans.
     * May expose sensitive data in traces.
     */
    Boolean includePrompt();

    /**
     * Include completion text in OpenTelemetry spans.
     * May expose sensitive data in traces.
     */
    Boolean includeCompletion();

    /**
     * Include tool arguments in OpenTelemetry spans.
     * May expose sensitive data in traces.
     */
    Boolean includeToolArguments();

    /**
     * Include tool results in OpenTelemetry spans.
     * May expose sensitive data in traces.
     */
    Boolean includeToolResult();
}

ChatMemoryConfig Interface

Configuration for chat memory behavior.

// Package: io.quarkiverse.langchain4j.runtime.aiservice
/**
 * Configuration for chat memory.
 */
public interface ChatMemoryConfig {
    // Configuration properties for chat memory behavior
}

Configuration Examples

application.properties

# Request/Response Logging
quarkus.langchain4j.log-requests=true
quarkus.langchain4j.log-responses=true

# Global Timeout
quarkus.langchain4j.timeout=60s

# Global Temperature
quarkus.langchain4j.temperature=0.7

# Guardrails
quarkus.langchain4j.guardrails.max-retries=5

# Tracing (use with caution - may expose sensitive data)
quarkus.langchain4j.tracing.include-prompt=false
quarkus.langchain4j.tracing.include-completion=false
quarkus.langchain4j.tracing.include-tool-arguments=true
quarkus.langchain4j.tracing.include-tool-result=true

Model-Specific Configuration

# OpenAI GPT-4
quarkus.langchain4j.openai.gpt-4.api-key=${OPENAI_API_KEY}
quarkus.langchain4j.openai.gpt-4.model-name=gpt-4
quarkus.langchain4j.openai.gpt-4.temperature=0.7
quarkus.langchain4j.openai.gpt-4.timeout=60s
quarkus.langchain4j.openai.gpt-4.max-tokens=2000
quarkus.langchain4j.openai.gpt-4.log-requests=true
quarkus.langchain4j.openai.gpt-4.log-responses=true

# OpenAI GPT-3.5 Turbo
quarkus.langchain4j.openai.gpt-3-5-turbo.api-key=${OPENAI_API_KEY}
quarkus.langchain4j.openai.gpt-3-5-turbo.model-name=gpt-3.5-turbo
quarkus.langchain4j.openai.gpt-3-5-turbo.temperature=0.3
quarkus.langchain4j.openai.gpt-3-5-turbo.timeout=30s
quarkus.langchain4j.openai.gpt-3-5-turbo.max-tokens=1000

# Anthropic Claude
quarkus.langchain4j.anthropic.claude.api-key=${ANTHROPIC_API_KEY}
quarkus.langchain4j.anthropic.claude.model-name=claude-3-opus-20240229
quarkus.langchain4j.anthropic.claude.temperature=1.0
quarkus.langchain4j.anthropic.claude.max-tokens=4096

Chat Memory Configuration

# In-memory chat memory
quarkus.langchain4j.chat-memory.type=in-memory
quarkus.langchain4j.chat-memory.max-messages=100

# Redis chat memory
quarkus.langchain4j.chat-memory.type=redis
quarkus.langchain4j.chat-memory.redis.host=localhost
quarkus.langchain4j.chat-memory.redis.port=6379

Embedding Store Configuration

# In-memory embedding store
quarkus.langchain4j.embedding-store.type=in-memory

# Chroma embedding store
quarkus.langchain4j.embedding-store.type=chroma
quarkus.langchain4j.embedding-store.chroma.base-url=http://localhost:8000

# Redis embedding store
quarkus.langchain4j.embedding-store.type=redis
quarkus.langchain4j.embedding-store.redis.host=localhost
quarkus.langchain4j.embedding-store.redis.port=6379

Environment-Specific Configuration

application-dev.properties

# Development settings
quarkus.langchain4j.log-requests=true
quarkus.langchain4j.log-responses=true
quarkus.langchain4j.timeout=120s
quarkus.langchain4j.temperature=0.8

# Use cheaper models in development
quarkus.langchain4j.openai.dev.model-name=gpt-3.5-turbo

application-prod.properties

# Production settings
quarkus.langchain4j.log-requests=false
quarkus.langchain4j.log-responses=false
quarkus.langchain4j.timeout=30s
quarkus.langchain4j.temperature=0.5

# Use production-grade models
quarkus.langchain4j.openai.prod.model-name=gpt-4

Programmatic Configuration

Accessing Configuration

import io.quarkiverse.langchain4j.runtime.config.LangChain4jConfig;
import jakarta.enterprise.context.ApplicationScoped;
import jakarta.inject.Inject;
import org.eclipse.microprofile.config.inject.ConfigProperty;
import java.time.Duration;
import java.util.Optional;

@ApplicationScoped
public class ConfigConsumer {

    @Inject
    LangChain4jConfig config;

