Skip to content
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
2 changes: 1 addition & 1 deletion docker-compose.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -262,7 +262,7 @@ services:
- audio

nv-ingest-ms-runtime:
image: nvcr.io/nvidia/nemo-microservices/nv-ingest:26.03.0-RC1
image: nvcr.io/nvidia/nemo-microservices/nv-ingest:26.03.0-RC2
shm_size: 40gb # Should be at minimum 30% of assigned memory per Ray documentation
build:
context: ${NV_INGEST_ROOT:-.}
Expand Down
2 changes: 1 addition & 1 deletion docs/docs/extraction/helm.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,4 +3,4 @@
<!-- Use this documentation to deploy [NeMo Retriever Library](overview.md) by using Helm. -->

To deploy [NeMo Retriever Library](overview.md) by using Helm,
refer to [NeMo Retriever Helm Charts](https://github.com/NVIDIA/NeMo-Retriever/blob/release/26.03.0-RC1/helm/README.md).
refer to [NeMo Retriever Helm Charts](https://github.com/NVIDIA/NeMo-Retriever/blob/release/26.03.0-RC2/helm/README.md).
2 changes: 1 addition & 1 deletion docs/docs/extraction/quickstart-guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ h. Run the command `docker ps`. You should see output similar to the following.
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
uv venv --python 3.12 nv-ingest-dev
source nv-ingest-dev/bin/activate
uv pip install nv-ingest==26.03.0-RC1 nv-ingest-api==26.03.0-RC1 nv-ingest-client==26.03.0-RC1
uv pip install nv-ingest==26.03.0-RC2 nv-ingest-api==26.03.0-RC2 nv-ingest-client==26.03.0-RC2
```

!!! tip
Expand Down
2 changes: 1 addition & 1 deletion docs/docs/extraction/quickstart-library-mode.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ Use the following procedure to prepare your environment.
```
uv venv --python 3.12 nvingest && \
source nvingest/bin/activate && \
uv pip install nemo-retriever==26.03.0-RC1 milvus-lite==2.4.12
uv pip install nemo-retriever==26.03.0-RC2 milvus-lite==2.4.12
```

!!! tip
Expand Down
2 changes: 1 addition & 1 deletion helm/Chart.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ apiVersion: v2
name: nv-ingest
description: NV-Ingest Microservice
type: application
version: 26.03.0-RC1
version: 26.03.0-RC2
maintainers:
- name: NVIDIA Corporation
url: https://www.nvidia.com/
Expand Down
88 changes: 44 additions & 44 deletions helm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ To install or upgrade the Helm chart, run the following code.
helm upgrade \
--install \
nv-ingest \
https://helm.ngc.nvidia.com/nvidia/nemo-microservices/charts/nv-ingest-26.03.0-RC1.tgz \
https://helm.ngc.nvidia.com/nvidia/nemo-microservices/charts/nv-ingest-26.03.0-RC2.tgz \
-n ${NAMESPACE} \
--username '$oauthtoken' \
--password "${NGC_API_KEY}" \
Expand All @@ -54,7 +54,7 @@ helm upgrade \
--set ngcApiSecret.create=true \
--set ngcApiSecret.password="${NGC_API_KEY}" \
--set image.repository="nvcr.io/nvidia/nemo-microservices/nv-ingest" \
--set image.tag="26.03.0-RC1"
--set image.tag="26.03.0-RC2"
```

Optionally you can create your own versions of the `Secrets` if you do not want to use the creation via the helm chart.
