Are you interested in staying up-to-date with industry-leading AI coverage? Join our daily and weekly newsletters for the latest updates and exclusive content. Learn More
Cohere has recently announced the release of updated versions of its application programming interfaces (APIs) for its AI models Chat, Embed, Rerank, and Classify.
These new API updates, collectively known as API V2, are designed to align more closely with AI industry standards, making it easier for developers to transition their applications to be powered by Cohere’s models instead of competitors like OpenAI, Anthropic, Google, Mistral, and Meta.
Earlier this month, Andreessen Horowitz (A16z) general partner Martin Casado shared a graph showing the results of a survey from AI API platform Kong, involving 800 enterprise leaders and their usage of large language models (LLMs).
On the chart, OpenAI’s ChatGPT led with 27% market share, followed by Microsoft’s Azure AI cloud service with 18%, and Google Gemini with 17%. Cohere trailed at 5%, showcasing the company’s need to gain ground in winning over enterprise customers, despite being co-founded by former Google researchers behind the 2017 Transformer paper that revolutionized the generative AI era.
Survey results of nearly 800 enterprise folks on LLM market share (run by Kong). Most notable to me is the dramatic gain in Gemini use. Amazing job by the Alphabet team. pic.twitter.com/5EZx8IBBUT
— martin_casado (@martin_casado) September 14, 2024
Enhanced reliability with more precise settings
One of the key changes in the V2 API release is the requirement for developers to specify the model version in their API calls.
Previously, this field was optional, leading to potential issues when new models were released and the default model changed.
By making the model version mandatory, Cohere ensures consistent application performance, especially in scenarios involving Embed models where using different versions can affect results.
The updated Chat API introduces several enhancements, including consolidating input parameters into a single messages array, streamlining the input process for more complex use cases where roles such as system or assistant can be assigned to the latest message in a chat sequence.
Cohere’s new APIs also improve tool integration by using JSON schema instead of Python types in the V2 release, making the process more flexible and compatible with various applications.
Furthermore, each tool call now includes a unique ID, allowing the API to accurately match tool results with their corresponding calls, a feature lacking in the V1 API.
For streaming interactions, the V2 Chat API has transitioned from JSON-stream events to Server Sent Events (SSE), enhancing user experience with better responsiveness.
Support for existing APIs
Cohere confirms that the V1 suite of APIs will remain supported, ensuring developers who are not yet ready to migrate can still rely on current implementations.
No breaking changes are expected for the V1 API or its associated SDKs.
However, upgrading to V2 is recommended for enhanced stability and access to the latest features, including model version enforcement and advanced chat capabilities.
Resources for developers
To aid the transition to API V2, Cohere has released a new SDK and an OpenAPI specification for its updated endpoint.
These resources, along with a detailed Chat Migration Guide, are available on the Cohere platform. Developers are encouraged to provide feedback and suggestions through the company’s Discord community.
Cohere’s API V2 release marks a significant advancement in making its platform more accessible and efficient for developers. With these updates, the company aims to provide a streamlined development experience and attract users from OpenAI and other popular APIs.
VB Daily
Stay in the know! Get the latest news in your inbox daily
Thanks for subscribing. Check out more VB newsletters here.
An error occured.
and incorporate them seamlessly into the new content without introducing new ,