In many content tranformer configurations settings for Large Language Models can be configured. This page summarizes the settings.

Open Llama Configuration

1. Specify the URL

2. For embeddings

   1. Embedding model: here you can provide the name of the embedding model, you want to use. For example mxbai-embed-large

   2. You can also specify an embedding dimension. A good default value is 1536 which all of our proposed schemas use.

3. For completions

   1. Choose a completion model

4. Use authentication. If enabled, the Suite can use basic authentication for communicating with the embedding endpoint. Please provide an according username and password.

5. Public keys for SSL certificates: this configuration is needed, if you run the environment with self-signed certificates, or certificates which are not known to the Java key store.
   We use a straight-forward approach to validate SSL certificates. In order to render a certificate valid, add the modulus of the public key into this text field. You can access this modulus by viewing the certificate within the browser.

Azure OpenAI GPT Configuration

1. GPT Endpoint: Offer the endpoint such as <https://<baseUrl>>.openai.azure.com/openai/deployments/<deploymentName>/chat/embeddings?api-version=<version>

2. Password: here please add your API key which you can configure in the OpenAI configuration in the Azure portal.

3. For embedding, you can also specify an embedding dimension. A good default value is 1536 which all of our proposed schemas use.

LM Studio Configuration

1. Specify the URL

2. The transformer only uses the loaded model right now. A specification at request time is not supported.

3. For embeddings

   1. You can also specify an embedding dimension. A good default value is 1536 which all of our proposed schemas use.

4. Use authentication. If enabled, the Suite can use basic authentication for communicating with the embedding endpoint. Please provide an according username and password.

5. Public keys for SSL certificates: this configuration is needed, if you run the environment with self-signed certificates, or certificates which are not known to the Java key store.
   We use a straight-forward approach to validate SSL certificates. In order to render a certificate valid, add the modulus of the public key into this text field. You can access this modulus by viewing the certificate within the browser.

VLLM Configuration

1. Specify the URL

   1. Please note that by VLLM design, the transformer only uses the loaded models

2. For embeddings

   1. You can also specify an embedding dimension. A good default value is 1536 which all of our proposed schemas use.

3. Use authentication. If enabled, the Suite can use basic authentication for communicating with the embedding endpoint. Please provide an according username and password.

4. Public keys for SSL certificates: this configuration is needed, if you run the environment with self-signed certificates, or certificates which are not known to the Java key store.
   We use a straight-forward approach to validate SSL certificates. In order to render a certificate valid, add the modulus of the public key into this text field. You can access this modulus by viewing the certificate within the browser.