configure — Setup & Management

The configure command is your tool for setting up AI providers, managing profiles, and customizing Rawi’s behavior.

Basic Usage

rawi configure [options]

Quick Start

# Interactive setup (recommended for first-time users)
rawi configure

# View current configuration
rawi configure --show

# List all profiles
rawi configure --list

Options

Configuration Options

Option	Description	Example
`-p, --profile <profile>`	Profile name to configure	`--profile work`
`--provider <provider>`	AI provider	`--provider openai`
`--model <model>`	AI model name	`--model gpt-4o`
`--api-key <apiKey>`	API key for the provider	`--api-key sk-...`
`--base-url <baseURL>`	Custom base URL	`--base-url https://api.openai.com/v1`
`--temperature <temp>`	Sampling temperature (0-2)	`--temperature 0.7`
`--max-tokens <tokens>`	Maximum response tokens	`--max-tokens 2048`
`--language <lang>`	Language (english, arabic)	`--language english`

Provider-Specific Options

Azure OpenAI

Option	Description	Required
`--resource-name <name>`	Azure resource name	✅
`--api-version <version>`	API version	❌ (default: 2024-10-01-preview)

Amazon Bedrock

Option	Description	Required
`--region <region>`	AWS region	❌ (default: us-east-1)
`--access-key-id <id>`	AWS access key ID	❌*
`--secret-access-key <key>`	AWS secret access key	❌*
`--session-token <token>`	AWS session token	❌
`--use-provider-chain`	Use AWS credential provider chain	❌*

*Either explicit credentials or provider chain required

Management Options

Option	Description
`-s, --show`	Show current configuration
`-l, --list`	List all profiles
`-d, --delete <profile>`	Delete a configuration profile

Interactive Configuration

The interactive mode guides you through the setup process step by step.

Start Interactive Setup

rawi configure

Interactive Flow

Choose Provider: Select from available AI providers
Select Model: Pick from provider’s available models
Enter Credentials: Provide API keys or authentication details
Configure Options: Set temperature, tokens, language
Test Configuration: Verify the setup works

Example Interactive Session

$ rawi configure

🤖 Welcome to Rawi configuration!

? Select an AI provider: (Use arrow keys)
❯ OpenAI (GPT-4, GPT-3.5)
  Anthropic (Claude)
  Google (Gemini)
  Ollama (Local AI)
  Azure OpenAI
  AWS Bedrock
  xAI (Grok)
  LM Studio

? Select a model:
❯ gpt-4o (Latest GPT-4 model)
  gpt-4o-mini (Faster, cheaper GPT-4)
  gpt-3.5-turbo (Fast and efficient)

? Enter your OpenAI API key: sk-********************************

? Set temperature (0-2, higher = more creative): 0.7

? Set max tokens (1-100000): 2048

? Select language:
❯ English
  Arabic (العربية)

✅ Configuration saved successfully!
✅ Testing connection... Success!

You can now use: rawi ask "Hello, world!"

Manual Configuration

For automation or advanced users, configure directly with command-line options.

Quick Provider Setup

OpenAI

# Basic OpenAI setup
rawi configure --provider openai --model gpt-4o --api-key sk-your-key

# With custom settings
rawi configure --provider openai --model gpt-4o-mini --api-key sk-your-key \
  --temperature 0.3 --max-tokens 1500

Anthropic

# Claude setup
rawi configure --provider anthropic --model claude-3-5-sonnet-20241022 \
  --api-key sk-ant-your-key

# For long-form analysis
rawi configure --provider anthropic --model claude-3-5-sonnet-20241022 \
  --api-key sk-ant-your-key --temperature 0.1 --max-tokens 4000

Google

# Gemini setup
rawi configure --provider google --model gemini-1.5-pro \
  --api-key your-google-key

Ollama (Local AI)

# Local Llama 2 setup
rawi configure --provider ollama --model llama2 \
  --base-url http://localhost:11434

# Custom local model
rawi configure --provider ollama --model codellama:13b \
  --base-url http://localhost:11434

Azure OpenAI

# Azure setup (requires resource name)
rawi configure --provider azure --model gpt-4 \
  --api-key your-azure-key \
  --resource-name your-resource \
  --base-url https://your-resource.openai.azure.com

Amazon Bedrock

# Using AWS credentials
rawi configure --provider bedrock --model anthropic.claude-3-sonnet-20240229-v1:0 \
  --region us-east-1 \
  --access-key-id your-access-key \
  --secret-access-key your-secret-key

# Using AWS credential provider chain
rawi configure --provider bedrock --model anthropic.claude-3-sonnet-20240229-v1:0 \
  --region us-east-1 \
  --use-provider-chain

Profile Management

Profiles allow you to maintain different configurations for different use cases.

