From 96957913b3e8a2d554d90b6592d3d6b29ff6ac21 Mon Sep 17 00:00:00 2001 From: Siraj R Aizlewood <siraj@aurelio.ai> Date: Wed, 31 Jan 2024 10:25:38 +0400 Subject: [PATCH] Created Folders and Files --- semantic_router/splitters/__init__.py | 0 semantic_router/splitters/base.py | 0 semantic_router/splitters/cav_sim.py | 4 ++++ semantic_router/splitters/consecutive_sim.py | 3 +++ semantic_router/splitters/cumulative_sim.py | 3 +++ 5 files changed, 10 insertions(+) create mode 100644 semantic_router/splitters/__init__.py create mode 100644 semantic_router/splitters/base.py create mode 100644 semantic_router/splitters/cav_sim.py create mode 100644 semantic_router/splitters/consecutive_sim.py create mode 100644 semantic_router/splitters/cumulative_sim.py diff --git a/semantic_router/splitters/__init__.py b/semantic_router/splitters/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/semantic_router/splitters/base.py b/semantic_router/splitters/base.py new file mode 100644 index 00000000..e69de29b diff --git a/semantic_router/splitters/cav_sim.py b/semantic_router/splitters/cav_sim.py new file mode 100644 index 00000000..67afac63 --- /dev/null +++ b/semantic_router/splitters/cav_sim.py @@ -0,0 +1,4 @@ + +""" +cav_sim stands for "cumulative average vector similarity", as in this code the cumulative average of the embedding vectors are compared to the next embedding vector. +""" \ No newline at end of file diff --git a/semantic_router/splitters/consecutive_sim.py b/semantic_router/splitters/consecutive_sim.py new file mode 100644 index 00000000..892f7d18 --- /dev/null +++ b/semantic_router/splitters/consecutive_sim.py @@ -0,0 +1,3 @@ +""" +Called "consecutive sim" because we check the similarities of consecutive document embeddings (compare ith to i+1th document embedding). +""" \ No newline at end of file diff --git a/semantic_router/splitters/cumulative_sim.py b/semantic_router/splitters/cumulative_sim.py new file mode 100644 index 00000000..7c7c35b7 --- /dev/null +++ b/semantic_router/splitters/cumulative_sim.py @@ -0,0 +1,3 @@ +""" +Called "cumulative sim" because we check the similarities of the embeddings of cumulative concatenated documents with the next document. +""" \ No newline at end of file -- GitLab