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

..

.sqlx

fix: resolve 75 mem-cli compilation errors

2026-09-08 01:11:14 +00:00

migrations

feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48)

2026-09-11 01:11:15 +00:00

src

fix: resolve 75 mem-cli compilation errors

2026-09-08 01:11:14 +00:00

Cargo.toml

test: unskip test_chunk_document + fix compilation errors

2026-09-05 14:58:13 -07:00