Refactor lvm related examples (#1333)

Author: Spycsh

MultimodalQnA/docker_compose/amd/gpu/rocm/README.md

@@ -39,7 +39,7 @@ docker build --no-cache -t opea/embedding:latest --build-arg https_proxy=$https_
 Build lvm-llava image
 
 ```bash
-docker build --no-cache -t opea/lvm-llava:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/llava/dependency/Dockerfile .
+docker build --no-cache -t opea/lvm-llava:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/integrations/dependency/llava/Dockerfile .
 ```
 
 ### 3. Build retriever-multimodal-redis Image
@@ -85,7 +85,7 @@ Then run the command `docker images`, you will have the following 8 Docker Image
 
 1. `opea/dataprep-multimodal-redis:latest`
 2. `ghcr.io/huggingface/text-generation-inference:2.4.1-rocm`
-3. `opea/lvm-tgi:latest`
+3. `opea/lvm:latest`
 4. `opea/retriever-multimodal-redis:latest`
 5. `opea/embedding:latest`
 6. `opea/embedding-multimodal-bridgetower:latest`
@@ -193,7 +193,7 @@ curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
      -d '{"prompt":"Describe the image please.", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}'
 ```
 
-5. lvm-llava-svc
+5. lvm
 
 ```bash
 curl http://${host_ip}:9399/v1/lvm \

MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -24,7 +24,7 @@ services:
     container_name: dataprep-multimodal-redis
     depends_on:
       - redis-vector-db
-      - lvm-tgi
+      - lvm
     ports:
       - "6007:6007"
     environment:
@@ -116,9 +116,9 @@ services:
     ipc: host
     command: --model-id ${LVM_MODEL_ID} --max-input-tokens 3048 --max-total-tokens 4096
     restart: unless-stopped
-  lvm-tgi:
-    image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
-    container_name: lvm-tgi
+  lvm:
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm
     depends_on:
       - tgi-rocm
     ports:
@@ -128,6 +128,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
+      LVM_COMPONENT_NAME: "OPEA_TGI_LLAVA_LVM"
       LVM_ENDPOINT: ${LVM_ENDPOINT}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
@@ -140,7 +141,7 @@ services:
       - dataprep-multimodal-redis
       - embedding
       - retriever-redis
-      - lvm-tgi
+      - lvm
     ports:
       - "8888:8888"
     environment:

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

@@ -36,7 +36,7 @@ lvm-llava
 ================
 Port 8399 - Open to 0.0.0.0/0
 
-lvm-llava-svc
+lvm
 ===
 Port 9399 - Open to 0.0.0.0/0
 
@@ -132,13 +132,13 @@ docker build --no-cache -t opea/retriever-redis:latest --build-arg https_proxy=$
 Build lvm-llava image
 
 ```bash
-docker build --no-cache -t opea/lvm-llava:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/llava/dependency/Dockerfile .
+docker build --no-cache -t opea/lvm-llava:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/integrations/dependency/llava/Dockerfile .
 ```
 
-Build lvm-llava-svc microservice image
+Build lvm microservice image
 
 ```bash
-docker build --no-cache -t opea/lvm-llava-svc:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/llava/Dockerfile .
+docker build --no-cache -t opea/lvm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/Dockerfile .
 ```
 
 ### 4. Build dataprep-multimodal-redis Image
@@ -179,7 +179,7 @@ cd ../../../
 Then run the command `docker images`, you will have the following 11 Docker Images:
 
 1. `opea/dataprep-multimodal-redis:latest`
-2. `opea/lvm-llava-svc:latest`
+2. `opea/lvm:latest`
 3. `opea/lvm-llava:latest`
 4. `opea/retriever-multimodal-redis:latest`
 5. `opea/whisper:latest`
@@ -271,7 +271,7 @@ curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
      -d '{"prompt":"Describe the image please.", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}'
 ```
 
-6. lvm-llava-svc
+6. lvm
 
 ```bash
 curl http://${host_ip}:9399/v1/lvm \

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

@@ -100,9 +100,9 @@ services:
       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}
-    container_name: lvm-llava-svc
+  lvm:
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm
     depends_on:
       - lvm-llava
     ports:
@@ -112,6 +112,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
+      LVM_COMPONENT_NAME: "OPEA_LLAVA_LVM"
       LVM_ENDPOINT: ${LVM_ENDPOINT}
     restart: unless-stopped
   multimodalqna:
@@ -122,7 +123,7 @@ services:
       - dataprep-multimodal-redis
       - embedding
       - retriever-redis
-      - lvm-llava-svc
+      - lvm
     ports:
       - "8888:8888"
     environment:

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

@@ -86,10 +86,10 @@ Build TGI Gaudi image
 docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
 ```
 
-Build lvm-tgi microservice image
+Build lvm microservice image
 
