Stefano Fiorucci
Stefano Fiorucci
We are introducing new HuggingFaceAPI Generators and Embedders. We are also deprecating: - `HuggingFaceTGIGenerator` - `HuggingFaceTGIChatGenerator` - `HuggingFaceTEITextEmbedder` - `HuggingFaceTEIDocumentEmbedder` These components should be removed in 2.3.0. We should also...
`PyPDFToDocument` was refactored in #7362 `converter_name` and `CONVERTERS_REGISTRY` are deprecated and should be removed in 2.3.0.
We have several **Embedders** on Haystack 2.0 - API based: OpenAI, Cohere, Jina... - Sentence Transformers - HF Text Embedding Inference - Fastembed - HF Optimum Some focus on simplicity,...
Hey @LLukas22! I'm Stefano and I work on the **Haystack** project. I found `llm-rs-python` by chance and started experimenting with it on my laptop and was really impressed! 💣 So...
`extractor_type` and `try_others` init parameters will be ignored, starting from version 2.2.0 and must be removed in 2.4.0. See #7705 for more information.
In the past, only OpenAI provided support for function calling. Today, many Language Model providers/libraries support this feature, using Tools specification or similar. Also in the context of the upcoming...
**Is your feature request related to a problem? Please describe.** Llama CPP generators don't support streaming. **Describe the solution you'd like** Implement support for streaming, as done for other generators...
From [StackOverflow](https://stackoverflow.com/questions/78282522/how-to-use-googleaigeminichatgenerator-for-haystack-with-googles-gemini). We should investigate. --- I am trying my best to run this tutorial right off the Haystack website using Google Colab: https://docs.haystack.deepset.ai/reference/integrations-google-ai It works up until I reach...
Tests fail because of this: https://github.com/deepset-ai/haystack-core-integrations/blob/9ed323080bcc82ff70e9a0f56a6c2561fec42c2e/.github/workflows/amazon_bedrock.yml#L65-L66 Even if unit tests do not need authentication, they can't run because this step fails.
Supporting hybrid (sparse+dense embedding) retrieval should be quite simple, now that all abstractions and components are in place. Sparse embedding retrieval in isolation should be investigated: Pinecone does not provide...