Expand Down Expand Up @@ -105,7 +105,7 @@ For more information, refer to [NV-Ingest-Client](https://github.com/NVIDIA/nv-i
# Just to be cautious we remove any existing installation
pip uninstall nv-ingest-client

pip install nv-ingest-client==26.03.0-RC1
pip install nv-ingest-client==26.03.0-RC2
```

#### Rest Endpoint Ingress
Expand Down Expand Up @@ -347,7 +347,7 @@ You can also use NV-Ingest's Python client API to interact with the service runn
| fullnameOverride | string | `""` | |
| image.pullPolicy | string | `"IfNotPresent"` | |
| image.repository | string | `"nvcr.io/nvidia/nemo-microservices/nv-ingest"` | |
| image.tag | string | `"26.03.0-RC1"` | |
| image.tag | string | `"26.03.0-RC2"` | |
| imagePullSecrets[0].name | string | `"ngc-api"` | |
| imagePullSecrets[1].name | string | `"ngc-secret"` | |
| ingress.annotations | object | `{}` | |
Expand Down Expand Up @@ -465,46 +465,6 @@ You can also use NV-Ingest's Python client API to interact with the service runn
| nimOperator.graphic_elements.storage.pvc.create | bool | `true` | |
| nimOperator.graphic_elements.storage.pvc.size | string | `"25Gi"` | |
| nimOperator.graphic_elements.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.rerankqa.authSecret | string | `"ngc-api"` | |
| nimOperator.rerankqa.enabled | bool | `false` | |
| nimOperator.rerankqa.env[0].name | string | `"NIM_HTTP_API_PORT"` | |
| nimOperator.rerankqa.env[0].value | string | `"8000"` | |
| nimOperator.rerankqa.env[1].name | string | `"NIM_TRITON_LOG_VERBOSE"` | |
| nimOperator.rerankqa.env[1].value | string | `"1"` | |
| nimOperator.rerankqa.expose.service.grpcPort | int | `8001` | |
| nimOperator.rerankqa.expose.service.port | int | `8000` | |
| nimOperator.rerankqa.expose.service.type | string | `"ClusterIP"` | |
| nimOperator.rerankqa.image.pullPolicy | string | `"IfNotPresent"` | |
| nimOperator.rerankqa.image.pullSecrets[0] | string | `"ngc-secret"` | |
| nimOperator.rerankqa.image.repository | string | `"nvcr.io/nim/nvidia/llama-nemotron-rerank-1b-v2"` | |
| nimOperator.rerankqa.image.tag | string | `"1.10.0"` | |
| nimOperator.rerankqa.replicas | int | `1` | |
| nimOperator.rerankqa.resources.limits."nvidia.com/gpu" | int | `1` | |
| nimOperator.rerankqa.storage.pvc.create | bool | `true` | |
| nimOperator.rerankqa.storage.pvc.size | string | `"50Gi"` | |
| nimOperator.rerankqa.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.ocr.authSecret | string | `"ngc-api"` | |
| nimOperator.ocr.enabled | bool | `true` | |
| nimOperator.ocr.env[0].name | string | `"OMP_NUM_THREADS"` | |
| nimOperator.ocr.env[0].value | string | `"8"` | |
| nimOperator.ocr.env[1].name | string | `"NIM_HTTP_API_PORT"` | |
| nimOperator.ocr.env[1].value | string | `"8000"` | |
| nimOperator.ocr.env[2].name | string | `"NIM_TRITON_LOG_VERBOSE"` | |
| nimOperator.ocr.env[2].value | string | `"1"` | |
| nimOperator.ocr.env[3].name | string | `"NIM_TRITON_MAX_BATCH_SIZE"` | |
| nimOperator.ocr.env[3].value | string | `"32"` | |
| nimOperator.ocr.expose.service.grpcPort | int | `8001` | |
| nimOperator.ocr.expose.service.port | int | `8000` | |
| nimOperator.ocr.expose.service.type | string | `"ClusterIP"` | |
| nimOperator.ocr.image.pullPolicy | string | `"IfNotPresent"` | |
| nimOperator.ocr.image.pullSecrets[0] | string | `"ngc-secret"` | |
| nimOperator.ocr.image.repository | string | `"nvcr.io/nim/nvidia/nemotron-ocr-v1"` | |
| nimOperator.ocr.image.tag | string | `"1.3.0"` | |
| nimOperator.ocr.replicas | int | `1` | |
| nimOperator.ocr.resources.limits."nvidia.com/gpu" | int | `1` | |
| nimOperator.ocr.storage.pvc.create | bool | `true` | |
| nimOperator.ocr.storage.pvc.size | string | `"25Gi"` | |
| nimOperator.ocr.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.nemotron_nano_12b_v2_vl.authSecret | string | `"ngc-api"` | |
| nimOperator.nemotron_nano_12b_v2_vl.enabled | bool | `false` | |
| nimOperator.nemotron_nano_12b_v2_vl.env[0].name | string | `"NIM_HTTP_API_PORT"` | |
Expand Down Expand Up @@ -547,6 +507,28 @@ You can also use NV-Ingest's Python client API to interact with the service runn
| nimOperator.nimCache.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.nimService.namespaces | list | `[]` | |
