Is your feature request related to a problem? Please describe.
QualCoder's AI integration could be expanded to include the GWDG SAIA API. Currently, accessing these models (like Gemma 4 31B Instruct) requires manual config.ini edits.
Describe the solution you'd like
Would it be possible to add SAIA as a built-in AI provider? Since SAIA is fully OpenAI-compatible, it could integrate seamlessly into the existing AI settings.
Describe alternatives you've considered
Continuing with manual config.ini edits, routing through third-party proxies (adding latency and privacy overhead), or relying solely on paid commercial APIs.
Additional context
SAIA offers a standard OpenAI-compatible interface supporting text, vision, embeddings, and reasoning models. Full docs: https://docs.hpc.gwdg.de/services/ai-services/saia/index.html
I have already successfully tested the integration via config.ini using the following configuration:
[ai_model_Gemma4_SAIA]
desc = Gemma 4 31B Instruct via SAIA API (GWDG)
access_info_url = https://docs.hpc.gwdg.de/services/chat-ai/models/index.html
large_model = gemma-4-31b-it
large_model_context_window = 256000
fast_model = gemma-4-31b-it
fast_model_context_window = 256000
reasoning_effort = default
api_base = https://chat-ai.academiccloud.de/v1
api_key = <your_api_key>
If you find this useful, I’d be glad to implement it as a pull request.
Is your feature request related to a problem? Please describe.
QualCoder's AI integration could be expanded to include the GWDG SAIA API. Currently, accessing these models (like Gemma 4 31B Instruct) requires manual
config.iniedits.Describe the solution you'd like
Would it be possible to add SAIA as a built-in AI provider? Since SAIA is fully OpenAI-compatible, it could integrate seamlessly into the existing AI settings.
Describe alternatives you've considered
Continuing with manual
config.iniedits, routing through third-party proxies (adding latency and privacy overhead), or relying solely on paid commercial APIs.Additional context
SAIA offers a standard OpenAI-compatible interface supporting text, vision, embeddings, and reasoning models. Full docs: https://docs.hpc.gwdg.de/services/ai-services/saia/index.html
I have already successfully tested the integration via
config.iniusing the following configuration:If you find this useful, I’d be glad to implement it as a pull request.