GPT4All Embeddings

[MoLa_Data]

Hi all

I’m playing with the learnathon workflow from the other day and I’m trying to create embeddings through gpt4all but I think it’s currently not possible, am I correct or can it be done?

Thanks!!

[MoLa_Data]

Let me explain better, I want to say if it works with FAISS or Chroma (create vector), it doesn’t work for me in version 5.2 nighly.

Thank you.

[Alex_JW]

Hey @MoLa_Data,
from which update page did you install the extension? The Embeddings4All Connector node should work. Could you elaborate on the error?

Best,
Alex

[MoLa_Data]

Although it runs, but work well?
Is there an example in the hub?

[mlauber71]

@MoLa_Data I created a workflow based on an example from “KNIME AI Learnathon” using GPT4All local models. I was able to create a (local) Vector Store from the example with the PDF document from the coffee machine and pose the questions to it with the help of GPT4All (you might have to load the whole workflow group):

GPT4All - Create your own LLM Vector Store – mlauber71

The chatbot does not (yet?) work. It uses KNIME 5.2 (nightly build).

The first results do look promising, querying a 24 page coffee machine manual with a local LLM (so no data sent to OpenAI …).

Edit: please note the suggested prompt (from the original workflow). Depending on the model these might have to be adapted. And they also might be crucial.

[MoLa_Data]

In Andalusia, we say when some friend helps us to fix an important problem ¡si es que tengo que quererte! thanks a lot!!!

[mlauber71]

@MoLa_Data thank you for the question It inspired me to try to turn this local LLM and Vector Store thing into some sort of chat system:

GPT4All - Create your own LLM Vector Store – mlauber71

[AdrienneNGreene]

thank you for the information, I have a question, should i ask it here or start a new thread?

[MoLa_Data]

Wow great article, that is exactly my first idea.

Could you give me permisión to write in Spanish about your article and the workflows of Paolo and you?

[mlauber71]

@MoLa_Data you might write in Spanish about this . Maybe you include a link to the article.

Creating a Local LLM Vector Store from PDFs with KNIME and GPT4All

Would be interesting to see an example with Spanish content. I am planning to use a German specific model with this.

[MoLa_Data]

Thank you so much,

as always I say, this community is amazing!!

[mlauber71]

@AdrienneNGreene maybe start a new thread

[MarkChapman]

@mlauber71

I created a workflow based on an example from “KNIME AI Learnathon” using GPT4All local models. Ehallpass I was able to create a (local) Vector Store from the example with the PDF document from the coffee machine and pose the questions to it with the help of GPT4All (you might have to load the whole workflow group):

GPT4All - Create your own LLM Vector Store – KNIME Community Hub

Thanks for sharing the solution.It help me a lot.