How kkg2001/ai-testcase-generator works
This is a Streamlit AI test-case generator. Users paste requirements or upload a PDF, DOCX, text, or Markdown document; the app can optionally retrieve QA guidance, then generates a structured suite that users can review and export. The source excerpts show the UI orchestration, document extraction, generation, provider setup, schema, and optional Chroma-backed RAG. Provider implementation supports Groq and Gemini; although the UI mentions Ollama, its implementation is not shown here.
Main entry points: app.py Streamlit workflow · generator.py Suite generation · llm_provider.py LLM provider setup · rag.py RAG retrieval
Components 11
User interface
- Streamlit workflow
app.py - Review and export
app.py
Requirements input
- Document extraction
src/document_loader.py
Test generation
- Suite generation
src/generator.py - LLM provider setup
src/llm_provider.py - Test suite schema
src/models.py
Knowledge retrieval
- RAG retrieval
src/rag.py - Chroma knowledge store
src/rag.py
Other components
- QA user
- Groq API
- Gemini API
Connections 13
- QA user → Streamlit workflow: provides requirements
app.py - Streamlit workflow → Document extraction: loads upload
app.py - Streamlit workflow → Suite generation: requests suite
app.py - Streamlit workflow → RAG retrieval: queries context
app.py - RAG retrieval → Chroma knowledge store: queries and stores
src/rag.py - Suite generation → LLM provider setup: creates model
src/generator.py - Suite generation → Test suite schema: validates suite
src/generator.py - LLM provider setup → Groq API: creates client
src/llm_provider.py - LLM provider setup → Gemini API: creates client
src/llm_provider.py - Suite generation → Streamlit workflow: returns suite
app.py - Streamlit workflow → Review and export: renders and exports
app.py - Suite generation → Review and export: converts to dataframe
app.py - Review and export → QA user: presents suite
app.py