Hey there, developers! We’ve got some exciting news to share with you all.
The Straico API has just been updated with two brand-new parameters that will give you even more control over the responses generated by all ML models. Get ready to take your projects to the next level!
🎯 MAX_TOKENS
- This parameter allows you to set the maximum number of tokens (words) in the response.
- Adjust this to control the length and verbosity of the output.
- Perfect for tailoring the response length to your specific needs.
- It’s important to review the
max_outputlimit for each model, which is the maximum number of tokens the model can generate. You can find this information in the model details at:/v0/models/v1/models
- Setting the
max_tokensparameter higher than the model’smax_outputmay result in truncated responses.
🔥 TEMPERATURE
- The temperature parameter adjusts the “creativity” of the AI model.
- Lower values (0.1-1.0) result in more conservative, factual responses.
- Higher values (1.0-2.0) lead to more diverse, imaginative outputs.
- Experiment with different temperatures to find the perfect balance for your use case.
🚀 Getting Started
To start using these new parameters, simply include them in your API requests to the following endpoints:
/v0/prompt/completion/v1/prompt/completion
We can’t wait to see how you’ll leverage these new features to build even more powerful and engaging AI-driven applications. As always, feel free to reach out to our support team if you have any questions or need further assistance.
Happy coding, everyone! 🚀
