Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adjust NIM endpoint inference endpoints, and adding http endpoints #183

Merged
merged 2 commits into from
Oct 22, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 17 additions & 7 deletions helm/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -73,10 +73,12 @@ replicaCount: 1
## @param resources.requests.memory [default: 16Gi] Specify request for memory
resources:
limits:
memory: 32Gi
memory: 90Gi
nvidia.com/gpu: 1
cpu: "36000m"
requests:
memory: 16Gi
memory: 24Gi
cpu: "16000m"


## @param tmpDirSize [default: 8Gi] Specify the amount of space to reserve for temporary storage
Expand Down Expand Up @@ -253,15 +255,19 @@ redis:
## @skip envVars.REDIS_MORPHEUS_TASK_QUEUE
## @skip envVars.CACHED_GRPC_ENDPOINT
## @skip envVars.CACHED_HTTP_ENDPOINT
## @skip envVars.CACHED_INFER_ENDPOINT
## @skip envVars.PADDLE_GRPC_ENDPOINT
## @skip envVars.PADDLE_HTTP_ENDPOINT
## @skip envVars.PADDLE_INFER_ENDPOINT
## @skip envVars.YOLOX_GRPC_ENDPOINT
## @skip envVars.YOLOX_HTTP_ENDPOINT
## @skip envVars.YOLOX_INFER_ENDPOINT
## @skip envVars.DEPLOT_GRPC_ENDPOINT
## @skip envVars.DEPLOT_HTTP_ENDPOINT
## @skip envVars.DEPLOT_INFER_ENDPOINT
envVars:
MESSAGE_CLIENT_HOST: "nv-ingest-ms-runtime"
MESSAGE_CLIENT_PORT: "7670"
MESSAGE_CLIENT_HOST: "nv-ingest-redis-master"
MESSAGE_CLIENT_PORT: "6379"
REDIS_MORPHEUS_TASK_QUEUE: "morpheus_task_queue"
NV_INGEST_DEFAULT_TIMEOUT_MS: "1234"

Expand All @@ -270,13 +276,17 @@ envVars:
MINIO_BUCKET: nv-ingest

CACHED_GRPC_ENDPOINT: nv-ingest-cached:8001
CACHED_HTTP_ENDPOINT: ""
CACHED_HTTP_ENDPOINT: http://nv-ingest-cached:8000/v1/infer
CACHED_INFER_ENDPOINT: grpc
PADDLE_GRPC_ENDPOINT: nv-ingest-paddle:8001
PADDLE_HTTP_ENDPOINT: ""
PADDLE_HTTP_ENDPOINT: http://nv-ingest-paddle:8000/v1/infer
PADDLE_INFER_PROTOCOL: grpc
YOLOX_GRPC_ENDPOINT: nv-ingest-yolox:8001
YOLOX_HTTP_ENDPOINT: ""
YOLOX_HTTP_ENDPOINT: http://nv-ingest-yolox:8000/v1/infer
YOLOX_INFER_PROTOCOL: grpc
DEPLOT_GRPC_ENDPOINT: ""
DEPLOT_HTTP_ENDPOINT: http://nv-ingest-deplot:8000/v1/chat/completions
DEPLOT_INFER_PROTOCOL: http

EMBEDDING_NIM_ENDPOINT: "http://nv-ingest-embedding:8000/v1"
MILVUS_ENDPOINT: "http://nv-ingest-milvus:19530"
Expand Down
4 changes: 3 additions & 1 deletion src/nv_ingest/api/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
# its affiliates is strictly prohibited.

import logging
import os

from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
Expand All @@ -24,7 +25,8 @@
trace.set_tracer_provider(TracerProvider())
tracer = trace.get_tracer(__name__)

exporter = OTLPSpanExporter(endpoint="otel-collector:4317", insecure=True)
otel_endpoint = os.getenv("OTEL_EXPORTER_OTLP_ENDPOINT", "otel-collector:4317")
exporter = OTLPSpanExporter(endpoint=otel_endpoint, insecure=True)
span_processor = BatchSpanProcessor(exporter)
trace.get_tracer_provider().add_span_processor(span_processor)

Expand Down
Loading