Merge branch 'main' into fix_tei_gaudi_image_version

.github/workflows/_example-workflow.yml

@@ -77,6 +77,10 @@ jobs:
               git clone https://github.com/vllm-project/vllm.git
               cd vllm && git rev-parse HEAD && cd ../
           fi
+          if [[ $(grep -c "vllm-hpu:" ${docker_compose_yml}) != 0 ]]; then
+               git clone https://github.com/HabanaAI/vllm-fork.git vllm-fork
+               cd vllm-fork && git rev-parse HEAD && cd ../
+          fi
           git clone https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git checkout ${{ inputs.opea_branch }} && git rev-parse HEAD && cd ../
 

FaqGen/tests/test_compose_on_gaudi.sh

@@ -101,13 +101,30 @@ function validate_microservices() {
 }
 
 function validate_megaservice() {
-    # Curl the Mega Service
-    validate_services \
-    "${ip_address}:8888/v1/faqgen" \
-    "Text Embeddings Inference" \
-    "mega-faqgen" \
-    "faqgen-gaudi-backend-server" \
-    '{"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'
+    local SERVICE_NAME="mega-faqgen"
+    local DOCKER_NAME="faqgen-gaudi-backend-server"
+    local EXPECTED_RESULT="Embeddings"
+    local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
+    local URL="${ip_address}:8888/v1/faqgen"
+    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL")
+    if [ "$HTTP_STATUS" -eq 200 ]; then
+        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+
+        local CONTENT=$(curl -s -X POST -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+
+        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
+            echo "[ $SERVICE_NAME ] Content is as expected."
+        else
+            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
+            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+            exit 1
+        fi
+    else
+        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
+        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+        exit 1
+    fi
+    sleep 1s
 }
 
 function validate_frontend() {

FaqGen/tests/test_compose_on_xeon.sh

@@ -101,13 +101,30 @@ function validate_microservices() {
 }
 
 function validate_megaservice() {
-    # Curl the Mega Service
-    validate_services \
-    "${ip_address}:8888/v1/faqgen" \
-    "Text Embeddings Inference" \
-    "mega-faqgen" \
-    "faqgen-xeon-backend-server" \
-    '{"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'
+    local SERVICE_NAME="mega-faqgen"
+    local DOCKER_NAME="faqgen-xeon-backend-server"
+    local EXPECTED_RESULT="Embeddings"
+    local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
+    local URL="${ip_address}:8888/v1/faqgen"
+    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL")
+    if [ "$HTTP_STATUS" -eq 200 ]; then
+        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+
+        local CONTENT=$(curl -s -X POST -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+
+        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
+            echo "[ $SERVICE_NAME ] Content is as expected."
+        else
+            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
+            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+            exit 1
+        fi
+    else
+        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
+        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+        exit 1
+    fi
+    sleep 1s
 }
 
 function validate_frontend() {

MultimodalQnA/README.md

@@ -2,7 +2,7 @@
 
 Suppose you possess a set of videos and wish to perform question-answering to extract insights from these videos. To respond to your questions, it typically necessitates comprehension of visual cues within the videos, knowledge derived from the audio content, or often a mix of both these visual elements and auditory facts. The MultimodalQnA framework offers an optimal solution for this purpose.
 
-`MultimodalQnA` addresses your questions by dynamically fetching the most pertinent multimodal information (frames, transcripts, and/or captions) from your collection of videos. For this purpose, MultimodalQnA utilizes [BridgeTower model](https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-gaudi), a multimodal encoding transformer model which merges visual and textual data into a unified semantic space. During the video ingestion phase, the BridgeTower model embeds both visual cues and auditory facts as texts, and those embeddings are then stored in a vector database. When it comes to answering a question, the MultimodalQnA will fetch its most relevant multimodal content from the vector store and feed it into a downstream Large Vision-Language Model (LVM) as input context to generate a response for the user.
+`MultimodalQnA` addresses your questions by dynamically fetching the most pertinent multimodal information (frames, transcripts, and/or captions) from your collection of videos, images, and audio files. For this purpose, MultimodalQnA utilizes [BridgeTower model](https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-gaudi), a multimodal encoding transformer model which merges visual and textual data into a unified semantic space. During the ingestion phase, the BridgeTower model embeds both visual cues and auditory facts as texts, and those embeddings are then stored in a vector database. When it comes to answering a question, the MultimodalQnA will fetch its most relevant multimodal content from the vector store and feed it into a downstream Large Vision-Language Model (LVM) as input context to generate a response for the user.
 
