Allycat is an end to end open-source RAG pipeline for website content. It can scape websites clean up content index content, vectorize and store them in a vector database and a UI for queries. The entire stack is open source. It supports LLMs and embedding models running locally or using an inference service. repo Here is the architecture of Allycat. Talks / Workshops Using Allycat 2025-Nov: Allycat workshop at QConSF session details ...
Data Prep Kit accelerates unstructured data preparation for LLM app developers. Developers can use Data Prep Kit to cleanse, transform, and enrich use case-specific unstructured data to pre-train LLMs, fine-tune LLMs, instruct-tune LLMs, or build Retrieval Augmented Generation (RAG) applications for LLMs. Data Prep Kit can scale from a single laptop to a cluster scale. Repo: data-prep-kit/data-prep-kit My Contribution to Data Prep Kit I worked with the dev team to make Data Prep Kit more accessible to new users and easy to use. ...