Skip to content

Commit

Permalink
Remove references to ea-participants private registry (NVIDIA#411)
Browse files Browse the repository at this point in the history 
Remove references to ea-participants, add Python 3.10 support only, add missing NIM_NGC_API_KEY
  • Loading branch information
@nkmcalli
nkmcalli authored Feb 7, 2025
1 parent 799f469 commit 87206ed
Show file tree
Hide file tree
Showing 5 changed files with 43 additions and 33 deletions.
14 changes: 10 additions & 4 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,8 @@ A service that:
- [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) (NVIDIA Driver >= `535`, CUDA >= `12.2`)
- [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)

> [!Note]
> You install Python in a later step. NVIDIA-Ingest only supports [Python version 3.10](https://www.python.org/downloads/release/python-3100/).
## Quickstart

Expand Down Expand Up @@ -90,13 +92,17 @@ Password: <Your Key>
```

> [!NOTE]
> during the early access (EA) phase, your API key must be created as a member of `nemo-microservice / ea-participants` which you may join by applying for early access here: https://developer.nvidia.com/nemo-microservices-early-access/join. When approved, switch your profile to this org / team, then the key you generate will have access to the resources outlined below.
> During the early access (EA) phase, you must apply for early access here: https://developer.nvidia.com/nemo-microservices-early-access/join.
> When your early access is approved, follow the instructions in the email to create an organization and team, link your profile, and generate your NGC API key.
4. Create a .env file that contains your NGC API keys. For more information, refer to [](docs/docs/user-guide/developer-guide/environment-config.md).

4. Create a .env file containing your NGC API key, and the following paths:
```
# Container images must access resources from NGC.
NGC_API_KEY=... # Optional, set this if you are deploying NIMs locally from NGC
NVIDIA_BUILD_API_KEY=... # Optional, set this is you are using build.nvidia.com NIMs
NGC_API_KEY=<key to download containers from NGC>
NIM_NGC_API_KEY=<key to download model files after containers start>
NVIDIA_BUILD_API_KEY=<key to use NIMs that are hosted on build.nvidia.com>
```

> [!NOTE]
Expand Down
41 changes: 17 additions & 24 deletions deploy/pdf-blueprint.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -148,35 +148,28 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES\n",
"c4a41bd9d958 zilliz/attu:v2.3.5 \"docker-entrypoint.s…\" 38 seconds ago Up 35 seconds 0.0.0.0:3001->3000/tcp, [::]:3001->3000/tcp milvus-attu\n",
"62de6f97826b milvusdb/milvus:v2.4.9-gpu \"/tini -- milvus run…\" 38 seconds ago Up 35 seconds (healthy) 0.0.0.0:9091->9091/tcp, :::9091->9091/tcp, 0.0.0.0:19530->19530/tcp, :::19530->19530/tcp milvus-standalone\n",
"7d35d9906139 nvcr.io/ohlfw0olaadg/ea-participants/cached:0.2.0 \"/opt/nvidia/nvidia_…\" 38 seconds ago Up 35 seconds 0.0.0.0:8006->8000/tcp, [::]:8006->8000/tcp, 0.0.0.0:8007->8001/tcp, [::]:8007->8001/tcp, 0.0.0.0:8008->8002/tcp, [::]:8008->8002/tcp nv-ingest-cached-1\n",
"935bdcaed4c2 nvcr.io/nim/nvidia/nv-embedqa-e5-v5:1.1.0 \"/opt/nvidia/nvidia_…\" 38 seconds ago Up 35 seconds 0.0.0.0:8012->8000/tcp, [::]:8012->8000/tcp, 0.0.0.0:8013->8001/tcp, [::]:8013->8001/tcp, 0.0.0.0:8014->8002/tcp, [::]:8014->8002/tcp nv-ingest-embedding-1\n",
"7757c5b9d91d nvcr.io/ohlfw0olaadg/ea-participants/deplot:1.0.0 \"/opt/nvidia/nvidia_…\" 38 seconds ago Up 36 seconds 0.0.0.0:8003->8000/tcp, [::]:8003->8000/tcp, 0.0.0.0:8004->8001/tcp, [::]:8004->8001/tcp, 0.0.0.0:8005->8002/tcp, [::]:8005->8002/tcp nv-ingest-deplot-1\n",
"d06efa8b41e4 nvcr.io/ohlfw0olaadg/ea-participants/nv-yolox-structured-images-v1:0.2.0 \"/opt/nvidia/nvidia_…\" 38 seconds ago Up 35 seconds 0.0.0.0:8000-8002->8000-8002/tcp, :::8000-8002->8000-8002/tcp nv-ingest-yolox-1\n",
"915a823ddd12 nvcr.io/ohlfw0olaadg/ea-participants/paddleocr:0.2.0 \"/opt/nvidia/nvidia_…\" 38 seconds ago Up 36 seconds 0.0.0.0:8009->8000/tcp, [::]:8009->8000/tcp, 0.0.0.0:8010->8001/tcp, [::]:8010->8001/tcp, 0.0.0.0:8011->8002/tcp, [::]:8011->8002/tcp nv-ingest-paddle-1\n",
"3daba715acbb nvcr.io/ohlfw0olaadg/ea-participants/nv-ingest:24.10.1 \"/opt/conda/envs/nv_…\" 38 seconds ago Up 36 seconds (health: starting) 0.0.0.0:7670-7671->7670-7671/tcp, :::7670-7671->7670-7671/tcp nv-ingest-nv-ingest-ms-runtime-1\n",
"2eed8df71ae9 quay.io/coreos/etcd:v3.5.5 \"etcd -advertise-cli…\" 38 seconds ago Up 37 seconds (healthy) 2379-2380/tcp milvus-etcd\n",
"52d833abcb3e openzipkin/zipkin \"start-zipkin\" 38 seconds ago Up 37 seconds (healthy) 9410/tcp, 0.0.0.0:9411->9411/tcp, :::9411->9411/tcp nv-ingest-zipkin-1\n",
