From 61c6e742d51dbcb4df4aa0af5697e79dc435070d Mon Sep 17 00:00:00 2001
From: Debanjum Singh Solanky <debanjum@gmail.com>
Date: Tue, 24 Sep 2024 12:42:32 -0700
Subject: [PATCH] Truncate chat context to max tokens for offline, openai chat
 actors too

---
 src/khoj/routers/helpers.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/khoj/routers/helpers.py b/src/khoj/routers/helpers.py
index 0fd40e5a..0098526d 100644
--- a/src/khoj/routers/helpers.py
+++ b/src/khoj/routers/helpers.py
@@ -632,6 +632,7 @@ async def send_message_to_model_wrapper(
             messages=truncated_messages,
             loaded_model=loaded_model,
             model=chat_model,
+            max_prompt_size=max_tokens,
             streaming=False,
             response_type=response_type,
         )
@@ -721,6 +722,7 @@ def send_message_to_model_wrapper_sync(
             system_message=system_message,
             model_name=chat_model,
             loaded_model=loaded_model,
+            max_prompt_size=max_tokens,
             vision_enabled=vision_available,
             model_type=conversation_config.model_type,
         )
@@ -729,6 +731,7 @@ def send_message_to_model_wrapper_sync(
             messages=truncated_messages,
             loaded_model=loaded_model,
             model=chat_model,
+            max_prompt_size=max_tokens,
             streaming=False,
             response_type=response_type,
         )
@@ -739,6 +742,7 @@ def send_message_to_model_wrapper_sync(
             user_message=message,
             system_message=system_message,
             model_name=chat_model,
+            max_prompt_size=max_tokens,
             vision_enabled=vision_available,
             model_type=conversation_config.model_type,
         )