replace langchain/langchain:latest with python:3.11-slim (#669)

chensuyue · web-flow · commit 6ce65514e1c3 · 2024-09-12T13:24:50.000+08:00
* replace langchain/langchain:latest with python:3.11-slim

Signed-off-by: chensuyue &lt;suyue.chen@intel.com&gt;

* fix test

Signed-off-by: chensuyue &lt;suyue.chen@intel.com&gt;

---------

Signed-off-by: chensuyue &lt;suyue.chen@intel.com&gt;
diff --git a/comps/embeddings/mosec/langchain/Dockerfile b/comps/embeddings/mosec/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/embeddings/multimodal/multimodal_langchain/Dockerfile b/comps/embeddings/multimodal/multimodal_langchain/Dockerfile
@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/embeddings/multimodal_clip/Dockerfile b/comps/embeddings/multimodal_clip/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/embeddings/tei/langchain/Dockerfile b/comps/embeddings/tei/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/guardrails/llama_guard/langchain/Dockerfile b/comps/guardrails/llama_guard/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ENV LANG=C.UTF-8
 
diff --git a/comps/guardrails/toxicity_detection/Dockerfile b/comps/guardrails/toxicity_detection/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ENV LANG=C.UTF-8
 
diff --git a/comps/intent_detection/langchain/Dockerfile b/comps/intent_detection/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/knowledgegraphs/langchain/Dockerfile b/comps/knowledgegraphs/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"  # Set this to "cpu" or "gpu"
 
diff --git a/comps/llms/faq-generation/tgi/langchain/Dockerfile b/comps/llms/faq-generation/tgi/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/llms/summarization/tgi/langchain/Dockerfile b/comps/llms/summarization/tgi/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/llms/text-generation/ollama/langchain/Dockerfile b/comps/llms/text-generation/ollama/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     curl \
diff --git a/comps/llms/text-generation/tgi/Dockerfile b/comps/llms/text-generation/tgi/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/llms/text-generation/vllm/langchain/Dockerfile b/comps/llms/text-generation/vllm/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"  # Set this to "cpu" or "gpu"
 
diff --git a/comps/llms/text-generation/vllm/ray/Dockerfile b/comps/llms/text-generation/vllm/ray/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/ragas/tgi/langchain/Dockerfile b/comps/ragas/tgi/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/reranks/mosec/langchain/Dockerfile b/comps/reranks/mosec/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/retrievers/multimodal/redis/langchain/Dockerfile b/comps/retrievers/multimodal/redis/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/retrievers/pathway/langchain/Dockerfile b/comps/retrievers/pathway/langchain/Dockerfile
@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/retrievers/pgvector/langchain/Dockerfile b/comps/retrievers/pgvector/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     libgl1-mesa-glx \
diff --git a/comps/retrievers/pinecone/langchain/Dockerfile b/comps/retrievers/pinecone/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/retrievers/redis/langchain/Dockerfile b/comps/retrievers/redis/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/retrievers/vdms/langchain/Dockerfile b/comps/retrievers/vdms/langchain/Dockerfile
@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"
 
diff --git a/comps/web_retrievers/chroma/langchain/Dockerfile b/comps/web_retrievers/chroma/langchain/Dockerfile
@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-FROM langchain/langchain:latest
+FROM python:3.11-slim
 
 ARG ARCH="cpu"  # Set this to "cpu" or "gpu"
 
diff --git a/tests/llms/test_llms_text-generation_tgi.sh b/tests/llms/test_llms_text-generation_tgi.sh
@@ -21,10 +21,10 @@ function build_docker_images() {
 
 function start_service() {
     tgi_endpoint_port=5004
-    export your_hf_llm_model=$1
+    export hf_llm_model=$1
     # Remember to set HF_TOKEN before invoking this test!
     export HF_TOKEN=${HF_TOKEN}
-    docker run -d --name="test-comps-llm-tgi-endpoint" -p $tgi_endpoint_port:80 -v ./data:/data --shm-size 1g -e HF_TOKEN=${HF_TOKEN} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id ${your_hf_llm_model} --max-input-tokens 1024 --max-total-tokens 2048
+    docker run -d --name="test-comps-llm-tgi-endpoint" -p $tgi_endpoint_port:80 -v ~/.cache/huggingface/hub:/data --shm-size 1g -e HF_TOKEN=${HF_TOKEN} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id ${hf_llm_model} --max-input-tokens 1024 --max-total-tokens 2048
     export TGI_LLM_ENDPOINT="http://${ip_address}:${tgi_endpoint_port}"
 
     llm_port=5005
@@ -34,9 +34,9 @@ function start_service() {
     # check whether tgi is fully ready
     n=0
     until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
-        docker logs test-comps-llm-tgi-endpoint >> ${LOG_PATH}/llm-tgi.log
+        docker logs test-comps-llm-tgi-endpoint >> ${LOG_PATH}/${hf_llm_model}-llm-tgi.log
         n=$((n+1))
-        if grep -q Connected ${LOG_PATH}/llm-tgi.log; then
+        if grep -q Connected ${LOG_PATH}/${hf_llm_model}-llm-tgi.log; then
             break
         fi
         sleep 5s
diff --git a/tests/retrievers/test_retrievers_pinecone_langchain.sh b/tests/retrievers/test_retrievers_pinecone_langchain.sh
@@ -33,7 +33,7 @@ function start_service() {
     export HUGGINGFACEHUB_API_TOKEN=$HF_TOKEN
     retriever_port=5054
     unset http_proxy
-    docker run -d --name="test-comps-retriever-pinecone-server" -p ${retriever_port}:7000 --ipc=host -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e PINECONE_API_KEY=$PINECONE_API_KEY -e PINECONE_INDEX_NAME=$PINECONE_INDEX_NAME -e INDEX_NAME=$PINECONE_INDEX_NAME opea/retriever-pinecone:comps
+    docker run -d --name="test-comps-retriever-pinecone-server" -p ${retriever_port}:7000 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e PINECONE_API_KEY=$PINECONE_API_KEY -e PINECONE_INDEX_NAME=$PINECONE_INDEX_NAME -e INDEX_NAME=$PINECONE_INDEX_NAME opea/retriever-pinecone:comps
 
     sleep 2m
 }
diff --git a/tests/retrievers/test_retrievers_redis_langchain.sh b/tests/retrievers/test_retrievers_redis_langchain.sh
@@ -34,9 +34,10 @@ function start_service() {
     # redis retriever
     export REDIS_URL="redis://${ip_address}:5010"
     export INDEX_NAME="rag-redis"
+    export HUGGINGFACEHUB_API_TOKEN=$HF_TOKEN
     retriever_port=5435
     # unset http_proxy
-    docker run -d --name="test-comps-retriever-redis-server" -p ${retriever_port}:7000 --ipc=host -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME opea/retriever-redis:comps
+    docker run -d --name="test-comps-retriever-redis-server" -p ${retriever_port}:7000 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME opea/retriever-redis:comps
 
     sleep 3m
 }
