Jonas Maison

LIDC-IDRI-0086,(0040, 0007) Scheduled Procedure Step Descriptio LO: 'CT, CHEST, W CONTRAST' LIDC-IDRI-0094,(0040, 0007) Scheduled Procedure Step Descriptio LO: 'CT,CHEST,W CONTRAST' LIDC-IDRI-0095,(0040, 0007) Scheduled Procedure Step Descriptio LO: 'CT,CHEST,W CONTRAST' LIDC-IDRI-0098,(0040,...

Hi @notmatthancock , Yes we should keep this open (maybe add a _"warning `contrast_used` labels not accurate"_ to the README.md?) Unfortunately some DICOM tags for contrast agent are missing, especially...

Replace all `nn.Conv2d(3, dim_in, 3, 1, 1)` in `model.py` with `nn.Conv2d(1, dim_in, 3, 1, 1)`

`RuntimeError: Given groups=1, weight of size 64 1 3 3, expected input[1, 3, 256, 256] to have 1 channels, but got 3 channels instead` add `print(x.size())` before `out = self.main(x)`....

The instructions above are from Bard, the google's chatgpt.

do the e2e tests with exports fail when using the kili user client? (they should)

> > do the e2e tests with exports fail when using the kili user client? (they should) > > there is no export e2e test notebooks the current solution only...

Yes I guess it would be relatively easy to implement: - `__aenter__` would be empty - `__aexit__` would call `__exit__`, followed by a `await logger.complete()` maybe? For now, I'm making...

@hassiebp I'm using azure openai To reproduce: ```python import asyncio from langfuse.openai import AsyncAzureOpenAI async def main(): client = AsyncAzureOpenAI( api_key="123456", azure_endpoint="https://eastus.api.cognitive.microsoft.com", api_version="2024-09-01-preview", azure_deployment="o1-preview-2024-09-12", ) response = await client.chat.completions.create( model="o1-preview-2024-09-12",...

@hassiebp I'm using this: https://learn.microsoft.com/en-gb/azure/ai-services/openai/how-to/create-resource?pivots=web-portal Unfortunately, 2.57.10 does not solve the problem: ```text 6 validation errors for UpdateGenerationBody usageDetails -> completion_tokens_details value is not a valid integer (type=type_error.integer) usageDetails ->...