From 024b7a964ba6b3741f5818404f617f150ac2c19d Mon Sep 17 00:00:00 2001
From: Oliver Baer <75138893+mrwind-up-bird@users.noreply.github.com>
Date: Wed, 25 Mar 2026 22:16:24 +0100
Subject: [PATCH] fix(autofix): Unbounded batch processing in embedding

---
 app/services/embedding.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/app/services/embedding.py b/app/services/embedding.py
index 695ffc9..a6f5567 100644
--- a/app/services/embedding.py
+++ b/app/services/embedding.py
@@ -4,6 +4,8 @@
 
 from litellm import aembedding
 
+# Maximum total texts to prevent memory exhaustion
+MAX_TOTAL_TEXTS = 10000
 # Default embedding model — small, fast, cheap
 DEFAULT_EMBEDDING_MODEL = "text-embedding-3-small"
 DEFAULT_EMBEDDING_DIMENSIONS = 1536
@@ -22,6 +24,10 @@ async def embed_texts(
         model: Embedding model name (LiteLLM format). Defaults to text-embedding-3-small.
         api_key: Optional provider API key. If None, uses env vars (OPENAI_API_KEY, etc.).
 
+    
+    # Prevent processing extremely large text collections
+    if len(texts) > MAX_TOTAL_TEXTS:
+        raise ValueError(f"Too many texts to embed: {len(texts)}. Maximum allowed: {MAX_TOTAL_TEXTS}")
     Returns:
         List of embedding vectors (same order as input texts).
     """