From 4d016c1cb8d08f4928df4f0ab781390453167978 Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Thu, 13 Nov 2025 08:16:06 +0100
Subject: [PATCH] Update env-configuration.mdx

---
 docs/getting-started/env-configuration.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/getting-started/env-configuration.mdx b/docs/getting-started/env-configuration.mdx
index 9b6b61c..3a26607 100644
--- a/docs/getting-started/env-configuration.mdx
+++ b/docs/getting-started/env-configuration.mdx
@@ -2048,7 +2048,7 @@ When configuring `RAG_FILE_MAX_SIZE` and `RAG_FILE_MAX_COUNT`, ensure that the v
 
 - Type: `int`
 - Default: `1`
-- Description: Sets the batch size for embedding in RAG (Retrieval-Augmented Generator) models.
+- Description: Controls how many text chunks are embedded in a single API request when using external embedding providers (Ollama, OpenAI, or Azure OpenAI). Higher values (20-100+; max 16000) process documents faster by sending more API requests, but may exceed API rate limits, while lower values (1-10) are more stable but slower. Default is 1 (safest option if you are API rate limit constrained, but slowest option). This setting only applies to external embedding engines, not the default SentenceTransformers engine.
 - Persistence: This environment variable is a `PersistentConfig` variable.
 
 #### `RAG_EMBEDDING_CONTENT_PREFIX`