This right here is the key difference! Yes anyone can vibe code a replacement for many apps - but will it still run 2 years later (assuming they get it 'running' in an prod environment at all

If the 'source information' cannot be linked to a person in the organisation, then it doesnt really belong in the RAG document store as authorative information.

The real lightbulb moment is when you realise the ONLY thing a RAG passes to the LLM is a short string of search results with small chunks of text. This changes it from 'magic' to 'ahh, ok - I need better search results'. With small models you cannot pass a lot of search results ( TOP_K=5 is probably the limit ), otherwise the small models 'forget context'.

It is fun trying to get decent results - and it is a rabbithole, next step I am going into is pre-summarising files and folders.

I open sourced the code I was using - https://github.com/acutesoftware/lifepim-ai-core

https://github.com/acutesoftware/lifepim-ai-core

Only been public a few days, so please let me know if there are glaring issues.

LangChain has the embeddings for major providers:

  def build_vectorstore(docs):
    """
    Create vectorstore from documents using configured embedding model.
    """
    # Choose embedding model
    if cfg.EMBED_MODEL.lower() == "openai":
        embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
    elif cfg.EMBED_MODEL.lower() == "huggingface":
        from langchain_community.embeddings import HuggingFaceEmbeddings
        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    elif cfg.EMBED_MODEL.lower() == "nomic-embed-text":
        from langchain_ollama import OllamaEmbeddings
        embeddings = OllamaEmbeddings(model=cfg.EMBED_MODEL)

And this is what is causing the friction against LLM's (which are quite useful for getting up to speed with a new concept / language ), the programming itself is the fun bit - I still want to do that bit!

I would be wary investing time in learning / using any new products from them.

I am really pleased they continue to work on this - it is a lot of work, but it needs to be done and checked manually, once done the base stuff shouldn't change much and it will be a great common sense check for generated content.

Yes you can - just save them locally?

Very low frequency updates mainly about information management and data.

Most popular article was "What software will you trust when you get senile?" - https://www.lifepim.com/blog/5856_What_software_will_you_tru...

A nice next step or addition would be to take the results and remesh them to lower poly models so it can be used in a game engine to walk around in.

2. AI will improve and showcase several new cool 'tricks' but commercially it will continue to focus on guiding users to watch more ads.

3. An increase in the number of streaming media services will make the average user realize they need to pay quite a lot money to 'watch stuff' - either a new unified package will appear for a reasonable price, or piracy will increase.

I'd love to see a schematic exported or even shown as you press simulate (you clearly have it the components and links in memory somewhere to do the simulation). This would be great for debugging.