diff --git a/servers/unraid/supermemory-poc/README.md b/servers/unraid/supermemory-poc/README.md index b884c75..af9a534 100644 --- a/servers/unraid/supermemory-poc/README.md +++ b/servers/unraid/supermemory-poc/README.md @@ -48,7 +48,7 @@ image build is required. The server creates its client bearer token at: -`/mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768/api-key` +`/mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768-r2/api-key` Read it through an authorized unRaid/Arcane console without printing it into logs. Save it only as `SUPERMEMORY_API_KEY` in the `supermemory-lab` Hermes @@ -85,7 +85,9 @@ used by Hermes. The earlier local `Xenova/bge-m3` and LiteLLM-backed embedding experiments are preserved under their old data directories because embedding plans cannot be changed in place. This deployment uses the fresh -`data-gemini-embedding-2-768` directory. The one-shot `supermemory-smoke` +`data-gemini-embedding-2-768-r2` directory. The `r2` store rotates the +auto-generated Supermemory client key after the first native-provider +diagnostic exposed the original key in its startup log. The one-shot `supermemory-smoke` service verifies the locked embedding plan, tracks the exact document ID to a terminal state, observes legacy v3 search, gates on v4 document and Chinese hybrid search, checks provenance metadata, and exercises the profile and @@ -100,6 +102,16 @@ document, but both v4 and v3 searches returned no hit. The old smoke mixed list-wide status checks and did not track the newly created document, so this native Gemini run uses a new store and a stricter document-specific gate. +On 2026-09-09, native Gemini direct checks succeeded for both +`gemini-embedding-2` at 768 dimensions and Supermemory's native LLM default. +The v4 `documents` and `hybrid` searches returned the expected Chinese marker +and provenance metadata, while legacy `/v3/search` returned no results. The +self-hosted server-v0.0.8 binary returned 404 for `/v4/conversations`, even +though the self-hosting overview describes that route as part of the full API. +Keep conversation ingest as a failing smoke gate: document RAG can proceed in +isolation, but Hermes auto-capture/session ingest is not validated on this +binary. + ## Evaluation guardrails - Score raw Supermemory API retrieval separately from the Hermes answer. In diff --git a/servers/unraid/supermemory-poc/compose.yaml b/servers/unraid/supermemory-poc/compose.yaml index e0613a7..91e321e 100644 --- a/servers/unraid/supermemory-poc/compose.yaml +++ b/servers/unraid/supermemory-poc/compose.yaml @@ -81,7 +81,7 @@ services: volumes: - /mnt/user/appdata/supermemory-poc/bin:/opt/supermemory/bin:ro - /mnt/user/appdata/supermemory-poc/bin/ca-certificates.crt:/etc/ssl/certs/ca-certificates.crt:ro - - /mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768:/var/lib/supermemory + - /mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768-r2:/var/lib/supermemory networks: br0: ipv4_address: ${SUPERMEMORY_IPV4_ADDRESS:?set an unused LAN address in Arcane environment} @@ -112,7 +112,7 @@ services: - /opt/supermemory-poc/smoke.sh volumes: - ./smoke.sh:/opt/supermemory-poc/smoke.sh:ro - - /mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768:/var/lib/supermemory + - /mnt/user/appdata/supermemory-poc/data-gemini-embedding-2-768-r2:/var/lib/supermemory security_opt: - no-new-privileges:true cap_drop: