anything-llm VS embedchain

anything-llm looks pretty interesting and easy to use https://github.com/Mintplex-Labs/anything-llm

You can just fork AnythingLLM for a very advanced starting point or just straight rip the code ive already written to build yours 🚀

AnythingLLM also works on an Intel Mac (i develop it on an intel mac) and can use any GGUF model to do local inferencing. Includes document embedding + local vector database so i can do chatting with documents and even coding inside of it. Pretty much a ChatGPT equilivent i can run locally via the repo or docker.

If you want a UI you can leverage https://github.com/Mintplex-Labs/anything-llm and do all your coding in localhost with a locally running model.

You can use embedchain[1] to connect various data sources and then get a RAG application running on your local and production very easily. Embedchain is an open source RAG framework and It follows a conventional but configurable approach.

The conventional approach is suitable for software engineer where they may not be less familiar with AI. The configurable approach is suitable for ML engineer where they have sophisticated uses and would want to configure chunking, indexing and retrieval strategies.

[1]: https://github.com/embedchain/embedchain

Langchain is a big wrapper in itself and people can't be bothered to even use that to write 10 lines of code. Look at the traction this project is getting https://github.com/embedchain/embedchain, at it's heart it's just using few modules from langchain. The whole thing, chunking+embedding+retrieval+promoting can be done in 100 lines without langchain and embedchain.

Embedchain: a framework to easily create LLM powered bots over any dataset [Link].