llm-docsum-tgi/-vllm => llm-docsum

Adapt to DocSum refactor: opea-project/GenAIComps#1101 Signed-off-by: Eero Tamminen <[email protected]>
opea-project · Jan 14, 2025 · 11982c5 · 11982c5
1 parent 353e526
commit 11982c5
Show file tree

Hide file tree

Showing 6 changed files with 5 additions and 10 deletions.
diff --git a/helm-charts/common/llm-uservice/ci-docsum-values.yaml b/helm-charts/common/llm-uservice/ci-docsum-values.yaml
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 image:
-  repository: opea/llm-docsum-tgi
+  repository: opea/llm-docsum
   tag: "latest"
 
 MAX_INPUT_TOKENS: 2048

diff --git a/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml b/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml
@@ -19,7 +19,7 @@ spec:
         - |
           max_retry=20;
           for ((i=1; i<=max_retry; i++)); do
-          {{- if contains "llm-docsum-tgi" .Values.image.repository }}
+          {{- if contains "llm-docsum" .Values.image.repository }}
           # Try with docsum endpoint
             curl http://{{ include "llm-uservice.fullname" . }}:{{ .Values.service.port }}/v1/chat/docsum -sS --fail-with-body \
               -X POST \

diff --git a/helm-charts/common/llm-uservice/variant_docsum-values.yaml b/helm-charts/common/llm-uservice/variant_docsum-values.yaml
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 image:
-  repository: opea/llm-docsum-tgi
+  repository: opea/llm-docsum
   tag: "latest"
 
 MAX_INPUT_TOKENS: 2048

diff --git a/helm-charts/docsum/gaudi-vllm-values.yaml b/helm-charts/docsum/gaudi-vllm-values.yaml
@@ -7,11 +7,6 @@
 tgi:
   enabled: false
 
-llm-uservice:
-  image:
-    repository: opea/llm-docsum-vllm
-    tag: "latest"
-
 vllm:
   enabled: true
   image:

diff --git a/helm-charts/docsum/values.yaml b/helm-charts/docsum/values.yaml
@@ -59,7 +59,7 @@ affinity: {}
 # To override values in subchart llm-uservice
 llm-uservice:
   image:
-    repository: opea/llm-docsum-tgi
+    repository: opea/llm-docsum
   MAX_INPUT_TOKENS: "1024"
   MAX_TOTAL_TOKENS: "2048"
   LLM_MODEL_ID: Intel/neural-chat-7b-v3-3

diff --git a/microservices-connector/config/manifests/docsum-llm-uservice.yaml b/microservices-connector/config/manifests/docsum-llm-uservice.yaml
@@ -94,7 +94,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "opea/llm-docsum-tgi:latest"
+          image: "opea/llm-docsum:latest"
           ports:
             - name: llm-uservice
               containerPort: 9000