"5164160eb3f2 minio/minio:RELEASE.2023-03-20T20-16-18Z \"/usr/bin/docker-ent…\" 38 seconds ago Up 37 seconds (healthy) 0.0.0.0:9000-9001->9000-9001/tcp, :::9000-9001->9000-9001/tcp minio\n",
"0c78b48918d7 redis/redis-stack \"/entrypoint.sh\" 38 seconds ago Up 36 seconds 0.0.0.0:6379->6379/tcp, :::6379->6379/tcp, 8001/tcp nv-ingest-redis-1\n",
"6e4459be6502 grafana/grafana \"/run.sh\" 38 seconds ago Up 37 seconds 0.0.0.0:3000->3000/tcp, :::3000->3000/tcp grafana-service\n",
"1bb7b27d4f45 verb-workspace \"/tini -- supervisor…\" 16 minutes ago Up 16 minutes 127.0.0.1:8887->8887/tcp, 0.0.0.0:2222->22/tcp, [::]:2222->22/tcp verb-workspace\n"
]
}
],
"outputs": [],
"source": [
"!docker ps"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"After you run `docker ps` you should see output similar to the following that lists your container images and the status of each. If any status includes `starting`, wait for the container to start before you proceed.\n",
"\n",
"```text\n",
"CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS \n",
"9869e432cc04 zilliz/attu:v2.3.5 \"docker-entrypoint.s…\" About an hour ago Up About an hour 0.0.0.0:3001...\n",
"e02baf85ccc5 otel/opentelemetry-collector-contrib:0.91.0 \"/otelcol-contrib --…\" About an hour ago Up About an hour 0.0.0.0:4317...\n",
"4c3be36de11b milvusdb/milvus:v2.5.3-gpu \"/tini -- milvus run…\" About an hour ago Up About an hour (healthy) 0.0.0.0:9091...\n",
"...\n",
"```\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
Expand Down
4 changes: 2 additions & 2 deletions docs/docs/user-guide/developer-guide/environment-config.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -61,8 +61,8 @@

- **`NVIDIA_BUILD_API_KEY`**:
- **Description**: This key is for when you are using the build.nvidia.com endpoint instead of a self hosted Deplot NIM.
This is necessary only in some cases when it is different from `NGC_API_KEY`. If this is not specified, `NGC_API_KEY` will be used for bulid.nvidia.com.
This is necessary only in some cases when it is different from `NGC_API_KEY`. If this is not specified, `NGC_API_KEY` is used for build.nvidia.com.

- **`NIM_NGC_API_KEY`**:
- **Description**: This key is by NIM microservices inside docker containers to access NGC resources.
This is necessary only in some cases when it is different from `NGC_API_KEY`. If this is not specified, `NGC_API_KEY` will be used to access NGC resources.
This is necessary only in some cases when it is different from `NGC_API_KEY`. If this is not specified, `NGC_API_KEY` is used to access NGC resources.
3 changes: 3 additions & 0 deletions docs/docs/user-guide/getting-started/prerequisites.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,3 +16,6 @@ Before you begin using NVIDIA-Ingest, ensure the following hardware and software
- [Docker Compose](https://docs.docker.com/compose/install/)
- [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) (NVIDIA Driver >= `535`, CUDA >= `12.2`)
- [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)

> [!Note]
> You install Python later. NVIDIA-Ingest only supports [Python version 3.10](https://www.python.org/downloads/release/python-3100/).
14 changes: 11 additions & 3 deletions docs/docs/user-guide/getting-started/quickstart-guide.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,12 +28,20 @@ Username: $oauthtoken
Password: <Your Key>
```

> **NOTE:** During the early access (EA) phase, your API key must be created as a member of `nemo-microservice / ea-participants` that you might join by applying for early access [here:](https://developer.nvidia.com/nemo-microservices-early-access/join). When approved, switch your profile to this organization or team. Then, the key you generate will have access to the resources outlined below.
> [!NOTE]
> During the early access (EA) phase, you must apply for early access here: https://developer.nvidia.com/nemo-microservices-early-access/join.
> When your early access is approved, follow the instructions in the email to create an organization and team, link your profile, and generate your NGC API key.

4. Create a .env file containing your NGC API key and the following paths. For more information, refer to [](../developer-guide/environment-config.md).

4. Create a .env file containing your NGC API key and the following paths:
```
# Container images must access resources from NGC.
NGC_API_KEY=...
NGC_API_KEY=<key to download containers from NGC>
NIM_NGC_API_KEY=<key to download model files after containers start>
NVIDIA_BUILD_API_KEY=<key to use NIMs that are hosted on build.nvidia.com>
DATASET_ROOT=<PATH_TO_THIS_REPO>/data
NV_INGEST_ROOT=<PATH_TO_THIS_REPO>
```
Expand Down

0 comments on commit 87206ed

Please sign in to comment.