Embeddings Models

Karini AI supports integrations with the following Embeddings Model providers and custom models. Using these models, users can create model endpoints in Karini AI model hub.

  1. Amazon Bedrock

  2. OpenAI

  3. Azure OpenAI

  4. Databricks

  5. Amazon SageMaker

Add New Model Endpoint

To add a new model endpoint to the model hub, do the following:

  1. On the Model Endpoints menu, select Embeddings model endpoint tab and click Add New.

  2. Select a model provider and associated model id in the list.

  3. User has option to override default configurations such as max tokens and pricing. Refer to this table for detailed configuration parameter information for each model provider.

  4. By default, the organization level credentials are used to access the model. User can optionally overwrite credentials with a new set of model credentials.

  5. User can test the model endpoint request and response by using the Test endpoint button.

Review Model Endpoints

User can review the created model endpoints under Embeddings model endpoint tab. It includes following information:

  1. Model provider and model id.

  2. Dimensions, max tokens and tokenizer: The default values are displayed based on model specifications from the model provider.

  3. Model Price: The default price displays public pricing of the model inference per 1000 output tokens. This price is used in Karini AI Dashboards to calculate cost. User has the ability to override this price if needed - such as in case of special pricing agreement with the model provider.

  4. Link to view the the recipes in which the model endpoint is used.

  5. Link to view the model information including the cost and usage dashboard for the model endpoint.

Model Endpoint Configurations

The following table describes model endpoint configurations for each model provider. It also includes links to model provider reference documentation offering detailed information on model specifications, usage instructions, and API endpoints for effective integration and utilization.

ProviderModelConfig ParametersReference

Amazon Bedrock

Titan Embeddings G1 - Text

  1. Tokenizer: cl100k_base

  2. Embedding Dimensions: 1536

  3. Max Tokens: 8000

https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html https://docs.aws.amazon.com/bedrock/latest/userguide/titan-embedding-models.html

Amazon Bedrock

cohere.embed-multilingual-v3

  1. Tokenizer: cl100k_base

  2. Embedding Dimensions: 1024

  3. Max Tokens: 8191

https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html https://aws.amazon.com/bedrock/cohere-command-embed/

OpenAI

Text-Embeddings-3-Small

  1. Tokenizer: cl100k_base

  2. Embedding Dimension: 1536

  3. Max Tokens: 8191

https://platform.openai.com/docs/guides/

OpenAI

Text-Embeddings-3-Large

  1. Tokenizer: cl100k_base

  2. Embedding Dimension: 3072

  3. Max Tokens: 8191

https://platform.openai.com/docs/guides/embeddings

OpenAI

Text-Embeddings-ADA-002

  1. Tokenizer: cl100k_base

  2. Embedding Dimension: 1536

  3. Max Tokens: 8191

https://platform.openai.com/docs/guides/embeddings

Azure OpenAI

Text-Embeddings-3-Small

  1. Azure OpenAI API Base: Specific Azure OpenAI API Base URL

  2. Azure OpenAI Deployment Name: Name of the deployment resource within Azure OpenAI service.

  3. Tokenizer: cl100k_base

  4. Embedding Dimension:1536

  5. Max Tokens:8191

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models

Azure OpenAI

Text-Embeddings-3-Large

  1. Azure OpenAI API Base: Specific Azure OpenAI API Base URL

  1. Azure OpenAI Deployment Name: Name of the deployment resource within Azure OpenAI service.

  1. Tokenizer: cl100k_base

  1. Embedding Dimension:1536

  1. Max Tokens:8191

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models

Azure OpenAI

Text-Embeddings-ADA-002

  1. Azure OpenAI API Base: Specific Azure OpenAI API Base URL

  1. Azure OpenAI Deployment Name: Name of the deployment resource within Azure OpenAI service.

  1. Tokenizer: cl100k_base

  1. Embedding Dimension:1536

  1. Max Tokens:8191

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models

Databricks

  1. Tokenizer: cl100k_base

  2. Embedding Dimension: 1024

  3. Model Id: Unique Id of the model.

  4. Model Endpoint Name: Name of the model endpoint.

Amazon SageMaker

  1. Tokenizer: cl100k_base

  2. Embedding Dimension:

  3. Model Endpoint Name: Name of the model endpoint

  4. Max Tokens:

PreviousModel HubNextLarge Language Models (LLMs)

Last updated