Skip to content

Commit 8cfdaed

Browse files
committed
Support Nebius AI Studio
1 parent 720bb9d commit 8cfdaed

File tree

2 files changed

+33
-1
lines changed

2 files changed

+33
-1
lines changed

.github/workflows/test-nebius.yml

+24
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
name: Test on Nebius
2+
3+
on:
4+
push:
5+
branches: [main]
6+
workflow_dispatch:
7+
8+
jobs:
9+
test:
10+
runs-on: ubuntu-22.04
11+
timeout-minutes: 5
12+
steps:
13+
- uses: actions/checkout@v4
14+
15+
- run: node --version
16+
17+
- run: echo 'Which planet in our solar system is the largest?' | ./ask-llm.js | tee output.txt | grep -i jupiter
18+
timeout-minutes: 3
19+
env:
20+
LLM_API_BASE_URL: 'https://api.studio.nebius.ai/v1'
21+
LLM_API_KEY: ${{ secrets.NEBIUS_API_KEY }}
22+
LLM_CHAT_MODEL: 'meta-llama/Meta-Llama-3.1-8B-Instruct'
23+
24+
- run: cat output.txt

README.md

+9-1
Original file line numberDiff line numberDiff line change
@@ -82,13 +82,14 @@ export LLM_API_BASE_URL=http://127.0.0.1:10002/v1
8282
[![Test on Hyperbolic](https://github.com/ariya/ask-llm/actions/workflows/test-hyperbolic.yml/badge.svg)](https://github.com/ariya//ask-llm/actions/workflows/test-hyperbolic.yml)
8383
[![Test on Lepton](https://github.com/ariya/ask-llm/actions/workflows/test-lepton.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-lepton.yml)
8484
[![Test on Mistral](https://github.com/ariya/ask-llm/actions/workflows/test-mistral.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-mistral.yml)
85+
[![Test on Nebius](https://github.com/ariya/ask-llm/actions/workflows/test-nebius.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-nebius.yml)
8586
[![Test on Novita](https://github.com/ariya/ask-llm/actions/workflows/test-novita.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-novita.yml)
8687
[![Test on Octo](https://github.com/ariya/ask-llm/actions/workflows/test-octo.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-octo.yml)
8788
[![Test on OpenAI](https://github.com/ariya/ask-llm/actions/workflows/test-openai.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-openai.yml)
8889
[![Test on OpenRouter](https://github.com/ariya/ask-llm/actions/workflows/test-openrouter.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-openrouter.yml)
8990
[![Test on Together](https://github.com/ariya/ask-llm/actions/workflows/test-together.yml/badge.svg)](https://github.com/ariya/ask-llm/actions/workflows/test-together.yml)
9091

91-
Supported LLM services include [AI21](https://studio.ai21.com), [Deep Infra](https://deepinfra.com), [DeepSeek](https://platform.deepseek.com/), [Fireworks](https://fireworks.ai), [Groq](https://groq.com), [Hyperbolic](https://www.hyperbolic.xyz), [Lepton](https://lepton.ai), [Mistral](https://console.mistral.ai), [Novita](https://novita.ai), [Octo](https://octo.ai), [OpenAI](https://platform.openai.com), [OpenRouter](https://openrouter.ai), and [Together](https://www.together.ai).
92+
Supported LLM services include [AI21](https://studio.ai21.com), [Deep Infra](https://deepinfra.com), [DeepSeek](https://platform.deepseek.com/), [Fireworks](https://fireworks.ai), [Groq](https://groq.com), [Hyperbolic](https://www.hyperbolic.xyz), [Lepton](https://lepton.ai), [Mistral](https://console.mistral.ai), [Nebius](https://studio.nebius.ai), [Novita](https://novita.ai), [Octo](https://octo.ai), [OpenAI](https://platform.openai.com), [OpenRouter](https://openrouter.ai), and [Together](https://www.together.ai).
9293

9394
For configuration specifics, refer to the relevant section. The quality of answers can vary based on the model's performance.
9495

@@ -148,6 +149,13 @@ export LLM_API_KEY="yourownapikey"
148149
export LLM_CHAT_MODEL="open-mistral-7b"
149150
```
150151

152+
* [Nebius](https://studio.nebius.ai)
153+
```bash
154+
export LLM_API_BASE_URL=https://api.studio.nebius.ai/v1
155+
export LLM_API_KEY="yourownapikey"
156+
export LLM_CHAT_MODEL="meta-llama/Meta-Llama-3.1-8B-Instruct"
157+
```
158+
151159
* [Novita](https://novita.ai)
152160
```bash
153161
export LLM_API_BASE_URL=https://api.novita.ai/v3/openai

0 commit comments

Comments
 (0)