    @ConfigProperty(name = "quarkus.langchain4j.temperature")
    Optional<Double> temperature;

    public void printConfig() {
        System.out.println("Log requests: " + config.logRequests().orElse(false));
        System.out.println("Timeout: " + config.timeout().orElse(Duration.ofSeconds(30)));
        System.out.println("Temperature: " + config.temperature().orElse(0.7));
        System.out.println("Max retries: " + config.guardrails().maxRetries());
    }
}

Dynamic Configuration

import org.eclipse.microprofile.config.ConfigProvider;

public class DynamicConfig {

    public void loadConfig(String modelName) {
        String apiKey = ConfigProvider.getConfig()
            .getValue("quarkus.langchain4j." + modelName + ".api-key", String.class);

        Double temperature = ConfigProvider.getConfig()
            .getOptionalValue("quarkus.langchain4j." + modelName + ".temperature", Double.class)
            .orElse(0.7);
    }
}

Configuration Profiles

Use Quarkus profiles for different configurations:

# Default configuration
quarkus.langchain4j.temperature=0.7

# Development profile
%dev.quarkus.langchain4j.temperature=1.0
%dev.quarkus.langchain4j.log-requests=true

# Test profile
%test.quarkus.langchain4j.temperature=0.0
%test.quarkus.langchain4j.timeout=5s

# Production profile
%prod.quarkus.langchain4j.temperature=0.5
%prod.quarkus.langchain4j.log-requests=false

Observability Configuration

Metrics

# Enable metrics collection
quarkus.micrometer.enabled=true
quarkus.micrometer.binder.langchain4j.enabled=true

# Metrics export
quarkus.micrometer.export.prometheus.enabled=true

Tracing

# Enable OpenTelemetry tracing
quarkus.otel.enabled=true
quarkus.otel.traces.enabled=true

# Configure what to include in traces
quarkus.langchain4j.tracing.include-prompt=false
quarkus.langchain4j.tracing.include-completion=false
quarkus.langchain4j.tracing.include-tool-arguments=true
quarkus.langchain4j.tracing.include-tool-result=true

# OTLP exporter
quarkus.otel.exporter.otlp.endpoint=http://localhost:4317

Security Best Practices

API Keys

# Use environment variables for secrets
quarkus.langchain4j.openai.api-key=${OPENAI_API_KEY}
quarkus.langchain4j.anthropic.api-key=${ANTHROPIC_API_KEY}

# Or use configuration encryption
quarkus.langchain4j.openai.api-key=${enc:ENCRYPTED_VALUE}

Sensitive Data in Traces

# Disable sensitive data in traces for production
%prod.quarkus.langchain4j.tracing.include-prompt=false
%prod.quarkus.langchain4j.tracing.include-completion=false
%prod.quarkus.langchain4j.tracing.include-tool-arguments=false
%prod.quarkus.langchain4j.tracing.include-tool-result=false

# Enable for debugging in development
%dev.quarkus.langchain4j.tracing.include-prompt=true
%dev.quarkus.langchain4j.tracing.include-completion=true

Use Cases

Configuration is essential for:

Environment Management: Different settings for dev/test/prod
Performance Tuning: Adjust timeouts and model parameters
Cost Control: Configure cheaper models for non-critical operations
Observability: Control logging and tracing verbosity
Security: Manage API keys and sensitive data
Feature Flags: Enable/disable features per environment
Multi-Tenancy: Different configurations per tenant
A/B Testing: Test different model parameters

Version

tessl/maven-io-quarkiverse-langchain4j--quarkus-langchain4j-core

configuration.mddocs/reference/

Configuration

Capabilities

LangChain4jConfig Interface

GuardrailsConfig Interface

TracingConfig Interface

ChatMemoryConfig Interface

Configuration Examples

application.properties

Model-Specific Configuration

Chat Memory Configuration

Embedding Store Configuration

Environment-Specific Configuration

application-dev.properties

application-prod.properties

Programmatic Configuration

Accessing Configuration

Dynamic Configuration

Configuration Profiles

Observability Configuration

Metrics

Tracing

Security Best Practices

API Keys

Sensitive Data in Traces

Use Cases

Version

tessl/maven-io-quarkiverse-langchain4j--quarkus-langchain4j-core

configuration.md.css-3qkkll{font-size:var(--chakra-font-sizes-sm);font-weight:var(--chakra-font-weights-normal);color:var(--chakra-colors-gray-300);}docs/reference/

Configuration

Capabilities

LangChain4jConfig Interface

GuardrailsConfig Interface

TracingConfig Interface

ChatMemoryConfig Interface

Configuration Examples

application.properties

Model-Specific Configuration

Chat Memory Configuration

Embedding Store Configuration

Environment-Specific Configuration

application-dev.properties

application-prod.properties

Programmatic Configuration

Accessing Configuration

Dynamic Configuration

Configuration Profiles

Observability Configuration

Metrics

Tracing

Security Best Practices

API Keys

Sensitive Data in Traces

Use Cases

configuration.mddocs/reference/