4 projects
embedkit-py
Production embedding pipeline toolkit for building RAG systems with multiple chunking strategies, cached embeddings, and unified vector store interfaces.
dataweave-lib
Declarative data pipeline framework - define ETL workflows in YAML
promptguard-py
LLM Output Validation Framework - enforce schema compliance, detect PII, score hallucination risk, filter toxicity, and validate structured outputs.
testpilot-ai
Intelligent test generation framework using AST analysis and optional LLM enhancement