spring-projects / spring-projects/spring-ai

Add support for verbosity parameter in AzureOpenAiChatOptions for GPT-5 models

Open Beginner friendly
#4,927 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 10h
Merged PRs (30d)
5

Description

Expected Behavior
I would like to see a new field added to AzureOpenAiChatOptions (and its builder) to support the verbosity parameter.

  • Parameter Name: verbosity
  • Supported Values: low, medium, high
  • Target API: Azure OpenAI Chat Completion API (specifically for GPT-5 reasoning models)

Current Behavior
Currently, the AzureOpenAiChatOptions class in Spring AI lacks support for this parameter. As a result, users cannot configure the output verbosity (e.g., forcing more concise or detailed responses) when utilizing the latest GPT-5 series models on Azure.

Context
The new Azure OpenAI GPT-5 reasoning models have introduced a verbosity parameter that allows developers to provide granular control over how concise the model's output will be.
NEW GPT-5 reasoning features

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Locate AzureOpenAiChatOptions and its builder, then inspect neighboring option fields and how they are serialized for the Azure Chat Completion API. Done means verbosity accepts low, medium, and high and is available through the builder for GPT-5 reasoning models.

Written by the indexing model from the issue text.

Assessment

Tech stack
azure, java, spring
Domain
ai, api
Issue type
Feature
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.