 ```bash
-docker build --no-cache -t opea/lvm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/tgi-llava/Dockerfile .
+docker build --no-cache -t opea/lvm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/Dockerfile .
 ```
 
 ### 4. Build dataprep-multimodal-redis Image
@@ -128,7 +128,7 @@ docker build --no-cache -t opea/multimodalqna-ui:latest --build-arg https_proxy=
 Then run the command `docker images`, you will have the following 11 Docker Images:
 
 1. `opea/dataprep-multimodal-redis:latest`
-2. `opea/lvm-tgi:latest`
+2. `opea/lvm:latest`
 3. `ghcr.io/huggingface/tgi-gaudi:2.0.6`
 4. `opea/retriever-multimodal-redis:latest`
 5. `opea/whisper:latest`
@@ -220,7 +220,7 @@ curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
     -H 'Content-Type: application/json'
 ```
 
-6. lvm-tgi
+6. lvm
 
 ```bash
 curl http://${host_ip}:9399/v1/lvm \
@@ -274,7 +274,7 @@ curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     -F "files=@./${audio_fn}"
 ```
 
-Also, test dataprep microservice with generating an image caption using lvm-tgi
+Also, test dataprep microservice with generating an image caption using lvm
 
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \

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

@@ -24,7 +24,7 @@ services:
     container_name: dataprep-multimodal-redis
     depends_on:
       - redis-vector-db
-      - lvm-tgi
+      - lvm
     ports:
       - "6007:6007"
     environment:
@@ -115,9 +115,9 @@ services:
     ipc: host
     command: --model-id ${LVM_MODEL_ID} --max-input-tokens 3048 --max-total-tokens 4096
     restart: unless-stopped
-  lvm-tgi:
-    image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
-    container_name: lvm-tgi
+  lvm:
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm
     depends_on:
       - tgi-gaudi
     ports:
@@ -127,6 +127,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
+      LVM_COMPONENT_NAME: "OPEA_TGI_LLAVA_LVM"
       LVM_ENDPOINT: ${LVM_ENDPOINT}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
@@ -139,7 +140,7 @@ services:
       - dataprep-multimodal-redis
       - embedding
       - retriever-redis
-      - lvm-tgi
+      - lvm
     ports:
       - "8888:8888"
     environment:

MultimodalQnA/docker_image_build/build.yaml

@@ -38,21 +38,15 @@ services:
   lvm-llava:
     build:
       context: GenAIComps
-      dockerfile: comps/lvms/llava/dependency/Dockerfile
+      dockerfile: comps/lvms/src/integrations/dependency/llava/Dockerfile
     extends: multimodalqna
     image: ${REGISTRY:-opea}/lvm-llava:${TAG:-latest}
-  lvm-llava-svc:
+  lvm:
     build:
       context: GenAIComps
-      dockerfile: comps/lvms/llava/Dockerfile
+      dockerfile: comps/lvms/src/Dockerfile
     extends: multimodalqna
-    image: ${REGISTRY:-opea}/lvm-llava-svc:${TAG:-latest}
-  lvm-tgi:
-    build:
-      context: GenAIComps
-      dockerfile: comps/lvms/tgi-llava/Dockerfile
-    extends: multimodalqna
-    image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
   dataprep-multimodal-redis:
     build:
       context: GenAIComps

MultimodalQnA/tests/test_compose_on_gaudi.sh

@@ -22,7 +22,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm-tgi dataprep-multimodal-redis whisper"
+    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm dataprep-multimodal-redis whisper"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
@@ -214,12 +214,12 @@ function validate_microservices() {
         '{"inputs":"![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)What is this a picture of?\n\n","parameters":{"max_new_tokens":16, "seed": 42}}'
 
     # lvm
-    echo "Evaluating lvm-tgi"
+    echo "Evaluating lvm"
     validate_service \
         "http://${host_ip}:9399/v1/lvm" \
         '"text":"' \
-        "lvm-tgi" \
-        "lvm-tgi" \
+        "lvm" \
+        "lvm" \
         '{"retrieved_docs": [], "initial_query": "What is this?", "top_n": 1, "metadata": [{"b64_img_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC", "transcript_for_inference": "yellow image", "video_id": "8c7461df-b373-4a00-8696-9a2234359fe0", "time_of_frame_ms":"37000000", "source_video":"WeAreGoingOnBullrun_8c7461df-b373-4a00-8696-9a2234359fe0.mp4"}], "chat_template":"The caption of the image is: '\''{context}'\''. {question}"}'
 
     # data prep requiring lvm

MultimodalQnA/tests/test_compose_on_rocm.sh

@@ -23,7 +23,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm-tgi lvm-llava-svc dataprep-multimodal-redis whisper"
+    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm dataprep-multimodal-redis whisper"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1m
@@ -220,12 +220,12 @@ function validate_microservices() {
         '{"inputs":"![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)What is this a picture of?\n\n","parameters":{"max_new_tokens":16, "seed": 42}}'
 
