Skip to content

fix: The "tags" lack the key words related to the memory content. #999

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
whipser030 wants to merge 4 commits into
base: dev-20260202-v2.0.5
Choose a base branch
from
Open

fix: The "tags" lack the key words related to the memory content. #999

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3bd0959
fix: add fileurl to memoryvalue
Feb 2, 2026
55bb67d
Extract the phrases from the key and input them into the tags.
Feb 2, 2026
79f0d39
Merge branch 'dev-20260202-v2.0.5' into dev-20260202-v2.0.5_test
Feb 2, 2026
deb66c2
Merge branch 'dev-20260202-v2.0.5' into dev-20260202-v2.0.5_test
Feb 3, 2026
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
2 changes: 2 additions & 0 deletions src/memos/mem_reader/read_multi_modal/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
TextualMemoryItem,
TreeNodeTextualMemoryMetadata,
)
from memos.memories.textual.tree_text_memory.retrieve.retrieve_utils import FastTokenizer
from memos.utils import timed

from .utils import detect_lang, get_text_splitter
Expand Down Expand Up @@ -90,6 +91,7 @@ def __init__(self, embedder, llm=None):
"""
self.embedder = embedder
self.llm = llm
self.tokenizer = FastTokenizer(use_jieba=True, use_stopwords=True)

@abstractmethod
def create_source(
Expand Down
7 changes: 6 additions & 1 deletion src/memos/mem_reader/read_multi_modal/file_content_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -710,7 +710,7 @@ def _make_fallback(
chunk_idx: int, chunk_text: str, reason: str = "raw"
) -> TextualMemoryItem:
"""Create fallback memory item with raw chunk text."""
return _make_memory_item(
raw_chunk_mem = _make_memory_item(
value=chunk_text,
tags=[
"mode:fine",
Expand All @@ -721,6 +721,11 @@ def _make_fallback(
chunk_idx=chunk_idx,
chunk_content=chunk_text,
)
tags_list = self.tokenizer.tokenize_mixed(raw_chunk_mem.metadata.key)
tags_list = [tag for tag in tags_list if len(tag) > 1]
tags_list = sorted(tags_list, key=len, reverse=True)
raw_chunk_mem.metadata.tags.extend(tags_list[:5])
return raw_chunk_mem

# Handle empty chunks case
if not valid_chunks:
Expand Down