OpenAI Unveils Major Upgrades to Assistants API, Including File Search and Streaming Support

OpenAI Unveils Major Upgrades to Assistants API, Including File Search and Streaming Support

By
Yuri Petrovich Kuznetsov
2 min read

OpenAI has announced significant updates to its Assistants API, including an improved search tool called file_search that can process up to 10,000 files per Assistant - a 500x increase over the previous version. Additionally, the update introduces vector_store objects for seamless searches, granular control over token usage, support for common model configuration parameters, and the ability to use fine-tuned models. The API also now supports streaming, with added streaming and polling helper functions to the OpenAI Node and Python SDKs. Developers are encouraged to consult the migration guide to upgrade their tool usage to the latest version of the Assistants API.

Key Takeaways

  • OpenAI has announced major updates to its Assistants API, including an improved search tool called file_search, vector_store objects for seamless searches, granular control over token usage, and support for common model configuration parameters like temperature and peak P-value.
  • The API now supports streaming, and streaming and polling helper functions have been added to the OpenAI Node and Python SDKs.
  • The update also introduces the ability to use fine-tuned models, though initially limited to gpt-3.5-turbo-0125.
  • The API can now ingest up to 10,000 files per Assistant, a 500x increase over the previous version, making it more efficient for developers.
  • Developers are encouraged to consult the migration guide to upgrade their tool usage to the latest version of the Assistants API.

Analysis

OpenAI's substantial upgrades to its Assistants API, including the file_search tool capable of processing 10,000 files per Assistant, are poised to impact developers, businesses, and technology enthusiasts. The enhanced API introduces seamless searches, granular control over token usage, support for common model configuration parameters, and the ability to use fine-tuned models. These updates will likely boost efficiency for developers and enable them to build more advanced and powerful applications. In the short term, developers may need to invest time in consulting the migration guide to adapt to the latest version. However, in the long run, these advancements are expected to contribute to accelerated technological innovation, benefitting the broader tech industry.

Did You Know?

  • The API now supports streaming, and streaming and polling helper functions have been added to the OpenAI Node and Python SDKs.
  • The update also introduces the ability to use fine-tuned models, though initially limited to gpt-3.5-turbo-0125.
  • The API can now ingest up to 10,000 files per Assistant, a 500x increase over the previous version, making it more efficient for developers.

You May Also Like

This article is submitted by our user under the News Submission Rules and Guidelines. The cover photo is computer generated art for illustrative purposes only; not indicative of factual content. If you believe this article infringes upon copyright rights, please do not hesitate to report it by sending an email to us. Your vigilance and cooperation are invaluable in helping us maintain a respectful and legally compliant community.

Subscribe to our Newsletter

Get the latest in enterprise business and tech with exclusive peeks at our new offerings