We just upgraded AIGNE, which is one of the minor version updates we have made since its launch on May 4th.
Today's update coincided with Open AI's release of the latest version of the GPT-4o model, so our engineering team quickly expanded support for GPT-4o and conducted comprehensive testing to confirm that this newest model can be used in our current operating environment.
GPT-4o (“o” for “omni”) is a step towards much more natural human-computer interaction—it accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs. It can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time(opens in a new window) in a conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models.
Source: https://openai.com/index/hello-gpt-4o/
In AIGNE's AI Studio, within the Processing block of any Agent, you can choose to use the latest GPT-4o model in the LLM settings.
After modifying the model configuration, you can see that the corresponding model has adopted GPT-4o.
You can also select the default model of the entire project as GPT-4o, but currently we default to GPT-3.5 Turbo. In AIGNE, each Agent can independently use the model they need, this design can better natively support multi-model application architecture, that is, you can combine the characteristics and advantages of different models in the same application, or achieve the best performance and cost, and effectively improve data privacy and security.
Apart from the updates to the latest GPT-4o model from Open AI, AIGNE has also incorporated over 10 detailed updates and improvements based on feedback since its launch. We will continue to refine and update AIGNE to make it the best no-code application engine.