From 72a255303630d011c72f358b0a513f1161d2a589 Mon Sep 17 00:00:00 2001 From: Harsha Ramayanam Date: Fri, 16 Aug 2024 09:14:09 -0700 Subject: [PATCH] Fix image in docker compose yaml to use the built docker image tag from the README (#498) * Update README.md The `ray_serve:habana` doesn't exist (yet) in docker hub * Fixed the image in docker compose yaml Signed-off-by: Harsha Ramayanam --------- Signed-off-by: Harsha Ramayanam Co-authored-by: chen, suyue --- comps/llms/README.md | 2 +- comps/llms/text-generation/tgi/docker_compose_llm.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/comps/llms/README.md b/comps/llms/README.md index 584f2ba12..9c3867f03 100644 --- a/comps/llms/README.md +++ b/comps/llms/README.md @@ -40,7 +40,7 @@ docker run -it --name vllm_service -p 8008:80 -e HF_TOKEN=${HUGGINGFACEHUB_API_T ```bash export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} export TRUST_REMOTE_CODE=True -docker run -it --runtime=habana --name ray_serve_service -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -p 8008:80 -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN -e TRUST_REMOTE_CODE=$TRUST_REMOTE_CODE ray_serve:habana /bin/bash -c "ray start --head && python api_server_openai.py --port_number 80 --model_id_or_path ${your_hf_llm_model} --chat_processor ${your_hf_chatprocessor}" +docker run -it --runtime=habana --name ray_serve_service -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -p 8008:80 -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN -e TRUST_REMOTE_CODE=$TRUST_REMOTE_CODE opea/llm-ray:latest /bin/bash -c "ray start --head && python api_server_openai.py --port_number 80 --model_id_or_path ${your_hf_llm_model} --chat_processor ${your_hf_chatprocessor}" ``` ## 1.3 Verify the LLM Service diff --git a/comps/llms/text-generation/tgi/docker_compose_llm.yaml b/comps/llms/text-generation/tgi/docker_compose_llm.yaml index c1ab98dcc..9551979a7 100644 --- a/comps/llms/text-generation/tgi/docker_compose_llm.yaml +++ b/comps/llms/text-generation/tgi/docker_compose_llm.yaml @@ -14,7 +14,7 @@ services: shm_size: 1g command: --model-id ${LLM_MODEL_ID} llm: - image: opea/gen-ai-comps:llm-tgi-server + image: opea/llm-tgi:latest container_name: llm-tgi-server ports: - "9000:9000"