 The MultimodalQnA architecture shows below:
 
@@ -100,10 +100,12 @@ In the below, we provide a table that describes for each microservice component
 
 By default, the embedding and LVM models are set to a default value as listed below:
 
-| Service              | Model                                       |
-| -------------------- | ------------------------------------------- |
-| embedding-multimodal | BridgeTower/bridgetower-large-itm-mlm-gaudi |
-| LVM                  | llava-hf/llava-v1.6-vicuna-13b-hf           |
+| Service              | HW    | Model                                     |
+| -------------------- | ----- | ----------------------------------------- |
+| embedding-multimodal | Xeon  | BridgeTower/bridgetower-large-itm-mlm-itc |
+| LVM                  | Xeon  | llava-hf/llava-1.5-7b-hf                  |
+| embedding-multimodal | Gaudi | BridgeTower/bridgetower-large-itm-mlm-itc |
+| LVM                  | Gaudi | llava-hf/llava-v1.6-vicuna-13b-hf         |
 
 You can choose other LVM models, such as `llava-hf/llava-1.5-7b-hf ` and `llava-hf/llava-1.5-13b-hf`, as needed.
 

MultimodalQnA/docker_compose/intel/cpu/xeon/README.md

@@ -84,16 +84,18 @@ export INDEX_NAME="mm-rag-redis"
 export LLAVA_SERVER_PORT=8399
 export LVM_ENDPOINT="http://${host_ip}:8399"
 export EMBEDDING_MODEL_ID="BridgeTower/bridgetower-large-itm-mlm-itc"
+export LVM_MODEL_ID="llava-hf/llava-1.5-7b-hf"
 export WHISPER_MODEL="base"
 export MM_EMBEDDING_SERVICE_HOST_IP=${host_ip}
 export MM_RETRIEVER_SERVICE_HOST_IP=${host_ip}
 export LVM_SERVICE_HOST_IP=${host_ip}
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/multimodalqna"
+export DATAPREP_INGEST_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/ingest_with_text"
 export DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_transcripts"
 export DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_captions"
-export DATAPREP_GET_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_videos"
-export DATAPREP_DELETE_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_videos"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_files"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_files"
 ```
 
 Note: Please replace with `host_ip` with you external IP address, do not use localhost.
@@ -274,54 +276,76 @@ curl http://${host_ip}:9399/v1/lvm \
 
 6. dataprep-multimodal-redis
 
-Download a sample video
+Download a sample video, image, and audio file and create a caption
 
 ```bash
 export video_fn="WeAreGoingOnBullrun.mp4"
 wget http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/WeAreGoingOnBullrun.mp4 -O ${video_fn}
+
+export image_fn="apple.png"
+wget https://github.com/docarray/docarray/blob/main/tests/toydata/image-data/apple.png?raw=true -O ${image_fn}
+
+export caption_fn="apple.txt"
+echo "This is an apple."  > ${caption_fn}
+
+export audio_fn="AudioSample.wav"
+wget https://github.com/intel/intel-extension-for-transformers/raw/main/intel_extension_for_transformers/neural_chat/assets/audio/sample.wav -O ${audio_fn}
 ```
 
-Test dataprep microservice. This command updates a knowledge base by uploading a local video .mp4.
+Test dataprep microservice with generating transcript. This command updates a knowledge base by uploading a local video .mp4 and an audio .wav file.
 
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT} \
     -H 'Content-Type: multipart/form-data' \
-    -X POST -F "files=@./${video_fn}"
+    -X POST \
+    -F "files=@./${video_fn}" \
+    -F "files=@./${audio_fn}"
 ```
 
-Also, test dataprep microservice with generating caption using lvm microservice
+Also, test dataprep microservice with generating an image caption using lvm microservice
 
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT} \
     -H 'Content-Type: multipart/form-data' \
-    -X POST -F "files=@./${video_fn}"
+    -X POST -F "files=@./${image_fn}"
+```
+
+Now, test the microservice with posting a custom caption along with an image
+
+```bash
+curl --silent --write-out "HTTPSTATUS:%{http_code}" \
+    ${DATAPREP_INGEST_SERVICE_ENDPOINT} \
+    -H 'Content-Type: multipart/form-data' \
+    -X POST -F "files=@./${image_fn}" -F "files=@./${caption_fn}"
 ```
 
-Also, you are able to get the list of all videos that you uploaded:
+Also, you are able to get the list of all files that you uploaded:
 
