MLOps for GenAIExamples

ChatQnA/README.md

@@ -86,28 +86,22 @@ Now the TGI Gaudi will launch the FP8 model by default. Please note that current
 
 ## Launch Redis
 ```bash
-docker pull redis/redis-stack:latest
 docker compose -f langchain/docker/docker-compose-redis.yml up -d
 ```
 
 ## Launch LangChain Docker
 
-### Build LangChain Docker Image
-
-```bash
-cd langchain/docker/
-bash ./build_docker.sh
-```
-
-### Lanuch LangChain Docker
-
 Update the `HUGGINGFACEHUB_API_TOKEN` environment variable with your huggingface token in the `docker-compose-langchain.yml`
 
 ```bash
+cd langchain/docker
 docker compose -f docker-compose-langchain.yml up -d
 cd ../../
 ```
 
+> [!NOTE]
+> If you modified any files and want that change introduced in this step, add `--build` to the end of the command to build the container image instead of pulling it from dockerhub.
+
 ## Ingest data into redis
 
 After every time of redis container is launched, data should be ingested in the container ingestion steps:

ChatQnA/langchain/docker/Dockerfile

@@ -1,36 +1,23 @@
-FROM langchain/langchain
-
-ARG http_proxy
-ARG https_proxy
-ENV http_proxy=$http_proxy
-ENV https_proxy=$https_proxy
-
-RUN apt-get update && \
-    apt-get upgrade -y && \
-    apt-get install -y \
-        libgl1-mesa-glx \
-        libjemalloc-dev
-
-RUN pip install --upgrade pip \
-    sentence-transformers \
-    redis \
-    unstructured \
-    unstructured[all-docs] \
-    langchain-cli \
-    pydantic==1.10.13 \
-    langchain==0.1.12 \
-    poetry \
-    pymupdf \
-    easyocr \
-    langchain_benchmarks \
-    pyarrow \
-    jupyter \
-    intel-extension-for-pytorch \
-    intel-openmp
-
-ENV PYTHONPATH=/ws:/qna-app/app
-
-COPY qna-app /qna-app
-WORKDIR /qna-app
+FROM langchain/langchain:latest
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY requirements.txt /tmp/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r /tmp/requirements.txt
+
+ENV PYTHONPATH=/home/user:/home/user/qna-app/app
+
+WORKDIR /home/user/qna-app
+COPY qna-app /home/user/qna-app
 
 ENTRYPOINT ["/usr/bin/sleep", "infinity"]

ChatQnA/langchain/docker/docker-compose-langchain.yml

@@ -1,9 +1,16 @@
 version: '3'
 services:
   qna-rag-redis-server:
-    image: qna-rag-redis:latest
+    build:
+      args:
+        http_proxy: ${http_proxy}
+        https_proxy: ${https_proxy}
+      dockerfile: Dockerfile
+    image: intel/gen-ai-examples:qna-rag-redis-server
     container_name: qna-rag-redis-server
     environment:
+      - http_proxy=${http_proxy}
+      - https_proxy=${https_proxy}
       - "REDIS_PORT=6379"
       - "EMBED_MODEL=BAAI/bge-base-en-v1.5"
       - "REDIS_SCHEMA=schema_dim_768.yml"

ChatQnA/langchain/docker/requirements.txt

@@ -0,0 +1,16 @@
+cryptography==42.0.4
+easyocr
+intel-extension-for-pytorch
+intel-openmp
+jupyter
+langchain_benchmarks
+langchain-cli
+langchain==0.1.12
+poetry
+pyarrow
+pydantic==1.10.13
+pymupdf
+redis
+sentence-transformers
+unstructured
+unstructured[all-docs]

CodeGen/README.md

@@ -14,7 +14,7 @@ docker pull ghcr.io/huggingface/tgi-gaudi:1.2.1
 Alternatively, you can build the Docker image yourself with:
 
 ```bash
-bash ./serving/tgi_gaudi/build_docker.sh
+bash ./tgi_gaudi/build_docker.sh
 ```
 
 ## Launch TGI Gaudi Service
@@ -43,7 +43,7 @@ export TGI_ENDPOINT="xxx.xxx.xxx.xxx:8080"
 
 ## Launch Copilot Docker
 
-### Build Copilot Docker Image
+### Build Copilot Docker Image (Optional)
 
 ```bash
 cd codegen
@@ -54,10 +54,9 @@ cd ..
 ### Lanuch Copilot Docker
 
 ```bash
-docker run -it --net=host --ipc=host -v /var/run/docker.sock:/var/run/docker.sock copilot:latest
+docker run -it -e http_proxy=${http_proxy} -e https_proxy=${https_proxy} --net=host --ipc=host -v /var/run/docker.sock:/var/run/docker.sock intel/gen-ai-examples:copilot bash
 ```
 
-
 # Start Copilot Server
 
 ## Start the Backend Service

CodeGen/codegen/Dockerfile

@@ -12,14 +12,25 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM langchain/langchain
-RUN apt-get update && apt-get -y install libgl1-mesa-glx
-RUN pip install -U langchain-cli pydantic==1.10.13
-RUN pip install langchain==0.1.11
-RUN pip install shortuuid
-RUN pip install huggingface_hub
-RUN mkdir -p /ws
-ENV PYTHONPATH=/ws
-COPY codegen-app /codegen-app
-WORKDIR /codegen-app
-CMD ["/bin/bash"]
+FROM langchain/langchain:latest
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY requirements.txt /tmp/requirements.txt
+
+RUN pip install --no-cache-dir -U -r /tmp/requirements.txt
+
+ENV PYTHONPATH=/home/user:/home/user/codegen-app
+
+WORKDIR /home/user/codegen-app
+COPY codegen-app /home/user/codegen-app
+
+SHELL ["/bin/bash", "-c"]

CodeGen/codegen/requirements.txt

@@ -0,0 +1,5 @@
+huggingface_hub
+langchain-cli
+langchain==0.1.11
+pydantic==1.10.13
+shortuuid

DocSum/README.md

@@ -42,7 +42,7 @@ export TGI_ENDPOINT="http://xxx.xxx.xxx.xxx:8080"
 
 ## Launch Document Summary Docker
 
-### Build Document Summary Docker Image
+### Build Document Summary Docker Image (Optional)
 
