This is a Question-Answering system based on k8s-specific knowledge build on ChatGLM2-6B, serving by Ray. It's not ready for production, but we'll target for this.
- LangChain to build LLM applications.
- Ray for accelerating and serving.
- ChatGLM2-6B as a base model.
- BAAI/bge-base-zh-v1.5 for embedding in semantic search.
- FAISS as a vector database.
- Kubernetes Website
- Kubernetes Blogs
- Kubernetes Books (Only for research usage)
- Containerization, FAISS is for single node.
- More efficient text splitting ways designed for Chinese.
- More approaches to support semantic search, e.g. key-word embeddings.
- Raw data management, like new uploading and deleting.
- Vector data persistent.
- Continuous Pre-Training.
- and so on ...