Marko Henning
Marko Henning
Unfortunatelly not yet. I tried to run a sequential model with it, but for that it has to be an instance of class Layer. For now I test different possibilities,...
Regarding the first error > 'Cannot convert a symbolic Keras input/output to a numpy array. ' > TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error...
For me the error still remains. What python/Tensorflow version did you use for testing?
No. Unfortunately I can't test this in another environment, as haste does not install the libhaste_tf.so when I run pip(3) install haste_tf on neither a second PC (py 3.6) nor...
I tested it in a google colab (https://colab.research.google.com/drive/1mHuT35cnW5uOgulDjHGPf88gm74O9Caz?usp=sharing) and there the same error occurs.
Hey, thank you for figuring that out, I'll try that! But is there hope to get that fixed officially, without changing the keras core file?
I stumbled on that too, and found out that the sompy package from pip is infact not this one, but from https://github.com/ttlg/sompy (as you can see when clicking on 'Homepage'...
Hey, great PR and good catch that you linked mine! If I see it correctly, you iterate over all sources (knowledges and files) and collect all `collection_names`, before giving them...
For me this issue persists on Ubuntu 22.04 with vllm 0.6.0 (also with v0.4.2).
Do you mean the "RAG_TEMPLATE" ([link](https://docs.openwebui.com/getting-started/env-configuration#rag_template)), the one you set in the admin document settings? If yes, I'm not sure it is that easy to set it per knowledge base....