warning

🚧 Cortex.cpp is currently under development. Our documentation outlines the intended behavior of Cortex, which may not yet be fully implemented in the codebase.

cortex embeddings

info

This CLI command calls the following API endpoint:

• Embeddings

This command creates the embedding vector representing the input text.

Usage

info

You can use the --verbose flag to display more detailed output of the internal processes. To apply this flag, use the following format: cortex --verbose [subcommand].

MacOs/Linux

# Stable

cortex embeddings [options] [model_id] [message]

# Beta

cortex-beta embeddings [options] [model_id] [message]

# Nightly

cortex-nightly embeddings [options] [model_id] [message]

Windows

# Stable

cortex.exe embeddings [options] [model_id] [message]

# Beta

cortex-beta.exe embeddings [options] [model_id] [message]

# Nightly

cortex-nightly.exe embeddings [options] [model_id] [message]

info

This command uses a model_id from the model that you have downloaded or available in your file system.

Options

Option	Description	Required	Default value	Example
model_id	Specify the models to generate the embeddings.	No	Prompt to select from the available models	mistral
-i, --input <input>	Input text to embed, encoded as a string or array of tokens. For multiple inputs, pass an array of strings or token arrays.	Yes	-	-i "Hello, world!"
-e, --encoding_format <encoding_format>	Encoding format for the embeddings. Supported formats are float and int.	No	float	-e float
-d, --dimensions <dimensions>	Specify the number of dimensions for the resulting output embeddings. Supported only in some models.	No	-	-d 128
-h, --help	Display help information for the command.	No	-	-h