Julian Risch

@sjrl I added a test called `test_pipeline_serialization`, added `_get_request_headers` to all components and here is the example notebook with updated code up until the GitHub token is required. I commented...

@sjrl Finally ready for another review! We're using `"data"` instead of `"init_parameters"` in serialization now and all newly implemented tools expose `outputs_to_string`, `inputs_from_state`, and `outputs_to_state` as init parameters. I tested...

As discussed offline, we'll focus on one or two LLM providers (ChatGenerators) before we roll out any standardization across more LLM providers. StreamingChunk dataclass improvements have been released as part...

Thank you for opening this issue @King-pand ! We'll discuss in our engineering team if we can prioritize this issue for one of our next sprints. In the mean time,...

@micha-f @vblagoje please be aware of this larger refactoring of parts of the pgvector integration: https://github.com/deepset-ai/haystack-core-integrations/pull/1547

I am closing this PR due to inactivity but feel free to re-open.

JINA_API_KEY is set. ✅ There was already a key set but I chose to create a fresh one.

Hi @UmaisMu , Thank you for getting in touch. We'd appreciate an integration with MariaDB and are happy to provide guidance! Haystack has integrations with a variety of vector databases...

Yes that's right! There is an open PR, which is unfortunately stale and not ready to be merged yet so we'll need to pick up that work again.

Closing as we now track refactoring this integration in issue https://github.com/deepset-ai/haystack-core-integrations/issues/1417