 ```bash
 curl -X POST \
     -H "Content-Type: application/json" \
-    ${DATAPREP_GET_VIDEO_ENDPOINT}
+    ${DATAPREP_GET_FILE_ENDPOINT}
 ```
 
-Then you will get the response python-style LIST like this. Notice the name of each uploaded video e.g., `videoname.mp4` will become `videoname_uuid.mp4` where `uuid` is a unique ID for each uploaded video. The same video that are uploaded twice will have different `uuid`.
+Then you will get the response python-style LIST like this. Notice the name of each uploaded file e.g., `videoname.mp4` will become `videoname_uuid.mp4` where `uuid` is a unique ID for each uploaded file. The same files that are uploaded twice will have different `uuid`.
 
 ```bash
 [
     "WeAreGoingOnBullrun_7ac553a1-116c-40a2-9fc5-deccbb89b507.mp4",
-    "WeAreGoingOnBullrun_6d13cf26-8ba2-4026-a3a9-ab2e5eb73a29.mp4"
+    "WeAreGoingOnBullrun_6d13cf26-8ba2-4026-a3a9-ab2e5eb73a29.mp4",
+    "apple_fcade6e6-11a5-44a2-833a-3e534cbe4419.png",
+    "AudioSample_976a85a6-dc3e-43ab-966c-9d81beef780c.wav
 ]
 ```
 
-To delete all uploaded videos along with data indexed with `$INDEX_NAME` in REDIS.
+To delete all uploaded files along with data indexed with `$INDEX_NAME` in REDIS.
 
 ```bash
 curl -X POST \
     -H "Content-Type: application/json" \
-    ${DATAPREP_DELETE_VIDEO_ENDPOINT}
+    ${DATAPREP_DELETE_FILE_ENDPOINT}
 ```
 
 7. MegaService

MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -36,6 +36,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       PORT: ${EMBEDDER_PORT}
+    entrypoint: ["python", "bridgetower_server.py", "--device", "cpu", "--model_name_or_path", $EMBEDDING_MODEL_ID]
     restart: unless-stopped
   embedding-multimodal:
     image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest}
@@ -76,6 +77,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
+    entrypoint: ["python", "llava_server.py", "--device", "cpu", "--model_name_or_path", $LVM_MODEL_ID]
     restart: unless-stopped
   lvm-llava-svc:
     image: ${REGISTRY:-opea}/lvm-llava-svc:${TAG:-latest}
@@ -125,6 +127,7 @@ services:
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
       - BACKEND_SERVICE_ENDPOINT=${BACKEND_SERVICE_ENDPOINT}
+      - DATAPREP_INGEST_SERVICE_ENDPOINT=${DATAPREP_INGEST_SERVICE_ENDPOINT}
       - DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT=${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT}
       - DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT=${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT}
     ipc: host

MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -15,13 +15,15 @@ export INDEX_NAME="mm-rag-redis"
 export LLAVA_SERVER_PORT=8399
 export LVM_ENDPOINT="http://${host_ip}:8399"
 export EMBEDDING_MODEL_ID="BridgeTower/bridgetower-large-itm-mlm-itc"
+export LVM_MODEL_ID="llava-hf/llava-1.5-7b-hf"
 export WHISPER_MODEL="base"
 export MM_EMBEDDING_SERVICE_HOST_IP=${host_ip}
 export MM_RETRIEVER_SERVICE_HOST_IP=${host_ip}
 export LVM_SERVICE_HOST_IP=${host_ip}
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/multimodalqna"
+export DATAPREP_INGEST_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/ingest_with_text"
 export DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_transcripts"
 export DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_captions"
-export DATAPREP_GET_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_videos"
-export DATAPREP_DELETE_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_videos"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_files"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_files"

MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -40,10 +40,11 @@ export MM_RETRIEVER_SERVICE_HOST_IP=${host_ip}
 export LVM_SERVICE_HOST_IP=${host_ip}
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/multimodalqna"
+export DATAPREP_INGEST_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/ingest_with_text"
 export DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_transcripts"
 export DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/generate_captions"
-export DATAPREP_GET_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_videos"
-export DATAPREP_DELETE_VIDEO_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_videos"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_files"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_files"
 ```
 
 Note: Please replace with `host_ip` with you external IP address, do not use localhost.
@@ -224,56 +225,76 @@ curl http://${host_ip}:9399/v1/lvm \
 
