feat: Enhance File Parsing Pipeline with Chunk-Level Source Tracking & Unified Multi-Modal Parsing#645
Merged
fridayL merged 14 commits intoMemTensor:devfrom Dec 8, 2025
Merged
Conversation
…lPublic into feat/evaluation_doc_qa
…lPublic into feat/evaluation_doc_qa
CaralHsi
changed the title
fridayL
approved these changes
Dec 8, 2025
tianxing02
pushed a commit
to tianxing02/MemOS
that referenced
this pull request
Feb 24, 2026
…& Unified Multi-Modal Parsing (MemTensor#645) * fix: doc fine mode bug * fix: doc fine mode bug * feat: init longbench_v2 * feat: more strict embedder trucation * feat: parallel processing fine mode in multi-modal-fine * feat: update parsers; add chunk info into source; remove origin_part * feat: modify chunk_content in file-fine-parser
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Summary:
This PR focuses on strengthening the multi-modal file-parsing pipeline by establishing a clear, traceable mapping from file → chunk → memory item, while improving consistency and robustness across both fine and fast modes.
Key improvements include:
This update significantly enhances the structure, traceability, and reliability of the file-ingestion pipeline, while unifying multi-modal behavior and preparing the system for upcoming evaluation and doc-QA features.
Fix: #590
Docs Issue/PR: (docs-issue-or-pr-link)
Reviewer: @(reviewer)
Checklist: