Upgrade to Nemotron RC NIMs and NV-Ingest 26.1.2

Signed-off-by: Swapnil Masurekar <smasurekar@nvidia.com>

Author: smasurekar

README.md

@@ -105,9 +105,9 @@ This modular design ensures efficient query processing, accurate retrieval of in
 
     - [NVIDIA NIM llama-3_2-nv-embedqa-1b-v2](https://build.nvidia.com/nvidia/llama-3_2-nv-embedqa-1b-v2)
     - [NVIDIA NIM llama-3_2-nv-rerankqa-1b-v2](https://build.nvidia.com/nvidia/llama-3_2-nv-rerankqa-1b-v2)
-    - [NeMo Retriever Page Elements NIM](https://build.nvidia.com/nvidia/nemoretriever-page-elements-v3)
-    - [NeMo Retriever Table Structure NIM](https://build.nvidia.com/nvidia/nemoretriever-table-structure-v1)
-    - [NeMo Retriever Graphic Elements NIM](https://build.nvidia.com/nvidia/nemoretriever-graphic-elements-v1)
+    - [NeMo Retriever Page Elements NIM](https://build.nvidia.com/nvidia/nemotron-page-elements-v3)
+    - [NeMo Retriever Table Structure NIM](https://build.nvidia.com/nvidia/nemotron-table-structure-v1)
+    - [NeMo Retriever Graphic Elements NIM](https://build.nvidia.com/nvidia/nemotron-graphic-elements-v1)
     - [NeMo Retriever OCR NIM](https://build.nvidia.com/nvidia/nemoretriever-ocr)
 
 - Optional NIMs
@@ -202,9 +202,9 @@ Use of the models in this blueprint is governed by the [NVIDIA AI Foundation Mod
 
 ## Terms of Use
 This blueprint is governed by the [NVIDIA Agreements | Enterprise Software | NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [NVIDIA Agreements | Enterprise Software | Product Specific Terms for AI Product](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). The models are governed by the [NVIDIA Agreements | Enterprise Software | NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/) and the [NVIDIA RAG dataset](./data/multimodal/) which is governed by the [NVIDIA Asset License Agreement](https://github.com/NVIDIA-AI-Blueprints/rag/blob/main/data/LICENSE.DATA).
-The following models that are built with Llama are governed by the Llama 3.2 Community License Agreement: nvidia/llama-3.2-nv-embedqa-1b-v2 and nvidia/llama-3.2-nv-rerankqa-1b-v2 and llama-3.2-nemoretriever-1b-vlm-embed-v1.
+The following models that are built with Llama are governed by the Llama 3.2 Community License Agreement: nvidia/llama-nemotron-embed-1b-v2 and nvidia/llama-nemotron-rerank-1b-v2 and llama-3.2-nemoretriever-1b-vlm-embed-v1.
 
 ## Additional Information
 
-The [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/) for the llama-3.1-nemotron-nano-vl-8b-v1, llama-3.1-nemoguard-8b-content-safety and llama-3.1-nemoguard-8b-topic-control models. The [Llama 3.2 Community License Agreement](https://www.llama.com/llama3_2/license/) for the nvidia/llama-3.2-nv-embedqa-1b-v2, nvidia/llama-3.2-nv-rerankqa-1b-v2 and llama-3.2-nemoretriever-1b-vlm-embed-v1 models. The [Llama 3.3 Community License Agreement](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE) for the llama-3.3-nemotron-super-49b-v1.5 models. Built with Llama. Apache 2.0 for NVIDIA Ingest and for the nemoretriever-page-elements-v2, nemoretriever-table-structure-v1, nemoretriever-graphic-elements-v1, paddleocr and nemoretriever-ocr-v1 models.
+The [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/) for the llama-3.1-nemotron-nano-vl-8b-v1, llama-3.1-nemoguard-8b-content-safety and llama-3.1-nemoguard-8b-topic-control models. The [Llama 3.2 Community License Agreement](https://www.llama.com/llama3_2/license/) for the nvidia/llama-nemotron-embed-1b-v2, nvidia/llama-nemotron-rerank-1b-v2 and llama-3.2-nemoretriever-1b-vlm-embed-v1 models. The [Llama 3.3 Community License Agreement](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE) for the llama-3.3-nemotron-super-49b-v1.5 models. Built with Llama. Apache 2.0 for NVIDIA Ingest and for the nemoretriever-page-elements-v2, nemotron-table-structure-v1, nemotron-graphic-elements-v1, paddleocr and nemoretriever-ocr-v1 models.
 

deploy/compose/.env

@@ -22,8 +22,8 @@ export NVIDIA_API_KEY=${NGC_API_KEY}
 export APP_LLM_SERVERURL=nim-llm:8000
 export APP_FILTEREXPRESSIONGENERATOR_SERVERURL=nim-llm:8000
 export SUMMARY_LLM_SERVERURL=nim-llm:8000
-export APP_EMBEDDINGS_SERVERURL=nemoretriever-embedding-ms:8000/v1
-export APP_RANKING_SERVERURL=nemoretriever-ranking-ms:8000
+export APP_EMBEDDINGS_SERVERURL=nemotron-embedding-ms:8000/v1
+export APP_RANKING_SERVERURL=nemotron-ranking-ms:8000
 export OCR_GRPC_ENDPOINT=nemoretriever-ocr:8001
 export OCR_HTTP_ENDPOINT=http://nemoretriever-ocr:8000/v1/infer
 export OCR_INFER_PROTOCOL=grpc
@@ -50,11 +50,11 @@ export YOLOX_TABLE_STRUCTURE_INFER_PROTOCOL=grpc
 # export OCR_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-ocr
 # export OCR_INFER_PROTOCOL=http
 # export OCR_MODEL_NAME=scene_text_ensemble
-# export YOLOX_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-page-elements-v3
+# export YOLOX_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemotron-page-elements-v3
 # export YOLOX_INFER_PROTOCOL=http
-# export YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-graphic-elements-v1
+# export YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemotron-graphic-elements-v1
 # export YOLOX_GRAPHIC_ELEMENTS_INFER_PROTOCOL=http
-# export YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-table-structure-v1
+# export YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemotron-table-structure-v1
 # export YOLOX_TABLE_STRUCTURE_INFER_PROTOCOL=http
 # export APP_QUERYREWRITER_SERVERURL=""
 # export APP_QUERYREWRITER_MODELNAME="nvidia/llama-3.3-nemotron-super-49b-v1.5"

deploy/compose/docker-compose-ingestor-server.yaml

@@ -75,8 +75,8 @@ services:
 
       ##===Embedding Model specific configurations===
       # url on which embedding model is hosted. If "", Nvidia hosted API is used
-      APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemoretriever-embedding-ms:8000/v1"}
-      APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-3.2-nv-embedqa-1b-v2}
+      APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemotron-embedding-ms:8000/v1"}
+      APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-nemotron-embed-1b-v2}
       # For VLM Embedding Model (Nemoretriever-1b-vlm-embed-v1)
       # APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemotron-vlm-embedding-ms:8000/v1"}
       # APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-nemotron-embed-vl-1b-v2}
@@ -168,7 +168,7 @@ services:
       - "6379:6379"
 
   nv-ingest-ms-runtime:
-    image: nvcr.io/nvidia/nemo-microservices/nv-ingest:26.1.1
+    image: nvcr.io/nvidia/nemo-microservices/nv-ingest:26.1.2
     # cpuset: "0-15" # Uncomment to restrict this container to CPU cores 0–15
     shm_size: 40gb # Should be at minimum 30% of assigned memory per Ray documentation
     volumes:
@@ -234,13 +234,13 @@ services:
       - YOLOX_HTTP_ENDPOINT=${YOLOX_HTTP_ENDPOINT:-http://page-elements:8000/v1/infer}
       - YOLOX_INFER_PROTOCOL=${YOLOX_INFER_PROTOCOL:-grpc}
       # build.nvidia.com hosted yolox-graphics-elements endpoints.
-      #- YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-graphic-elements-v1
+      #- YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemotron-graphic-elements-v1
       #- YOLOX_GRAPHIC_ELEMENTS_INFER_PROTOCOL=http
       - YOLOX_GRAPHIC_ELEMENTS_GRPC_ENDPOINT=${YOLOX_GRAPHIC_ELEMENTS_GRPC_ENDPOINT:-graphic-elements:8001}
       - YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT=${YOLOX_GRAPHIC_ELEMENTS_HTTP_ENDPOINT:-http://graphic-elements:8000/v1/infer}
       - YOLOX_GRAPHIC_ELEMENTS_INFER_PROTOCOL=${YOLOX_GRAPHIC_ELEMENTS_INFER_PROTOCOL:-grpc}
       # build.nvidia.com hosted  yolox-table-elements endpoints.
-      #- YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemoretriever-table-structure-v1
+      #- YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT=https://ai.api.nvidia.com/v1/cv/nvidia/nemotron-table-structure-v1
       #- YOLOX_TABLE_STRUCTURE_INFER_PROTOCOL=http
       - YOLOX_TABLE_STRUCTURE_GRPC_ENDPOINT=${YOLOX_TABLE_STRUCTURE_GRPC_ENDPOINT:-table-structure:8001}
       - YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT=${YOLOX_TABLE_STRUCTURE_HTTP_ENDPOINT:-http://table-structure:8000/v1/infer}

deploy/compose/docker-compose-rag-server.yaml

@@ -94,17 +94,17 @@ services:
 
       ##===Embedding Model specific configurations===
       # url on which embedding model is hosted. If "", Nvidia hosted API is used
-      APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemoretriever-embedding-ms:8000/v1"}
-      APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-3.2-nv-embedqa-1b-v2}
+      APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemotron-embedding-ms:8000/v1"}
+      APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-nemotron-embed-1b-v2}
       APP_EMBEDDINGS_DIMENSIONS: ${APP_EMBEDDINGS_DIMENSIONS:-2048}
       # For VLM Embedding Model (Nemoretriever-1b-vlm-embed-v1)
       # APP_EMBEDDINGS_SERVERURL: ${APP_EMBEDDINGS_SERVERURL-"nemotron-vlm-embedding-ms:8000/v1"}
       # APP_EMBEDDINGS_MODELNAME: ${APP_EMBEDDINGS_MODELNAME:-nvidia/llama-nemotron-embed-vl-1b-v2}
 
       ##===Reranking Model specific configurations===
       # url on which ranking model is hosted. If "", Nvidia hosted API is used
-      APP_RANKING_SERVERURL: ${APP_RANKING_SERVERURL-"nemoretriever-ranking-ms:8000"}
-      APP_RANKING_MODELNAME: ${APP_RANKING_MODELNAME:-"nvidia/llama-3.2-nv-rerankqa-1b-v2"}
+      APP_RANKING_SERVERURL: ${APP_RANKING_SERVERURL-"nemotron-ranking-ms:8000"}
+      APP_RANKING_MODELNAME: ${APP_RANKING_MODELNAME:-"nvidia/llama-nemotron-rerank-1b-v2"}
       ENABLE_RERANKER: ${ENABLE_RERANKER:-True}
       # Default score threshold for filtering documents by reranker relevance (0.0 to 1.0)
       RERANKER_SCORE_THRESHOLD: ${RERANKER_SCORE_THRESHOLD:-${RERANKER_CONFIDENCE_THRESHOLD:-0.0}}

deploy/compose/nims.yaml

@@ -31,9 +31,9 @@ services:
       retries: 100
     profiles: ["", "rag"]
 
-  nemoretriever-embedding-ms:
-    container_name: nemoretriever-embedding-ms
-    image: nvcr.io/nim/nvidia/llama-3.2-nv-embedqa-1b-v2:1.10.1
+  nemotron-embedding-ms:
+    container_name: nemotron-embedding-ms
+    image: nvcr.io/nvstaging/nim/llama-nemotron-embed-1b-v2:1.12.0-rc.20260216115852-6fba925dcb63c190
     volumes:
     - ${MODEL_DIRECTORY:-./}:/opt/nim/.cache
     ports:
@@ -91,9 +91,9 @@ services:
       start_period: 10m
     profiles: ["vlm-embed", "vlm-ingest"]
 
