adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,265 Commits 37 Branches 16 Tags
d66d601e41d2e3279c588d87d045fe05d5e5c8f6
Commit Graph

22 Commits

Author SHA1 Message Date
lanceyq
4af9b02815 feat(memory): propagate temporal validity fields through extraction pipeline 
- Add valid_at/invalid_at passthrough in triplet extraction prompt (both zh/en)
- Propagate temporal_validity to EntityEntityEdge in ExtractionOrchestrator
- Use coalesce() for valid_at/invalid_at in Neo4j cypher queries to handle NULLs
- Fix workspace_id/config_id UUID parsing in read_memory config resolution
- Downgrade verbose extraction pipeline logs from info to debug
- Remove UUID and short API key patterns from sensitive filter to reduce false positives
- Standardize log message format (use = spacing, end_user_id label)
- Fix misindented TODO comment in write_pipeline.py
 2026-05-08 11:26:24 +08:00
lanceyq
7747ed7ac1 refactor(memory): enhance extraction ontology and add assistant pruning graph support 
- Expand entity type ontology with detailed definitions, examples, and notes
  (merged types: 地点设施, 物品设备, 产品服务, 软件平台, 角色职业, 知识能力, 偏好习惯目标, 称呼别名, 智能体)
- Add relation ontology taxonomy with 15 predicate categories and usage rules
- Strengthen reference resolution rules: resolve pronouns before extraction,
  skip unresolvable references entirely
- Add guidelines to avoid extracting abstract propositions, emotions, and
  low-value entities (effort/reward/success patterns)
- Add 7 new extraction examples covering edge cases
- Add AssistantOriginal/AssistantPruned node models and graph persistence
  (PRUNED_TO and BELONGS_TO_DIALOG edges, Neo4j indexes and constraints)
- Add graph_build_step.py for building graph nodes/edges from DialogData
- Update write_pipeline.py to pass assistant pruning nodes/edges to graph saver
- Update data_pruning.py with related preprocessing changes
 2026-05-08 11:26:24 +08:00
lanceyq
2355536b44 refactor(memory): add PilotWritePipeline and enrich extraction schema 
- Add dedicated PilotWritePipeline (statement → triplet → graph_build → layer-1 dedup, no Neo4j write)
- Add type_description/predicate_description fields across entity and triplet models, Cypher queries, and graph builders
- Refactor data_pruning with LRU cache and snapshot support; skip assistant chunks in extraction
- Remove strict Predicate enum whitelist; support statement_text alias in legacy extractor
- Wire PipelineSnapshot through preprocessing and emotion extraction for debug tracing
- Add PILOT_RUN_USE_REFACTORED_PIPELINE env toggle for pipeline selection
 2026-05-08 11:26:04 +08:00
lanceyq
627d6a0381 fix : add comments 2026-04-10 10:43:43 +08:00
lanceyq
15a863b41a feat(memory): unify alias extraction into metadata pipeline and deduplicate user entity nodes 
- Merge alias add/remove into MetadataExtractionResponse and Celery metadata task,
  removing the separate sync step from extraction_orchestrator
- Replace first-person pronouns ("我") with "用户" in statement extraction to
  preserve identity semantics for downstream metadata/alias extraction
- Update extract_statement.jinja2 prompt to enforce "用户" as subject for user
  statements instead of resolving to real names
- Add alias change instructions (aliases_to_add/aliases_to_remove) to
  extract_user_metadata.jinja2 with incremental merge logic
- Deduplicate special entities ("用户", "AI助手") in graph_saver by reusing
  existing Neo4j node IDs per end_user_id
- Sync final aliases from PgSQL to Neo4j user entity nodes after metadata write
 2026-04-09 21:55:59 +08:00
Eternity
89d188fbf3 Merge branch 'develop' into feature/multimodel_memory 
# Conflicts:
#	api/app/core/memory/storage_services/extraction_engine/knowledge_extraction/embedding_generation.py
#	api/app/repositories/neo4j/add_nodes.py
#	api/app/repositories/neo4j/cypher_queries.py
#	api/app/repositories/neo4j/graph_saver.py
#	api/app/services/memory_agent_service.py
#	api/app/services/multimodal_service.py
 2026-03-24 14:15:18 +08:00
Eternity
6bba574ca6 feat(memory, model): update multi-modal memory write and model list API 
- Adjust multi-modal memory write behavior for text and visual data
- Mask API keys in model list response to prevent exposure
- Add capability-based filtering to the model list API
 2026-03-24 13:54:15 +08:00
lanceyq
31b8a3764e 【change】 1.Standardize log specifications；2.Cluster settings trigger explicitly 2026-03-23 16:38:47 +08:00
Ke Sun
78316de411 Merge pull request #660 from SuanmoSuanyangTechnology/fix/remove-redundancies 
[changes] Remove the unused config_id
 2026-03-20 20:50:57 +08:00
lanceyq
e3795fe1ed [changes] Remove the unused config_id 2026-03-20 20:43:29 +08:00
lanceyq
72a2f2a7e8 [add] Introduce examples and triples to enrich the community summaries 2026-03-20 20:19:44 +08:00
lanceyq
f9fb480cc3 [changes] Community Clustering Retrieval Module 2026-03-16 13:38:38 +08:00
lanceyq
382e4c5377 [changes] The user's personal configuration and the clustering trigger boundary are clearly defined 2026-03-13 18:02:23 +08:00
lanceyq
6d8b1aede4 [add] Create the attribute values of the community nodes 2026-03-13 15:47:05 +08:00
lanceyq
db8257b67a [add] Create community nodes 2026-03-13 15:47:04 +08:00
Mark
7b72bf0cd0 Merge branch 'release/v0.2.3' into develop 
# Conflicts:
#	api/app/core/agent/langchain_agent.py
#	api/app/core/memory/agent/langgraph_graph/write_graph.py
#	api/app/repositories/neo4j/graph_saver.py
#	api/app/services/draft_run_service.py
 2026-02-06 14:48:50 +08:00
lixinyue11
c1941809e9 Fix/develop memory bug (#336) 
* 遗漏的历史映射

* 遗漏的历史映射

* fix_timeline_memories

* fix_timeline_memories

* write_gragp/bug_fix

* write_gragp/bug_fix

* write_gragp/bug_fix

* write_gragp/bug_fix

* Multiple independent transactions - single transaction

* memory_content ->memory_config_id

* memory_content ->memory_config_id
 2026-02-06 11:42:02 +08:00
lixinyue11
3364374dc6 Write Missing None (#321) 
* Write Missing None

* Write Missing None

* Write Missing None

* Apply suggestion from @sourcery-ai[bot]

Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>

* Write Missing None

---------

Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
 2026-02-05 10:50:10 +08:00
lixinyue
657d48a5f9 Multiple independent transactions - single transaction 2026-02-04 20:25:45 +08:00
lixinyue
3f906d81cb Multiple independent transactions - single transaction 2026-02-04 20:19:04 +08:00
lixinyue11
3601737869 Fix/memory bug fix (#171) 2026-01-26 11:53:34 +08:00
Ke Sun
c1adc62ec6 feat: Add base project structure with API and web components 2025-12-02 20:28:01 +08:00