diff --git a/.github/workflows/scripts/check_duplicated_image.py b/.github/workflows/scripts/check_duplicated_image.py index ed565b229..bcdf718f8 100644 --- a/.github/workflows/scripts/check_duplicated_image.py +++ b/.github/workflows/scripts/check_duplicated_image.py @@ -9,6 +9,8 @@ import sys import yaml images = {} +dockerfiles = {} +errors = [] def check_docker_compose_build_definition(file_path): @@ -30,18 +32,26 @@ def check_docker_compose_build_definition(file_path): if not os.path.isfile(dockerfile): # dockerfile not exists in the current repo context, assume it's in 3rd party context dockerfile = os.path.normpath(os.path.join(context, build.get("dockerfile", ""))) - item = {"file_path": file_path, "service": service, "dockerfile": dockerfile} + item = {"file_path": file_path, "service": service, "dockerfile": dockerfile, "image": image} if image in images and dockerfile != images[image]["dockerfile"]: - print("ERROR: !!! Found Conflicts !!!") - print(f"Image: {image}, Dockerfile: {dockerfile}, defined in Service: {service}, File: {file_path}") - print( + errors.append( + f"ERROR: !!! Found Conflicts !!!\n" + f"Image: {image}, Dockerfile: {dockerfile}, defined in Service: {service}, File: {file_path}\n" f"Image: {image}, Dockerfile: {images[image]['dockerfile']}, defined in Service: {images[image]['service']}, File: {images[image]['file_path']}" ) - sys.exit(1) else: # print(f"Add Image: {image} Dockerfile: {dockerfile}") images[image] = item + if dockerfile in dockerfiles and image != dockerfiles[dockerfile]["image"]: + errors.append( + f"WARNING: Different images using the same Dockerfile\n" + f"Dockerfile: {dockerfile}, Image: {image}, defined in Service: {service}, File: {file_path}\n" + f"Dockerfile: {dockerfile}, Image: {dockerfiles[dockerfile]['image']}, defined in Service: {dockerfiles[dockerfile]['service']}, File: {dockerfiles[dockerfile]['file_path']}" + ) + else: + dockerfiles[dockerfile] = item + def parse_arg(): parser = argparse.ArgumentParser( @@ -56,6 +66,12 @@ def main(): for file_path in args.files: check_docker_compose_build_definition(file_path) print("SUCCESS: No Conlicts Found.") + if errors: + for error in errors: + print(error) + sys.exit(1) + else: + print("SUCCESS: No Conflicts Found.") return 0 diff --git a/AudioQnA/docker_image_build/build.yaml b/AudioQnA/docker_image_build/build.yaml index 8bbdbcc3e..bc9f67d9c 100644 --- a/AudioQnA/docker_image_build/build.yaml +++ b/AudioQnA/docker_image_build/build.yaml @@ -41,12 +41,12 @@ services: dockerfile: comps/asr/src/Dockerfile extends: audioqna image: ${REGISTRY:-opea}/asr:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: audioqna - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} speecht5-gaudi: build: context: GenAIComps diff --git a/AudioQnA/kubernetes/intel/README_gmc.md b/AudioQnA/kubernetes/intel/README_gmc.md index 6c9e7394c..e64bdb21e 100644 --- a/AudioQnA/kubernetes/intel/README_gmc.md +++ b/AudioQnA/kubernetes/intel/README_gmc.md @@ -15,7 +15,7 @@ The AudioQnA application is defined as a Custom Resource (CR) file that the abov The AudioQnA uses the below prebuilt images if you choose a Xeon deployment - tgi-service: ghcr.io/huggingface/text-generation-inference:1.4 -- llm: opea/llm-tgi:latest +- llm: opea/llm-textgen:latest - asr: opea/asr:latest - whisper: opea/whisper:latest - tts: opea/tts:latest diff --git a/AvatarChatbot/docker_image_build/build.yaml b/AvatarChatbot/docker_image_build/build.yaml index 25c597c4e..2ff1a27b3 100644 --- a/AvatarChatbot/docker_image_build/build.yaml +++ b/AvatarChatbot/docker_image_build/build.yaml @@ -29,12 +29,12 @@ services: dockerfile: comps/asr/src/Dockerfile extends: avatarchatbot image: ${REGISTRY:-opea}/asr:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: avatarchatbot - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} speecht5-gaudi: build: context: GenAIComps diff --git a/AvatarChatbot/ui/gradio/app_gradio_demo_avatarchatbot.py b/AvatarChatbot/ui/gradio/app_gradio_demo_avatarchatbot.py index 19817d505..1aad8c56c 100644 --- a/AvatarChatbot/ui/gradio/app_gradio_demo_avatarchatbot.py +++ b/AvatarChatbot/ui/gradio/app_gradio_demo_avatarchatbot.py @@ -294,7 +294,7 @@ if __name__ == "__main__":

OPEA microservices deployed:

diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md b/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md index d9684e9db..f4bf0c0a7 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md @@ -44,7 +44,7 @@ CONTAINER ID IMAGE COMMAND 28d9a5570246 opea/chatqna-ui:latest "docker-entrypoint.s…" 2 minutes ago Up 2 minutes 0.0.0.0:5173->5173/tcp, :::5173->5173/tcp chatqna-gaudi-ui-server bee1132464cd opea/chatqna:latest "python chatqna.py" 2 minutes ago Up 2 minutes 0.0.0.0:8888->8888/tcp, :::8888->8888/tcp chatqna-gaudi-backend-server f810f3b4d329 opea/embedding-tei:latest "python embedding_te…" 2 minutes ago Up 2 minutes 0.0.0.0:6000->6000/tcp, :::6000->6000/tcp embedding-tei-server -325236a01f9b opea/llm-tgi:latest "python llm.py" 2 minutes ago Up 2 minutes 0.0.0.0:9000->9000/tcp, :::9000->9000/tcp llm-tgi-gaudi-server +325236a01f9b opea/llm-textgen:latest "python llm.py" 2 minutes ago Up 2 minutes 0.0.0.0:9000->9000/tcp, :::9000->9000/tcp llm-textgen-gaudi-server 2fa17d84605f opea/dataprep-redis:latest "python prepare_doc_…" 2 minutes ago Up 2 minutes 0.0.0.0:6007->6007/tcp, :::6007->6007/tcp dataprep-redis-server 69e1fb59e92c opea/retriever-redis:latest "/home/user/comps/re…" 2 minutes ago Up 2 minutes 0.0.0.0:7000->7000/tcp, :::7000->7000/tcp retriever-redis-server 313b9d14928a opea/reranking-tei:latest "python reranking_te…" 2 minutes ago Up 2 minutes 0.0.0.0:8000->8000/tcp, :::8000->8000/tcp reranking-tei-gaudi-server diff --git a/ChatQnA/docker_image_build/build.yaml b/ChatQnA/docker_image_build/build.yaml index 439c12fd6..e5f460a8d 100644 --- a/ChatQnA/docker_image_build/build.yaml +++ b/ChatQnA/docker_image_build/build.yaml @@ -71,24 +71,12 @@ services: dockerfile: comps/reranks/src/Dockerfile extends: chatqna image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: chatqna - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - llm-ollama: - build: - context: GenAIComps - dockerfile: comps/llms/src/text-generation/Dockerfile - extends: chatqna - image: ${REGISTRY:-opea}/llm-ollama:${TAG:-latest} - llm-vllm: - build: - context: GenAIComps - dockerfile: comps/llms/src/text-generation/Dockerfile - extends: chatqna - image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} dataprep-redis: build: context: GenAIComps diff --git a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-remote-inference.yaml b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-remote-inference.yaml index 453ff404a..4fa9d7c1a 100644 --- a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-remote-inference.yaml +++ b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-remote-inference.yaml @@ -774,7 +774,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-vllm:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: Always ports: - name: llm-uservice diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm-remote-inference.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm-remote-inference.yaml index 3262b5420..91f503cec 100644 --- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm-remote-inference.yaml +++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm-remote-inference.yaml @@ -682,7 +682,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-vllm:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: Always ports: - name: llm-uservice diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml index eabff7f86..2ffd4433b 100644 --- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml +++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml @@ -811,7 +811,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-vllm:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: Always ports: - name: llm-uservice diff --git a/CodeGen/docker_compose/amd/gpu/rocm/README.md b/CodeGen/docker_compose/amd/gpu/rocm/README.md index a1ac0ce60..d8c6a4c88 100644 --- a/CodeGen/docker_compose/amd/gpu/rocm/README.md +++ b/CodeGen/docker_compose/amd/gpu/rocm/README.md @@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps ### Build Docker image -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### Build the MegaService Docker Image diff --git a/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml b/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml index 55abc832b..b558697d8 100644 --- a/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml +++ b/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml @@ -34,7 +34,7 @@ services: ipc: host command: --model-id ${CODEGEN_LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048 codegen-llm-server: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} container_name: codegen-llm-server depends_on: codegen-tgi-service: diff --git a/CodeGen/docker_compose/intel/cpu/xeon/README.md b/CodeGen/docker_compose/intel/cpu/xeon/README.md index e5ea8e7d5..8db3c15c8 100644 --- a/CodeGen/docker_compose/intel/cpu/xeon/README.md +++ b/CodeGen/docker_compose/intel/cpu/xeon/README.md @@ -19,7 +19,7 @@ Should the Docker image you seek not yet be available on Docker Hub, you can bui ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build the MegaService Docker Image @@ -43,7 +43,7 @@ docker build -t opea/codegen-ui:latest --build-arg https_proxy=$https_proxy --bu Then run the command `docker images`, you will have the following 3 Docker Images: -- `opea/llm-tgi:latest` +- `opea/llm-textgen:latest` - `opea/codegen:latest` - `opea/codegen-ui:latest` @@ -60,7 +60,7 @@ docker build --no-cache -t opea/codegen-react-ui:latest --build-arg https_proxy= Then run the command `docker images`, you will have the following 3 Docker Images: -- `opea/llm-tgi:latest` +- `opea/llm-textgen:latest` - `opea/codegen:latest` - `opea/codegen-ui:latest` - `opea/codegen-react-ui:latest` (optional) diff --git a/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml b/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml index 96226fe21..28940c9ba 100644 --- a/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml +++ b/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml @@ -23,8 +23,8 @@ services: retries: 100 command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server depends_on: tgi-service: condition: service_healthy diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/README.md b/CodeGen/docker_compose/intel/hpu/gaudi/README.md index ef2692f0d..0006f019e 100644 --- a/CodeGen/docker_compose/intel/hpu/gaudi/README.md +++ b/CodeGen/docker_compose/intel/hpu/gaudi/README.md @@ -11,7 +11,7 @@ First of all, you need to build the Docker images locally. This step can be igno ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build the MegaService Docker Image @@ -46,7 +46,7 @@ docker build --no-cache -t opea/codegen-react-ui:latest --build-arg https_proxy= Then run the command `docker images`, you will have the following 3 Docker images: -- `opea/llm-tgi:latest` +- `opea/llm-textgen:latest` - `opea/codegen:latest` - `opea/codegen-ui:latest` - `opea/codegen-react-ui:latest` diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml index 7f7e71295..e2f72ff93 100644 --- a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml @@ -31,8 +31,8 @@ services: ipc: host command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-gaudi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-gaudi-server depends_on: tgi-service: condition: service_healthy diff --git a/CodeGen/docker_image_build/build.yaml b/CodeGen/docker_image_build/build.yaml index 9af65d777..aaee45977 100644 --- a/CodeGen/docker_image_build/build.yaml +++ b/CodeGen/docker_image_build/build.yaml @@ -23,9 +23,9 @@ services: dockerfile: ./docker/Dockerfile.react extends: codegen image: ${REGISTRY:-opea}/codegen-react-ui:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: codegen - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml index d0070dc96..30fb919f0 100644 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml @@ -325,7 +325,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml index a155af13a..1ebd1d4a4 100644 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml +++ b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml @@ -179,7 +179,7 @@ spec: - name: no_proxy value: securityContext: {} - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml index dc032cd25..1273b943a 100644 --- a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml +++ b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml @@ -326,7 +326,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/CodeGen/tests/test_compose_on_gaudi.sh b/CodeGen/tests/test_compose_on_gaudi.sh index 8e06a904d..cde88a64e 100644 --- a/CodeGen/tests/test_compose_on_gaudi.sh +++ b/CodeGen/tests/test_compose_on_gaudi.sh @@ -19,7 +19,7 @@ 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="codegen codegen-ui llm-tgi" + service_list="codegen codegen-ui llm-textgen" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 @@ -94,7 +94,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-gaudi-server" \ + "llm-textgen-gaudi-server" \ '{"query":"def print_hello_world():"}' } diff --git a/CodeGen/tests/test_compose_on_rocm.sh b/CodeGen/tests/test_compose_on_rocm.sh index a09a368b6..0690b502b 100644 --- a/CodeGen/tests/test_compose_on_rocm.sh +++ b/CodeGen/tests/test_compose_on_rocm.sh @@ -19,7 +19,7 @@ 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="codegen codegen-ui llm-tgi" + service_list="codegen codegen-ui llm-textgen" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu diff --git a/CodeGen/tests/test_compose_on_xeon.sh b/CodeGen/tests/test_compose_on_xeon.sh index e95052497..20a4a366e 100644 --- a/CodeGen/tests/test_compose_on_xeon.sh +++ b/CodeGen/tests/test_compose_on_xeon.sh @@ -19,7 +19,7 @@ function build_docker_images() { git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../ echo "Build all the images with --no-cache, check docker_image_build.log for details..." - service_list="codegen codegen-ui llm-tgi" + service_list="codegen codegen-ui llm-textgen" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu @@ -95,7 +95,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-server" \ + "llm-textgen-server" \ '{"query":"def print_hello_world():"}' } diff --git a/CodeTrans/docker_compose/amd/gpu/rocm/README.md b/CodeTrans/docker_compose/amd/gpu/rocm/README.md index 38954284e..fc80bcf92 100644 --- a/CodeTrans/docker_compose/amd/gpu/rocm/README.md +++ b/CodeTrans/docker_compose/amd/gpu/rocm/README.md @@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps ### Build Docker image -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### Build the MegaService Docker Image diff --git a/CodeTrans/docker_compose/amd/gpu/rocm/compose.yaml b/CodeTrans/docker_compose/amd/gpu/rocm/compose.yaml index e58041f80..a4c33cd3f 100644 --- a/CodeTrans/docker_compose/amd/gpu/rocm/compose.yaml +++ b/CodeTrans/docker_compose/amd/gpu/rocm/compose.yaml @@ -35,7 +35,7 @@ services: ipc: host command: --model-id ${CODETRANS_LLM_MODEL_ID} codetrans-llm-server: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} container_name: codetrans-llm-server depends_on: codetrans-tgi-service: diff --git a/CodeTrans/docker_compose/intel/cpu/xeon/README.md b/CodeTrans/docker_compose/intel/cpu/xeon/README.md index c574740e3..3c878adaa 100755 --- a/CodeTrans/docker_compose/intel/cpu/xeon/README.md +++ b/CodeTrans/docker_compose/intel/cpu/xeon/README.md @@ -19,7 +19,7 @@ First of all, you need to build Docker Images locally and