Skip to content

fix(suggestion_handler): split system+user so non-OpenAI LLMs accept the request #1528

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Ptah-CT wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(suggestion_handler): split system+user so non-OpenAI LLMs accept the request #1528

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 15 additions & 2 deletions src/memos/api/handlers/suggestion_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,8 +110,21 @@ def handle_get_suggestion_queries(
if text_mem_results:
memories = "\n".join([m.memory[:200] for m in text_mem_results])

# Generate suggestions using LLM
message_list = [{"role": "system", "content": suggestion_prompt.format(memories=memories)}]
# Generate suggestions using LLM.
# The prompt is split into system+user roles so the request stays
# valid for backends that reject system-only payloads (e.g. MiniMax
# `chat content is empty (2013)`, Anthropic `messages must not be empty`).
# OpenAI accepts either shape, so this is a safe widening.
message_list = [
{
"role": "system",
"content": "You generate suggestion queries based on the user's recent memories.",
},
{
"role": "user",
"content": suggestion_prompt.format(memories=memories),
},
]
response = llm.generate(message_list)
clean_response = clean_json_response(response)
response_json = json.loads(clean_response)
Expand Down