nxtgauge-ai-assistant/.env.example
Ashwin Kumar Sivakumar 4becb73ab0
Some checks failed
build-and-release / build (push) Failing after 1m5s
fix(ci): push image to Forgejo registry and update GitOps repo over HTTPS
The GitOps step relied on GITEOPS_REPO/GITEOPS_SSH_KEY secrets that were
never configured, and the registry login used a REGISTRY_HOSTPORT secret
that doesn't match this repo's actual registry setup. Switch to the
Forgejo registry directly and push the GitOps update over HTTPS with a
token, matching how other services in this org already deploy.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-16 20:33:14 +05:30

28 lines
1,014 B
Text

APP_HOST=0.0.0.0
APP_PORT=8080
RUST_LOG=info
DATABASE_URL=postgres://postgres:postgres@localhost:5432/nxtgauge_ai_assistant
# Local/laptop testing has no access to the in-cluster Ollama instance, so
# default to the LiteLLM gateway (https://llm.nxtgauge.com) instead of raw
# Ollama. Get LITELLM_API_KEY from secret/litellm-secrets in nxtgauge-ai.
LLM_PROVIDER=litellm
LITELLM_BASE_URL=https://llm.nxtgauge.com/v1
LITELLM_API_KEY=
LITELLM_MODEL=askash-main
# Only used when LLM_PROVIDER=ollama (e.g. running Ollama locally yourself).
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_CHAT_MODEL=smollm2:360m
OLLAMA_EMBED_MODEL=nomic-embed-text
HELP_CENTER_SEED_PATH=./seeds/help_articles.json
TICKETS_SOURCE=chatbot
NXTGAUGE_USERS_URL=http://localhost:9101
# Required: must match the JWT signing secret used by nxtgauge-backend-rust,
# and the AI service key nxtgauge-backend-rust expects on X-AI-Service-Key.
# Requests fail closed (401/500) if these are unset, rather than crashing.
JWT_SECRET=
AI_SERVICE_KEY=