Creating Profiles

# Work profile with enterprise settings
rawi configure --profile work \
  --provider azure \
  --model gpt-4 \
  --resource-name company-openai \
  --api-key work-key

# Personal profile with cost-effective settings
rawi configure --profile personal \
  --provider openai \
  --model gpt-3.5-turbo \
  --api-key personal-key \
  --temperature 0.8

# Local profile for privacy
rawi configure --profile local \
  --provider ollama \
  --model llama2 \
  --base-url http://localhost:11434

Managing Profiles

# List all profiles
rawi configure --list

# View specific profile
rawi configure --profile work --show

# Delete profile
rawi configure --delete personal

# Set default profile
rawi configure --profile work --set-default

Profile Examples

Development Profiles

# Code review profile (detailed analysis)
rawi configure --profile code-review \
  --provider anthropic \
  --model claude-3-5-sonnet-20241022 \
  --temperature 0.1 \
  --max-tokens 4000

# Quick development profile (fast responses)
rawi configure --profile dev-quick \
  --provider openai \
  --model gpt-3.5-turbo \
  --temperature 0.3 \
  --max-tokens 1000

# Local development profile (privacy)
rawi configure --profile dev-local \
  --provider ollama \
  --model codellama \
  --temperature 0.2

Writing Profiles

# Creative writing profile
rawi configure --profile creative \
  --provider openai \
  --model gpt-4 \
  --temperature 0.9 \
  --max-tokens 3000

# Technical writing profile
rawi configure --profile technical \
  --provider anthropic \
  --model claude-3-5-sonnet-20241022 \
  --temperature 0.3 \
  --max-tokens 2500

Advanced Configuration

Environment Variables

You can also configure Rawi using environment variables:

# API keys
export OPENAI_API_KEY="sk-your-openai-key"
export ANTHROPIC_API_KEY="sk-ant-your-anthropic-key"
export GOOGLE_API_KEY="your-google-key"

# Default profile
export RAWI_PROFILE="work"

# Default provider settings
export RAWI_PROVIDER="openai"
export RAWI_MODEL="gpt-4"
export RAWI_TEMPERATURE="0.7"

Configuration Files

Rawi stores configuration in:

Linux/macOS: ~/.config/rawi/
Windows: %APPDATA%/rawi/

Main config structure:

~/.config/rawi/
├── config.json          # Global settings
├── profiles/
│   ├── default.json      # Default profile
│   ├── work.json         # Work profile
│   └── personal.json     # Personal profile
└── history/              # Session history

Manual Configuration File Editing

# Edit main configuration
nano ~/.config/rawi/config.json

# Edit specific profile
nano ~/.config/rawi/profiles/work.json

# Backup configuration
cp -r ~/.config/rawi/ ~/rawi-config-backup/

Provider-Specific Setup Guides

OpenAI Setup

Get API Key: Visit platform.openai.com
Choose Model: gpt-4o (latest), gpt-4o-mini (cost-effective), gpt-3.5-turbo (fast)

Configure:

rawi configure --provider openai --model gpt-4o --api-key sk-your-key

Anthropic Setup

Get API Key: Visit console.anthropic.com
Choose Model: claude-3-5-sonnet-20241022 (recommended)

Configure:

rawi configure --provider anthropic --model claude-3-5-sonnet-20241022 --api-key sk-ant-your-key

Ollama Setup (Local AI)

Install Ollama: Visit ollama.ai and follow installation instructions

Pull a model:

ollama pull llama2
# or for coding:
ollama pull codellama

Configure Rawi:

rawi configure --provider ollama --model llama2

Troubleshooting Configuration

Common Issues

Configuration not saved:

# Check permissions
ls -la ~/.config/rawi/
# Create directory if missing
mkdir -p ~/.config/rawi/profiles/

API key not working:

# Test configuration
rawi info
# Verify API key format
rawi configure --show

Provider connection fails:

# Check network connectivity
curl -s https://api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY"

# Try different provider
rawi configure --provider anthropic

Ollama not connecting:

# Check if Ollama is running
ollama list
# Check base URL
rawi configure --provider ollama --base-url http://localhost:11434

Configuration Validation

# Test current configuration
rawi ask "test" --verbose

# Validate specific profile
rawi configure --profile work --test

# Check provider status
rawi provider --show openai

Migration and Backup

Export Configuration

# Export all profiles
rawi configure --export > rawi-config-backup.json

# Export specific profile
rawi configure --profile work --export > work-profile.json

Import Configuration

# Import configuration
rawi configure --import rawi-config-backup.json

# Import specific profile
rawi configure --profile work --import work-profile.json

Reset Configuration

# Reset all configuration
rawi configure --reset

# Reset specific profile
rawi configure --profile work --reset

# Delete all profiles
rawi configure --reset-all

Best Practices

Security

Use Environment Variables for API keys in production
Separate Profiles for different security contexts
Regular Key Rotation for enterprise environments
Local Providers for sensitive data

Performance

Appropriate Models: Use lighter models for simple tasks
Temperature Settings: Lower for factual tasks, higher for creative
Token Limits: Set reasonable limits to control costs
Profile Optimization: Different profiles for different use cases

Organization

Descriptive Profile Names: work-gpt4, personal-claude, local-dev
Environment-Specific Profiles: dev, staging, production
Task-Specific Profiles: code-review, writing, data-analysis