Merged
Conversation
Recent updates include: Updated feature request template and documentation links/images Added structure reorganizer and conflict resolver functionality Implemented OpenAI memory integration with evaluation guide Updated memory reader with bug fixes Key changes: Template improvements, new conflict resolution tools, memory system enhancements, and bug fixes.
## Description Bug Fixes: Fixed reorganizer bugs and argument errors Resolved None issue in reorganizer queue Updated Python version constraints New Features: Added support for multiple embedders (Ark/Volcengine, Universal API) Introduced Neo4j database integration and sharing capabilities Added evaluation pipeline (longmemeval) Implemented multi-language support and customizable system prompts Added MCP (Model Context Protocol) server support with client demo Improvements: Enhanced memory management with ID returns and clustering optimizations Simplified user onboarding with basic memos Expanded LLM API support and optimized dependency management Added development tools (download examples, issue templates, stale management) Documentation & DevOps: Updated issue/PR templates and workflows Improved multi-user example implementations with significant additions to embedding support, database backends, and user experience improvements.
…ctions in nebula; fix example
fridayL
approved these changes
Jul 27, 2025
Collaborator
fridayL
left a comment
fridayL
left a comment
There was a problem hiding this comment.
High-Level Summary
Adds NebulaGraph support alongside Neo4j backends.
Introduces a new configuration class for NebulaGraph.
Updates the factory and config systems to recognize the new backend.
Refactors and improves error handling and logging in several modules.
Bumps embedding dimensions from 768 to 3072 (likely for compatibility with new OpenAI embedding models).
Includes one new example script and a new backend implementation file.
Key Changes
- NebulaGraph Integration
New class: NebulaGraphDBConfig in src/memos/configs/graph_db.py for NebulaGraph-specific configuration (e.g., space, user_name, multi-db logic, embedding dimension).
GraphDBConfigFactory and GraphStoreFactory now map "nebular" to the new Nebula classes.
New backend implementation file: src/memos/graph_dbs/nebular.py (file added, content not shown in diff).
Example usage in examples/basic_modules/nebular_example.py. - Embedding Dimension Update
In multiple places in examples/basic_modules/neo4j_example.py, changes embedding dimension from 768 to 3072.
Updates related config fields to reflect the new default. - Improved Error Handling and Logging
In relation_reason_detector.py and reorganizer.py, error handling now logs full traceback information for easier debugging.
Refactors logic to better structure error handling and result returns. - API/Signature Changes
BaseGraphDB.get_by_metadata() changes its parameter from a dict to a list of dicts (likely for more complex filtering).
Adds new abstract method: get_structure_optimization_candidates()—intended to identify graph nodes for structure optimization. - Other Tweaks
Extends memory type support in Neo4j backend to include "OuterMemory".
Refines some edge naming conventions (e.g., “AGGREGATE_TO” instead of “AGGREGATES”).
Adds example usage of OpenAI’s new API endpoints for embeddings (via environment variables).
Review Comments
Strengths
Clean modular addition of a new backend—follows project conventions.
Good use of config factories and backend mapping for extensibility.
Improved error handling and diagnostics.
Embedding dimension update aligns with newer model standards.
Suggestions & Questions
Testing & Docs: Please ensure the new NebulaGraph backend and examples are covered by tests and documentation, especially since this adds a new database engine.
Migration: Existing users may be affected by the embedding dimension change (768→3072). Consider adding a migration note or supporting both dimensions for backward compatibility.
Config Consistency: “nebular” is the backend string—confirm if the backend should be “nebular” or “nebula” for clarity.
Edge Naming: Changing “AGGREGATES” to “AGGREGATE_TO” may affect downstream consumers; note this in changelogs.
Security: Avoid defaulting to placeholder API keys (“sk-xxxxx”) for production usage; remind users to set proper secrets.
New File Content: The new files (nebular.py, nebular_example.py) are added but not shown in the diff. Please ensure these are complete and follow codebase standards
tangg555
pushed a commit
to tangg555/MemOS
that referenced
this pull request
Jul 29, 2025
* feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: docker settings modify * Update tree_config.json * Update simple_openapi_memos.py * feat: docker settings modify * feat: support nebular database * Update Dockerfile * Update docker-compose.yml * Update tree_config.json * Update simple_openapi_memos.py * Rename .env.example to docker/.env.example * feat: update requirement.txt * feat: update requirement.txt * feat: update requirement.txt * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: fix multi-tanant bug for nebula; add create index; fix some functions in nebula; fix example * fix: search bug; * fix index and multi-db-name * feat: finish get-by-metadata in nebula * feat: finish get_structure_optimization_candidates * fix: return value in nebula * feat: fix all nebula issue * feat: create pool connecting * fix: reorganize bug * add several edge types to nebula * feat: change edge name in nebula * fix: bug for graph not found * fix: fail to create db bug * delete test nebula in temp * fix: no node_not_exist bug --------- Co-authored-by: chunyu li <[email protected]> Co-authored-by: stx <[email protected]> Co-authored-by: Tianxing Shi <[email protected]>
tianxing02
added a commit
to tianxing02/MemOS
that referenced
this pull request
Feb 24, 2026
* feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: one-click deployment with docker * feat: docker settings modify * Update tree_config.json * Update simple_openapi_memos.py * feat: docker settings modify * feat: support nebular database * Update Dockerfile * Update docker-compose.yml * Update tree_config.json * Update simple_openapi_memos.py * Rename .env.example to docker/.env.example * feat: update requirement.txt * feat: update requirement.txt * feat: update requirement.txt * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: support nebular database * feat: fix multi-tanant bug for nebula; add create index; fix some functions in nebula; fix example * fix: search bug; * fix index and multi-db-name * feat: finish get-by-metadata in nebula * feat: finish get_structure_optimization_candidates * fix: return value in nebula * feat: fix all nebula issue * feat: create pool connecting * fix: reorganize bug * add several edge types to nebula * feat: change edge name in nebula * fix: bug for graph not found * fix: fail to create db bug * delete test nebula in temp * fix: no node_not_exist bug --------- Co-authored-by: chunyu li <[email protected]> Co-authored-by: stx <[email protected]> Co-authored-by: Tianxing Shi <[email protected]>
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
3 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: (summary)
Fix: #(issue)
Docs Issue/PR: (docs-issue-or-pr-link)
Reviewer: @(reviewer)
Checklist: