klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-05 05:39:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Truncate chat context to max tokens for offline, openai chat actors too

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2024-09-24 12:42:32 -07:00
parent e306e6ca94
commit 61c6e742d5
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/khoj/routers/helpers.py
View File

@@ -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,
)