-  nemoretriever-ranking-ms:
-    container_name: nemoretriever-ranking-ms
-    image: nvcr.io/nim/nvidia/llama-3.2-nv-rerankqa-1b-v2:1.8.0
+  nemotron-ranking-ms:
+    container_name: nemotron-ranking-ms
+    image: nvcr.io/nvstaging/nim/llama-nemotron-rerank-1b-v2:1.10.0-rc.20260219005237-7e2370934c6f9b9c
     volumes:
     - ${MODEL_DIRECTORY:-./}:/opt/nim/.cache
     ports:
@@ -119,7 +119,7 @@ services:
     profiles: ["", "rag", "vlm-generation"]
 
   page-elements:
-    image: ${YOLOX_IMAGE:-nvcr.io/nim/nvidia/nemoretriever-page-elements-v3}:${YOLOX_TAG:-1.7.0}
+    image: ${YOLOX_IMAGE:-nvcr.io/nvstaging/nim/nemotron-page-elements-v3}:${YOLOX_TAG:-1.8.0-rc.20260218170155-6b1b2aa9dfefc9c3}
     shm_size: 16gb
     ports:
       - "8000:8000"
@@ -157,7 +157,7 @@ services:
     profiles: ["", "ingest", "vlm-ingest"]
 
   graphic-elements:
-    image: ${YOLOX_GRAPHIC_ELEMENTS_IMAGE:-nvcr.io/nim/nvidia/nemoretriever-graphic-elements-v1}:${YOLOX_GRAPHIC_ELEMENTS_TAG:-1.6.0}
+    image: ${YOLOX_GRAPHIC_ELEMENTS_IMAGE:-nvcr.io/nvstaging/nim/nemotron-graphic-elements-v1}:${YOLOX_GRAPHIC_ELEMENTS_TAG:-1.8.0-rc.20260218170144-35d5a3f270662864}
     shm_size: 16gb
     ports:
       - "8003:8000"
@@ -183,7 +183,7 @@ services:
     profiles: ["", "ingest", "vlm-ingest"]
 
   table-structure:
-    image: ${YOLOX_TABLE_STRUCTURE_IMAGE:-nvcr.io/nim/nvidia/nemoretriever-table-structure-v1}:${YOLOX_TABLE_STRUCTURE_TAG:-1.6.0}
+    image: ${YOLOX_TABLE_STRUCTURE_IMAGE:-nvcr.io/nvstaging/nim/nemotron-table-structure-v1}:${YOLOX_TABLE_STRUCTURE_TAG:-1.8.0-rc.20260218170204-cca5cb850146dbbc}
     shm_size: 16gb
     ports:
       - "8006:8000"

deploy/helm/nvidia-blueprint-rag/Chart.yaml

@@ -4,7 +4,7 @@ dependencies:
 - condition: nv-ingest.enabled
   name: nv-ingest
   repository: https://helm.ngc.nvidia.com/nvidia/nemo-microservices
-  version: 26.1.1
+  version: 26.1.2
 - condition: eck-elasticsearch.enabled
   name: eck-elasticsearch
   repository: https://helm.elastic.co

deploy/helm/nvidia-blueprint-rag/endpoints.md

@@ -24,11 +24,11 @@ This document describes the configurable endpoints used by the RAG server and it
 
 ### Embedding Model
 - **APP_EMBEDDINGS_SERVERURL**: URL for the embedding model service (default: "nemo-retriever-embedding-ms:8000")
-- **APP_EMBEDDINGS_MODELNAME**: Name of the embedding model (default: "nvidia/llama-3.2-nv-embedqa-1b-v2")
+- **APP_EMBEDDINGS_MODELNAME**: Name of the embedding model (default: "nvidia/llama-nemotron-embed-1b-v2")
 
 ### Reranking Model
 - **APP_RANKING_SERVERURL**: URL for the ranking model service (default: "nemo-retriever-reranking-ms:8000")
-- **APP_RANKING_MODELNAME**: Name of the ranking model (default: "nvidia/llama-3.2-nv-rerankqa-1b-v2")
+- **APP_RANKING_MODELNAME**: Name of the ranking model (default: "nvidia/llama-nemotron-rerank-1b-v2")
 
 ### Reflection Model
 - **REFLECTION_LLM_SERVERURL**: URL for the reflection LLM service (default: "nim-llm:8000")
@@ -42,8 +42,8 @@ This document describes the configurable endpoints used by the RAG server and it
 
