Skip to main content

Using Anthropic models

Added in eventcatalog@2.38.0

EventCatalog Chat can be configured to use any Anthropic AI model.

This let's you talk to your architecture using the power of Anthropic models.

To use Anthropic models, you need to bring your Anthropic API keys to EventCatalog.

Installation​

1. Setup your license keys​

First, you need to get a license key for EventCatalog.

EventCatalog Chat is a paid feature, you can get a 14 day free trial of the EventCatalog Starter Plan on EventCatalog Cloud.

Once you have a license key, you can put it into your .env file.

.env
EVENTCATALOG_SCALE_LICENSE_KEY=<your-license-key>
ANTHROPIC_API_KEY=<your-anthropic-api-key>

2. Install the @eventcatalog/generator-ai plugin​

Next install the @eventcatalog/generator-ai plugin in your catalog directory.

npm install @eventcatalog/generator-ai

Configure the plugin in your eventcatalog.config.js file.

// rest of file 
generators: [
    [
        "@eventcatalog/generator-ai", {
            // optional, if you want to split markdown files into smaller chunks
            // Can help with your models (default false)
            splitMarkdownFiles: true,

            // optional, if you want to include users and teams in the documents (embeddings)
            // default is false, better search results without, but if you want the ability to ask questions about users and teams then set to true
            includeUsersAndTeams: false,

            // optional, if you want to include custom documentation in the documents (embeddings)
            // custom documentation is a feature that lets you bring any documentation into EventCatalog
            // default is true, but you can turn this off if you don't want to include custom documentation in the documents
            includeCustomDocumentation: false,
        }
    ],
],

Generate the documents and embeddings for your catalog by running the following command.

npm run generate

This will generate your documents and embeddings for your catalog. The model will use these documents and embeddings to answer your questions.

Keep in mind

This will create documents and embeddings for your catalog. You need to rerun this command whenever you make changes to your catalog.

3. Configure the Anthropic model​

Next, you need to configure the Anthropic model. Add the following to your eventcatalog.config.js file.

EventCatalog will default to the claude-3-7-sonnet-20250219 model. You can select from a range of models, see the models section for more information.

eventcatalog.config.js
chat: {
    // enable the chat or not (default true, for new catalogs)
    enabled: true,
    // Tells EventCatalog that we want to use Anthropic
    provider: 'anthropic',
    // Anthropic model to use (see a list of models in the models section)
    model: 'claude-3-7-sonnet-20250219',
}

You can also set temperature, topP, topK, frequencyPenalty, and presencePenalty for the Anthropic model. These have sensible defaults, but you can override them if you want to.

How to override the defaults for the Anthropic model

You can fine-tune the Anthropic model to your needs by setting the temperature, topP, topK, frequencyPenalty, and presencePenalty.

eventcatalog.config.js
chat: {
    // enable the chat or not (default true, for new catalogs)
    enabled: true,
    // Tells EventCatalog that we want to use Anthropic
    provider: 'anthropic',
    // Anthropic model to use (see a list of models in the models section)
    model: 'claude-3-7-sonnet-20250219',
    
    // defaults to 0.2
    temperature: 0.2, 

    // defaults to nothing
    topP: 0.95,

    // defaults to noting
    topK: 1,

    // defaults to 0
    frequencyPenalty: 0,

    // defaults to 0
    presencePenalty: 0,
}

4. Configure EventCatalog to run on a server​

You need to configure EventCatalog to run on a server, see the EventCatalog documentation for more information and the hosting options.

eventcatalog.config.js
// rest of the config...
// Default output is 'static', but you can change it to 'server' 
output: 'server'
"Why do I need to run EventCatalog on a server?"

Running EventCatalog on a server allows you to keep your API keys safe. EventCatalog will make a request to its server side code, to get a response from the Anthropic model. Your keys are never exposed to the client side code. You can use our DockerFile to run EventCatalog on a server, see the EventCatalog documentation for more information.

Run EventCatalog​

Once you have installed and configured the plugin, and enabled the chat in the eventcatalog.config.js file, you can run the catalog.

npm run generate
npm run dev

Navigate to the http://localhost:3000/chat and you should see the AI assistant.

EventCatalog Chat

"Did you know you can bring your own prompts to EventCatalog Chat?"

You can bring your own prompts to EventCatalog Chat. This lets you tailor the chat experience to your organization and teams. See the bring your own prompts section for more information.

Configuration​

You can configure the model, temperature, topP, topK, frequencyPenalty, and presencePenalty in the eventcatalog.config.js file.

eventcatalog.config.js
chat: {
    provider: 'anthropic',
    model: 'claude-3-7-sonnet-20250219',
    temperature: 0.5,
    topP: 1,
    topK: 1,
    frequencyPenalty: 0,
    presencePenalty: 0,
}

Models​

Here are a list of models that you can use with EventCatalog Chat.

  • claude-3-7-sonnet-20250219
  • claude-3-5-sonnet-latest
  • claude-3-5-sonnet-20241022
  • claude-3-5-sonnet-20240620
  • claude-3-5-haiku-latest
  • claude-3-5-haiku-20241022
  • claude-3-opus-latest
  • claude-3-opus-20240229
  • claude-3-sonnet-20240229
  • claude-3-haiku-20240307

You can find more information about the models in the Anthropic documentation.

Got a question? Or want to contribute?​

Found a good model for your catalog? Please let us know on Discord. Or if you need help configuring your model, please join us on Discord.

Have a question?​

If you have any questions, please join us on Discord.