From 09606a38d34faf980e7ba7c2f4484ce55cc0fc70 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 14 Jun 2025 19:34:07 -0700
Subject: [PATCH] Truncate web search results to at most 8192 tokens

---
 modules/web_search.py | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/modules/web_search.py b/modules/web_search.py
index ffd7e483..5b14be55 100644
--- a/modules/web_search.py
+++ b/modules/web_search.py
@@ -4,6 +4,7 @@ from datetime import datetime
 
 import requests
 
+from modules import shared
 from modules.logging_colors import logger
 
 
@@ -90,6 +91,22 @@ def perform_web_search(query, num_pages=3, max_workers=5):
         return []
 
 
+def truncate_content_by_tokens(content, max_tokens=8192):
+    """Truncate content to fit within token limit using binary search"""
+    if len(shared.tokenizer.encode(content)) <= max_tokens:
+        return content
+
+    left, right = 0, len(content)
+    while left < right:
+        mid = (left + right + 1) // 2
+        if len(shared.tokenizer.encode(content[:mid])) <= max_tokens:
+            left = mid
+        else:
+            right = mid - 1
+
+    return content[:left]
+
+
 def add_web_search_attachments(history, row_idx, user_message, search_query, state):
     """Perform web search and add results as attachments"""
     if not search_query:
@@ -126,7 +143,7 @@ def add_web_search_attachments(history, row_idx, user_message, search_query, sta
                 "name": result['title'],
                 "type": "text/html",
                 "url": result['url'],
-                "content": result['content']
+                "content": truncate_content_by_tokens(result['content'])
             }
             history['metadata'][key]["attachments"].append(attachment)