Skip to content

CI: DeepSeek v3

CI: DeepSeek v3 #22

Workflow file for this run

name: Test with Gemini
on: [workflow_dispatch, push, pull_request]
jobs:
zero-shot:
runs-on: ubuntu-22.04
timeout-minutes: 5
steps:
- uses: actions/checkout@v4
- run: echo 'Which planet in our solar system is the largest?' | ./query-llm.js | tee output.txt
env:
LLM_API_BASE_URL: 'https://generativelanguage.googleapis.com/v1beta'
LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
LLM_CHAT_MODEL: 'gemini-1.5-flash-8b'
LLM_ZERO_SHOT: 1
- run: cat output.txt
- run: grep -i jupiter output.txt
chain-of-thought:
runs-on: ubuntu-22.04
timeout-minutes: 5
steps:
- uses: actions/checkout@v4
- run: echo 'Which planet in our solar system is the largest?' | ./query-llm.js | tee output.txt
env:
LLM_API_BASE_URL: 'https://generativelanguage.googleapis.com/v1beta'
LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
LLM_CHAT_MODEL: 'gemini-1.5-flash-8b'
LLM_JSON_SCHEMA: 1
- run: cat output.txt
- run: grep -i jupiter output.txt
multi-turn:
needs: chain-of-thought
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- uses: actions/checkout@v4
- run: ./query-llm.js tests/canary-multi-turn.txt
env:
LLM_API_BASE_URL: 'https://generativelanguage.googleapis.com/v1beta'
LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
LLM_CHAT_MODEL: 'gemini-1.5-flash-8b'
LLM_JSON_SCHEMA: 1
high-school-stem:
needs: chain-of-thought
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- uses: actions/checkout@v4
- run: ./query-llm.js tests/high-school-stem.txt
env:
LLM_API_BASE_URL: 'https://generativelanguage.googleapis.com/v1beta'
LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
LLM_CHAT_MODEL: 'gemini-1.5-flash-8b'
LLM_JSON_SCHEMA: 1
general-knowledge:
needs: chain-of-thought
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- uses: actions/checkout@v4
- run: ./query-llm.js tests/general-knowledge.txt
env:
LLM_API_BASE_URL: 'https://generativelanguage.googleapis.com/v1beta'
LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
LLM_CHAT_MODEL: 'gemini-1.5-flash-8b'
LLM_JSON_SCHEMA: 1