enable llm-uservice to point to external llm endpoints

Signed-off-by: devpramod <pramod.pai@intel.com>

Author: devpramod

helm-charts/docsum/README.md

@@ -26,10 +26,11 @@ helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --set global.modelUs
 # helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/rocm-values.yaml
 # To use AMD ROCm device with TGI
 # helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/rocm-tgi-values.yaml
-# To use with OPEA KubeAI models installed to same cluster
-# helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/variant_external-llm-values.yaml --set externalLLM.LLM_SERVER_HOST="http://kubeai.kubeai/openai" --set externalLLM.LLM_SERVER_PORT="" --set externalLLM.LLM_MODEL="some-KubeAI-model" --set externalLLM.OPENAI_API_KEY=""
-# To use with other external OpenAI compatible LLM endpoints
-# helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/variant_external-llm-values.yaml --set externalLLM.LLM_SERVER_HOST="http://your-llm-server" --set externalLLM.LLM_MODEL="your-model" --set externalLLM.OPENAI_API_KEY="your-api-key"
+# To use with external OpenAI-compatible LLM endpoints (OpenAI, vLLM, TGI, etc.)
+# This configures the llm-uservice to connect to external LLM providers while maintaining DocSum compatibility
+# helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/variant_external-llm-values.yaml --set llm-uservice.env.OPENAI_API_KEY="your-api-key" --set llm-uservice.env.LLM_MODEL_ID="gpt-4-turbo"
+# For vLLM/TGI endpoints:
+# helm install docsum docsum --set global.HF_TOKEN=${HFTOKEN} --values docsum/variant_external-llm-values.yaml --set llm-uservice.env.LLM_ENDPOINT="http://your-vllm-server/v1" --set llm-uservice.env.LLM_MODEL_ID="your-model"
 ```
 
 ## Verify

helm-charts/docsum/templates/deployment.yaml

@@ -35,29 +35,15 @@ spec:
         - name: {{ .Release.Name }}
           env:
             - name: LLM_SERVICE_HOST_IP
-              {{- if .Values.externalLLM.enabled }}
-              value: {{ .Values.externalLLM.LLM_SERVER_HOST }}
-              {{- else }}
               value: {{ include "llm-uservice.fullname" (index .Subcharts "llm-uservice") }}
-              {{- end }}
             - name: LLM_SERVICE_PORT
-              {{- if .Values.externalLLM.enabled }}
-              value: {{ .Values.externalLLM.LLM_SERVER_PORT | default "80" | quote }}
-              {{- else }}
               value: {{ index .Values "llm-uservice" "service" "port" | quote }}
-              {{- end }}
             {{- if .Values.whisper.enabled }}
             - name: ASR_SERVICE_HOST_IP
               value: {{ include "whisper.fullname" (index .Subcharts "whisper") }}
             - name: ASR_SERVICE_PORT
               value: {{ index .Values "whisper" "service" "port" | quote }}
             {{- end }}
-            {{- if .Values.externalLLM.enabled }}
-            - name: LLM_MODEL
-              value: {{ .Values.externalLLM.LLM_MODEL }}
-            - name: OPENAI_API_KEY
-              value: {{ .Values.externalLLM.OPENAI_API_KEY }}
-            {{- end }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
           image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"

helm-charts/docsum/variant_external-llm-values.yaml

@@ -1,17 +1,18 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-# External LLM configuration override
-externalLLM:
-  enabled: true  # Enable external LLM service
-  LLM_SERVER_HOST: "http://your-llm-server"  # External LLM service host
-  LLM_SERVER_PORT: "80"  # Port for the external LLM service
-  LLM_MODEL: "your-model"  # LLM model to use
-  OPENAI_API_KEY: "your-api-key"  # OpenAI API key for authentication
-
-# Disable internal LLM service when using external LLM
+# External LLM configuration - configures llm-uservice to use external LLM providers
+# This keeps the llm-uservice wrapper (required for /v1/docsum endpoint) but connects it to external LLMs
 llm-uservice:
-  enabled: false
+  enabled: true  # Keep the wrapper service for DocSum compatibility
+  env:
+    # Configure llm-uservice to use external OpenAI-compatible endpoints
+    LLM_ENDPOINT: "https://api.openai.com/v1"  # External LLM API endpoint (OpenAI, vLLM, TGI, etc.)
+    OPENAI_API_KEY: "${OPENAI_API_KEY}"        # API key for authentication
+    LLM_MODEL_ID: "gpt-4-turbo"               # Model to use
+    TEXTGEN_BACKEND: "openai"                  # Backend type for OpenAI-compatible endpoints
+
+# Disable local inference services since we're using external LLMs
 vllm:
   enabled: false
 tgi: