From 30dbf3256a90aa9c87236ae304db1f3111ad97d2 Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Wed, 7 Oct 2026 13:05:25 +0200
Subject: [PATCH] fix: large files fail to upload when Milvus is the vector
 database (#31990)

With Milvus as the vector database, all chunks of a file were sent to Milvus in one request. Large files exceeded Milvus's default 64 MB request size limit, so processing ran through the whole embedding step and then failed with the error RESOURCE_EXHAUSTED. With a 4096-dimension embedding model this already happened at about 4,000 chunks, which is a few MB of text. Chunks are now sent in batches of 128, with and without ENABLE_MILVUS_MULTITENANCY_MODE.

Fixes #31989
---
 backend/open_webui/retrieval/vector/dbs/milvus.py | 15 +++++++--------
 .../retrieval/vector/dbs/milvus_multitenancy.py   |  3 ++-
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/backend/open_webui/retrieval/vector/dbs/milvus.py b/backend/open_webui/retrieval/vector/dbs/milvus.py
index 0bf4a5955d..2eefb8f67f 100644
--- a/backend/open_webui/retrieval/vector/dbs/milvus.py
+++ b/backend/open_webui/retrieval/vector/dbs/milvus.py
@@ -86,6 +86,11 @@ def _truncate_text(text: str) -> str:
     return text.encode()[:MILVUS_TEXT_MAX_LENGTH].decode(errors='ignore')
 
 
+def _write_in_batches(write: Callable[..., Any], collection_name: str, rows: list[dict]) -> None:
+    for start in range(0, len(rows), BM25_BACKFILL_BATCH_SIZE):
+        write(collection_name=collection_name, data=rows[start : start + BM25_BACKFILL_BATCH_SIZE])
+
+
 def _bm25_rows(rows: list[dict]) -> list[dict]:
     return [
         {
@@ -580,10 +585,7 @@ class MilvusClient(VectorDBBase):
                 row['data'] = {'text': text}
             data.append(row)
         try:
-            return self.client.insert(
-                collection_name=f'{self.collection_prefix}_{collection_name}',
-                data=data,
-            )
+            _write_in_batches(self.client.insert, f'{self.collection_prefix}_{collection_name}', data)
         except MilvusException as e:
             log.error(f'Milvus insert failed for {self.collection_prefix}_{collection_name} ({len(items)} items): {e}')
             raise
@@ -626,10 +628,7 @@ class MilvusClient(VectorDBBase):
                 row['data'] = {'text': text}
             data.append(row)
         try:
-            return self.client.upsert(
-                collection_name=f'{self.collection_prefix}_{collection_name}',
-                data=data,
-            )
+            _write_in_batches(self.client.upsert, f'{self.collection_prefix}_{collection_name}', data)
         except MilvusException as e:
             log.error(f'Milvus upsert failed for {self.collection_prefix}_{collection_name} ({len(items)} items): {e}')
             raise
diff --git a/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py b/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
index d0924fa9ae..b6306b88a5 100644
--- a/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
+++ b/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
@@ -26,6 +26,7 @@ from open_webui.retrieval.vector.dbs.milvus import (
     _metadata_exprs,
     _supports_bm25,
     _truncate_text,
+    _write_in_batches,
 )
 from open_webui.retrieval.vector.main import (
     GetResult,
@@ -237,7 +238,7 @@ class MilvusClient(VectorDBBase):
             )
 
         try:
-            self.client.insert(collection_name=mt_collection, data=entities)
+            _write_in_batches(self.client.insert, mt_collection, entities)
         except MilvusException as e:
             log.error(
                 f'Milvus insert failed (collection={mt_collection}, '