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
+28 -4
View File
@@ -52,13 +52,24 @@ impl AuthentikJwtIssuer {
/// From environment: AUTHENTIK_ISSUER, AUTHENTIK_CLIENT_ID, AUTHENTIK_CLIENT_SECRET
pub fn from_env() -> Result<Self> {
// Support both naming conventions: AUTHENTIK_* and memory-agent-oidc secret keys
let issuer = std::env::var("AUTHENTIK_ISSUER")
.map_err(|_| anyhow!("AUTHENTIK_ISSUER not set"))?;
.or_else(|_| std::env::var("ISSUER"))
.map_err(|_| anyhow!("AUTHENTIK_ISSUER or ISSUER not set"))?;
let client_id = std::env::var("AUTHENTIK_CLIENT_ID")
.map_err(|_| anyhow!("AUTHENTIK_CLIENT_ID not set"))?;
.or_else(|_| std::env::var("CLIENT_ID"))
.map_err(|_| anyhow!("AUTHENTIK_CLIENT_ID or CLIENT_ID not set"))?;
let client_secret = std::env::var("AUTHENTIK_CLIENT_SECRET")
.map_err(|_| anyhow!("AUTHENTIK_CLIENT_SECRET not set"))?;
.or_else(|_| std::env::var("CLIENT_SECRET"))
.map_err(|_| anyhow!("AUTHENTIK_CLIENT_SECRET or CLIENT_SECRET not set"))?;
tracing::info!(
target: "observability",
event = "authentik_jwt_init",
issuer = %issuer,
client_id = %client_id,
"Authentik JWT issuer initialized"
);
Ok(Self::new(&issuer, &client_id, &client_secret))
}
@@ -92,12 +103,25 @@ impl AuthentikJwtIssuer {
let client = reqwest::Client::new();
// Authentik OAuth2 token endpoint
let token_url = format!("{}/token/", self.issuer_url.trim_end_matches('/'));
// Use TOKEN_URL env var if set, otherwise derive from issuer
let token_url = std::env::var("TOKEN_URL")
.or_else(|_| std::env::var("AUTHENTIK_TOKEN_URL"))
.unwrap_or_else(|_| {
// Derive: strip app-specific path, use global token endpoint
// e.g., https://authentik.riotpiao.com/application/o/memory-agent/
// -> https://authentik.riotpiao.com/application/o/token/
if let Some(base) = self.issuer_url.rfind("/o/") {
format!("{}/o/token/", &self.issuer_url[..base])
} else {
format!("{}/token/", self.issuer_url.trim_end_matches('/'))
}
});
let params = [
("grant_type", "client_credentials"),
("client_id", &self.client_id),
("client_secret", &self.client_secret),
("scope", "openid roles"),
];
let response = client