Dev Projects
$ git push --dev_projects
Student Collaborative SWE Project
- Engineered a self-hosted LLM inference pipeline using Ollama: gemma 2b, eliminating reliance on third-party cloud AI APIs and keeping all user data processing local to the host machine.
- Designed and implemented a REST API layer (Spring Boot/Spring AI) with 4 endpoints for chat, summarization, and health-check monitoring, enabling secure communication between the frontend and the locally hosted model.
- Validated deployment by authoring the full setup process on multiple unconfigured machines and troubleshooting environment-specific failure points such as port conflicts, missing dependencies, and build tool issues.
Link to Repository:
Languages used:
Dependencies used:
IT Projects
$ sudo systemctl start IT_Projects