feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48)
CI / CI (push) Successful in 12m9s
Deploy / Tag & Push Latest (push) Failing after 41s
DB Migration / Run Migrations (push) Failing after 18s

## 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]>
This commit was merged in pull request #48.
This commit is contained in:
2026-09-11 01:11:15 +00:00
committed by rock
co-authored by rock
parent 6b18d81421
commit fb61de6b47
19 changed files with 859 additions and 268 deletions
+35 -9
View File
@@ -1,6 +1,6 @@
# Poimen Memory API Server
# Serves 7 HTTP endpoints for memory ingest, query, and management.
# Connects to memory-db (pgvector) for persistent storage.
# Serves HTTP endpoints for memory ingest, query, visualization.
# Connects to memory-db (pgvector) + api.riotpiao.com (LLM via Authentik JWT).
apiVersion: apps/v1
kind: Deployment
metadata:
@@ -60,13 +60,43 @@ spec:
key: password
- name: DATABASE_URL
value: "postgresql://$(DATABASE_USER):$(DATABASE_PASSWORD)@$(DATABASE_HOST):$(DATABASE_PORT)/$(DATABASE_NAME)?sslmode=disable"
# LLM Gateway API key
# LLM via api.riotpiao.com (Authentik JWT auth)
- name: LLM_ENDPOINT
value: "https://api.riotpiao.com/v1/chat/completions"
- name: LLM_API_BASE
value: "https://api.riotpiao.com/v1"
- name: LLM_MODEL
value: "ornith:35b"
# Authentik service account (memory-agent-oidc secret)
- name: AUTHENTIK_ISSUER
valueFrom:
secretKeyRef:
name: memory-agent-oidc
key: ISSUER
- name: AUTHENTIK_CLIENT_ID
valueFrom:
secretKeyRef:
name: memory-agent-oidc
key: CLIENT_ID
- name: AUTHENTIK_CLIENT_SECRET
valueFrom:
secretKeyRef:
name: memory-agent-oidc
key: CLIENT_SECRET
- name: TOKEN_URL
valueFrom:
secretKeyRef:
name: memory-agent-oidc
key: TOKEN_URL
# Server config
- name: MEM_API_KEY
valueFrom:
secretKeyRef:
name: poimen-memory-secrets
key: llm-api-key
# Server config (from ConfigMap)
- name: MEM_PORT
value: "8080"
- name: MEM_HOME
@@ -74,10 +104,7 @@ spec:
envFrom:
- configMapRef:
name: poimen-memory-config
- secretRef:
name: poimen-memory-auth
- secretRef:
name: poimen-memory-secrets
command: ["/app/mem"]
args:
- serve
- --port
@@ -110,7 +137,6 @@ spec:
- name: tmp
emptyDir:
sizeLimit: 64Mi
# Tolerate control-plane nodes
tolerations:
- key: node-role.kubernetes.io/control-plane
operator: Exists