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 chat

info

This CLI command calls the following API endpoint:

• Download Model (The command only calls this endpoint if the specified model is not downloaded yet.)
• Install Engine (The command only calls this endpoint if the specified engine is not downloaded yet.)
• Start Model
• Chat Completions (The command makes a call to this endpoint if the -c option is used.)

This command starts a chat session with a specified model, allowing you to interact directly with it through an interactive chat interface.

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 chat [options] <model_id> -m <message>

# Beta

cortex-beta chat [options] <model_id> -m <message>

# Nightly

cortex-nightly chat [options] <model_id> -m <message>

Windows

# Stable

cortex.exe chat [options] <model_id> -m <message>

# Beta

cortex-beta.exe chat [options] <model_id> -m <message>

# Nightly

cortex-nightly.exe chat [options] <model_id> -m <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	Model ID to chat with.	Yes	-	mistral
-m, --message <message>	Message to send to the model	Yes	-	-m "Hello, model!"
-h, --help	Display help information for the command.	No	-	-h