Feature/issue 25/create chat with repo compoent

[innovation64]

• Refactor the code to use JSON as the database.
• Didn't use llamaindex, instead used the built-in Chroma index.
• Add code blocks at the end of each query.
• Directly use md_content content for embedding.
• LLM tokenization search and global retrieval completed.
• Vector retrieval uses Chroma's built-in engine.
• Not suitable for multi-turn conversations; it's too long, and one round typically exceeds 4096 tokens.
• Add a tree structure summary.
• No fixed database is established; the program automatically updates upon each restart.
• Add a log file to track keywords and recall embeddings.