diff --git a/docs/extras/modules/data_connection/document_transformers/post_retrieval/_category_.yml b/docs/extras/modules/data_connection/document_transformers/post_retrieval/_category_.yml new file mode 100644 index 00000000000..c5760e60bde --- /dev/null +++ b/docs/extras/modules/data_connection/document_transformers/post_retrieval/_category_.yml @@ -0,0 +1 @@ +label: 'Post retrieval' diff --git a/docs/extras/modules/data_connection/document_transformers/post_retrieval/long_context_reorder.ipynb b/docs/extras/modules/data_connection/document_transformers/post_retrieval/long_context_reorder.ipynb index b77aa2f3acf..adaa4890c91 100644 --- a/docs/extras/modules/data_connection/document_transformers/post_retrieval/long_context_reorder.ipynb +++ b/docs/extras/modules/data_connection/document_transformers/post_retrieval/long_context_reorder.ipynb @@ -1,15 +1,16 @@ { "cells": [ { + "attachments": {}, "cell_type": "markdown", "id": "fc0db1bc", "metadata": {}, "source": [ "# Lost in the middle: The problem with long contexts\n", "\n", - "No matter the architecture of your model, there is a sustancial performance degradation when you include 10+ retrieved documents.\n", - "In brief: When models must access relevant information in the middle of long contexts, then tend to ignore the provided documents.\n", - "See: https://arxiv.org/abs//2307.03172\n", + "No matter the architecture of your model, there is a substantial performance degradation when you include 10+ retrieved documents.\n", + "In brief: When models must access relevant information in the middle of long contexts, then tend to ignore the provided documents.\n", + "See: https://arxiv.org/abs/2307.03172\n", "\n", "To avoid this issue you can re-order documents after retrieval to avoid performance degradation." ]