Hi everyone, We are exploring Discourse AI to provide a conversational assistant within our Discourse forum for helping users with navigation, features, categories, topics, and general forum-related questions. We have access to our organization’s own LLM APIs for GPT and Claude, and we would like …

Have tried selecting openAI as the provider and tried still not able to configure.. Any other way or recommendation??

[afbeelding] Soumya_Ranjan_Mishra: 而非直接使用 OpenAI 的公共 API 我也是使用的这种API，我的模型ID是gpt-5.6-sol，目前运行正常。

Can you tell me how did you configured.. For me its not running after providing all details..

在管理后台的AI-LLM-未配置的LLM模版，选择GPT-5.6 Sol，然后输入第三方API提供的两个信息：托管模型的服务的 URL：比如 ai.com/v1/responses 托管模型的服务的 API 密钥：第三方提供的下方可以点击按钮“运行测试”，如果失败的话，可能是因为URL填写格式是错误的。

Yes after giving all this information am getting internal server error message [image]

我测试了你的URL并没有返回你的这个图片的信息，请问你这张图片是在哪个页面的信息。我没有输入API密钥运行测试的结果是：非流式传输请求失败：{“message”:“Unauthorized”}

看起来你似乎需要截图出来你的完整配置页面

Is there a more detailed error in the logs at forum.example.com/logs?

Configuring Discourse AI with internal OpenAI APIs

Ondersteuning

Falco (Falco) 17 augustus 2026 om 17:21 2

Pick openai as the provider, and configure the URL with the one you have.

Topic		Antwoorden	Weergaven
How to use internal AI endpoints? Support ai	8	402	6 juli 2026
Configure API Keys for OpenAI Integrations how-to , ai	11	4121	11 november 2024
Internal Server Error 500- Manual configuration [ Discourse AI] Support ai	7	411	5 september 2025
Feature request: improve Discourse AI LLM setup (model discovery) and add AI config import/export Feature ai	0	133	26 januari 2026
Self-Hosting an OpenSource LLM for DiscourseAI Self-Hosting ai	12	4259	6 juli 2026

Configuring Discourse AI with internal OpenAI APIs

Gerelateerde topics