Skip to content

docs(mem_reader): sync MemReader backends, fine_transfer, and config fields#429

Open
CaralHsi wants to merge 1 commit intoMemTensor:v2from
CaralHsi:docs/update-mem_reader-20260323
Open

docs(mem_reader): sync MemReader backends, fine_transfer, and config fields#429
CaralHsi wants to merge 1 commit intoMemTensor:v2from
CaralHsi:docs/update-mem_reader-20260323

Conversation

@CaralHsi
Copy link
Copy Markdown
Collaborator

Summary

Align MemReader documentation with current MemOS source code. Updates include:

  • Added explicit backend names (simple_struct, multimodal_struct) to class references
  • Fixed fine_transfer_simple_mem parameter description (expects nested windows, not flat list)
  • Updated read_multi_modal/ parser list to match actual parsers (ImageParser, FileContentParser, ToolParser)
  • Replaced outdated chat_window_max_tokens top-level config with chat_chunker factory config
  • Added undocumented config fields: general_llm, image_parser_llm

Verification

  • All referenced classes exist in code (Check 1)
  • Import paths verified (Check 2)
  • Method signatures match code (Check 3)
  • Config fields match code (Check 4)
  • N/A - no API endpoint changes (Check 5)

Cross-Language

  • Chinese (content/cn/) counterpart needs separate update

Code Reference

Based on MemOS main branch HEAD

Made with Cursor

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant