The steps would then be: 1. Embed your private data in chunks and store the resulting embeddings in a vector database 2. In your prompting workflow, when a user queries the chat model, embed their query using the embedding model 3. Retrieve the most similar chunks of text from your vector database based on cosine similarity 4. In the chat response, provide it the context of those chunks of text
For example, if you asked "who have I discussed Ubuntu with?", it might retrieve emails that have similar content. Then the model will be able to answer informed by that context.
How do you encode the private data into the vectors? It is a bunch of text but how do you choose the vector values in the first place? What software does that? Isn’t that basically an ML task with its own weights, that’s what classifiers do!
I was surprised everyone had been writing about that but neglecting to explain this piece. Like math textbooks that “leave it as an exercise to the reader”.
Claude with its 100k context window doesn’t need to do this vector encoding. Is there anything like that in open source AI at the moment ?
It breaks other things like model downloading, but once I got it to a working state for myself, I figured why not put it up there in case its useful. If I have time, I'll try to rework it a little bit with more parameters and less dockerfile repetition to fit the main project better.
Gpt4all[1] offers a similar 'simple setup' but with application exe downloads, but is arguably more like open core because the gpt4all makers (nomic?) want to sell you the vector database addon stuff on top.
[1]https://github.com/nomic-ai/gpt4all
I like this one because it feels more private / is not being pushed by a company that can do a rug pull. This can still do a rug pull, but it would be harder to do.
I guess ooba one-click doesn't come with a model included, but is that really enough of a hurdle to stop someone from getting it going?
Maybe I'm not seeing the value proposition of this. Glad to be enlightened!
Anyone see if it contains utilities to import models from huggingface/github?
Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
In Germany, a trademark can be lost if it becomes a "Gattungsbegriff" (generic term). This happens when a trademark becomes so well-known and widely used that it becomes the common term for a product or service, rather than being associated with a specific company or brand.
For example, if a company invented a new type of vacuum cleaner and trademarked the name, but then people started using that name to refer to all vacuum cleaners, not just those made by the company, the trademark could be at risk of becoming a generic term; which would lead to a deletion of the trademark. I think this is basically what happens to GPT here.
Btw, there are some interesting exampls from the past were trademarks were lost due to the brand name becoming too popular: Vaseline and Fön (hairdryer; everyone in Germany uses the term "Fön").
I also found some trademarks which are at risk of being lost: "Lego", "Tupperware", "Post" (Deutsche Post/DHL), and "Jeep".
I don't know how all this stuff works in America though. But it would honestly suck if you'd approve such a generic term as a trademark :/
What OpenAI did was the opposite of what you describe, they took an already-generic term and used it for a product name. I wouldn't be surprised if they can't actually trademark that.
OpenAI has applied to the United States Patent and Trademark Office (USPTO) to seek domestic trademark registration for the term “GPT” in the field of AI.[64] OpenAI sought to expedite handling of its application, but the USPTO declined that request in April 2023.
As an aside, UmbrelOS actually seems like a cool concept by itself btw, good to see these "self hosted cloud" projects coming together in a unified UI, I may investigate this more at some point.
this for zero shot instructions: https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-...
easiest way would be https://github.com/oobabooga/text-generation-webui
a little more complex way I do is I have a stack with llama.cpp server, a openai adapter, and bettergpt as frontend using the openai adapter as the custom endpoint. bettergpt ux beats oogaboga by a long way (and chatgpt on certain aspects)
