haystack-core-integrations

haystack-core-integrations copied to clipboard

Add NvidiaChatGenerator component

1

**Is your feature request related to a problem? Please describe.** The current Nvidia integration comprises a `NvidiaTextEmbedder`, `NvidiaDocumentEmbedder`, `NvidiaRanker` and`NvidiaGenerator` but no `NvidiaChatGenerator`. We should implement a `NvidiaChatGenerator` component and...

julian-risch

New Converter based on Markitdown from Microsoft

3

## Summary and motivation Markitdown is a new open source library (MIT license) from Microsoft (https://github.com/microsoft/markitdown). It's a utility tool for converting various files to Markdown (e.g., for indexing, text...

paulmartrencharpro

**Is your feature request related to a problem? Please describe.** After adding AsyncPipeline in Haystack 2.10 we should add a run_async method to each ChatGenerator that is IO-bound. **ChatGenerators**

mathislucka

**Is your feature request related to a problem? Please describe.** As we released AsyncPipeline in 2.10, we should add run_async methods for all relevant retrievers. --- By @anakin87: When adding...

mathislucka

If the `generation_kwargs` was set like this: https://github.com/deepset-ai/haystack-core-integrations/blob/00c43748edac70fbcd4efbca1a467138446c7edf/integrations/langfuse/example/basic_rag.py#L42 It would not be logged. ```json { "haystack.component.input_types": { "messages": "list", "generation_kwargs": "NoneType", "tools": "NoneType" }, "haystack.component.input_spec": { "messages": { "type": "typing.List[haystack.dataclasses.chat_message.ChatMessage]",...

henryclw

add run_async to weaviate retrievers

3

mathislucka

sjrl

sjrl

sjrl

sjrl