106 lines
5.4 KiB
Bash
106 lines
5.4 KiB
Bash
# apps/ai-service configuration — every setting is a field on `Settings` in
|
|
# config.py, which is the authority. Copy to `.env` and edit.
|
|
#
|
|
# cp apps/ai-service/.env.example apps/ai-service/.env
|
|
#
|
|
# Values shown are the CODE DEFAULTS from config.py unless marked otherwise.
|
|
# Production uses `.env.prod`, which is gitignored and lives on the host.
|
|
# Never commit a real secret to this file.
|
|
#
|
|
# Reference: docs/15-configuration.md
|
|
|
|
|
|
# ─── Operating mode ──────────────────────────────────────────────────────────
|
|
# These three decide which runtime graph bootstrap.py builds. See
|
|
# docs/10-rag-orchestration.md.
|
|
|
|
# `cohere-v4` = semantic query embedding against the corpus's own vector space
|
|
# (needs live AWS Bedrock).
|
|
# `disabled` = no retrieval at all. /ready still returns 200 but
|
|
# POST /v1/rag/query returns 503. This is the setting the test
|
|
# suite uses.
|
|
# No other value is accepted — bootstrap.py raises at startup.
|
|
EMBEDDING_PROVIDER=disabled
|
|
|
|
# `disabled` = retrieval-only, single-turn, verbatim source quotes.
|
|
# No RagAgent, no query understanding, no multi-turn.
|
|
# `stub` = runs the whole answer path (prompt, schema parsing,
|
|
# grounding, fallback) with NO cloud call.
|
|
# `bedrock-converse` = DeepSeek / Qwen / GLM / Nova via the Converse API.
|
|
# `bedrock-claude` = Anthropic via the Messages path.
|
|
ANSWER_PROVIDER=disabled
|
|
|
|
# Bedrock model id for the generation/understanding/entailment calls.
|
|
ANSWER_MODEL_ID=deepseek.v3.2
|
|
|
|
|
|
# ─── Vector store ────────────────────────────────────────────────────────────
|
|
QDRANT_URL=http://localhost:6333
|
|
QDRANT_COLLECTION=duocthu_v1
|
|
# Only needed for a Qdrant instance that requires auth. SECRET.
|
|
# QDRANT_API_KEY=
|
|
|
|
# Must match the `dimensions` recorded in the `<collection>__manifest` sidecar,
|
|
# or startup fails with ManifestMismatch and the process does not come up.
|
|
EMBEDDING_DIMENSIONS=1024
|
|
|
|
# Score floor for the dense routes only. The deterministic section route is an
|
|
# exact payload match and never compares against this.
|
|
EVIDENCE_MINIMUM_SCORE=0.12
|
|
|
|
|
|
# ─── PostgreSQL ──────────────────────────────────────────────────────────────
|
|
# Retrieval traces, conversation turns, answer feedback. All three writes are
|
|
# fail-open: an outage degrades memory/tracing, never an answer. SECRET.
|
|
POSTGRES_DSN=postgresql://duoc_thu:duoc_thu@localhost:5432/duoc_thu
|
|
|
|
|
|
# ─── AWS ─────────────────────────────────────────────────────────────────────
|
|
# Credentials come from the standard boto3 chain — in production, the EC2
|
|
# instance's IAM role. Do NOT put AWS keys in this file.
|
|
AWS_REGION=us-east-1
|
|
|
|
# Optional cross-encoder rerank (cohere.rerank-v3-5:0) on the similarity /
|
|
# overview fallback. Fail-open. The section route never reranks.
|
|
RERANK_ENABLED=false
|
|
|
|
|
|
# ─── Per-request budget ──────────────────────────────────────────────────────
|
|
# Checked BETWEEN provider calls; it cannot cancel a call already in flight
|
|
# (that is bounded by read_timeout=20 in adapters/bedrock_converse.py). The
|
|
# browser timeout in ChatPanel.tsx is derived from these — raising them without
|
|
# raising that will make the client give up first.
|
|
MAX_WALL_CLOCK_MS=40000
|
|
MAX_LLM_CALLS_PER_TURN=8
|
|
|
|
|
|
# ─── Drug catalog ────────────────────────────────────────────────────────────
|
|
# Defaults to a repo-relative path resolved from config.py. The container image
|
|
# flattens apps/ai-service/ into its own root, so that default is wrong there
|
|
# and .env.prod must set this explicitly (the Dockerfile bakes the file in):
|
|
# ENTITIES_PATH=./ingestion_data/drug_entities.json
|
|
|
|
|
|
# ─── Observability ───────────────────────────────────────────────────────────
|
|
METRICS_ENABLED=true
|
|
|
|
# Optional bearer token for GET /metrics. Empty = unauthenticated, which is the
|
|
# current production setting and is only safe because ai-service publishes no
|
|
# host port and Caddy proxies only `web`. SET THIS before exposing the service
|
|
# through an Ingress — metrics carry query volumes, provider failure counts and
|
|
# abstain reasons. SECRET.
|
|
METRICS_TOKEN=
|
|
|
|
# Opt-in so a deployment with no collector keeps answering. The Docker and
|
|
# Kubernetes observability profiles turn this on.
|
|
OTEL_ENABLED=false
|
|
OTEL_SERVICE_NAME=ai-service
|
|
OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318/v1/traces
|
|
OTEL_SAMPLE_RATIO=1.0
|
|
|
|
|
|
# ─── Misc ────────────────────────────────────────────────────────────────────
|
|
APP_NAME=vsf-duoc-thu-ai-service
|
|
# Label only; also sent as `deployment.environment` on the OTel resource.
|
|
ENVIRONMENT=local
|