| nimOperator.nimService.resources | object | `{}` | |
| nimOperator.ocr.authSecret | string | `"ngc-api"` | |
| nimOperator.ocr.enabled | bool | `true` | |
| nimOperator.ocr.env[0].name | string | `"OMP_NUM_THREADS"` | |
| nimOperator.ocr.env[0].value | string | `"8"` | |
| nimOperator.ocr.env[1].name | string | `"NIM_HTTP_API_PORT"` | |
| nimOperator.ocr.env[1].value | string | `"8000"` | |
| nimOperator.ocr.env[2].name | string | `"NIM_TRITON_LOG_VERBOSE"` | |
| nimOperator.ocr.env[2].value | string | `"1"` | |
| nimOperator.ocr.env[3].name | string | `"NIM_TRITON_MAX_BATCH_SIZE"` | |
| nimOperator.ocr.env[3].value | string | `"32"` | |
| nimOperator.ocr.expose.service.grpcPort | int | `8001` | |
| nimOperator.ocr.expose.service.port | int | `8000` | |
| nimOperator.ocr.expose.service.type | string | `"ClusterIP"` | |
| nimOperator.ocr.image.pullPolicy | string | `"IfNotPresent"` | |
| nimOperator.ocr.image.pullSecrets[0] | string | `"ngc-secret"` | |
| nimOperator.ocr.image.repository | string | `"nvcr.io/nim/nvidia/nemotron-ocr-v1"` | |
| nimOperator.ocr.image.tag | string | `"1.3.0"` | |
| nimOperator.ocr.replicas | int | `1` | |
| nimOperator.ocr.resources.limits."nvidia.com/gpu" | int | `1` | |
| nimOperator.ocr.storage.pvc.create | bool | `true` | |
| nimOperator.ocr.storage.pvc.size | string | `"25Gi"` | |
| nimOperator.ocr.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.page_elements.authSecret | string | `"ngc-api"` | |
| nimOperator.page_elements.enabled | bool | `true` | |
| nimOperator.page_elements.env[0].name | string | `"NIM_HTTP_API_PORT"` | |
Expand Down Expand Up @@ -589,6 +571,24 @@ You can also use NV-Ingest's Python client API to interact with the service runn
| nimOperator.page_elements.storage.pvc.create | bool | `true` | |
| nimOperator.page_elements.storage.pvc.size | string | `"25Gi"` | |
| nimOperator.page_elements.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.rerankqa.authSecret | string | `"ngc-api"` | |
| nimOperator.rerankqa.enabled | bool | `false` | |
| nimOperator.rerankqa.env[0].name | string | `"NIM_HTTP_API_PORT"` | |
| nimOperator.rerankqa.env[0].value | string | `"8000"` | |
| nimOperator.rerankqa.env[1].name | string | `"NIM_TRITON_LOG_VERBOSE"` | |
| nimOperator.rerankqa.env[1].value | string | `"1"` | |
| nimOperator.rerankqa.expose.service.grpcPort | int | `8001` | |
| nimOperator.rerankqa.expose.service.port | int | `8000` | |
| nimOperator.rerankqa.expose.service.type | string | `"ClusterIP"` | |
| nimOperator.rerankqa.image.pullPolicy | string | `"IfNotPresent"` | |
| nimOperator.rerankqa.image.pullSecrets[0] | string | `"ngc-secret"` | |
| nimOperator.rerankqa.image.repository | string | `"nvcr.io/nim/nvidia/llama-nemotron-rerank-1b-v2"` | |
| nimOperator.rerankqa.image.tag | string | `"1.10.0"` | |
| nimOperator.rerankqa.replicas | int | `1` | |
| nimOperator.rerankqa.resources.limits."nvidia.com/gpu" | int | `1` | |
| nimOperator.rerankqa.storage.pvc.create | bool | `true` | |
| nimOperator.rerankqa.storage.pvc.size | string | `"50Gi"` | |
| nimOperator.rerankqa.storage.pvc.volumeAccessMode | string | `"ReadWriteOnce"` | |
| nimOperator.table_structure.authSecret | string | `"ngc-api"` | |
| nimOperator.table_structure.enabled | bool | `true` | |
| nimOperator.table_structure.env[0].name | string | `"NIM_HTTP_API_PORT"` | |
Expand Down
6 changes: 3 additions & 3 deletions helm/README.md.gotmpl
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ To install or upgrade the Helm chart, run the following code.
helm upgrade \
--install \
nv-ingest \
https://helm.ngc.nvidia.com/nvidia/nemo-microservices/charts/nv-ingest-26.03.0-RC1.tgz \
https://helm.ngc.nvidia.com/nvidia/nemo-microservices/charts/nv-ingest-26.03.0-RC2.tgz \
-n ${NAMESPACE} \
--username '$oauthtoken' \
--password "${NGC_API_KEY}" \
Expand All @@ -55,7 +55,7 @@ helm upgrade \
--set ngcApiSecret.create=true \
--set ngcApiSecret.password="${NGC_API_KEY}" \
--set image.repository="nvcr.io/nvidia/nemo-microservices/nv-ingest" \
--set image.tag="26.03.0-RC1"
--set image.tag="26.03.0-RC2"
```

Optionally you can create your own versions of the `Secrets` if you do not want to use the creation via the helm chart.