     # lvm
-    echo "Evaluating lvm-llava-svc"
+    echo "Evaluating lvm"
     validate_service \
         "http://${host_ip}:9399/v1/lvm" \
         '"text":"' \
-        "lvm-tgi" \
-        "lvm-tgi" \
+        "lvm" \
+        "lvm" \
         '{"retrieved_docs": [], "initial_query": "What is this?", "top_n": 1, "metadata": [{"b64_img_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC", "transcript_for_inference": "yellow image", "video_id": "8c7461df-b373-4a00-8696-9a2234359fe0", "time_of_frame_ms":"37000000", "source_video":"WeAreGoingOnBullrun_8c7461df-b373-4a00-8696-9a2234359fe0.mp4"}], "chat_template":"The caption of the image is: '\''{context}'\''. {question}"}'
 
     # data prep requiring lvm

MultimodalQnA/tests/test_compose_on_xeon.sh

@@ -22,7 +22,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm-llava lvm-llava-svc dataprep-multimodal-redis whisper"
+    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding retriever-redis lvm-llava lvm dataprep-multimodal-redis whisper"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1m
@@ -212,12 +212,12 @@ function validate_microservices() {
         '{"prompt":"Describe the image please.", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}'
 
     # lvm
-    echo "Evaluating lvm-llava-svc"
+    echo "Evaluating lvm"
     validate_service \
         "http://${host_ip}:9399/v1/lvm" \
         '"text":"' \
-        "lvm-llava-svc" \
-        "lvm-llava-svc" \
+        "lvm" \
+        "lvm" \
         '{"retrieved_docs": [], "initial_query": "What is this?", "top_n": 1, "metadata": [{"b64_img_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC", "transcript_for_inference": "yellow image", "video_id": "8c7461df-b373-4a00-8696-9a2234359fe0", "time_of_frame_ms":"37000000", "source_video":"WeAreGoingOnBullrun_8c7461df-b373-4a00-8696-9a2234359fe0.mp4"}], "chat_template":"The caption of the image is: '\''{context}'\''. {question}"}'
 
     # data prep requiring lvm

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

@@ -71,10 +71,10 @@ docker build -t opea/reranking:latest --build-arg https_proxy=$https_proxy --bui
 ### 4. Build LVM Image (Xeon)
 
 ```bash
-docker build -t opea/video-llama-lvm-server:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/video-llama/dependency/Dockerfile .
+docker build -t opea/lvm-video-llama:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/integrations/dependency/video-llama/Dockerfile .
 
 # LVM Service Image
-docker build -t opea/lvm-video-llama:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/video-llama/Dockerfile .
+docker build -t opea/lvm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/Dockerfile .
 ```
 
 ### 5. Build Dataprep Image
@@ -109,11 +109,16 @@ Then run the command `docker images`, you will have the following 8 Docker Image
 1. `opea/dataprep-multimodal-vdms:latest`
 2. `opea/embedding-multimodal-clip:latest`
 3. `opea/retriever-vdms:latest`
+   <<<<<<< HEAD
 4. `opea/reranking:latest`
 5. `opea/video-llama-lvm-server:latest`
-6. `opea/lvm-video-llama:latest`
-7. `opea/videoqna:latest`
-8. `opea/videoqna-ui:latest`
+6. # `opea/lvm-video-llama:latest`
+7. `opea/reranking-tei:latest`
+8. `opea/lvm-video-llama:latest`
+9. `opea/lvm:latest`
+   > > > > > > > d93597cbfd9da92b956adb3673c9e5d743c181af
+10. `opea/videoqna:latest`
+11. `opea/videoqna-ui:latest`
 
 ## 🚀 Start Microservices
 
@@ -275,7 +280,7 @@ docker compose up -d
 
    In first startup, this service will take times to download the LLM file. After it's finished, the service will be ready.
 
-   Use `docker logs video-llama-lvm-server` to check if the download is finished.
+   Use `docker logs lvm-video-llama` to check if the download is finished.
 
    ```bash
    curl -X POST \

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

@@ -75,8 +75,8 @@ services:
       DATAPREP_GET_VIDEO_LIST_ENDPOINT: ${DATAPREP_GET_VIDEO_LIST_ENDPOINT}
     restart: unless-stopped
   lvm-video-llama:
-    image: ${REGISTRY:-opea}/video-llama-lvm-server:${TAG:-latest}
-    container_name: video-llama-lvm-server
+    image: ${REGISTRY:-opea}/lvm-video-llama:${TAG:-latest}
+    container_name: lvm-video-llama
     ports:
       - "9009:9009"
     ipc: host
@@ -90,15 +90,16 @@ services:
       - video-llama-model:/home/user/model
     restart: unless-stopped
   lvm:
-    image: ${REGISTRY:-opea}/lvm-video-llama:${TAG:-latest}
-    container_name: lvm-video-llama
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm
     ports:
       - "9000:9000"
     ipc: host
     environment:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       no_proxy: ${no_proxy}
+      LVM_COMPONENT_NAME: "OPEA_VIDEO_LLAMA_LVM"
       LVM_ENDPOINT: ${LVM_ENDPOINT}
     restart: unless-stopped
     depends_on: