Configuration

AIA offers flexible configuration through command-line options, environment variables, configuration files, and prompt file directives.

Configuration Precedence

AIA determines configuration settings using this order (highest to lowest priority):

1. Embedded config directives (in prompt files): //config model = gpt-4
2. Command-line arguments: --model gpt-4
3. Environment variables: export AIA_MODEL=gpt-4
4. Configuration files: ~/.aia/config.yml
5. Default values

Configuration Methods

1. Command-Line Arguments

aia --model gpt-4 --temperature 0.8 --chat my_prompt

2. Environment Variables

export AIA_MODEL=gpt-4
export AIA_TEMPERATURE=0.8
export AIA_PROMPTS_DIR=~/my-prompts

3. Configuration File

Create ~/.aia/config.yml:

model: gpt-4
temperature: 0.8
prompts_dir: ~/my-prompts
chat: false
verbose: true

4. Embedded Directives (in prompt files)

//config model = gpt-4
//config temperature = 0.8
//config chat = true

Your prompt content here...

Essential Configuration Options

The most commonly used configuration options:

Option	Default	Description
model	gpt-4o-mini	AI model to use
prompts_dir	~/.prompts	Directory containing prompts
out_file	temp.md	Default output file
temperature	0.7	Model creativity (0.0-1.0)
chat	false	Start in chat mode
role	``	Role/system prompt to use
verbose	false	Show detailed output

Complete Configuration Reference

Config Item Name	CLI Options	Default Value	Environment Variable
adapter	--adapter	ruby_llm	AIA_ADAPTER
aia_dir		~/.aia	AIA_DIR
append	-a, --append	false	AIA_APPEND
chat	--chat	false	AIA_CHAT
clear	--clear	false	AIA_CLEAR
config_file	-c, --config_file	~/.aia/config.yml	AIA_CONFIG_FILE
debug	-d, --debug	false	AIA_DEBUG
embedding_model	--em, --embedding_model	text-embedding-ada-002	AIA_EMBEDDING_MODEL
frequency_penalty	--frequency_penalty	0.0	AIA_FREQUENCY_PENALTY
fuzzy	-f, --fuzzy	false	AIA_FUZZY
image_quality	--iq, --image_quality	standard	AIA_IMAGE_QUALITY
image_size	--is, --image_size	1024x1024	AIA_IMAGE_SIZE
image_style	--style, --image_style	vivid	AIA_IMAGE_STYLE
log_file	-l, --log_file	~/.prompts/_prompts.log	AIA_LOG_FILE
markdown	--md, --markdown	true	AIA_MARKDOWN
max_tokens	--max_tokens	2048	AIA_MAX_TOKENS
model	-m, --model	gpt-4o-mini	AIA_MODEL
next	-n, --next	nil	AIA_NEXT
out_file	-o, --out_file	temp.md	AIA_OUT_FILE
parameter_regex	--regex	'(?-mix:([[A-Z _|]+]))'	AIA_PARAMETER_REGEX
pipeline	--pipeline	[]	AIA_PIPELINE
presence_penalty	--presence_penalty	0.0	AIA_PRESENCE_PENALTY
prompt_extname		.txt	AIA_PROMPT_EXTNAME
prompts_dir	-p, --prompts_dir	~/.prompts	AIA_PROMPTS_DIR
refresh	--refresh	7 (days)	AIA_REFRESH
require_libs	--rq --require	[]	AIA_REQUIRE_LIBS
role	-r, --role		AIA_ROLE
roles_dir		~/.prompts/roles	AIA_ROLES_DIR
roles_prefix	--roles_prefix	roles	AIA_ROLES_PREFIX
speak	--speak	false	AIA_SPEAK
speak_command		afplay	AIA_SPEAK_COMMAND
speech_model	--sm, --speech_model	tts-1	AIA_SPEECH_MODEL
system_prompt	--system_prompt		AIA_SYSTEM_PROMPT
temperature	-t, --temperature	0.7	AIA_TEMPERATURE
terse	--terse	false	AIA_TERSE
tool_paths	--tools	[]	AIA_TOOL_PATHS
allowed_tools	--at --allowed_tools	nil	AIA_ALLOWED_TOOLS
rejected_tools	--rt --rejected_tools	nil	AIA_REJECTED_TOOLS
top_p	--top_p	1.0	AIA_TOP_P
transcription_model	--tm, --transcription_model	whisper-1	AIA_TRANSCRIPTION_MODEL
verbose	-v, --verbose	false	AIA_VERBOSE
voice	--voice	alloy	AIA_VOICE

Configuration Examples

Basic Setup

# ~/.bashrc or ~/.zshrc
export AIA_MODEL=gpt-4o-mini
export AIA_PROMPTS_DIR=~/my-prompts
export AIA_VERBOSE=true
export AIA_OUT_FILE=./temp.md

Advanced Configuration File

# ~/.aia/config.yml
model: gpt-4
temperature: 0.8
max_tokens: 4000
prompts_dir: ~/my-prompts
verbose: true
markdown: true
shell: true
erb: true

# Tools configuration
tool_paths:
  - ~/my-tools
  - shared
allowed_tools:
  - read_file
  - write_file
  - run_shell_command

# Audio settings
speak: false
voice: alloy
speak_command: afplay

Dynamic Configuration in Prompts

# In a prompt file
//config model = gpt-4
//config temperature = 0.9
//config max_tokens = 4000
//config out_file = analysis_result.md

Analyze the following data and provide insights...

For advanced configuration, see Prompt Directives and Shell Integration.