LangChain4j Chat

Since Camel 4.5

Only producer is supported

The LangChain4j Chat Component allows you to integrate with any LLM supported by LangChain4j.

Maven users will need to add the following dependency to their pom.xml for this component:

<dependency>
    <groupId>org.apache.camel</groupId>
    <artifactId>camel-langchain4j-chat</artifactId>
    <version>x.x.x</version>
    <!-- use the same version as your Camel core version -->
</dependency>

URI format

langchain4j-chat:chatIdId[?options]

Where chatId can be any string to uniquely identify the endpoint

Configuring Options

Camel components are configured on two separate levels:

  • component level

  • endpoint level

Configuring Component Options

At the component level, you set general and shared configurations that are, then, inherited by the endpoints. It is the highest configuration level.

For example, a component may have security settings, credentials for authentication, urls for network connection and so forth.

Some components only have a few options, and others may have many. Because components typically have pre-configured defaults that are commonly used, then you may often only need to configure a few options on a component; or none at all.

You can configure components using:

  • the Component DSL.

  • in a configuration file (application.properties, *.yaml files, etc).

  • directly in the Java code.

Configuring Endpoint Options

You usually spend more time setting up endpoints because they have many options. These options help you customize what you want the endpoint to do. The options are also categorized into whether the endpoint is used as a consumer (from), as a producer (to), or both.

Configuring endpoints is most often done directly in the endpoint URI as path and query parameters. You can also use the Endpoint DSL and DataFormat DSL as a type safe way of configuring endpoints and data formats in Java.

A good practice when configuring options is to use Property Placeholders.

Property placeholders provide a few benefits:

  • They help prevent using hardcoded urls, port numbers, sensitive information, and other settings.

  • They allow externalizing the configuration from the code.

  • They help the code to become more flexible and reusable.

The following two sections list all the options, firstly for the component followed by the endpoint.

Component Options

The LangChain4j Chat component supports 5 options, which are listed below.

Name Description Default Type

chatOperation (producer)

Required Operation in case of Endpoint of type CHAT. The value is one of the values of org.apache.camel.component.langchain4j.chat.LangChain4jChatOperations.

Enum values:

  • CHAT_SINGLE_MESSAGE

  • CHAT_SINGLE_MESSAGE_WITH_PROMPT

  • CHAT_MULTIPLE_MESSAGES

CHAT_SINGLE_MESSAGE

LangChain4jChatOperations

configuration (producer)

The configuration.

LangChain4jChatConfiguration

lazyStartProducer (producer)

Whether the producer should be started lazy (on the first message). By starting lazy you can use this to allow CamelContext and routes to startup in situations where a producer may otherwise fail during starting and cause the route to fail being started. By deferring this startup to be lazy then the startup failure can be handled during routing messages via Camel’s routing error handlers. Beware that when the first message is processed then creating and starting the producer may take a little time and prolong the total processing time of the processing.

false

boolean

autowiredEnabled (advanced)

Whether autowiring is enabled. This is used for automatic autowiring options (the option must be marked as autowired) by looking up in the registry to find if there is a single instance of matching type, which then gets configured on the component. This can be used for automatic configuring JDBC data sources, JMS connection factories, AWS Clients, etc.

true

boolean

chatModel (advanced)

Autowired Chat Language Model of type dev.langchain4j.model.chat.ChatLanguageModel.

ChatLanguageModel

Endpoint Options

The LangChain4j Chat endpoint is configured using URI syntax:

langchain4j-chat:chatId

With the following path and query parameters:

Path Parameters (1 parameters)

Name Description Default Type

chatId (producer)

Required The id.

String

Query Parameters (3 parameters)

Name Description Default Type

chatOperation (producer)

Required Operation in case of Endpoint of type CHAT. The value is one of the values of org.apache.camel.component.langchain4j.chat.LangChain4jChatOperations.

Enum values:

  • CHAT_SINGLE_MESSAGE

  • CHAT_SINGLE_MESSAGE_WITH_PROMPT

  • CHAT_MULTIPLE_MESSAGES

CHAT_SINGLE_MESSAGE

LangChain4jChatOperations

lazyStartProducer (producer (advanced))

Whether the producer should be started lazy (on the first message). By starting lazy you can use this to allow CamelContext and routes to startup in situations where a producer may otherwise fail during starting and cause the route to fail being started. By deferring this startup to be lazy then the startup failure can be handled during routing messages via Camel’s routing error handlers. Beware that when the first message is processed then creating and starting the producer may take a little time and prolong the total processing time of the processing.

false

boolean

chatModel (advanced)

Autowired Chat Language Model of type dev.langchain4j.model.chat.ChatLanguageModel.

ChatLanguageModel

Message Headers

The LangChain4j Chat component supports 1 message header(s), which is/are listed below:

Name Description Default Type

CamelLangChain4jChatPromptTemplate (producer)

Constant: PROMPT_TEMPLATE

The prompt Template.

String

Spring Boot Auto-Configuration

When using langchain4j-chat with Spring Boot make sure to use the following Maven dependency to have support for auto configuration:

<dependency>
  <groupId>org.apache.camel.springboot</groupId>
  <artifactId>camel-langchain4j-chat-starter</artifactId>
  <version>x.x.x</version>
  <!-- use the same version as your Camel core version -->
</dependency>

The component supports 6 options, which are listed below.

