Enables version-controlled golden dataset management and semantic evaluation for RAG/LLM pipelines using TF-IDF cosine similarity, without requiring an LLM API key.
Enables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation.
Evaluates RAG outputs on faithfulness, answer relevancy, and context precision using an LLM-as-a-Judge backend. Exposes tools for running evaluations, scoring individual samples, and checking thresholds, enabling CI gating and on-demand assessment via MCP.
Enables LLMs to search and retrieve information from large technical documentation (OpenAPI specs, markdown) via intelligent chunking and semantic search.