Skip to content

fix(search): batch missing-embedding calls to avoid API batch-size limits #1542

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
octo-patch wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −1
Open

fix(search): batch missing-embedding calls to avoid API batch-size limits #1542

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
9 changes: 8 additions & 1 deletion src/memos/api/handlers/search_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@

from typing import Any

_EMBED_BATCH_SIZE = 16 # max documents per embedder call to avoid API batch-size limits

from memos.api.handlers.base_handler import BaseHandler, HandlerDependencies
from memos.api.handlers.formatters_handler import rerank_knowledge_mem
from memos.api.product_models import APISearchRequest, SearchResponse
Expand Down Expand Up @@ -446,7 +448,12 @@ def _extract_embeddings(self, memories: list[dict[str, Any]]) -> list[list[float
missing_documents.append(mem.get("memory", ""))

if missing_indices:
computed = self.searcher.embedder.embed(missing_documents)
computed: list[list[float]] = []
for i in range(0, len(missing_documents), _EMBED_BATCH_SIZE):
batch = missing_documents[i : i + _EMBED_BATCH_SIZE]
batch_result = self.searcher.embedder.embed(batch)
if batch_result:
computed.extend(batch_result)
for idx, embedding in zip(missing_indices, computed, strict=False):
embeddings[idx] = embedding
memories[idx]["metadata"]["embedding"] = embedding
Expand Down
Loading