feat: modify internet search #152
Merged
Conversation
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
fridayL
approved these changes
Jul 24, 2025
tangg555
pushed a commit
to tangg555/MemOS
that referenced
this pull request
Jul 29, 2025
* feat: modify internet search * feat: modify internet search * feat: modify internet search * feat: modify internet search * fix: unittest for tree_searcher * feat: add source to memory key
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Outdated suggestions cannot be applied.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 enhances the Xinyu-based internet retrieval module with improved chunking, deduplication, and integration logic. It also simplifies the retrieval flow in "fine" mode and improves configurability.
Added Sentence-Level Chunking + Embedding
• Integrates SentenceChunker to split result content into semantically meaningful sentence chunks.
• Each chunk is independently embedded and returned as a TextualMemoryItem.
Multi-chunk Result Processing
• Each search result may now generate multiple memory items (based on content chunking).
• _process_result method handles individual results with parallel processing (ThreadPoolExecutor).
Memory-Level Deduplication
• Duplicates are removed based on the memory content field to ensure uniqueness.
Introduced OuterMemory Type
• All retrieved internet items are labeled with memory_type="OuterMemory" for better downstream control and separation.
Extended Config Support
• XinyuSearchConfig now accepts a chunker config (via ChunkerConfigFactory).
• Default search engine switched to Bing (disabled Baidu).
Enhanced Example Script
• tree_textual_memory.py updated with a usage example for mode="fine" and internet-based retrieval.
Removed Legacy Reasoning Step
• Removed reasoner.reason() call from "fine" mode to simplify logic (now pure retrieval + ranking).
Fix: #153
Docs Issue/PR: (docs-issue-or-pr-link)
Reviewer: @fridayL
Checklist: