RAG & Retrieval

Open-source embedding database for building AI apps with retrieval.

Program — don't prompt — your language models. Compile declarative pipelines into optimized prompts.

Data framework for connecting custom data sources to LLMs — ingestion, indexing, retrieval.

Open toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.

Evaluation toolkit for your RAG and agent pipelines — faithfulness, relevance, and more.