install the python pac ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build MegaService Docker Image @@ -46,7 +46,7 @@ docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-a Then run the command `docker images`, you will have the following Docker Images: -- `opea/llm-tgi:latest` +- `opea/llm-textgen:latest` - `opea/codetrans:latest` - `opea/codetrans-ui:latest` - `opea/nginx:latest` diff --git a/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml b/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml index 896243786..b818956fa 100644 --- a/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml +++ b/CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml @@ -23,8 +23,8 @@ services: retries: 100 command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server depends_on: tgi-service: condition: service_healthy diff --git a/CodeTrans/docker_compose/intel/hpu/gaudi/README.md b/CodeTrans/docker_compose/intel/hpu/gaudi/README.md index c0ca35fcf..668af444e 100755 --- a/CodeTrans/docker_compose/intel/hpu/gaudi/README.md +++ b/CodeTrans/docker_compose/intel/hpu/gaudi/README.md @@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally and install the python pac ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --no-cache --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --no-cache --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build MegaService Docker Image @@ -38,7 +38,7 @@ docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-a Then run the command `docker images`, you will have the following Docker Images: -- `opea/llm-tgi:latest` +- `opea/llm-textgen:latest` - `opea/codetrans:latest` - `opea/codetrans-ui:latest` - `opea/nginx:latest` diff --git a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml index c1c6c4c53..cbccde060 100644 --- a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml @@ -31,8 +31,8 @@ services: ipc: host command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-gaudi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-gaudi-server depends_on: tgi-service: condition: service_healthy diff --git a/CodeTrans/docker_image_build/build.yaml b/CodeTrans/docker_image_build/build.yaml index 3f3ec36a0..d9a565fcd 100644 --- a/CodeTrans/docker_image_build/build.yaml +++ b/CodeTrans/docker_image_build/build.yaml @@ -17,12 +17,12 @@ services: dockerfile: ./docker/Dockerfile extends: codetrans image: ${REGISTRY:-opea}/codetrans-ui:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: codetrans - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} nginx: build: context: GenAIComps diff --git a/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml b/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml index a778a8529..a632517c9 100644 --- a/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml +++ b/CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml @@ -325,7 +325,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml b/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml index a2efecf44..870231944 100644 --- a/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml +++ b/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml @@ -326,7 +326,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/CodeTrans/tests/test_compose_on_gaudi.sh b/CodeTrans/tests/test_compose_on_gaudi.sh index ecab66c6f..b913a5c2e 100644 --- a/CodeTrans/tests/test_compose_on_gaudi.sh +++ b/CodeTrans/tests/test_compose_on_gaudi.sh @@ -19,7 +19,7 @@ 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="codetrans codetrans-ui llm-tgi nginx" + service_list="codetrans codetrans-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 @@ -103,7 +103,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-gaudi-server" \ + "llm-textgen-gaudi-server" \ '{"query":" ### System: Please translate the following Golang codes into Python codes. ### Original codes: '\'''\'''\''Golang \npackage main\n\nimport \"fmt\"\nfunc main() {\n fmt.Println(\"Hello, World!\");\n '\'''\'''\'' ### Translated codes:"}' } diff --git a/CodeTrans/tests/test_compose_on_rocm.sh b/CodeTrans/tests/test_compose_on_rocm.sh index 322e9174c..3a5801dd7 100644 --- a/CodeTrans/tests/test_compose_on_rocm.sh +++ b/CodeTrans/tests/test_compose_on_rocm.sh @@ -20,7 +20,7 @@ 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="codetrans codetrans-ui llm-tgi nginx" + service_list="codetrans codetrans-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm diff --git a/CodeTrans/tests/test_compose_on_xeon.sh b/CodeTrans/tests/test_compose_on_xeon.sh index 1d883dfdb..4b0538cda 100644 --- a/CodeTrans/tests/test_compose_on_xeon.sh +++ b/CodeTrans/tests/test_compose_on_xeon.sh @@ -19,7 +19,7 @@ function build_docker_images() { git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../ echo "Build all the images with --no-cache, check docker_image_build.log for details..." - service_list="codetrans codetrans-ui llm-tgi nginx" + service_list="codetrans codetrans-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu @@ -102,7 +102,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-server" \ + "llm-textgen-server" \ '{"query":" ### System: Please translate the following Golang codes into Python codes. ### Original codes: '\'''\'''\''Golang \npackage main\n\nimport \"fmt\"\nfunc main() {\n fmt.Println(\"Hello, World!\");\n '\'''\'''\'' ### Translated codes:"}' } diff --git a/FaqGen/docker_compose/amd/gpu/rocm/README.md b/FaqGen/docker_compose/amd/gpu/rocm/README.md index 49b99666f..d628b8784 100644 --- a/FaqGen/docker_compose/amd/gpu/rocm/README.md +++ b/FaqGen/docker_compose/amd/gpu/rocm/README.md @@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps ### Build Docker image -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ## 🚀 Start Microservices and MegaService diff --git a/MultimodalQnA/README.md b/MultimodalQnA/README.md index 08de5686a..2e730bb88 100644 --- a/MultimodalQnA/README.md +++ b/MultimodalQnA/README.md @@ -100,12 +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 | 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 | +| Service | HW | Model | +| ------------- | ----- | ----------------------------------------- | +| embedding-tei | Xeon | BridgeTower/bridgetower-large-itm-mlm-itc | +| LVM | Xeon | llava-hf/llava-1.5-7b-hf | +| embedding-tei | 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. diff --git a/MultimodalQnA/docker_compose/amd/gpu/rocm/README.md b/MultimodalQnA/docker_compose/amd/gpu/rocm/README.md index 58ecec485..062b912d1 100644 --- a/MultimodalQnA/docker_compose/amd/gpu/rocm/README.md +++ b/MultimodalQnA/docker_compose/amd/gpu/rocm/README.md @@ -28,10 +28,10 @@ cd GenAIComps docker build --no-cache -t opea/embedding-multimodal-bridgetower:latest --build-arg EMBEDDER_PORT=$EMBEDDER_PORT --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile . ``` -Build embedding-multimodal microservice image +Build embedding-tei microservice image ```bash -docker build --no-cache -t opea/embedding-multimodal:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . +docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . ``` ### 2. Build LVM Images @@ -87,7 +87,7 @@ Then run the command `docker images`, you will have the following 8 Docker Image 2. `ghcr.io/huggingface/text-generation-inference:2.4.1-rocm` 3. `opea/lvm-tgi:latest` 4. `opea/retriever-multimodal-redis:latest` -5. `opea/embedding-multimodal:latest` +5. `opea/embedding-tei:latest` 6. `opea/embedding-multimodal-bridgetower:latest` 7. `opea/multimodalqna:latest` 8. `opea/multimodalqna-ui:latest` @@ -98,11 +98,11 @@ Then run the command `docker images`, you will have the following 8 Docker Image By default, the multimodal-embedding and LVM models are set to a default value as listed below: -| Service | Model | -| -------------------- | ------------------------------------------- | -| embedding-multimodal | BridgeTower/bridgetower-large-itm-mlm-gaudi | -| LVM | llava-hf/llava-1.5-7b-hf | -| LVM | Xkev/Llama-3.2V-11B-cot | +| Service | Model | +| ------------- | ------------------------------------------- | +| embedding-tei | BridgeTower/bridgetower-large-itm-mlm-gaudi | +| LVM | llava-hf/llava-1.5-7b-hf | +| LVM | Xkev/Llama-3.2V-11B-cot | Note: @@ -158,7 +158,7 @@ curl http://${host_ip}:${EMBEDDER_PORT}/v1/encode \ -d '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' ``` -2. embedding-multimodal +2. embedding-tei ```bash curl http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings \ diff --git a/MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml b/MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml index ab467d7d3..c334485cc 100644 --- a/MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml +++ b/MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml @@ -55,9 +55,9 @@ services: start_period: 30s 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} - container_name: embedding-multimodal + embedding-tei: + image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest} + container_name: embedding-tei depends_on: embedding-multimodal-bridgetower: condition: service_healthy @@ -138,7 +138,7 @@ services: depends_on: - redis-vector-db - dataprep-multimodal-redis - - embedding-multimodal + - embedding-tei - retriever-redis - lvm-tgi ports: diff --git a/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md b/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md index 9295d30f8..fc6cd934c 100644 --- a/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md +++ b/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md @@ -24,7 +24,7 @@ embedding-multimodal-bridgetower ===================== Port 6006 - Open to 0.0.0.0/0 -embedding-multimodal +embedding-tei ========= Port 6000 - Open to 0.0.0.0/0 @@ -115,10 +115,10 @@ cd GenAIComps docker build --no-cache -t opea/embedding-multimodal-bridgetower:latest --build-arg EMBEDDER_PORT=$EMBEDDER_PORT --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile . ``` -Build embedding-multimodal microservice image +Build embedding-tei microservice image ```bash -docker build --no-cache -t opea/embedding-multimodal:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . +docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . ``` ### 2. Build retriever-multimodal-redis Image @@ -184,7 +184,7 @@ Then run the command `docker images`, you will have the following 11 Docker Imag 4. `opea/retriever-multimodal-redis:latest` 5. `opea/whisper:latest` 6. `opea/redis-vector-db` -7. `opea/embedding-multimodal:latest` +7. `opea/embedding-tei:latest` 8. `opea/embedding-multimodal-bridgetower:latest` 9. `opea/multimodalqna:latest` 10. `opea/multimodalqna-ui:latest` @@ -195,10 +195,10 @@ Then run the command `docker images`, you will have the following 11 Docker Imag By default, the multimodal-embedding and LVM models are set to a default value as listed below: -| Service | Model | -| -------------------- | ------------------------------------------- | -| embedding-multimodal | BridgeTower/bridgetower-large-itm-mlm-gaudi | -| LVM | llava-hf/llava-1.5-7b-hf | +| Service | Model | +| ------------- | ------------------------------------------- | +| embedding-tei | BridgeTower/bridgetower-large-itm-mlm-gaudi | +| LVM | llava-hf/llava-1.5-7b-hf | ### Start all the services Docker Containers @@ -227,7 +227,7 @@ curl http://${host_ip}:${EMBEDDER_PORT}/v1/encode \ -d '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' ``` -2. embedding-multimodal +2. embedding-tei ```bash curl http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings \ diff --git a/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml b/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml index 9a04cb98a..3c41dfb3e 100644 --- a/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml +++ b/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml @@ -55,9 +55,9 @@ services: start_period: 30s 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} - container_name: embedding-multimodal + embedding-tei: + image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest} + container_name: embedding-tei depends_on: embedding-multimodal-bridgetower: condition: service_healthy @@ -120,7 +120,7 @@ services: depends_on: - redis-vector-db - dataprep-multimodal-redis - - embedding-multimodal + - embedding-tei - retriever-redis - lvm-llava-svc ports: diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md index bc16365cf..c4476d5d1 100644 --- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md @@ -66,10 +66,10 @@ cd GenAIComps docker build --no-cache -t opea/embedding-multimodal-bridgetower:latest --build-arg EMBEDDER_PORT=$EMBEDDER_PORT --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile . ``` -Build embedding-multimodal microservice image +Build embedding-tei microservice image ```bash -docker build --no-cache -t opea/embedding-multimodal:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . +docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile . ``` ### 2. Build retriever-multimodal-redis Image @@ -133,7 +133,7 @@ Then run the command `docker images`, you will have the following 11 Docker Imag 4. `opea/retriever-multimodal-redis:latest` 5. `opea/whisper:latest` 6. `opea/redis-vector-db` -7. `opea/embedding-multimodal:latest` +7. `opea/embedding-tei:latest` 8. `opea/embedding-multimodal-bridgetower:latest` 9. `opea/multimodalqna:latest` 10. `opea/multimodalqna-ui:latest` @@ -144,10 +144,10 @@ Then run the command `docker images`, you will have the following 11 Docker Imag By default, the multimodal-embedding and LVM models are set to a default value as listed below: -| Service | Model | -| -------------------- | ------------------------------------------- | -| embedding-multimodal | BridgeTower/bridgetower-large-itm-mlm-gaudi | -| LVM | llava-hf/llava-v1.6-vicuna-13b-hf | +| Service | Model | +| ------------- | ------------------------------------------- | +| embedding-tei | BridgeTower/bridgetower-large-itm-mlm-gaudi | +| LVM | llava-hf/llava-v1.6-vicuna-13b-hf | ### Start all the services Docker Containers @@ -176,7 +176,7 @@ curl http://${host_ip}:${EMBEDDER_PORT}/v1/encode \ -d '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' ``` -2. embedding-multimodal +2. embedding-tei ```bash curl http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings \ diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml index 02537cb55..5319b5456 100644 --- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -55,9 +55,9 @@ services: start_period: 30s 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} - container_name: embedding-multimodal + embedding-tei: + image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest} + container_name: embedding-tei depends_on: embedding-multimodal-bridgetower: condition: service_healthy @@ -137,7 +137,7 @@ services: depends_on: - redis-vector-db - dataprep-multimodal-redis - - embedding-multimodal + - embedding-tei - retriever-redis - lvm-tgi ports: diff --git a/MultimodalQnA/docker_image_build/build.yaml b/MultimodalQnA/docker_image_build/build.yaml index 2a5d3b0f7..3d6d805af 100644 --- a/MultimodalQnA/docker_image_build/build.yaml +++ b/MultimodalQnA/docker_image_build/build.yaml @@ -23,12 +23,12 @@ services: dockerfile: comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile extends: multimodalqna image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower:${TAG:-latest} - embedding-multimodal: + embedding-tei: build: context: GenAIComps dockerfile: comps/embeddings/src/Dockerfile extends: multimodalqna - image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest} + image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest} retriever-redis: build: context: GenAIComps diff --git a/MultimodalQnA/tests/test_compose_on_gaudi.sh b/MultimodalQnA/tests/test_compose_on_gaudi.sh index a0279d5b4..7c72f0564 100644 --- a/MultimodalQnA/tests/test_compose_on_gaudi.sh +++ b/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-multimodal retriever-redis lvm-tgi dataprep-multimodal-redis whisper" + service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-tei retriever-redis lvm-tgi dataprep-multimodal-redis whisper" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 @@ -144,19 +144,19 @@ function validate_microservices() { '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' # embedding microservice - echo "Validating embedding-multimodal" + echo "Validating embedding-tei" validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text" : "This is some sample text."}' validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text": {"text" : "This is some sample text."}, "image" : {"url": "https://github.com/docarray/docarray/blob/main/tests/toydata/image-data/apple.png?raw=true"}}' sleep 1m # retrieval can't curl as expected, try to wait for more time diff --git a/MultimodalQnA/tests/test_compose_on_rocm.sh b/MultimodalQnA/tests/test_compose_on_rocm.sh index ade7187ed..2d69fca5f 100644 --- a/MultimodalQnA/tests/test_compose_on_rocm.sh +++ b/MultimodalQnA/tests/test_compose_on_rocm.sh @@ -23,7 +23,7 @@ function build_docker_images() { git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${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-multimodal retriever-redis lvm-tgi lvm-llava-svc dataprep-multimodal-redis whisper" + service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-tei retriever-redis lvm-tgi lvm-llava-svc dataprep-multimodal-redis whisper" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker images && sleep 1m @@ -150,19 +150,19 @@ function validate_microservices() { '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' # embedding microservice - echo "Validating embedding-multimodal" + echo "Validating embedding-tei" validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text" : "This is some sample text."}' validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text": {"text" : "This is some sample text."}, "image" : {"url": "https://github.com/docarray/docarray/blob/main/tests/toydata/image-data/apple.png?raw=true"}}' sleep 1m # retrieval can't curl as expected, try to wait for more time diff --git a/MultimodalQnA/tests/test_compose_on_xeon.sh b/MultimodalQnA/tests/test_compose_on_xeon.sh index e49f265ab..d69e8cdcb 100644 --- a/MultimodalQnA/tests/test_compose_on_xeon.sh +++ b/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-multimodal retriever-redis lvm-llava lvm-llava-svc dataprep-multimodal-redis whisper" + service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-tei retriever-redis lvm-llava lvm-llava-svc dataprep-multimodal-redis whisper" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker images && sleep 1m @@ -142,19 +142,19 @@ function validate_microservices() { '{"text":"This is example", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}' # embedding microservice - echo "Validating embedding-multimodal" + echo "Validating embedding-tei" validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text" : "This is some sample text."}' validate_service \ "http://${host_ip}:$MM_EMBEDDING_PORT_MICROSERVICE/v1/embeddings" \ '"embedding":[' \ - "embedding-multimodal" \ - "embedding-multimodal" \ + "embedding-tei" \ + "embedding-tei" \ '{"text": {"text" : "This is some sample text."}, "image" : {"url": "https://github.com/docarray/docarray/blob/main/tests/toydata/image-data/apple.png?raw=true"}}' sleep 1m # retrieval can't curl as expected, try to wait for more time diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md index ac2e40492..52ac9b0ae 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md @@ -33,7 +33,7 @@ docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$ht #### Use TGI as backend ```bash -docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build --no-cache -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 5. Build Dataprep Image diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml index 7ec6c40d4..586e31ba8 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml @@ -153,8 +153,8 @@ services: retries: 100 command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server depends_on: tgi_service: condition: service_healthy @@ -224,8 +224,8 @@ services: retries: 30 command: --model-id ${LLM_MODEL_ID_CODEGEN} llm_codegen: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server-codegen + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server-codegen depends_on: tgi_service_codegen: condition: service_healthy diff --git a/ProductivitySuite/docker_image_build/build.yaml b/ProductivitySuite/docker_image_build/build.yaml index 490bd6185..182ebd5a6 100644 --- a/ProductivitySuite/docker_image_build/build.yaml +++ b/ProductivitySuite/docker_image_build/build.yaml @@ -29,12 +29,12 @@ services: dockerfile: comps/reranks/src/Dockerfile extends: chatqna image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: chatqna - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} dataprep-redis: build: context: GenAIComps diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml index c3a65e92b..7f67360c3 100644 --- a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml +++ b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml @@ -615,7 +615,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml index 5eb3cd6eb..d18a4e950 100644 --- a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml @@ -171,7 +171,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/ProductivitySuite/tests/test_compose_on_xeon.sh b/ProductivitySuite/tests/test_compose_on_xeon.sh index 6b2f3cdd4..19cec0116 100755 --- a/ProductivitySuite/tests/test_compose_on_xeon.sh +++ b/ProductivitySuite/tests/test_compose_on_xeon.sh @@ -241,7 +241,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm-microservice" \ - "llm-tgi-server" \ + "llm-textgen-server" \ '{"query":"What is Deep Learning?"}' # FAQGen llm microservice @@ -257,7 +257,7 @@ function validate_microservices() { "${ip_address}:9001/v1/chat/completions" \ "data: " \ "llm_codegen" \ - "llm-tgi-server-codegen" \ + "llm-textgen-server-codegen" \ '{"query":"def print_hello_world():"}' result=$(curl -X 'POST' \ diff --git a/SearchQnA/docker_compose/intel/cpu/xeon/README.md b/SearchQnA/docker_compose/intel/cpu/xeon/README.md index e669dd4d9..2b1e8bb30 100644 --- a/SearchQnA/docker_compose/intel/cpu/xeon/README.md +++ b/SearchQnA/docker_compose/intel/cpu/xeon/README.md @@ -27,7 +27,7 @@ docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$ht ### 4. Build LLM Image ```bash -docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build --no-cache -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 5. Build MegaService Docker Image @@ -54,7 +54,7 @@ Then run the command `docker images`, you will have following images ready: 1. `opea/embedding-tei:latest` 2. `opea/web-retriever-chroma:latest` 3. `opea/reranking-tei:latest` -4. `opea/llm-tgi:latest` +4. `opea/llm-textgen:latest` 5. `opea/searchqna:latest` 6. `opea/searchqna-ui:latest` diff --git a/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml b/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml index e3c1cb11f..9aefc6624 100644 --- a/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml +++ b/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml @@ -111,8 +111,8 @@ services: retries: 100 command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server depends_on: tgi-service: condition: service_healthy diff --git a/SearchQnA/docker_compose/intel/hpu/gaudi/README.md b/SearchQnA/docker_compose/intel/hpu/gaudi/README.md index 1bf646bb3..472c2efb1 100644 --- a/SearchQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/SearchQnA/docker_compose/intel/hpu/gaudi/README.md @@ -29,7 +29,7 @@ docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$ht ### 4. Build LLM Image ```bash -docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build --no-cache -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 5. Build MegaService Docker Image @@ -54,7 +54,7 @@ Then run the command `docker images`, you will have 1. `opea/embedding-tei:latest` 2. `opea/web-retriever-chroma:latest` 3. `opea/reranking-tei:latest` -4. `opea/llm-tgi:latest` +4. `opea/llm-textgen:latest` 5. `opea/searchqna:latest` ## 🚀 Set the environment variables diff --git a/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml index a8ede9146..1e44952d8 100644 --- a/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -128,8 +128,8 @@ services: ipc: host command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-gaudi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-gaudi-server depends_on: tgi-service: condition: service_healthy diff --git a/SearchQnA/docker_image_build/build.yaml b/SearchQnA/docker_image_build/build.yaml index c2f42cdce..8d16f1df3 100644 --- a/SearchQnA/docker_image_build/build.yaml +++ b/SearchQnA/docker_image_build/build.yaml @@ -35,9 +35,9 @@ services: dockerfile: comps/reranks/src/Dockerfile extends: searchqna image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: searchqna - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} diff --git a/SearchQnA/tests/test_compose_on_gaudi.sh b/SearchQnA/tests/test_compose_on_gaudi.sh index c023db795..af4049281 100644 --- a/SearchQnA/tests/test_compose_on_gaudi.sh +++ b/SearchQnA/tests/test_compose_on_gaudi.sh @@ -19,7 +19,7 @@ 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="searchqna searchqna-ui embedding-tei web-retriever-chroma reranking-tei llm-tgi" + service_list="searchqna searchqna-ui embedding-tei web-retriever-chroma reranking-tei llm-textgen" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 diff --git a/SearchQnA/tests/test_compose_on_xeon.sh b/SearchQnA/tests/test_compose_on_xeon.sh index d6c55978c..7a21b706c 100644 --- a/SearchQnA/tests/test_compose_on_xeon.sh +++ b/SearchQnA/tests/test_compose_on_xeon.sh @@ -19,7 +19,7 @@ function build_docker_images() { git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../ echo "Build all the images with --no-cache, check docker_image_build.log for details..." - service_list="searchqna searchqna-ui embedding-tei web-retriever-chroma reranking-tei llm-tgi" + service_list="searchqna searchqna-ui embedding-tei web-retriever-chroma reranking-tei llm-textgen" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 diff --git a/Translation/docker_compose/amd/gpu/rocm/README.md b/Translation/docker_compose/amd/gpu/rocm/README.md index 2ead1f53d..38b017634 100644 --- a/Translation/docker_compose/amd/gpu/rocm/README.md +++ b/Translation/docker_compose/amd/gpu/rocm/README.md @@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps ### Build Docker image -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### Build the MegaService Docker Image diff --git a/Translation/docker_compose/amd/gpu/rocm/compose.yaml b/Translation/docker_compose/amd/gpu/rocm/compose.yaml index b3835cd11..2ee2a9c2c 100644 --- a/Translation/docker_compose/amd/gpu/rocm/compose.yaml +++ b/Translation/docker_compose/amd/gpu/rocm/compose.yaml @@ -35,8 +35,8 @@ services: ipc: host command: --model-id ${TRANSLATION_LLM_MODEL_ID} translation-llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: translation-llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: translation-llm-textgen-server depends_on: translation-tgi-service: condition: service_healthy diff --git a/Translation/docker_compose/intel/cpu/xeon/README.md b/Translation/docker_compose/intel/cpu/xeon/README.md index f5f26bbea..f1f109a17 100644 --- a/Translation/docker_compose/intel/cpu/xeon/README.md +++ b/Translation/docker_compose/intel/cpu/xeon/README.md @@ -34,7 +34,7 @@ Follow the instructions below to build the docker images from source. ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build MegaService Docker Image @@ -65,7 +65,7 @@ docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-a Then run the command `docker images`, you will have the following Docker Images: -1. `opea/llm-tgi:latest` +1. `opea/llm-textgen:latest` 2. `opea/translation:latest` 3. `opea/translation-ui:latest` 4. `opea/nginx:latest` @@ -119,7 +119,7 @@ docker compose up -d > Note: The docker images will be automatically downloaded from `docker hub`: ```bash -docker pull opea/llm-tgi:latest +docker pull opea/llm-textgen:latest docker pull opea/translation:latest docker pull opea/translation-ui:latest docker pull opea/nginx:latest diff --git a/Translation/docker_compose/intel/cpu/xeon/compose.yaml b/Translation/docker_compose/intel/cpu/xeon/compose.yaml index 459c89144..d876f99f2 100644 --- a/Translation/docker_compose/intel/cpu/xeon/compose.yaml +++ b/Translation/docker_compose/intel/cpu/xeon/compose.yaml @@ -25,8 +25,8 @@ services: shm_size: 1g command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-server depends_on: tgi-service: condition: service_healthy diff --git a/Translation/docker_compose/intel/hpu/gaudi/README.md b/Translation/docker_compose/intel/hpu/gaudi/README.md index d99fee7fc..432d42a81 100644 --- a/Translation/docker_compose/intel/hpu/gaudi/README.md +++ b/Translation/docker_compose/intel/hpu/gaudi/README.md @@ -26,7 +26,7 @@ Follow the instructions below to build the docker images from source. ```bash git clone https://github.com/opea-project/GenAIComps.git cd GenAIComps -docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . +docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile . ``` ### 2. Build MegaService Docker Image @@ -57,7 +57,7 @@ docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-a Then run the command `docker images`, you will have the following four Docker Images: -1. `opea/llm-tgi:latest` +1. `opea/llm-textgen:latest` 2. `opea/translation:latest` 3. `opea/translation-ui:latest` 4. `opea/nginx:latest` @@ -111,7 +111,7 @@ docker compose up -d > Note: The docker images will be automatically downloaded from `docker hub`: ```bash -docker pull opea/llm-tgi:latest +docker pull opea/llm-textgen:latest docker pull opea/translation:latest docker pull opea/translation-ui:latest docker pull opea/nginx:latest diff --git a/Translation/docker_compose/intel/hpu/gaudi/compose.yaml b/Translation/docker_compose/intel/hpu/gaudi/compose.yaml index a22d1ad04..de3714aca 100644 --- a/Translation/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/Translation/docker_compose/intel/hpu/gaudi/compose.yaml @@ -33,8 +33,8 @@ services: - "./data:/data" command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048 llm: - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} - container_name: llm-tgi-gaudi-server + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} + container_name: llm-textgen-gaudi-server depends_on: tgi-service: condition: service_healthy diff --git a/Translation/docker_image_build/build.yaml b/Translation/docker_image_build/build.yaml index 3f84f7a3a..faf758555 100644 --- a/Translation/docker_image_build/build.yaml +++ b/Translation/docker_image_build/build.yaml @@ -17,12 +17,12 @@ services: dockerfile: ./docker/Dockerfile extends: translation image: ${REGISTRY:-opea}/translation-ui:${TAG:-latest} - llm-tgi: + llm-textgen: build: context: GenAIComps dockerfile: comps/llms/src/text-generation/Dockerfile extends: translation - image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest} + image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest} nginx: build: context: GenAIComps diff --git a/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml b/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml index f8e2b6e65..334f69d7e 100644 --- a/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml +++ b/Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml @@ -285,7 +285,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml b/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml index 61a487a0d..997b9cede 100644 --- a/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml +++ b/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml @@ -286,7 +286,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/llm-tgi:latest" + image: "opea/llm-textgen:latest" imagePullPolicy: IfNotPresent ports: - name: llm-uservice diff --git a/Translation/tests/test_compose_on_gaudi.sh b/Translation/tests/test_compose_on_gaudi.sh index f2e0c42cf..1f2f94a3c 100644 --- a/Translation/tests/test_compose_on_gaudi.sh +++ b/Translation/tests/test_compose_on_gaudi.sh @@ -19,7 +19,7 @@ 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="translation translation-ui llm-tgi nginx" + service_list="translation translation-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 @@ -102,7 +102,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-gaudi-server" \ + "llm-textgen-gaudi-server" \ '{"query":"Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"}' } diff --git a/Translation/tests/test_compose_on_rocm.sh b/Translation/tests/test_compose_on_rocm.sh index ff9724cf6..880a36b6d 100644 --- a/Translation/tests/test_compose_on_rocm.sh +++ b/Translation/tests/test_compose_on_rocm.sh @@ -19,7 +19,7 @@ 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="translation translation-ui llm-tgi nginx" + service_list="translation translation-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm @@ -105,7 +105,7 @@ function validate_microservices() { "${TRANSLATION_HOST_IP}:9000/v1/chat/completions" \ "data: " \ "translation-llm" \ - "translation-llm-tgi-server" \ + "translation-llm-textgen-server" \ '{"query":"Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"}' } diff --git a/Translation/tests/test_compose_on_xeon.sh b/Translation/tests/test_compose_on_xeon.sh index 06c2f0e43..438f29a4b 100644 --- a/Translation/tests/test_compose_on_xeon.sh +++ b/Translation/tests/test_compose_on_xeon.sh @@ -19,7 +19,7 @@ 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="translation translation-ui llm-tgi nginx" + service_list="translation translation-ui llm-textgen nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu @@ -104,7 +104,7 @@ function validate_microservices() { "${ip_address}:9000/v1/chat/completions" \ "data: " \ "llm" \ - "llm-tgi-server" \ + "llm-textgen-server" \ '{"query":"Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"}' } diff --git a/VideoQnA/docker_compose/intel/cpu/xeon/README.md b/VideoQnA/docker_compose/intel/cpu/xeon/README.md index d5a29df73..6890e213d 100644 --- a/VideoQnA/docker_compose/intel/cpu/xeon/README.md +++ b/VideoQnA/docker_compose/intel/cpu/xeon/README.md @@ -65,7 +65,7 @@ docker build -t opea/retriever-vdms:latest --build-arg https_proxy=$https_proxy ### 3. Build Rerank Image ```bash -docker build -t opea/reranking-videoqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/src/Dockerfile . +docker build -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/src/Dockerfile . ``` ### 4. Build LVM Image (Xeon) @@ -109,7 +109,7 @@ Then run the command `docker images`, you will have the following 8 Docker Image 1. `opea/dataprep-multimodal-vdms:latest` 2. `opea/embedding-multimodal-clip:latest` 3. `opea/retriever-vdms:latest` -4. `opea/reranking-videoqna:latest` +4. `opea/reranking-tei:latest` 5. `opea/video-llama-lvm-server:latest` 6. `opea/lvm-video-llama:latest` 7. `opea/videoqna:latest` diff --git a/VideoQnA/docker_compose/intel/cpu/xeon/compose.yaml b/VideoQnA/docker_compose/intel/cpu/xeon/compose.yaml index 47479a414..29e8e454c 100644 --- a/VideoQnA/docker_compose/intel/cpu/xeon/compose.yaml +++ b/VideoQnA/docker_compose/intel/cpu/xeon/compose.yaml @@ -61,8 +61,8 @@ services: volumes: - /home/$USER/.cache/huggingface/hub:/home/user/.cache/huggingface/hub reranking: - image: ${REGISTRY:-opea}/reranking-videoqna:${TAG:-latest} - container_name: reranking-videoqna-server + image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest} + container_name: reranking-tei-server ports: - "8000:8000" ipc: host diff --git a/VideoQnA/docker_image_build/build.yaml b/VideoQnA/docker_image_build/build.yaml index 9b9e5e02e..db18ebd9a 100644 --- a/VideoQnA/docker_image_build/build.yaml +++ b/VideoQnA/docker_image_build/build.yaml @@ -35,12 +35,12 @@ services: dockerfile: comps/retrievers/vdms/langchain/Dockerfile extends: videoqna image: ${REGISTRY:-opea}/retriever-vdms:${TAG:-latest} - reranking-videoqna: + reranking-tei: build: context: GenAIComps dockerfile: comps/reranks/src/Dockerfile extends: videoqna - image: ${REGISTRY:-opea}/reranking-videoqna:${TAG:-latest} + image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest} video-llama-lvm-server: build: context: GenAIComps diff --git a/VideoQnA/tests/test_compose_on_xeon.sh b/VideoQnA/tests/test_compose_on_xeon.sh index 081b14407..e5b1f808e 100755 --- a/VideoQnA/tests/test_compose_on_xeon.sh +++ b/VideoQnA/tests/test_compose_on_xeon.sh @@ -51,7 +51,7 @@ function start_services() { sleep 1m # List of containers running uvicorn - list=("dataprep-vdms-server" "embedding-multimodal-server" "retriever-vdms-server" "reranking-videoqna-server" "video-llama-lvm-server" "lvm-video-llama" "videoqna-xeon-backend-server") + list=("dataprep-vdms-server" "embedding-multimodal-server" "retriever-vdms-server" "reranking-tei-server" "video-llama-lvm-server" "lvm-video-llama" "videoqna-xeon-backend-server") # Define the maximum time limit in seconds TIME_LIMIT=5400 @@ -176,7 +176,7 @@ function validate_microservices() { "${ip_address}:8000/v1/reranking" \ "video_url" \ "reranking" \ - "reranking-videoqna-server" \ + "reranking-tei-server" \ '{ "retrieved_docs": [{"doc": [{"text": "retrieved text"}]}], "initial_query": "query", diff --git a/docker_images_list.md b/docker_images_list.md index 2336df9e3..7618bf3c7 100644 --- a/docker_images_list.md +++ b/docker_images_list.md @@ -2,7 +2,7 @@ A list of released OPEA docker images in https://hub.docker.com/, contains all relevant images from the GenAIExamples, GenAIComps and GenAIInfra projects. Please expect more public available images in the future release. -Take ChatQnA for example. ChatQnA is a chatbot application service based on the Retrieval Augmented Generation (RAG) architecture. It consists of [opea/embedding-tei](https://hub.docker.com/r/opea/embedding-tei), [opea/retriever-redis](https://hub.docker.com/r/opea/retriever-redis), [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei), [opea/llm-tgi](https://hub.docker.com/r/opea/llm-tgi), [opea/dataprep-redis](https://hub.docker.com/r/opea/dataprep-redis), [opea/chatqna](https://hub.docker.com/r/opea/chatqna), [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) and [opea/chatqna-conversation-ui](https://hub.docker.com/r/opea/chatqna-conversation-ui) (Optional) multiple microservices. Other services are similar, see the corresponding README for details. +Take ChatQnA for example. ChatQnA is a chatbot application service based on the Retrieval Augmented Generation (RAG) architecture. It consists of [opea/embedding-tei](https://hub.docker.com/r/opea/embedding-tei), [opea/retriever-redis](https://hub.docker.com/r/opea/retriever-redis), [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei), [opea/llm-textgen](https://hub.docker.com/r/opea/llm-textgen), [opea/dataprep-redis](https://hub.docker.com/r/opea/dataprep-redis), [opea/chatqna](https://hub.docker.com/r/opea/chatqna), [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) and [opea/chatqna-conversation-ui](https://hub.docker.com/r/opea/chatqna-conversation-ui) (Optional) multiple microservices. Other services are similar, see the corresponding README for details. ## Example images @@ -57,7 +57,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the | [opea/dataprep-vdms](https://hub.docker.com/r/opea/dataprep-vdms) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/dataprep/vdms/langchain/Dockerfile) | This docker image exposes an OPEA dataprep microservice based on VDMS vectordb for use by GenAI applications. | | [opea/embedding-langchain-mosec](https://hub.docker.com/r/opea/embedding-langchain-mosec) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/3rd_parties/nginx/src/Dockerfile) | The docker image exposed the OPEA mosec embedding microservice base on Langchain framework for GenAI application use | | [opea/embedding-multimodal-clip](https://hub.docker.com/r/opea/embedding-multimodal-clip) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/integrations/dependency/clip/Dockerfile) | The docker image exposes OPEA multimodal CLIP-based embedded microservices for use by GenAI applications | -| [opea/embedding-multimodal](https://hub.docker.com/r/opea/embedding-multimodal) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile) | The docker image exposes OPEA multimodal embedded microservices for use by GenAI applications | +| [opea/embedding-tei](https://hub.docker.com/r/opea/embedding-tei) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile) | The docker image exposes OPEA multimodal embedded microservices for use by GenAI applications | | [opea/embedding-multimodal-bridgetower](https://hub.docker.com/r/opea/embedding-multimodal-bridgetower) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile) | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications | | [opea/embedding-multimodal-bridgetower-gaudi](https://hub.docker.com/r/opea/embedding-multimodal-bridgetower-gaudi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile.intel_hpu) | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications on the Gaudi | | [opea/embedding-tei](https://hub.docker.com/r/opea/embedding-tei) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile) | The docker image exposed the OPEA embedding microservice upon tei docker image for GenAI application use | @@ -71,10 +71,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the | [opea/guardrails-pii-detection](https://hub.docker.com/r/opea/guardrails-pii-detection) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/pii_detection/Dockerfile) | The docker image exposed the OPEA guardrail microservice to provide PII detection for GenAI application use | | [opea/llm-docsum-tgi](https://hub.docker.com/r/opea/llm-docsum-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/summarization/tgi/langchain/Dockerfile) | This docker image is designed to build a document summarization microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a document summary. | | [opea/llm-faqgen-tgi](https://hub.docker.com/r/opea/llm-faqgen-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/faq-generation/tgi/langchain/Dockerfile) | This docker image is designed to build a frequently asked questions microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a FAQ. | -| [opea/llm-native](https://hub.docker.com/r/opea/llm-native) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile) | The docker image exposed the OPEA LLM microservice based on native for GenAI application use | -| [opea/llm-ollama](https://hub.docker.com/r/opea/llm-ollama) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile) | The docker image exposed the OPEA LLM microservice based on ollama for GenAI application use | -| [opea/llm-tgi](https://hub.docker.com/r/opea/llm-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile) | The docker image exposed the OPEA LLM microservice upon TGI docker image for GenAI application use | -| [opea/llm-vllm](https://hub.docker.com/r/opea/llm-vllm) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile) | The docker image exposed the OPEA LLM microservice upon vLLM docker image for GenAI application use | +| [opea/llm-textgen](https://hub.docker.com/r/opea/llm-textgen) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile) | The docker image exposed the OPEA LLM microservice upon TGI docker image for GenAI application use | | [opea/llava-gaudi](https://hub.docker.com/r/opea/llava-hpu) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/dependency/Dockerfile.intel_hpu) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use on the Gaudi | | [opea/lvm-tgi](https://hub.docker.com/r/opea/lvm-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/tgi-llava/Dockerfile) | This docker image is designed to build a large visual model (LVM) microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a answer to question. | | [opea/lvm-llava](https://hub.docker.com/r/opea/lvm-llava) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/dependency/Dockerfile) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) server for GenAI application use | @@ -82,10 +79,6 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the | [opea/lvm-video-llama](https://hub.docker.com/r/opea/lvm-video-llama) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/video-llama/Dockerfile) | The docker image exposed the OPEA microservice running Video-Llama as a large visual model (LVM) for GenAI application use | | [opea/nginx](https://hub.docker.com/r/opea/nginx) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/3rd_parties/nginx/src/Dockerfile) | The docker image exposed the OPEA nginx microservice for GenAI application use | | [opea/promptregistry-mongo-server](https://hub.docker.com/r/opea/promptregistry-mongo-server) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/prompt_registry/mongo/Dockerfile) | The docker image exposes the OPEA Prompt Registry microservices which based on MongoDB database, designed to store and retrieve user's preferred prompts | -| [opea/reranking-videoqna](https://hub.docker.com/r/opea/reranking-videoqna) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/src/Dockerfile) | The docker image exposed the OPEA reranking microservice for reranking the results of VideoQnA use casesfor GenAI application use | -| [opea/reranking-fastrag](https://hub.docker.com/r/opea/reranking-fastrag) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/src/Dockerfile) | The docker image exposed the OPEA reranking microservice base on fastrag for GenAI application use | -| [opea/reranking-langchain-mosec](https://hub.docker.com/r/opea/reranking-langchain-mosec) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/src/Dockerfile) | The docker image exposed the OPEA mosec reranking microservice base on Langchain framework for GenAI application use | -| [opea/reranking-langchain-mosec-endpoint](https://hub.docker.com/r/opea/reranking-langchain-mosec-endpoint) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/src/Dockerfile) | The docker image exposed the OPEA mosec reranking endpoint microservice base on Langchain framework for GenAI application use | | [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/src/Dockerfile) | The docker image exposed the OPEA reranking microservice based on tei docker image for GenAI application use | | [opea/retriever-milvus](https://hub.docker.com/r/opea/retriever-milvus) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/milvus/langchain/Dockerfile) | The docker image exposed the OPEA retrieval microservice based on milvus vectordb for GenAI application use | | [opea/retriever-pathway](https://hub.docker.com/r/opea/retriever-pathway) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/pathway/langchain/Dockerfile) | The docker image exposed the OPEA retrieval microservice with pathway for GenAI application use |