After identifying the most suitable model through experiments in the Lab, use the Launchpad to prepare your model for integration.

The Launchpad combines settings from Params and Repositories to bring you one last step to tweak your models before integrating them. You can always come back and launch any updates you make to your model at any time, allowing for easy model switching in your application.

The Launchpad allows you to easily launch and integrate your customized models into your projects using the SDKs. It provides a streamlined and intuitive interface for selecting and deploying models, making it simple to incorporate powerful AI capabilities into your applications.

​

Launching A Model

​

Model Selection

In the Launchpad, you will see a list of available models. Browse through the models and select the one that best suits your requirements.

​

Model Configuration

​

Parameters

Specify any required parameters or options specific to the chosen model.

Customize the model’s behavior according to your needs with the following settings:

• Temperature This parameter in language models affects the creativity or diversity of the generated text. You can set the randomness level (0 to 1). Higher values increase randomness, and the results will be more creative, with the model generating more diverse output. Lower values result in more focused and deterministic output (great for working with repositories).

• Max Tokens Limit for generated tokens in a chat, constrained by the model’s context length (value 0 means no limit).

• System Prompt The system prompt sets the initial context and direction for the model’s responses. It should be carefully selected to align with the specific topic and desired style of the conversation.

• Limit Sets the maximum number of top-matching documents to retrieve based on similarity.

• Similarity Measures how closely a query matches document embeddings. Higher values indicate greater similarity, ranging from 0 to 1.

​

Adding A Repository (RAG)

Link a repository to the model to enable RAG. Just click on the Add Repo button and select the repository of your choice. This ensures that the model has access to the latest information and data from the repositories of you chose.

You can also add multiple repositories to the same model.

---

​

Adding An Action/Integration

Tool calling usually takes a lot of code to set up. With Prem, you can add an action to your model by just clicking on the Add Action button and selecting the action from the tool of your choice.

​

Launching the Model

Once you have configured the model, click on the “Launch” button. The Launchpad will initiate the model launching process, which may take a few moments depending on the model’s size and complexity.

​

Integrate with the SDK

Now that your model is launched with its latest changes, you can easily integrate it into your application with the SDK.

​

See the history of your launched models

Under the Launchpad, you can see the history of your launched models. You can view which model is currently in use and which models have been launched. We provide you with additional information such as the number of traces and how many repositories are linked to each model.