rblundon/homelab
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

openviking: repoint embedding+vlm api_base :8002->:8001

Browse Source 
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
This commit is contained in:
Maria Hill
2026-08-20 13:46:41 -05:00
parent ab1e32711d
commit e301770adc
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
cluster/platform/openviking/values.yaml
View File

@@ -140,7 +140,7 @@ config:
embedding: embedding:
dense: dense:
provider: "openai" provider: "openai"
api_base: "http://astro-orbiter:8002/v1" api_base: "http://astro-orbiter:8001/v1"
api_key: "${OPENVIKING_EMBEDDING_API_KEY}" # Placeholder: "local-nomic" or similar api_key: "${OPENVIKING_EMBEDDING_API_KEY}" # Placeholder: "local-nomic" or similar
model: "nomic-embed-text-v1.5" model: "nomic-embed-text-v1.5"
dimension: 768 dimension: 768
@@ -179,7 +179,7 @@ config:
# max_concurrent: 4 (recommend capping background indexing load on shared VLM) # max_concurrent: 4 (recommend capping background indexing load on shared VLM)
# ============================================================================ # ============================================================================
vlm: vlm:
api_base: "http://astro-orbiter:8002/v1" api_base: "http://astro-orbiter:8001/v1"
api_key: "${OPENVIKING_VLM_API_KEY}" # Placeholder: "local-llama" or similar api_key: "${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 # 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 # (caused every summarization call to fail with 400 model not found, endless