mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-15 00:16:46 +00:00
Alex
00be2c05ad
Query embedding moved to the Celery worker, but nothing that ships was updated to consume the queue it dispatches to. - Add `embeddings` to every worker `-Q` list (compose x3, k8s, devcontainer, sandbox README). Without it a search blocked for EMBEDDINGS_DELEGATE_TIMEOUT and then answered with no retrieved context, because classic_rag swallows the dispatch error and skips the source -- bad answers, not an error. - Skip the task_postrun heap reclaim for the embed task. The full gc.collect() was written for docling/torch parses; on a worker holding the ONNX model it measured ~86ms against ~8ms for the embed itself, a 9x slowdown of the round trip for a task that allocates a few kilobytes. - Resolve the installation pin in the re-embed script. It never imports application.app, so an install pinned in app_metadata with no EMBEDDINGS_NAME set -- every stock k8s deployment, whose manifests carry no embedding config -- would rewrite its whole index with the legacy default and stamp sources.model to match, then be told by the boot warning to run it again. - Fail fast for 30s after a failed dispatch. fanout.embed_questions falls back to letting each store embed its own query, so one dead-worker retrieval paid the timeout once in the fan-out and again per source. - Forget the task result. Nothing reads it back: the key is per-dispatch UUID, not content-addressed, so a repeated query mints another. Left alone every search leaked ~17KB for result_expires (7 days) into the Redis the broker shares -- on the bundled k8s manifest (1Gi, no maxmemory policy) that is an OOMKill that takes the broker with it. - Release the model ensure_vector_schema loads to read the width of an unregistered model, in a process that delegates and would never call it. The width still comes from the model, not the table, so the mismatch check the hook exists for keeps working. - Correct the docs that said otherwise: embeddings.md claimed the standard deployment worked unchanged, upgrading.mdx said no action was needed, and the settings table listed none of the three delegation settings.
150 lines
4.0 KiB
YAML
150 lines
4.0 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: docsgpt-api
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: docsgpt-api
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: docsgpt-api
|
|
spec:
|
|
initContainers:
|
|
# Block pod start until Postgres accepts connections. The `postgres-init`
|
|
# Job is responsible for running alembic migrations; this container only
|
|
# waits for the server to be reachable.
|
|
- name: wait-for-postgres
|
|
image: postgres:16-alpine
|
|
command:
|
|
- sh
|
|
- -c
|
|
- |
|
|
until pg_isready -h postgres -p 5432 -U docsgpt -d docsgpt; do
|
|
echo "Waiting for postgres..."; sleep 2;
|
|
done
|
|
containers:
|
|
- name: docsgpt-api
|
|
image: arc53/docsgpt
|
|
ports:
|
|
- containerPort: 7091
|
|
resources:
|
|
limits:
|
|
memory: "4Gi"
|
|
cpu: "2"
|
|
requests:
|
|
memory: "2Gi"
|
|
cpu: "1"
|
|
envFrom:
|
|
- secretRef:
|
|
name: docsgpt-secrets
|
|
env:
|
|
- name: FLASK_APP
|
|
value: "application/app.py"
|
|
- name: DEPLOYMENT_TYPE
|
|
value: "cloud"
|
|
- name: POSTGRES_URI
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: docsgpt-secrets
|
|
key: POSTGRES_URI
|
|
# Disable in-app auto-bootstrap. The `postgres-init` Job under
|
|
# deployment/k8s/jobs/ owns schema creation and Alembic migrations,
|
|
# so application pods must not race with it on rollout.
|
|
- name: AUTO_MIGRATE
|
|
value: "false"
|
|
- name: AUTO_CREATE_DB
|
|
value: "false"
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: docsgpt-worker
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: docsgpt-worker
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: docsgpt-worker
|
|
spec:
|
|
initContainers:
|
|
- name: wait-for-postgres
|
|
image: postgres:16-alpine
|
|
command:
|
|
- sh
|
|
- -c
|
|
- |
|
|
until pg_isready -h postgres -p 5432 -U docsgpt -d docsgpt; do
|
|
echo "Waiting for postgres..."; sleep 2;
|
|
done
|
|
containers:
|
|
- name: docsgpt-worker
|
|
image: arc53/docsgpt
|
|
# `parsing` queue carries read_document/parse_document; required for its await to resolve.
|
|
# For heavy/OCR parsing, run a separate deployment with `-Q parsing` (and GPU env).
|
|
command: ["celery", "-A", "application.app.celery", "worker", "-l", "INFO", "-n", "worker.%h", "-Q", "docsgpt,parsing,embeddings"]
|
|
resources:
|
|
limits:
|
|
memory: "4Gi"
|
|
cpu: "2"
|
|
requests:
|
|
memory: "2Gi"
|
|
cpu: "1"
|
|
envFrom:
|
|
- secretRef:
|
|
name: docsgpt-secrets
|
|
env:
|
|
- name: DEPLOYMENT_TYPE
|
|
value: "cloud"
|
|
- name: API_URL
|
|
value: "http://<your-api-endpoint>"
|
|
- name: POSTGRES_URI
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: docsgpt-secrets
|
|
key: POSTGRES_URI
|
|
# Disable in-app auto-bootstrap. The `postgres-init` Job under
|
|
# deployment/k8s/jobs/ owns schema creation and Alembic migrations,
|
|
# so application pods must not race with it on rollout.
|
|
- name: AUTO_MIGRATE
|
|
value: "false"
|
|
- name: AUTO_CREATE_DB
|
|
value: "false"
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: docsgpt-frontend
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: docsgpt-frontend
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: docsgpt-frontend
|
|
spec:
|
|
containers:
|
|
- name: docsgpt-frontend
|
|
image: arc53/docsgpt-fe
|
|
ports:
|
|
- containerPort: 5173
|
|
resources:
|
|
limits:
|
|
memory: "1Gi"
|
|
cpu: "1"
|
|
requests:
|
|
memory: "256Mi"
|
|
cpu: "100m"
|
|
env:
|
|
- name: VITE_API_HOST
|
|
value: "http://<your-api-endpoint>"
|
|
- name: VITE_API_STREAMING
|
|
value: "true"
|