| English🌎 | 简体中文🀄 |
Welcome to my GitHub page!
I am a machine learning algorithm engineer with a strong passion for open-source technologies. Here, you can find a variety of projects I have been involved in, ranging from small tools to large-scale applications, covering multiple domains such as ML, CV, NLP, and more. I am committed to delivering high-quality code and useful tools to help solve practical problems and drive technological advancements.
Here are some of my main projects and contributions on GitHub:
Data-Follower This is one of my proudest projects, an interactive machine learning application developed using the Streamlit framework. With a guided interface, users can quickly train machine learning models and conveniently make predictions using pre-trained models.
PyDepGraph This is a personal project I initiated to address the issue of Python package dependencies in daily development work. I have open-sourced it so that others can benefit from it and contribute as well.
Aesopica This project curates a collection of English versions of Aesop’s fables and utilizes AIGC technology to generate the content (moral) and illustrations for each fable. Finally, it applies TTS technology to synthesize animated videos.
Feed-Monitoring-Tool is an asynchronous tool that uses coroutines and timers to parse Feed information sources, save news containing keywords, and push them to chat groups through Feishu robots.
MRKL-AgentBot is a groundbreaking project that uses the LangChain framework to connect various types of components. It is a MRKL application research system developed with Agent modules, containing Chat, RAG, and Agents.
Shiny-jiebaR This is one of my earliest open-source projects. It utilizes the jieba Chinese word segmentation library and the R Shiny framework to create a cloud-based word segmentation application.
In addition to these projects, the following open-source projects have greatly helped me and have sparked my strong interest:
I believe in the power of open-source and the importance of collaboration. Therefore, I encourage you to explore my projects, ask questions, provide suggestions, and contribute improvements. If you are interested in any of the projects I am currently working on or have any collaboration opportunities, please feel free to contact me.
Simple example of usage of streamlit and FastAPI for ML model serving.
To run the example in a machine running Docker and docker-compose, run:
docker-compose build
docker-compose up
To visit the FastAPI documentation of the resulting service, visit http://localhost:8500 with a web browser.
To visit the streamlit UI, visit http://localhost:8501.
Logs can be inspected via:
docker-compose logs
Thank you for visiting my GitHub page! I hope you enjoy my projects and find them beneficial.