7 Commits

Include renames

Author	SHA1	Message	Date
poimenandrock	fb61de6b47	feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48) ... ## Changes ### Entity Extraction - Switch from WikiLinkFallbackExtractor to LlmEntityExtractor when LLM_ENDPOINT set - `clean_llm_response()`: strips `<think>` tags, markdown fences, extracts JSON - Handle array responses (Ollama returns `[...]` not `{entities: [...]}`) - EntityType custom Deserialize: unknown variants → Unknown (no crash) - Increase timeout 30s→90s, max_tokens 500→1500 for reasoning models - Graceful reflection fallback: keep entities if verification fails ### Fact Extraction (NEW) - LlmFactExtractor: LLM-based relationship extraction between entity pairs - Validates source/target against known entity list (drops hallucinated edges) - Same robust JSON cleaning for reasoning models + Ollama - IngestWorker auto-selects LLM vs Simple based on LLM_ENDPOINT env ### K8s Deployment - Add `command: ["/app/mem"]` (fix args replacing CMD) - Add LLM_ENDPOINT, LLM_MODEL env vars for in-cluster LLM ## E2E Tested (local Ollama qwen2.5:3b) - 12 entities extracted (person, tool, concept, organization) - 5 edges with relationships and facts - 781 tests pass ## Zep Paper Alignment (§2.2) - Entity extraction + resolution (§2.2.1) - Fact extraction between entity pairs (§2.2.2) - Temporal edge invalidation ready (t_valid/t_invalid schema) - Reflection verification (§2.2.1, graceful fallback) --------- Co-authored-by: rock <[email protected]> Reviewed-on: #48 Co-authored-by: poimen <[email protected]>	2026-09-11 01:11:15 +00:00
Story Crater Bot	57f87f494a	chore: reduce memory-db cluster from 3 to 2 instances ... CHANGES: - k8s/infra/databases/memory-db.yaml: instances 3 → 2 - Updated comment from '3 instances' to '2 instances' REASONING: - Reduces resource overhead (high availability at 2 is sufficient) - Maintains quorum for failover (minimum 2 for HA) - Saves memory/CPU allocation on homelab cluster - ArgoCD will manage rollout automatically DEPLOYMENT: - ArgoCD will detect spec change and reconcile - CNPG will scale down one pod - Data preserved (3→2 replication, no data loss)	2026-08-28 08:16:02 -07:00
Story Crater Bot	b923e0ad68	feat: M2.2 CNPG memory-db with pgvector (declarative, 3 instances)	2026-08-27 20:39:49 -07:00
Story Crater Bot	9ca988aeb3	Downsize memory-db to 2 instances	2026-08-22 23:53:05 -07:00
Story Crater Bot	af491564cd	Fix: use default longhorn (3 replicas), increase to 20Gi	2026-08-22 23:40:08 -07:00
Story Crater Bot	753435104d	Fix: use longhorn-imessage-local (WaitForFirstConsumer) for stable volume binding	2026-08-22 23:36:25 -07:00
Story Crater Bot	695e115212	Deploy Poimen Memory K8s cluster with ArgoCD tracking (M2.2, M3.5-M3.7)	2026-08-22 23:13:42 -07:00