Some nemotron replacements

Author: charlesbluca

helm/README.md

@@ -298,7 +298,7 @@ You can also use NV-Ingest's Python client API to interact with the service runn
 | envVars.AUDIO_GRPC_ENDPOINT | string | `"audio:50051"` |  |
 | envVars.AUDIO_INFER_PROTOCOL | string | `"grpc"` |  |
 | envVars.COMPONENTS_TO_READY_CHECK | string | `"ALL"` |  |
-| envVars.EMBEDDING_NIM_ENDPOINT | string | `"http://llama-32-nv-embedqa-1b-v2:8000/v1"` |  |
+| envVars.EMBEDDING_NIM_ENDPOINT | string | `"http://llama-nemotron-embed-1b-v2:8000/v1"` |  |
 | envVars.EMBEDDING_NIM_MODEL_NAME | string | `"nvidia/llama-nemotron-embed-1b-v2"` |  |
 | envVars.IMAGE_STORAGE_PUBLIC_BASE_URL | string | `""` |  |
 | envVars.IMAGE_STORAGE_URI | string | `"s3://nv-ingest/artifacts/store/images"` |  |

helm/mig/nv-ingest-mig-values-25x.yaml

@@ -38,7 +38,7 @@ nemotron-table-structure-v1:
       nvidia.com/gpu: 0
       nvidia.com/mig-1g.10gb: 1
 
-nvidia-nim-llama-32-nv-embedqa-1b-v2:
+nvidia-nim-llama-nemotron-embed-1b-v2:
   resources:
     limits:
       nvidia.com/gpu: 0
@@ -75,8 +75,8 @@ text-embedding-nim:
       nvidia.com/gpu: 0
       nvidia.com/mig-1g.10gb: 1
 
-# If you want to deploy llama-32-nv-rerankqa-1b-v2
-llama-32-nv-rerankqa-1b-v2:
+# If you want to deploy llama-nemotron-rerank-1b-v2
+llama-nemotron-rerank-1b-v2:
   resources:
     limits:
       nvidia.com/gpu: 0

helm/mig/nv-ingest-mig-values.yaml

@@ -48,7 +48,7 @@ nimOperator:
         nvidia.com/gpu: "0"
         nvidia.com/mig-1g.20gb: 1
 
-  # If you want to deploy llama-32-nv-rerankqa-1b-v2
+  # If you want to deploy llama-nemotron-rerank-1b-v2
   llama_3_2_nv_rerankqa_1b_v2:
     enabled: true
     resources:

…emplates/llama-3.2-nv-embedqa-1b-v2.yaml …emplates/llama-nemotron-embed-1b-v2.yamlhelm/templates/llama-3.2-nv-embedqa-1b-v2.yaml renamed to helm/templates/llama-nemotron-embed-1b-v2.yaml helm/templates/llama-3.2-nv-embedqa-1b-v2.yaml renamed to helm/templates/llama-nemotron-embed-1b-v2.yaml

@@ -21,7 +21,7 @@ spec:
 apiVersion: apps.nvidia.com/v1alpha1
 kind: NIMService
 metadata:
-  name: llama-32-nv-embedqa-1b-v2
+  name: llama-nemotron-embed-1b-v2
 spec:
   image:
     repository: {{ .Values.nimOperator.embedqa.image.repository }}

…mplates/llama-3.2-nv-rerankqa-1b-v2.yaml …mplates/llama-nemotron-rerank-1b-v2.yamlhelm/templates/llama-3.2-nv-rerankqa-1b-v2.yaml renamed to helm/templates/llama-nemotron-rerank-1b-v2.yaml helm/templates/llama-3.2-nv-rerankqa-1b-v2.yaml renamed to helm/templates/llama-nemotron-rerank-1b-v2.yaml

@@ -21,7 +21,7 @@ spec:
 apiVersion: apps.nvidia.com/v1alpha1
 kind: NIMService
 metadata:
-  name: llama-32-nv-rerankqa-1b-v2
+  name: llama-nemotron-rerank-1b-v2
 spec:
   image:
     repository: {{ .Values.nimOperator.llama_3_2_nv_rerankqa_1b_v2.image.repository }}

…s/nemoretriever-graphic-elements-v1.yaml …plates/nemotron-graphic-elements-v1.yamlhelm/templates/nemoretriever-graphic-elements-v1.yaml renamed to helm/templates/nemotron-graphic-elements-v1.yaml helm/templates/nemoretriever-graphic-elements-v1.yaml renamed to helm/templates/nemotron-graphic-elements-v1.yaml

@@ -170,7 +170,7 @@ envVars:
   AUDIO_GRPC_ENDPOINT: "audio:50051"
   AUDIO_INFER_PROTOCOL: "grpc"
 
-  EMBEDDING_NIM_ENDPOINT: "http://llama-32-nv-embedqa-1b-v2:8000/v1"
+  EMBEDDING_NIM_ENDPOINT: "http://llama-nemotron-embed-1b-v2:8000/v1"
   EMBEDDING_NIM_MODEL_NAME: "nvidia/llama-nemotron-embed-1b-v2"
 
   NEMOTRON_PARSE_HTTP_ENDPOINT: http://nemotron-parse:8000/v1/chat/completions