Long term plan
henomis opened this issue · comments
Long term plan
- implement agent see https://github.com/ColinEberhardt/langchain-mini/blob/main/index.mjs
- implement tools
- see https://github.com/imartinez/privateGPT
- see https://medium.com/llamaindex-blog/a-new-document-summary-index-for-llm-powered-qa-systems-9a32ece2f9ec
- plan and execute agent must wrap each step with CoT agent https://python.langchain.com/en/latest/modules/agents/plan_and_execute.html
- remove
pipeline.Llm.LlmMode
usei, ok = llm.(interface{Completion()})
to understand the llm type. Remove "llm" from struct fields.
I've came across your project today, I'm excited to start looking at the source code and applying to some experiments.
This project looks promising and well-architected, thanks for your efforts. I'm looking forward to contribute