chengyjonathan
chengyjonathan
+1 Cant import any of these. When I look in the __init__ file, only the default pipe is available. So the others like img2img didn't make it in.
I'm also running into this: python 3.8.5 doccano 1.8.2 linux
> I think any custom retriever could do this. Or using the query fusion retriever and passing in all the retrievers you want to mix > > > > https://docs.llamaindex.ai/en/stable/examples/retrievers/relative_score_dist_fusion/?h=query+fusion...
I tried doing the following. Where I keep the images, but I don't try to parse text from them. And I thought supplying the filenames, using the filename function, would...
My understanding is that "include_extra_info" is enabled by default. And that should be prepending each document text with the metadata text (in this case the filename). But I might be...
I got this to work in an unintended way I think. Where I overwrote the Image Parser to use the filename as the text string for the Image document. Though...
The issue this brings, however, is that if you try to do multimodal queries. Ie. (Find me this image and tell me something from a different document). The response will...
Ohhh, i see now. Thank you
I ran into the same issue but in the img_inpaint function for the gradio scripts.
I can get around this by explicitly passing all the args, but I'm not sure if this is the intended behavior