Deepseek Ruby SDK
A Ruby SDK for interacting with the Deepseek AI API. This SDK provides a simple and intuitive interface for making API calls, handling responses, and managing errors.
Features
- 🚀 Simple and intuitive interface
- ⚡️ Automatic retries with exponential backoff
- 🛡️ Comprehensive error handling
- ⚙️ Flexible configuration options
- 🔒 Secure API key management
- 📝 Detailed response handling
Table of Contents
- Installation
- Quick Start
- Configuration
- API Reference
- Usage Examples
- Error Handling
- Retry Handling
- Development
- Contributing
- Support
- License
Installation
Add this line to your application's Gemfile:
gem 'deepseek-client'And then execute:
$ bundle installOr install it yourself as:
$ gem install deepseek-clientQuick Start
require 'deepseek'
# Initialize client
client = Deepseek::Client.new(api_key: 'your-api-key')
# Make a chat completion request
response = client.chat(
messages: [
{ role: 'user', content: 'What is artificial intelligence?' }
],
model: 'deepseek-chat'
)
puts response['choices'][0]['message']['content']Configuration
Basic Configuration
client = Deepseek::Client.new(
api_key: 'your-api-key',
timeout: 60, # Custom timeout in seconds
max_retries: 3 # Number of retries for failed requests
)Environment Variables
The SDK supports configuration through environment variables:
DEEPSEEK_API_KEY=your-api-key
DEEPSEEK_API_BASE_URL=https://api.deepseek.com # Optional
DEEPSEEK_TIMEOUT=30 # Optional
DEEPSEEK_MAX_RETRIES=3 # OptionalAPI Reference
Available Methods
chat(messages:, model: 'deepseek-chat', **params)
Make a chat completion request.
Parameters:
-
messages(Array, required): Array of message objects -
model(String, optional): Model to use, defaults to 'deepseek-chat' -
temperature(Float, optional): Sampling temperature
Response Format:
{
"choices" => [{
"message" => {
"content" => "Hello! How can I help you today?",
"role" => "assistant"
},
"finish_reason" => "stop"
}],
"created" => 1677649420,
"id" => "chatcmpl-123",
"model" => "deepseek-chat",
"usage" => {
"completion_tokens" => 17,
"prompt_tokens" => 57,
"total_tokens" => 74
}
}Usage Examples
Chat with System Message
response = client.chat(
messages: [
{ role: 'system', content: 'You are a friendly AI assistant.' },
{ role: 'user', content: 'Hello!' }
],
temperature: 0.7,
model: 'deepseek-chat'
)Conversation with History
conversation = [
{ role: 'user', content: 'What is your favorite color?' },
{ role: 'assistant', content: 'I don\'t have personal preferences, but I can discuss colors!' },
{ role: 'user', content: 'Tell me about blue.' }
]
response = client.chat(
messages: conversation,
temperature: 0.8
)Advanced Configuration Example
client = Deepseek::Client.new(
api_key: ENV['DEEPSEEK_API_KEY'],
timeout: 60, # Custom timeout
max_retries: 5, # Custom retry limit
api_base_url: 'https://custom.deepseek.api.com' # Custom API URL
)Error Handling
The SDK provides comprehensive error handling for various scenarios:
begin
response = client.chat(messages: messages)
rescue Deepseek::AuthenticationError => e
# Handle authentication errors (e.g., invalid API key)
puts "Authentication error: #{e.message}"
rescue Deepseek::RateLimitError => e
# Handle rate limit errors
puts "Rate limit exceeded: #{e.message}"
rescue Deepseek::InvalidRequestError => e
# Handle invalid request errors
puts "Invalid request: #{e.message}"
rescue Deepseek::ServiceUnavailableError => e
# Handle API service errors
puts "Service error: #{e.message}"
rescue Deepseek::APIError => e
# Handle other API errors
puts "API error: #{e.message}"
endRetry Handling
The SDK automatically handles retries with exponential backoff for failed requests:
- Automatic retry on network failures
- Exponential backoff strategy
- Configurable max retry attempts
- Retry on rate limits and server errors
Development
After checking out the repo, run bin/setup to install dependencies. Then, run rake spec to run the tests. You can also run bin/console for an interactive prompt that will allow you to experiment.
Running Tests
bundle exec rake specRunning the Console
bin/consoleContributing
Bug reports and pull requests are welcome on GitHub at https://github.com/nagstler/deepseek-ruby. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the code of conduct.
For detailed contribution guidelines, please see our Contributing Guide.
Support
If you discover any issues or have questions, please create an issue on GitHub.
License
The gem is available as open source under the terms of the MIT License. See LICENSE.txt for details.
Code of Conduct
Everyone interacting in the Deepseek project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the code of conduct.