diff --git a/docker/.env.example b/docker/.env.example
index 058046596..2b3d10629 100644
--- a/docker/.env.example
+++ b/docker/.env.example
@@ -164,6 +164,7 @@ GID='1000'
# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
# EMBEDDING_BASE_PATH='http://127.0.0.1:4000'
# GENERIC_OPEN_AI_EMBEDDING_API_KEY='sk-123abc'
+# GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS=500
###########################################
######## Vector Database Selection ########
@@ -299,4 +300,4 @@ GID='1000'
# Enable simple SSO passthrough to pre-authenticate users from a third party service.
# See https://docs.anythingllm.com/configuration#simple-sso-passthrough for more information.
-# SIMPLE_SSO_ENABLED=1
\ No newline at end of file
+# SIMPLE_SSO_ENABLED=1
diff --git a/frontend/src/components/EmbeddingSelection/GenericOpenAiOptions/index.jsx b/frontend/src/components/EmbeddingSelection/GenericOpenAiOptions/index.jsx
index e524a263e..84ae4ab8b 100644
--- a/frontend/src/components/EmbeddingSelection/GenericOpenAiOptions/index.jsx
+++ b/frontend/src/components/EmbeddingSelection/GenericOpenAiOptions/index.jsx
@@ -1,4 +1,8 @@
+import React, { useState } from "react";
+import { CaretDown, CaretUp } from "@phosphor-icons/react";
+
export default function GenericOpenAiEmbeddingOptions({ settings }) {
+ const [showAdvancedControls, setShowAdvancedControls] = useState(false);
return (
<div className="w-full flex flex-col gap-y-7">
<div className="w-full flex items-center gap-[36px] mt-1.5 flex-wrap">
@@ -69,6 +73,46 @@ export default function GenericOpenAiEmbeddingOptions({ settings }) {
/>
</div>
</div>
+ <div className="flex justify-start mt-4">
+ <button
+ onClick={(e) => {
+ e.preventDefault();
+ setShowAdvancedControls(!showAdvancedControls);
+ }}
+ className="text-white hover:text-white/70 flex items-center text-sm"
+ >
+ {showAdvancedControls ? "Hide" : "Show"} advanced settings
+ {showAdvancedControls ? (
+ <CaretUp size={14} className="ml-1" />
+ ) : (
+ <CaretDown size={14} className="ml-1" />
+ )}
+ </button>
+ </div>
+ <div hidden={!showAdvancedControls}>
+ <div className="w-full flex items-start gap-4">
+ <div className="flex flex-col w-60">
+ <div className="flex flex-col gap-y-1 mb-4">
+ <label className="text-white text-sm font-semibold flex items-center gap-x-2">
+ Max concurrent Chunks
+ <p className="!text-xs !italic !font-thin">optional</p>
+ </label>
+ </div>
+ <input
+ type="number"
+ name="GenericOpenAiEmbeddingMaxConcurrentChunks"
+ className="bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
+ placeholder="500"
+ min={1}
+ onScroll={(e) => e.target.blur()}
+ defaultValue={settings?.GenericOpenAiEmbeddingMaxConcurrentChunks}
+ required={false}
+ autoComplete="off"
+ spellCheck={false}
+ />
+ </div>
+ </div>
+ </div>
</div>
);
}
diff --git a/server/.env.example b/server/.env.example
index 723b3a644..ba56517a8 100644
--- a/server/.env.example
+++ b/server/.env.example
@@ -154,6 +154,7 @@ SIG_SALT='salt' # Please generate random string at least 32 chars long.
# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
# EMBEDDING_BASE_PATH='http://127.0.0.1:4000'
# GENERIC_OPEN_AI_EMBEDDING_API_KEY='sk-123abc'
+# GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS=500
###########################################
######## Vector Database Selection ########
diff --git a/server/models/systemSettings.js b/server/models/systemSettings.js
index 9bd4a7bf1..dd54b8e36 100644
--- a/server/models/systemSettings.js
+++ b/server/models/systemSettings.js
@@ -193,6 +193,8 @@ const SystemSettings = {
process.env.EMBEDDING_MODEL_MAX_CHUNK_LENGTH,
GenericOpenAiEmbeddingApiKey:
!!process.env.GENERIC_OPEN_AI_EMBEDDING_API_KEY,
+ GenericOpenAiEmbeddingMaxConcurrentChunks:
+ process.env.GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS || 500,
// --------------------------------------------------------
// VectorDB Provider Selection Settings & Configs
diff --git a/server/utils/EmbeddingEngines/genericOpenAi/index.js b/server/utils/EmbeddingEngines/genericOpenAi/index.js
index d3ec30721..f26a070cc 100644
--- a/server/utils/EmbeddingEngines/genericOpenAi/index.js
+++ b/server/utils/EmbeddingEngines/genericOpenAi/index.js
@@ -14,13 +14,26 @@ class GenericOpenAiEmbedder {
});
this.model = process.env.EMBEDDING_MODEL_PREF ?? null;
- // Limit of how many strings we can process in a single pass to stay with resource or network limits
- this.maxConcurrentChunks = 500;
-
+ // this.maxConcurrentChunks is delegated to the getter below.
// Refer to your specific model and provider you use this class with to determine a valid maxChunkLength
this.embeddingMaxChunkLength = 8_191;
}
+ /**
+ * returns the `GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS` env variable as a number
+ * or 500 if the env variable is not set or is not a number.
+ * @returns {number}
+ */
+ get maxConcurrentChunks() {
+ if (!process.env.GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS)
+ return 500;
+ if (
+ isNaN(Number(process.env.GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS))
+ )
+ return 500;
+ return Number(process.env.GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS);
+ }
+
async embedTextInput(textInput) {
const result = await this.embedChunks(
Array.isArray(textInput) ? textInput : [textInput]
diff --git a/server/utils/helpers/updateENV.js b/server/utils/helpers/updateENV.js
index d547930a5..2c4384621 100644
--- a/server/utils/helpers/updateENV.js
+++ b/server/utils/helpers/updateENV.js
@@ -267,6 +267,10 @@ const KEY_MAPPING = {
envKey: "GENERIC_OPEN_AI_EMBEDDING_API_KEY",
checks: [],
},
+ GenericOpenAiEmbeddingMaxConcurrentChunks: {
+ envKey: "GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS",
+ checks: [nonZero],
+ },
// Vector Database Selection Settings
VectorDB: {