sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 15:38:55 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

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
Show stats 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,
)