Expand Down Expand Up @@ -107,7 +107,7 @@ For more information, refer to [NV-Ingest-Client](https://github.com/NVIDIA/nv-i
# Just to be cautious we remove any existing installation
pip uninstall nv-ingest-client

pip install nv-ingest-client==26.03.0-RC1
pip install nv-ingest-client==26.03.0-RC2
```

#### Rest Endpoint Ingress
Expand Down
2 changes: 1 addition & 1 deletion helm/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ nameOverride: ""
image:
pullPolicy: IfNotPresent
repository: "nvcr.io/nvidia/nemo-microservices/nv-ingest"
tag: "26.03.0-RC1"
tag: "26.03.0-RC2"

## @section Pod Configuration
## @param podAnnotations [object] Sets additional annotations on the main deployment pods
Expand Down
14 changes: 7 additions & 7 deletions nemo_retriever/pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -30,9 +30,9 @@ dependencies = [
"typer>=0.12.0",
"pyyaml>=6.0",
"lancedb",
"nv-ingest==26.03.0-RC1",
"nv-ingest-api==26.03.0-RC1",
"nv-ingest-client==26.03.0-RC1",
"nv-ingest==26.03.0rc2",
"nv-ingest-api==26.03.0rc2",
"nv-ingest-client==26.03.0rc2",
"fastapi>=0.114.0",
"uvicorn[standard]>=0.30.0",
"httpx>=0.27.0",
Expand All @@ -57,10 +57,10 @@ dependencies = [
"einops",
"easydict",
"addict",
"nemotron-page-elements-v3>=0.dev0",
"nemotron-graphic-elements-v1>=0.dev0",
"nemotron-table-structure-v1>=0.dev0",
"nemotron-ocr>=0.dev0",
"nemotron-page-elements-v3==3.0.1",
"nemotron-graphic-elements-v1==1.0.0",
"nemotron-table-structure-v1==1.0.0",
"nemotron-ocr==1.0.1",
"markitdown",
"timm==1.0.22",
"accelerate==1.12.0",
Expand Down
2 changes: 1 addition & 1 deletion src/nv_ingest/api/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
app = FastAPI(
title="NV-Ingest Microservice",
description="Service for ingesting heterogenous datatypes",
version="26.03.0-RC1",
version="26.03.0-RC2",
contact={
"name": "NVIDIA Corporation",
"url": "https://nvidia.com",
Expand Down
8 changes: 4 additions & 4 deletions tools/harness/nemotron-nightly.txt
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
# Usage: pip install -r tools/harness/nemotron-nightly.txt --force-reinstall --no-deps
--index-url https://test.pypi.org/simple/

nemotron-page-elements-v3>=0.dev0
nemotron-graphic-elements-v1>=0.dev0
nemotron-table-structure-v1>=0.dev0
nemotron-ocr>=0.dev0
nemotron-page-elements-v3==3.0.1
nemotron-graphic-elements-v1==1.0.0
nemotron-table-structure-v1==1.0.0
nemotron-ocr==1.0.1
14 changes: 7 additions & 7 deletions tools/harness/pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -10,15 +10,15 @@ dependencies = [
"pyyaml>=6.0",
"requests>=2.32.5",
"pynvml>=11.5.0",
"nv-ingest==26.03.0-RC1",
"nv-ingest-api==26.03.0-RC1",
"nv-ingest-client==26.03.0-RC1",
"nv-ingest==26.03.0rc2",
"nv-ingest-api==26.03.0rc2",
"nv-ingest-client==26.03.0rc2",
"milvus-lite==2.4.12",
"pypdfium2>=4.30.0,<5.0.0",
"nemotron-page-elements-v3>=0.dev0",
"nemotron-graphic-elements-v1>=0.dev0",
"nemotron-table-structure-v1>=0.dev0",
"nemotron-ocr>=0.dev0",
"nemotron-page-elements-v3==3.0.1",
"nemotron-graphic-elements-v1==1.0.0",
"nemotron-table-structure-v1==1.0.0",
"nemotron-ocr==1.0.1",
]

[project.scripts]
Expand Down
2 changes: 1 addition & 1 deletion tools/harness/test_configs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ active:
kubectl_bin: microk8s kubectl # kubectl binary command (e.g., "kubectl", "microk8s kubectl")
kubectl_sudo: null # Prepend sudo to kubectl commands (null = same as helm_sudo)
chart: nemo-microservices/nv-ingest # Remote chart reference (set to null to use local chart from ./helm)
chart_version: 26.03.0-RC1 # Chart version (required for remote charts)
chart_version: 26.03.0-RC2 # Chart version (required for remote charts)
release: nv-ingest
namespace: nv-ingest
values_file: .helm-env # Optional: path to values file
Expand Down
Loading