Corentin Meyer
Corentin Meyer
> [@lambda-science](https://github.com/lambda-science) Is this fully working for you now? I have a DSPy application served by FastAPI and I get full usage when using sync non-streaming modules, but if I...
It feels like it can track some components in AsyncPipeline but not generator and then the chain is broken. My other non async pipeline run and track fine. My two...
Yep, should be updated for numpy 2.0 I guess, got the error. `numpy.core.multiarray failed to import`
Update: I removed the data augmentation layers so it works but I get widly different results between the model in ONNX version or Keras version. ```python import keras import numpy...
Following this, it looks great ! Thank you
+1 to this :)
I have EXACTLY the same issue with Elasticache Serverless. Ditching it also.
Adding my thoughts here because for me it's one of my first priority for next evolution of our haystack-based pipelines: The ability to embed images, store and retrieve them from...
Very interested in this feature as Bedrock is a major gen AI provider in corporate environnement. We can't use PydanticAI without support for this for our company use-cases.
One thing to have in mind also: renaming the `paths` argument to `sources` with the same type as other converters to be in line with what other converters expect :)