Release Notes
v2.0.1-rc1
⬆️ Upgrade Notes
- The
HuggingFaceTGIGenerator
andHuggingFaceTGIChatGenerator
components have been modified to be compatible with
huggingface_hub>=0.22.0
.
If you use these components, you may need to upgrade thehuggingface_hub
library.
To do this, run the following command in your environment:pip install "huggingface_hub>=0.22.0"
🚀 New Features
- Introduce a new
SparseEmbedding
class which can be used to store a sparse vector representation of a Document.
It will be instrumental to support Sparse Embedding Retrieval with the subsequent introduction of Sparse Embedders and Sparse Embedding Retrievers. - Adds
streaming_callback
parameter toHuggingFaceLocalGenerator
, allowing users to handle streaming responses.
⚡️ Enhancement Notes
- In Jupyter notebooks, the image of the Pipeline will no longer be displayed automatically.
The textual representation of the Pipeline will be displayed. To display the Pipeline image, use theshow
method of the Pipeline object. - Set
max_new_tokens
default to 512 in Hugging Face generators.
🐛 Bug Fixes
- Fixes
HuggingFaceTEITextEmbedder
returning an embedding of incorrect shape when used with a Text-Embedding-Inference endpoint deployed using Docker. - Add the
@component
decorator toHuggingFaceTGIChatGenerator
.
The lack of this decorator made it impossible to use theHuggingFaceTGIChatGenerator
in a pipeline. - Fixes
Pipeline.run()
logic so Components that have all their inputs with a default are run in the correct order.
This happened we gather a list of Components to run internally when running the Pipeline in the order they are added during creation of the Pipeline.
This caused some Components to run before they received all their inputs.