acutesoftware

That is good, but it should be qualified a little.

If the algorithm simply says "sort by most recent", then it is pretty good.

It is the profit driven algorithms that are doing the damage.

> and maintain

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

This highlights that all RAG systems should be using metadata embedded into each of the vectorstores. Any result from the LLM needs to have a link to a document / chunk - which is turn links to a 'source file' which (should) have the file system owners id or another method of linking to a person.

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.

Switching models when running locally is fairly easy - as long as you have them downloaded you can switch them in and out with a just a config setting - cant quite remember, but you may need to rebuild the vectorstore when switching though.

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)

I think it was the modal dialog box that forced you to stop what you were doing and click 'piss off clippy', rather than being able to ignore it.

> Some people love programming, for the sake of programming itself.

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!

Very well done - it took me several attempts to get the hang of Blender and I still only know / used half those shortcuts. Thanks for the easy to use tips!

I think Google has lost all faith in terms of keeping projects around - especially when they involve data locked into a mildly complex system without a complete migration path out.

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

Cyc seemed to be the best application for proper AI in my opinion - all the ML and LLM tricks are statistically really good, but you need to parse it through Cyc to check for common sense.

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.

Our ETL process is heavily monitored so we never miss a days data, but we got a surprising error "cant build aggregates - missing data, aborting MV refresh, data will be a day old". It was the year to date (YTD) calculation - no data for 29/2/2023 to compare to today.

> "You can't just take the CSS stylesheets and references and store them."

Yes you can - just save them locally?

Well, you can - you can have a policy that forces payments from a select group. Some users will complain when "No, you cant pay with 2 chickens every 3rd full moon", but that is too bad.