 6. Multimodal Dataprep Microservice
 
-Download a sample video
+Download a sample video, image, and audio file and create a caption
 
 ```bash
 export video_fn="WeAreGoingOnBullrun.mp4"
 wget http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/WeAreGoingOnBullrun.mp4 -O ${video_fn}
-```
 
-Test dataprep microservice. This command updates a knowledge base by uploading a local video .mp4.
+export image_fn="apple.png"
+wget https://github.com/docarray/docarray/blob/main/tests/toydata/image-data/apple.png?raw=true -O ${image_fn}
+
+export caption_fn="apple.txt"
+echo "This is an apple."  > ${caption_fn}
+
+export audio_fn="AudioSample.wav"
+wget https://github.com/intel/intel-extension-for-transformers/raw/main/intel_extension_for_transformers/neural_chat/assets/audio/sample.wav -O ${audio_fn}
+```
 
-Test dataprep microservice with generating transcript using whisper model
+Test dataprep microservice with generating transcript. This command updates a knowledge base by uploading a local video .mp4 and an audio .wav file.
 
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT} \
     -H 'Content-Type: multipart/form-data' \
-    -X POST -F "files=@./${video_fn}"
+    -X POST \
+    -F "files=@./${video_fn}" \
+    -F "files=@./${audio_fn}"
 ```
 
-Also, test dataprep microservice with generating caption using lvm-tgi
+Also, test dataprep microservice with generating an image caption using lvm-tgi
 
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT} \
     -H 'Content-Type: multipart/form-data' \
-    -X POST -F "files=@./${video_fn}"
+    -X POST -F "files=@./${image_fn}"
+```
+
+Now, test the microservice with posting a custom caption along with an image
+
+```bash
+curl --silent --write-out "HTTPSTATUS:%{http_code}" \
+    ${DATAPREP_INGEST_SERVICE_ENDPOINT} \
+    -H 'Content-Type: multipart/form-data' \
+    -X POST -F "files=@./${image_fn}" -F "files=@./${caption_fn}"
 ```
 
-Also, you are able to get the list of all videos that you uploaded:
+Also, you are able to get the list of all files that you uploaded:
 
 ```bash
 curl -X POST \
     -H "Content-Type: application/json" \
-    ${DATAPREP_GET_VIDEO_ENDPOINT}
+    ${DATAPREP_GET_FILE_ENDPOINT}
 ```
 
-Then you will get the response python-style LIST like this. Notice the name of each uploaded video e.g., `videoname.mp4` will become `videoname_uuid.mp4` where `uuid` is a unique ID for each uploaded video. The same video that are uploaded twice will have different `uuid`.
+Then you will get the response python-style LIST like this. Notice the name of each uploaded file e.g., `videoname.mp4` will become `videoname_uuid.mp4` where `uuid` is a unique ID for each uploaded file. The same files that are uploaded twice will have different `uuid`.
 
 ```bash
 [
     "WeAreGoingOnBullrun_7ac553a1-116c-40a2-9fc5-deccbb89b507.mp4",
-    "WeAreGoingOnBullrun_6d13cf26-8ba2-4026-a3a9-ab2e5eb73a29.mp4"
+    "WeAreGoingOnBullrun_6d13cf26-8ba2-4026-a3a9-ab2e5eb73a29.mp4",
+    "apple_fcade6e6-11a5-44a2-833a-3e534cbe4419.png",
+    "AudioSample_976a85a6-dc3e-43ab-966c-9d81beef780c.wav
 ]
 ```
 
-To delete all uploaded videos along with data indexed with `$INDEX_NAME` in REDIS.
+To delete all uploaded files along with data indexed with `$INDEX_NAME` in REDIS.
 
 ```bash
 curl -X POST \
     -H "Content-Type: application/json" \
-    ${DATAPREP_DELETE_VIDEO_ENDPOINT}
+    ${DATAPREP_DELETE_FILE_ENDPOINT}
 ```
 
 7. MegaService

MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -36,6 +36,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       PORT: ${EMBEDDER_PORT}
+    entrypoint: ["python", "bridgetower_server.py", "--device", "hpu", "--model_name_or_path", $EMBEDDING_MODEL_ID]
     restart: unless-stopped
   embedding-multimodal:
     image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest}
@@ -139,6 +140,7 @@ services:
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
       - BACKEND_SERVICE_ENDPOINT=${BACKEND_SERVICE_ENDPOINT}
+      - DATAPREP_INGEST_SERVICE_ENDPOINT=${DATAPREP_INGEST_SERVICE_ENDPOINT}
       - DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT=${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT}
       - DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT=${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT}
     ipc: host