 ### Model Configuration
 - **NEXT_PUBLIC_MODEL_NAME**: Name of the LLM model used in the frontend (default: "nvidia/llama-3.3-nemotron-super-49b-v1.5")
-- **VITE_EMBEDDING_MODEL**: Name of the embedding model used in the frontend (default: "nvidia/llama-3.2-nv-embedqa-1b-v2")
-- **VITE_RERANKER_MODEL**: Name of the reranker model used in the frontend (default: "nvidia/llama-3.2-nv-rerankqa-1b-v2")
+- **VITE_EMBEDDING_MODEL**: Name of the embedding model used in the frontend (default: "nvidia/llama-nemotron-embed-1b-v2")
+- **VITE_RERANKER_MODEL**: Name of the reranker model used in the frontend (default: "nvidia/llama-nemotron-rerank-1b-v2")
 
 ## Monitoring and Tracing Endpoints
 

deploy/helm/nvidia-blueprint-rag/values.yaml

@@ -183,14 +183,14 @@ envVars:
 
   ##===Embedding Model specific configurations===
   # URL on which embedding model is hosted. If "", Nvidia hosted API is used
-  APP_EMBEDDINGS_SERVERURL: "nemoretriever-embedding-ms:8000/v1"
-  APP_EMBEDDINGS_MODELNAME: "nvidia/llama-3.2-nv-embedqa-1b-v2"
+  APP_EMBEDDINGS_SERVERURL: "nemotron-embedding-ms:8000/v1"
+  APP_EMBEDDINGS_MODELNAME: "nvidia/llama-nemotron-embed-1b-v2"
   APP_EMBEDDINGS_DIMENSIONS: "2048"
 
   ##===Reranking Model specific configurations===
   # URL on which ranking model is hosted. If "", Nvidia hosted API is used
-  APP_RANKING_SERVERURL: "nemoretriever-ranking-ms:8000"
-  APP_RANKING_MODELNAME: "nvidia/llama-3.2-nv-rerankqa-1b-v2"
+  APP_RANKING_SERVERURL: "nemotron-ranking-ms:8000"
+  APP_RANKING_MODELNAME: "nvidia/llama-nemotron-rerank-1b-v2"
   ENABLE_RERANKER: "True"
   # Default score threshold for filtering documents by reranker relevance (0.0 to 1.0)
   RERANKER_SCORE_THRESHOLD: "0.0"
@@ -349,8 +349,8 @@ ingestor-server:
     ## APP_EMBEDDINGS_APIKEY and SUMMARY_LLM_APIKEY are loaded from secrets automatically.
 
     # === Embeddings Configurations ===
-    APP_EMBEDDINGS_SERVERURL: "nemoretriever-embedding-ms:8000/v1"
-    APP_EMBEDDINGS_MODELNAME: "nvidia/llama-3.2-nv-embedqa-1b-v2"
+    APP_EMBEDDINGS_SERVERURL: "nemotron-embedding-ms:8000/v1"
+    APP_EMBEDDINGS_MODELNAME: "nvidia/llama-nemotron-embed-1b-v2"
     APP_EMBEDDINGS_DIMENSIONS: "2048"
 
     # === NV-Ingest Configurations ===
@@ -716,10 +716,10 @@ nimOperator:
     enabled: true
     replicas: 1
     service:
-      name: "nemoretriever-embedding-ms"
+      name: "nemotron-embedding-ms"
     image:
-      repository: nvcr.io/nim/nvidia/llama-3.2-nv-embedqa-1b-v2
-      tag: "1.10.1"
+      repository: nvcr.io/nvstaging/nim/llama-nemotron-embed-1b-v2
+      tag: "1.12.0-rc.20260216115852-6fba925dcb63c190"
       pullPolicy: IfNotPresent
     resources:
       limits:
@@ -795,10 +795,10 @@ nimOperator:
     enabled: true
     replicas: 1
     service:
-      name: "nemoretriever-ranking-ms"
+      name: "nemotron-ranking-ms"
     image:
-      repository: nvcr.io/nim/nvidia/llama-3.2-nv-rerankqa-1b-v2
-      tag: "1.8.0"
+      repository: nvcr.io/nvstaging/nim/llama-nemotron-rerank-1b-v2
+      tag: "1.10.0-rc.20260219005237-7e2370934c6f9b9c"
       pullPolicy: IfNotPresent
     resources:
       limits:
@@ -870,7 +870,7 @@ nv-ingest:
     create: false
   image:
     repository: "nvcr.io/nvidia/nemo-microservices/nv-ingest"
-    tag: "26.1.1"
+    tag: "26.1.2"
   resources:
     limits:
       nvidia.com/gpu: 0
@@ -896,8 +896,8 @@ nv-ingest:
     RAY_num_server_call_thread: "1"
     RAY_worker_num_grpc_internal_threads: "1"
 
