branch: externals/elisa
commit 960cfc940c42ce8a1e11951419ce0a4bfb2b9b4f
Author: Sergey Kostyaev <kostyaev.serg...@wb.ru>
Commit: Sergey Kostyaev <kostyaev.serg...@wb.ru>
Enable custom batch size for embeddings calculation
Added a new customizable variable `elisa-batch-size` to allow users to
set the batch size for embeddings calculations. Modified the
`elisa-embeddings` function to use this batch size when dividing
chunks into batches for processing.
---
elisa.el | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/elisa.el b/elisa.el
index 1dd57a9a96..afab3c1546 100644
--- a/elisa.el
+++ b/elisa.el
@@ -1,6 +1,6 @@
;;; elisa.el --- Emacs Lisp Information System Assistant -*- lexical-binding:
t -*-
-;; Copyright (C) 2024 Free Software Foundation, Inc.
+;; Copyright (C) 2024, 2025 Free Software Foundation, Inc.
;; Author: Sergey Kostyaev <sskosty...@gmail.com>
;; URL: http://github.com/s-kostyaev/elisa
@@ -279,6 +279,10 @@ If set, all quotes with similarity less than threshold
will be filtered out."
"Enable batch embeddings if supported."
:type 'boolean)
+(defcustom elisa-batch-size 300
+ "Batch size to send to provider during batch embeddings calculation."
+ :type 'integer)
+
(defun elisa-supported-complex-document-p (path)
"Check if PATH contain supported complex document."
(cl-find (file-name-extension path)
@@ -473,7 +477,8 @@ Return list of vectors."
(let ((provider elisa-embeddings-provider))
(if (and elisa-batch-embeddings-enabled
(member 'embeddings-batch (llm-capabilities provider)))
- (llm-batch-embeddings provider chunks)
+ (let ((batches (seq-partition chunks elisa-batch-size)))
+ (flatten-list (mapcar (lambda (batch) (llm-batch-embeddings provider
batch)) batches)))
(mapcar (lambda (chunk) (llm-embedding provider chunk)) chunks))))
(defun elisa-parse-info-manual (name collection-name)
@@ -1265,6 +1270,7 @@ Call ON-DONE callback with result as an argument after
FUNC evaluation done."
,(async-inject-variables "elisa-tar-executable")
,(async-inject-variables "elisa-prompt-rewriting-enabled")
,(async-inject-variables "elisa-batch-embeddings-enabled")
+ ,(async-inject-variables "elisa-batch-size")
,(async-inject-variables "elisa-rewrite-prompt-template")
,(async-inject-variables "elisa-semantic-split-function")
,(async-inject-variables
"elisa-webpage-extraction-function")
