Corentin Meyer
Corentin Meyer
+1 to this. LiteLLM could be the backend for all text generation and embedding node because it's highly compatible with a LOT of providers
Hey I wonder if there is any news on this ? I'm facing an issue, I have a 350mbits .ndpi image, and when loading it in RAM it takes like...
I am very interested by a similar feature. Copy/Pasting a message on Discord: "Is it possible when using .count() function of Qdrant to not count the number of chunks but...
> @lambda-science You can count with a filter, does that help? > > See: https://qdrant.tech/documentation/concepts/points/#counting-points Hello Not really because as I said, in the vector DB file are fragmented as...
Still interested in this functionally, I heard it was in roadmap
Is it still not possible to have a .lock file per workspace member ?
> I'd like to take this up if no one is working on it Hello @AnushreeBannadabhavi , I had the exact same requirement today about Tika not yielding the page...
@anakin87 This updated version with previous parsing method from Haystack 1.X seem's to work well to add the `\f` in the content so the Splitter can count them to know...
Proposed fix: https://github.com/deepset-ai/haystack/pull/8082
> @lambda-science would you please add a unit test, not as much to add some deep rigours unit test case here, but to have that test fail if tools was...