-    EMBEDDING_NIM_ENDPOINT: "http://nemoretriever-embedding-ms:8000/v1"
-    EMBEDDING_NIM_MODEL_NAME: "nvidia/llama-3.2-nv-embedqa-1b-v2"
+    EMBEDDING_NIM_ENDPOINT: "http://nemotron-embedding-ms:8000/v1"
+    EMBEDDING_NIM_MODEL_NAME: "nvidia/llama-nemotron-embed-1b-v2"
     MESSAGE_CLIENT_HOST: "rag-redis-master"
     MESSAGE_CLIENT_PORT: 6379
     MESSAGE_CLIENT_TYPE: "redis"
@@ -1049,8 +1049,8 @@ nv-ingest:
       tolerations: []
       replicaCount: 1
       image:
-        repository: nvcr.io/nim/nvidia/nemoretriever-graphic-elements-v1
-        tag: "1.6.0"
+        repository: nvcr.io/nvstaging/nim/nemotron-graphic-elements-v1
+        tag: "1.8.0-rc.20260218170144-35d5a3f270662864"
       env:
         - name: NIM_HTTP_API_PORT
           value: "8000"
@@ -1082,8 +1082,8 @@ nv-ingest:
       tolerations: []
       replicaCount: 1
       image:
-        repository: nvcr.io/nim/nvidia/nemoretriever-page-elements-v3
-        tag: "1.7.0"
+        repository: nvcr.io/nvstaging/nim/nemotron-page-elements-v3
+        tag: "1.8.0-rc.20260218170155-6b1b2aa9dfefc9c3"
       env:
         - name: NIM_HTTP_API_PORT
           value: "8000"
@@ -1133,8 +1133,8 @@ nv-ingest:
       tolerations: []
       replicaCount: 1
       image:
-        repository: nvcr.io/nim/nvidia/nemoretriever-table-structure-v1
-        tag: "1.6.0"
+        repository: nvcr.io/nvstaging/nim/nemotron-table-structure-v1
+        tag: "1.8.0-rc.20260218170204-cca5cb850146dbbc"
       env:
         - name: NIM_HTTP_API_PORT
           value: "8000"

deploy/workbench/README.md

@@ -75,4 +75,4 @@ Use of the models in this blueprint is governed by the [NVIDIA AI Foundation Mod
 ## Terms of Use
 This blueprint is governed by the [NVIDIA Agreements | Enterprise Software | NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [NVIDIA Agreements | Enterprise Software | Product Specific Terms for AI Product](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). The models are governed by the [NVIDIA Agreements | Enterprise Software | NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/) and the [NVIDIA RAG dataset](https://github.com/NVIDIA-AI-Blueprints/rag/tree/v2.0.0/data/multimodal) which is governed by the [NVIDIA Asset License Agreement](https://github.com/NVIDIA-AI-Blueprints/rag/blob/main/data/LICENSE.DATA).
 
-The following models that are built with Llama are governed by the [Llama 3.2 Community License Agreement](https://www.llama.com/llama3_2/license/): nvidia/llama-3.3-nemotron-super-49b-v1, nvidia/llama-3.2-nv-embedqa-1b-v2, and nvidia/llama-3.2-nv-rerankqa-1b-v2.
+The following models that are built with Llama are governed by the [Llama 3.2 Community License Agreement](https://www.llama.com/llama3_2/license/): nvidia/llama-3.3-nemotron-super-49b-v1, nvidia/llama-nemotron-embed-1b-v2, and nvidia/llama-nemotron-rerank-1b-v2.