Sebastian Husch Lee
Sebastian Husch Lee
### Related Issues - fixes #7017 ### Proposed Changes: Add Transformers Text Router based off of TransformersQueryClassifier (from Haystack v1) ### How did you test it? Still need to do...
**Is your feature request related to a problem? Please describe.** For RAG QA often we want to fully utilize the context window of the model by inserting as many retrieved...
**Is your feature request related to a problem? Please describe.** In Haystack v1 we had an option in the Preprocessor to add the original `page_number` to a Document's meta data...
**Is your feature request related to a problem? Please describe.** We have found the https://github.com/pdfminer/pdfminer.six package to perform well for text extraction from PDFs especially in cases that involve two-column...
See the proposal: https://github.com/deepset-ai/haystack/pull/5540 and see [feature request](https://github.com/deepset-ai/haystack/issues/4926) for Haystack v1 --- LLMs clients output strings, but many components expect other object types, and LLMs may produce output in a...
Update the [TableQa tutorial](https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/15_TableQA.ipynb) to reflect the linearized offsets will be deprecated in favor of offsets that specify the row and column indices of the table cell. TableCell was implemented...
Original issue: https://github.com/deepset-ai/haystack/issues/5675 While we have merged a basic version of TextDocumentSplitter, it doesn't support whitespace cleaning or tokenization so let's keep this issue open. @sjrl You wanted to share...
See the proposal: https://github.com/deepset-ai/haystack/pull/5540 and see [AnswersBuilder](https://github.com/deepset-ai/haystack/issues/5624) --- LLMs clients output strings, but many components expect other object types, and LLMs may produce output in a parsable format that can...