GPT Function Calling: A Leap Forward in AI Tool Creation

OpenAI's recent updates to its API models, including the introduction of function calling capabilities, longer context, and lower prices, mark a significant step forward in the evolution of AI tools. These updates not only enhance the capabilities of the models but also pave the way for the creation of more powerful AI tools.

Function Calling: Bridging the Gap Between AI and External Tools

One of the most exciting updates is the new function calling capability in the Chat Completions API. This feature allows developers to describe functions to GPT-4 and GPT-3.5-turbo, and the model can intelligently choose to output a JSON object containing arguments to call those functions. This is a new way to more reliably connect GPT's capabilities with external tools and APIs.

The models have been fine-tuned to both detect when a function needs to be called (depending on the user’s input) and to respond with JSON that adheres to the function signature. Function calling allows developers to get structured data back from the model. For example, developers can create chatbots that answer questions by calling external tools, convert queries into API calls or database queries, or extract structured data from text.

New Models and Lower Pricing: Making AI More Accessible

OpenAI has also introduced updated and more steerable versions of GPT-4 and GPT-3.5-turbo, along with a new 16k context version of GPT-3.5-turbo. This extended context length allows the model to support approximately 20 pages of text in a single request, enhancing its comprehension of larger texts.

In addition to these updates, OpenAI has also reduced the cost of using its models. The cost of the popular embedding model, text-embedding-ada-002, has been reduced by 75%, and the cost of input tokens for GPT-3.5-turbo has been reduced by 25%. This makes it more affordable for developers to use these powerful AI tools.

The Future of AI Tools

These updates to OpenAI's API models represent a significant leap forward in the development of AI tools. The introduction of function calling capabilities allows AI models to interact more effectively with external tools and APIs, enhancing their capabilities and making them more versatile. The updates to the models and the reduction in costs make these powerful AI tools more accessible to developers.

As AI continues to evolve, we can expect to see more advancements like these. These developments will continue to push the boundaries of what AI can do, leading to the creation of more powerful and versatile AI tools. The future of AI is indeed exciting, and we can't wait to see what comes next.