Skip to content
Reward Loyalty
Reward Loyalty
Buy Now
ESC

Searching...

Quick Links

Type to search • Press ↑ ↓ to navigate • Enter to select

Keep typing to search...

No results found

No documentation matches ""

Documentation
Back to Home Buy Reward Loyalty

AI Writing Assistant.

Configure AI-powered text assistance for Partners using OpenAI, DeepSeek, or local models.

Jan 2, 2026

The AI Writing Assistant helps Partners create and improve text content directly within the dashboard. When enabled, an AI button appears in supported text fields, offering quick transformations like improving grammar, adjusting tone, or generating content.

What It Does

Feature Description
Text Improvement Refine grammar, spelling, and clarity
Tone Adjustments Make text more formal, casual, or friendly
Content Generation Generate descriptions, summaries, and copy
Quick Transformations One-click formatting and style changes

Supported Providers

The system uses an OpenAI-compatible API format, supporting multiple providers:

Provider Description Cost
OpenAI GPT models from OpenAI Pay-per-use API
DeepSeek Alternative AI with competitive pricing Pay-per-use API
LM Studio Run open-source models locally Free (local hardware)

All providers use the same configuration variables, making it easy to switch between them.

Configuration

Enable AI features by adding the following to your .env file:

OpenAI

OPENAI_ENABLED=true
OPENAI_API_KEY="your-api-key"
OPENAI_MODEL="gpt-5-nano"
OPENAI_BASE_URL="https://api.openai.com/v1"

DeepSeek

OPENAI_ENABLED=true
OPENAI_API_KEY="your-deepseek-key"
OPENAI_MODEL="deepseek-chat"
OPENAI_BASE_URL="https://api.deepseek.com"
OPENAI_API_URL="https://api.deepseek.com"

LM Studio (Local)

OPENAI_ENABLED=true
OPENAI_API_KEY="lm-studio"
OPENAI_BASE_URL="http://localhost:1234/v1"

After updating your .env file, clear the config cache:

php artisan config:clear

OpenAI Setup

To use OpenAI's GPT models:

  1. Visit platform.openai.com and create an account
  2. Navigate to API Keys in your dashboard
  3. Click Create new secret key and name it for reference
  4. Copy the key immediately—it won't be shown again
  5. Add the key to your .env file as OPENAI_API_KEY

Recommended Models

OpenAI's GPT-5 family provides the best balance of quality and cost. For the AI Writing Assistant:

Model Best For Context Window
gpt-5-nano Most use cases—fastest and most affordable 400K tokens
gpt-5-mini Complex writing requiring more reasoning 400K tokens
gpt-4.1-mini Non-reasoning tasks, fast responses 1M tokens

Note: Legacy models (gpt-3.5-turbo, gpt-4o, gpt-4o-mini) still work but are not recommended. Use gpt-5-nano for the best price-to-performance ratio.

For the latest models and pricing, see OpenAI's model documentation.

DeepSeek Setup

DeepSeek provides an OpenAI-compatible API with competitive pricing:

  1. Create an account at platform.deepseek.com
  2. Navigate to your API dashboard
  3. Generate an API key
  4. Add the DeepSeek configuration to your .env file

DeepSeek Models

Model Description
deepseek-chat General-purpose conversational model
deepseek-coder Optimized for code-related tasks

LM Studio Setup

LM Studio lets you run open-source AI models locally—ideal for development, testing, or privacy-focused deployments.

Installation

  1. Download LM Studio from lmstudio.ai
  2. Install and launch the application
  3. Search for and download a model (e.g., Llama 3.2, Mistral, or Qwen)

Starting the Local Server

  1. Open LM Studio
  2. Go to the Local Server tab
  3. Select your downloaded model
  4. Click Start Server
  5. The API will be available at http://localhost:1234/v1

Recommended Local Models

For text writing assistance, consider:

  • Llama 3.2 8B — Good balance of speed and quality
  • Mistral 7B — Fast and efficient
  • Qwen 2.5 7B — Strong multilingual support

Model quality depends on your hardware. Start with smaller models (7B–8B parameters) if you have limited RAM.

Troubleshooting

Connection Errors

Issue Solution
"API key invalid" Verify the key is copied correctly with no extra spaces
"Connection refused" Check network connectivity or firewall settings
"Model not found" Confirm the model name matches your provider's documentation

LM Studio Issues

Issue Solution
Connection refused Ensure the local server is running
Port already in use Check if another service uses port 1234
Slow responses Try a smaller model or check system resources
Server crashes Reduce context length or use a quantized model

General Tips

  • Clear cache after any .env changes: php artisan config:clear
  • Check logs in storage/logs/laravel.log for error details
  • Test the API with a curl command before troubleshooting the app

Related Topics