 ```bash
 cd langchain/docker/
@@ -53,7 +53,7 @@ cd ../../
 ### Lanuch Document Summary Docker
 
 ```bash
-docker run -it --net=host --ipc=host -v /var/run/docker.sock:/var/run/docker.sock document-summarize:latest
+docker run -it --net=host --ipc=host -e http_proxy=${http_proxy} -e https_proxy=${https_proxy} -v /var/run/docker.sock:/var/run/docker.sock intel/gen-ai-examples:document-summarize bash
 ```
 
 

DocSum/langchain/docker/Dockerfile

@@ -1,35 +1,21 @@
-FROM langchain/langchain
+FROM langchain/langchain:latest
 
-ARG http_proxy
-ARG https_proxy
-ENV http_proxy=$http_proxy
-ENV https_proxy=$https_proxy
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev
 
-RUN apt-get update && \
-    apt-get upgrade -y && \
-    apt-get install -y \
-        libgl1-mesa-glx \
-        libjemalloc-dev
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
 
-RUN pip install --upgrade pip \
-    sentence-transformers \
-    langchain-cli \
-    pydantic==1.10.13 \
-    langchain==0.1.12 \
-    poetry \
-    langchain_benchmarks \
-    pyarrow \
-    jupyter \
-    docx2txt \
-    pypdf \
-    beautifulsoup4 \
-    python-multipart \
-    intel-extension-for-pytorch \
-    intel-openmp
+USER user
 
-ENV PYTHONPATH=/ws:/summarize-app/app
+COPY requirements.txt /tmp/requirements.txt
 
-COPY summarize-app /summarize-app
-WORKDIR /summarize-app
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r /tmp/requirements.txt
 
-CMD ["/bin/bash"]
+ENV PYTHONPATH=/home/user:/home/user/summarize-app/app
+
+WORKDIR /home/user/summarize-app
+COPY summarize-app /home/user/summarize-app

DocSum/langchain/docker/requirements.txt

@@ -0,0 +1,14 @@
+beautifulsoup4
+docx2txt
+intel-extension-for-pytorch
+intel-openmp
+jupyter
+langchain_benchmarks
+langchain-cli
+langchain==0.1.12
+poetry
+pyarrow
+pydantic==1.10.13
+pypdf
+python-multipart
+sentence-transformers

VisualQnA/README.md

@@ -12,13 +12,13 @@ This example guides you through how to deploy a [LLaVA](https://llava-vl.github.
 
 ```
 cd serving/
-docker build . --build-arg http_proxy=${http_proxy} --build-arg https_proxy=${http_proxy} -t llava_gaudi:latest
+docker build . --build-arg http_proxy=${http_proxy} --build-arg https_proxy=${http_proxy} -t intel/gen-ai-examples:llava-gaudi
 ```
 
 2. Start the LLaVA service on Intel Gaudi2
 
 ```
-docker run -d -p 8084:80 -p 8085:8000 -v ./data:/root/.cache/huggingface/hub/ -e http_proxy=$http_proxy -e https_proxy=$http_proxy -v $PWD/llava_server:/llava_server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host llava_gaudi
+docker run -d -p 8084:80 -p 8085:8000 -v ./data:/root/.cache/huggingface/hub/ -e http_proxy=$http_proxy -e https_proxy=$http_proxy -v $PWD/llava_server:/llava_server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host intel/gen-ai-examples:llava-gaudi
 ```
 
 Here are some explanation about the above parameters:

VisualQnA/serving/Dockerfile

@@ -13,22 +13,29 @@
 # limitations under the License.
 
 # HABANA environment
-FROM vault.habana.ai/gaudi-docker/1.14.0/ubuntu22.04/habanalabs/pytorch-installer-2.1.1 as hpu
+FROM vault.habana.ai/gaudi-docker/1.14.0/ubuntu22.04/habanalabs/pytorch-installer-2.1.1 AS hpu
+RUN rm -rf /etc/ssh/ssh_host*
 
 # Set environment variables
 ENV LANG=en_US.UTF-8
-ENV PYTHONPATH=/root:/usr/lib/habanalabs/:/optimum-habana
+ENV PYTHONPATH=/home/user:/usr/lib/habanalabs/:/optimum-habana
 
 # Install required branch
-RUN git clone https://github.com/lkk12014402/optimum-habana.git && \
-    cd optimum-habana && \
-    git checkout enable_llava_generation
+RUN git clone https://github.com/lkk12014402/optimum-habana.git /optimum-habana -b enable_llava_generation
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY requirements.txt /tmp/requirements.txt
 
 # Install dependency
-RUN pip install --upgrade-strategy eager optimum[habana] && \
-    pip install fastapi uvicorn
+RUN pip install --no-cache-dir -U -r /tmp/requirements.txt
 
 # work dir should contains the server
 WORKDIR /llava_server
+COPY llava_server /llava_server
 
-ENTRYPOINT ["python", "llava_server.py"]
+ENTRYPOINT ["python", "llava_server.py"]

VisualQnA/serving/requirements.txt

@@ -0,0 +1,4 @@
+eager
+fastapi
+optimum[habana]
+uvicorn