In December 2024, Zhenya Zhu developed a local demo API service for the Shubhamsaboo/LightRAG repository, focusing on rapid experimentation with content ingestion and retrieval. Leveraging Python and FastAPI, Zhenya integrated the LightRAG framework with a local Ollama instance to provide endpoints for querying, inserting text, and uploading files, all backed by embeddings and model completion capabilities. The service was designed to operate against a default index directory, supporting reproducible testing workflows. Zhenya also performed code formatting improvements to enhance maintainability. This work established a robust prototype for validating embeddings and model-completion features in LLM-integrated applications.