Name Description Default Type

camel.component.langchain4j-chat.autowired-enabled

Whether autowiring is enabled. This is used for automatic autowiring options (the option must be marked as autowired) by looking up in the registry to find if there is a single instance of matching type, which then gets configured on the component. This can be used for automatic configuring JDBC data sources, JMS connection factories, AWS Clients, etc.

true

Boolean

camel.component.langchain4j-chat.chat-model

Chat Language Model of type dev.langchain4j.model.chat.ChatLanguageModel. The option is a dev.langchain4j.model.chat.ChatLanguageModel type.

ChatLanguageModel

camel.component.langchain4j-chat.chat-operation

Operation in case of Endpoint of type CHAT. The value is one of the values of org.apache.camel.component.langchain4j.chat.LangChain4jChatOperations.

LangChain4jChatOperations

camel.component.langchain4j-chat.configuration

The configuration. The option is a org.apache.camel.component.langchain4j.chat.LangChain4jChatConfiguration type.

LangChain4jChatConfiguration

camel.component.langchain4j-chat.enabled

Whether to enable auto configuration of the langchain4j-chat component. This is enabled by default.

Boolean

camel.component.langchain4j-chat.lazy-start-producer

Whether the producer should be started lazy (on the first message). By starting lazy you can use this to allow CamelContext and routes to startup in situations where a producer may otherwise fail during starting and cause the route to fail being started. By deferring this startup to be lazy then the startup failure can be handled during routing messages via Camel’s routing error handlers. Beware that when the first message is processed then creating and starting the producer may take a little time and prolong the total processing time of the processing.

false

Boolean

Using a specific Chat Model

The Camel LangChain4j chat component provides an abstraction for interacting with various types of Large Language Models (LLMs) supported by LangChain4j.

To integrate with a specific Large Language Model, users should follow these steps:

Example of Integrating with OpenAI

Add the dependency for LangChain4j OpenAI support:

<dependency>
      <groupId>dev.langchain4j</groupId>
      <artifactId>langchain4j-open-ai</artifactId>
    <version>x.x.x</version>
</dependency>

Init the OpenAI Chat Language Model, and add it to the Camel Registry:

ChatLanguageModel model = OpenAiChatModel.builder()
                .apiKey(openApiKey)
                .modelName(GPT_3_5_TURBO)
                .temperature(0.3)
                .timeout(ofSeconds(3000))
                .build();
context.getRegistry().bind("chatModel", model);

Use the model in the Camel LangChain4j Chat Producer

 from("direct:chat")
      .to("langchain4j-chat:test?chatModel=#chatModel")

To switch to another Large Language Model and its corresponding dependency, replace the langchain4j-open-ai dependency with the appropriate dependency for the desired model. Update the initialization parameters accordingly in the code snippet provided above.

Send a prompt with variables

To send a prompt with variables, use the Operation type LangChain4jChatOperations.CHAT_SINGLE_MESSAGE_WITH_PROMPT. This operation allows you to send a single prompt message with dynamic variables, which will be replaced with values provided in the request.

Example of route :

 from("direct:chat")
      .to("langchain4j-chat:test?chatModel=#chatModel&chatOperation=CHAT_SINGLE_MESSAGE_WITH_PROMPT")

Example of usage:

var promptTemplate = "Create a recipe for a {{dishType}} with the following ingredients: {{ingredients}}";

Map<String, Object> variables = new HashMap<>();
variables.put("dishType", "oven dish");
variables.put("ingredients", "potato, tomato, feta, olive oil");

String response = template.requestBodyAndHeader("direct:chat", variables,
                LangChain4jChat.Headers.PROMPT_TEMPLATE, promptTemplate, String.class);

Chat with history

You can send a new prompt along with the chat message history by passing all messages in a list of type dev.langchain4j.data.message.ChatMessage. Use the Operation type LangChain4jChatOperations.CHAT_MULTIPLE_MESSAGES. This operation allows you to continue the conversation with the context of previous messages.

Example of route :

 from("direct:chat")
      .to("langchain4j-chat:test?chatModel=#chatModel&chatOperation=CHAT_MULTIPLE_MESSAGES")

Example of usage:

List<ChatMessage> messages = new ArrayList<>();
messages.add(new SystemMessage("You are asked to provide recommendations for a restaurant based on user reviews."));
// Add more chat messages as needed

String response = template.requestBody("direct:send-multiple", messages, String.class);

Chat with Tool

Camel langchain4j-chat component as a consumer can be used to implement a LangChain tool. Right now tools are supported only via the OpenAiChatModel backed by OpenAI APIs.

Tool Input parameter can be defined as an Endpoint multiValue option in the form of parameter.<name>=<type>, or via the endpoint option camelToolParameter for a programmatic approach. The parameters can be found as headers in the consumer route, in particular, if you define parameter.userId=5, in the consumer route ${header.userId} can be used.

Example of a producer and a consumer:

from("direct:test")
    .to("langchain4j-chat:test1?chatOperation=CHAT_MULTIPLE_MESSAGES");

from("langchain4j-chat:test1?description=Query user database by number&parameter.number=integer")
    .to("sql:SELECT name FROM users WHERE id = :#number");

Example of usage:

List<ChatMessage> messages = new ArrayList<>();
        messages.add(new SystemMessage("""
                You provide information about specific user name querying the database given a number.
                """));
        messages.add(new UserMessage("""
                What is the name of the user 1?
                """));

        Exchange message = fluentTemplate.to("direct:test").withBody(messages).request(Exchange.class);
Back to top