Nov 07, 2023 11:20 am
OpenAI launches Assistants API, allowing developers to customize AI assistants with "one click"
At OpenAI's first developer conference today, OpenAI launched the Assistants API, a "purpose-built AI tool" that leverages "extra knowledge" to help developers build AI assistants in their own applications.
OpenAI stated that the Assistants API provides three functions: "Code interpreter", "Retrieval" and "Function calling" to help users handle "heavy work":
- "Code Interpreter" allows developers to write and run Python code in a sandbox execution environment, generate graphical charts, and process files with different data and formats, and allows AI assistants to iteratively run the code to solve challenging code and math problems etc.
- Retrieval enhances the assistant with knowledge outside the model, such as proprietary domain data, product information, or user-provided documentation.
- "Function Call" enables the assistant to call a developer-defined function and incorporate the function response into its message.
OpenAI said that the Assistants API is designed to achieve flexibility, and the range of use cases includes "natural language-based data analysis applications", "code assistants", "artificial intelligence-based vacation planners", "DJs", "smart canvases" and more.
It is reported that a key update introduced by the Assistants API is to provide persistent and infinitely long threads (Threading), allowing developers to hand over thread state management to OpenAI and solve the problem of context window length constraints. (IT Home)