mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-12-29 16:08:38 +00:00
1876c41f07
* Add lost in the middle ranker * Add release note * Julian's feedback: more precise version of truncate * Better comments for the litm algorithm * Sebastian PR feedback * Add check for invalid values of word_count_threshold * Remove _truncate as it is not needed any more --------- Co-authored-by: Darja Fokina <daria.f93@gmail.com>
19 lines
1.0 KiB
YAML
19 lines
1.0 KiB
YAML
---
|
|
prelude: >
|
|
We're excited to introduce a new ranker to Haystack - LostInTheMiddleRanker.
|
|
It reorders documents based on the "Lost in the Middle" order, a strategy that
|
|
places the most relevant paragraphs at the beginning or end of the context,
|
|
while less relevant paragraphs are positioned in the middle. This ranker,
|
|
based on the research paper "Lost in the Middle: How Language Models Use Long
|
|
Contexts" by Liu et al., can be leveraged in Retrieval-Augmented Generation
|
|
(RAG) pipelines.
|
|
features:
|
|
- |
|
|
The LostInTheMiddleRanker can be used like other rankers in Haystack. After
|
|
initializing LostInTheMiddleRanker with the desired parameters, it can be
|
|
used to rank/reorder a list of documents based on the "Lost in the Middle"
|
|
order - the most relevant documents are located at the top and bottom of
|
|
the returned list, while the least relevant documents are found in the
|
|
middle. We advise that you use this ranker in combination with other rankers,
|
|
and to place it towards the end of the pipeline.
|