From e301770adc186089b527557b00bc084a81815706 Mon Sep 17 00:00:00 2001 From: Maria Hill Date: Thu, 20 Aug 2026 13:46:41 -0500 Subject: [PATCH] openviking: repoint embedding+vlm api_base :8002->:8001 astro-orbiter llama-server-router retired :8002 on 2026-08-18 (llama-swap now serves the OpenAI-compatible API on :8001). OpenViking still pointed at the dead :8002, so every search/find call failed: dense embedding -> Connection error -> 500 INTERNAL server error on /api/v1/search/search and /api/v1/search/find. Verified from the pod: :8002 = connection refused, :8001/v1/embeddings (nomic-embed-text-v1.5) = 200 with vectors. Repoints embedding.dense.api_base and vlm.api_base to :8001. t_abc05db5 --- cluster/platform/openviking/values.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/cluster/platform/openviking/values.yaml b/cluster/platform/openviking/values.yaml index 3913b37..c4c9b99 100644 --- a/cluster/platform/openviking/values.yaml +++ b/cluster/platform/openviking/values.yaml @@ -140,7 +140,7 @@ config: embedding: dense: provider: "openai" - api_base: "http://astro-orbiter:8002/v1" + api_base: "http://astro-orbiter:8001/v1" api_key: "${OPENVIKING_EMBEDDING_API_KEY}" # Placeholder: "local-nomic" or similar model: "nomic-embed-text-v1.5" dimension: 768 @@ -179,7 +179,7 @@ config: # max_concurrent: 4 (recommend capping background indexing load on shared VLM) # ============================================================================ vlm: - api_base: "http://astro-orbiter:8002/v1" + api_base: "http://astro-orbiter:8001/v1" api_key: "${OPENVIKING_VLM_API_KEY}" # Placeholder: "local-llama" or similar # Fixed 2026-08-15: "llama3.1-8b" does not exist on astro-orbiter's /v1/models # (caused every summarization call to fail with 400 model not found, endless