Adding Support for Nvidia Hosted Models #3525

New Issue

2025-11-11T15:33:18-06:00

GiteaMirror commented

2025-11-11 15:33:18 -06:00

Originally created by @YashM8 on GitHub (Jan 31, 2025).

Nvidia follows a simple api calls using the OpenAI library but with a different base_url. For example -

from openai import OpenAI

client = OpenAI(
  base_url = "https://integrate.api.nvidia.com/v1",
  api_key = "$API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC"
)

completion = client.chat.completions.create(
  model="deepseek-ai/deepseek-r1",
  messages=[{"role":"user","content":"Which number is larger, 9.11 or 9.8?"}],
  temperature=0.6,
  top_p=0.7,
  max_tokens=4096,
  stream=True
)

for chunk in completion:
  if chunk.choices[0].delta.content is not None:
    print(chunk.choices[0].delta.content, end="")

A UI modification that lets us change this base_url would be nice.

Originally created by @YashM8 on GitHub (Jan 31, 2025). Nvidia follows a simple api calls using the OpenAI library but with a different `base_url`. For example - ``` from openai import OpenAI client = OpenAI( base_url = "https://integrate.api.nvidia.com/v1", api_key = "$API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC" ) completion = client.chat.completions.create( model="deepseek-ai/deepseek-r1", messages=[{"role":"user","content":"Which number is larger, 9.11 or 9.8?"}], temperature=0.6, top_p=0.7, max_tokens=4096, stream=True ) for chunk in completion: if chunk.choices[0].delta.content is not None: print(chunk.choices[0].delta.content, end="") ``` A UI modification that lets us change this `base_url` would be nice.

GiteaMirror closed this issue

2025-11-11 15:33:18 -06:00

GiteaMirror referenced this issue

2025-11-11 17:44:02 -06:00

[PR #3525] [MERGED] i18n: Updated Catalan Translations #8062

GiteaMirror referenced this issue

2026-04-20 03:25:30 -05:00

[PR #3525] [MERGED] i18n: Updated Catalan Translations #21266

GiteaMirror referenced this issue

2026-04-25 10:36:35 -05:00

[PR #3525] [MERGED] i18n: Updated Catalan Translations #36896

GiteaMirror referenced this issue