Julian Risch

Hello @sanjayc2 if you run the docker command, it means you are running OpenSearch locally on your own machine. In that case you don't need any AWS account. If you...

@MetroCat69 Thanks for opening this PR. We are not aware of any good way to work around the limit of 3 full-text search (FTS) indexes on the free-tier MongoDB Atlas...

There are some smaller linter issues that need to be fixed: https://github.com/deepset-ai/haystack-core-integrations/actions/runs/14581768683/job/40899798526?pr=1663 You can run the linter locally with `hatch run lint:all`. Regarding the renaming of the secret `MONGO_CONNECTION_STRING_2`, we...

With the free-tier MongoDB Atlas cluster that we currently use in the continuous integration tests, we can't merge this branch right away. I'll close it for now but feel free...

@davidsbatista @TuanaCelik The issue mentions that "This will make the new sentence window retreval tutorial simpler". So we should follow up on this by simplifying the tutorial https://haystack.deepset.ai/tutorials/42_sentence_window_retriever

WIP draft: https://github.com/deepset-ai/haystack/pull/9167

Following the introduction of image support in Haystack 2.16.0, we added image support to a larger number of model providers (Amazon Bedrock, Anthropic, Azure, Google, Hugging Face API, Meta Llama...

For context, link to an example for prompt caching: https://github.com/deepset-ai/haystack-core-integrations/pull/1300/files#diff-c9173d1750430b1d796e26865cf0ca1fb91a9ec7016ff989aab26f3fd949eb62R62

@alexkreidler Thank you for the feature suggestion. Based on the [fastembed documentation](https://qdrant.github.io/fastembed/examples/FastEmbed_GPU/), my understanding is that this feature would require `pip install fastembed-gpu`. `fastemebd-gpu` cannot be installed in the same...

AzureOCRConverter could be moved to Haystack core integrations while we keep ChatGenerator in Haystack core.