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

hindsight: move LLM to local astro-orbiter Qwen3.8-27B (off Nous free tier)

Browse Source
This commit is contained in:
Hermes Agent service account
2026-08-28 21:00:47 -05:00
parent 9bfc9384e4
commit 9bc29508d7
1 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
cluster/applications/hindsight/values.yaml
View File

@@ -49,18 +49,19 @@ existingSecret: hindsight-credentials
# ---------------------------------------------------------------------------- # ----------------------------------------------------------------------------
# API container environment (explicit env entries; the chart renders this map # API container environment (explicit env entries; the chart renders this map
# to individual env vars). LLM points at the Nous free-tier inference API # to individual env vars). LLM points at the LOCAL astro-orbiter Qwen node
# (OpenAI-compatible). HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from # (OpenAI-compatible) — moved OFF the Nous free tier (solar-pro4 was 404/dead).
# the existingSecret via envFrom (1Password `nous` item). # HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from the existingSecret
# via envFrom (1Password `nous` item); the local node ignores it but the secret
# still satisfies the chart's envFrom contract.
# ---------------------------------------------------------------------------- # ----------------------------------------------------------------------------
api: api:
env: env:
HINDSIGHT_API_LLM_BASE_URL: "https://inference-api.nousresearch.com/v1" HINDSIGHT_API_LLM_BASE_URL: "http://astro-orbiter:8001/v1"
HINDSIGHT_API_LLM_PROVIDER: "openai" HINDSIGHT_API_LLM_PROVIDER: "openai"
# Primary LLM. Timeout raised to 300s (ingress) so a slow agentic reflect # Primary LLM: local astro-orbiter Qwen3.8-27B-Q4_K_M (LAN-fast, off Nous free tier).
# (~132s on solar-pro4) completes; verified tool-calling + grounded output. HINDSIGHT_API_LLM_MODEL: "Qwen3.8-27B-Q4_K_M"
HINDSIGHT_API_LLM_MODEL: "upstage/solar-pro4:free" # Fallback (documented, NOT deployed): upstage/solar-pro4:free (Nous) — use if the local node is ever down.
# Fallback (documented, NOT deployed): stepfun/step-3.7-flash:free
# ---------------------------------------------------------------------------- # ----------------------------------------------------------------------------
# Ingress via the chart's native template. # Ingress via the chart's native template.