From 0082bcf19f19e4c9b26f53f9f7f1d5ad80faae7a Mon Sep 17 00:00:00 2001 From: ZiyiXia Date: Thu, 6 Feb 2025 10:03:42 +0000 Subject: [PATCH] update docs --- docs/requirements.txt | 1 + docs/source/Introduction/reranker.rst | 4 ++++ docs/source/bge/bge_m3.rst | 1 + 3 files changed, 6 insertions(+) diff --git a/docs/requirements.txt b/docs/requirements.txt index 7ac4bb0..c301cd0 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,5 +1,6 @@ sphinx myst-nb +myst_parser sphinx-design pydata-sphinx-theme # furo \ No newline at end of file diff --git a/docs/source/Introduction/reranker.rst b/docs/source/Introduction/reranker.rst index 05df215..d0da73d 100644 --- a/docs/source/Introduction/reranker.rst +++ b/docs/source/Introduction/reranker.rst @@ -1,6 +1,10 @@ Reranker ======== +.. tip:: + + If you are already familiar with the concepts, take a look at the :doc:`BGE rerankers <../bge/index>`! + Reranker, or Cross-Encoder, is a model that refines the ranking of candidate pairs (e.g., query-document pairs) by jointly encoding and scoring them. Typically, we use embedder as a Bi-Encoder. It first computes the embeddings of two input sentences, then compute their similarity using metrics such as cosine similarity or Euclidean distance. diff --git a/docs/source/bge/bge_m3.rst b/docs/source/bge/bge_m3.rst index 2cfe594..f4b73a4 100644 --- a/docs/source/bge/bge_m3.rst +++ b/docs/source/bge/bge_m3.rst @@ -3,6 +3,7 @@ BGE-M3 ====== BGE-M3 is a compound and powerful embedding model distinguished for its versatility in: + - **Multi-Functionality**: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. - **Multi-Linguality**: It can support more than 100 working languages. - **Multi-Granularity**: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens.