Skip to content

github-action.md

Latest commit

 

History

History
162 lines (123 loc) · 4.33 KB

github-action.md

File metadata and controls

162 lines (123 loc) · 4.33 KB
Raw

QWED GitHub Action

Neurosymbolic verification for your CI/CD pipeline

GitHub Marketplace Version

What is QWED?

QWED combines Neural Networks (LLMs) with Symbolic Reasoning (SymPy, Z3) to provide deterministic verification of AI outputs.

Use cases:

  • ✅ Verify mathematical calculations in PRs
  • ✅ Check logical reasoning in documentation
  • ✅ Detect unsafe code patterns
  • ✅ Validate LLM outputs before deployment

Quick Start

Add this to your .github/workflows/verify.yml:

name: Verify with QWED

on: [push, pull_request]

jobs:
  verify:
    runs-on: ubuntu-latest
    steps:
      - name: Verify Calculation
        uses: QWED-AI/qwed-verification@v2.2.0
        with:
          query: "What is the derivative of x^2?"
          provider: "openai"
          api-key: ${{ secrets.OPENAI_API_KEY }}

Inputs

Input Description Required Default
query Question or statement to verify ✅ Yes -
provider LLM provider (openai, anthropic, gemini) No openai
api-key API key for LLM provider No -
model Model name (e.g., gpt-4o-mini) No gpt-4o-mini
mask-pii Enable PII masking (true/false) No false
verification-type Type: auto, math, logic, code No auto

Outputs

Output Description
verified Verification result (true/false)
value Verified value or result
confidence Confidence score (0.0-1.0)
evidence JSON evidence of verification

Examples

Verify Math in PRs

- name: Check Math
  uses: QWED-AI/qwed-verification@v2.2.0
  with:
    query: "What is 2^10?"
    provider: "openai"
    api-key: ${{ secrets.OPENAI_API_KEY }}

Verify Logic

- name: Check Logic
  uses: QWED-AI/qwed-verification@v2.2.0
  with:
    query: "Is (A AND NOT A) satisfiable?"
    provider: "anthropic"
    api-key: ${{ secrets.ANTHROPIC_API_KEY }}

Check Code Security

- name: Security Check
  uses: QWED-AI/qwed-verification@v2.2.0
  with:
    query: |
      Is this code safe?
      ```python
      eval(user_input)
      ```
    verification-type: "code"

Enterprise: PII Masking

- name: Secure Verification
  uses: QWED-AI/qwed-verification@v2.2.0
  with:
    query: "User email: john@example.com, calculate 2+2"
    mask-pii: "true"
    provider: "openai"
    api-key: ${{ secrets.OPENAI_API_KEY }}

Privacy & Security

  • 🔒 PII Masking: Automatically mask sensitive data (emails, SSNs, credit cards)
  • 🏠 Local Option: Use local LLMs (Ollama) for zero cloud exposure
  • 🔐 API Keys: Use GitHub Secrets for secure credential management
  • ✅ Open Source: Full transparency, no black boxes

How It Works

Your Query
    ↓
LLM Response (GPT-4, Claude, etc.)
    ↓
Symbolic Verification (SymPy, Z3, AST)
    ↓
✅ Deterministic Proof or ❌ Verification Failure

Example:

  • Query: "What is the derivative of x^2?"
  • LLM says: "2x"
  • SymPy computes: diff(x**2, x) = 2*x
  • QWED: ✅ MATCH! Verified with 100% confidence

Requirements

API Keys (choose one):

  • OpenAI: OPENAI_API_KEY
  • Anthropic: ANTHROPIC_API_KEY
  • Google: GOOGLE_API_KEY

Or use local LLMs (Ollama) for free!

Documentation

Support

License

Apache 2.0 - See LICENSE

Made with 💜 by QWED-AI