Manual

Reminder: this is in alpha.

Enjoy these sample commands in lieu of a formal doc.

Tiles

Commands in this section are intended for regular users. Most user-facing functionality is available through slash commands in the chat REPL.

Onboarding

This is what the first run looks like when you type tiles in your terminal.

CLI Commands


tiles                          # Onboarding and launching REPL
tiles account create <nickname> # Create root identity (nickname optional)
tiles account set-nickname     # Set nickname
tiles account                  # Show account details
tiles data set-path <path>     # Set data directory
tiles run [MODELFILE_PATH]     # Run a model (default if not provided)
tiles run -m                   # Run with experimental memory model
tiles update                   # Check for and install app updates

Examples


# Onboarding and launching REPL
tiles
 
# Create root identity (nickname optional)
tiles account create alice
 
# Set nickname
tiles account set-nickname
 
# Show account details
tiles account
 
# Set data directory
tiles data set-path ~/.tiles/data
 
# Run a model (default if not provided)
tiles run
 
# Run a model from a specific Modelfile
tiles run ./path/to/Modelfile
 
# Run with experimental memory model
tiles run -m
 
# Check for and install app updates
tiles update

Tilekit

Commands in this section are meant for developers.

Prompt Optimization

We have DSRs (dspy-rs) built into the Tiles CLI to automatically optimize system prompts in Modelfiles.

CLI Commands


tiles optimize <MODELFILE_PATH> [--data <path>] [--model <provider:model-name>]  # Optimize SYSTEM prompt in Modelfile

Examples


# Optimize SYSTEM prompt in a Modelfile
tiles optimize path/to/Modelfile
 
# Optimize with custom training data
tiles optimize ./Modelfile --data training-data.json
 
# Optimize using a specific model
tiles optimize ./Modelfile --model anthropic:claude-3-5-sonnet-20240620

Optimize Command Details

The tiles optimize command refines the SYSTEM prompt in your Modelfile automatically using DSRs (dspy-rs) and the COPRO optimizer.

Basic Usage:


tiles optimize path/to/Modelfile

By default, this will:

Generate 5 synthetic examples automatically if you do not provide your own training data
Use openai:gpt-4o-mini as the optimization model
Update your Modelfile in-place with the improved SYSTEM prompt

Options:

--data <path> - Provide your own training data as a JSON file
--model <provider:model-name> - Specify a different model to use for optimization

Requirements:

Your Modelfile must contain a starting SYSTEM prompt, so the optimizer knows what it should build upon.

Training Data Format:

If supplying your own data, use JSON structured like this:


[
  {
    "input": "User query here",
    "output": "Expected AI response here"
  }
]

Example:

Let’s say you have a Modelfile:


FROM llama3
SYSTEM "You are a helpful assistant."

To optimize its SYSTEM prompt using Claude:


export ANTHROPIC_API_KEY=sk-ant-...
tiles optimize ./Modelfile --model anthropic:claude-3-5-sonnet-20240620

This will rewrite the SYSTEM line with a more effective version based on the optimization process.