Dockerfile.cypher.intel_hpu

# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

# HABANA environment
FROM vault.habana.ai/gaudi-docker/1.20.1/ubuntu22.04/habanalabs/pytorch-installer-2.6.0 AS hpu

ENV LANG=en_US.UTF-8
ARG REPO=https://github.com/huggingface/optimum-habana.git
ARG REPO_VER=v1.15.0

RUN apt-get update && apt-get install -y --no-install-recommends --fix-missing \
    git-lfs \
    libjemalloc-dev

#RUN useradd -m -s /bin/bash user && \
#    mkdir -p /home/user && \
#    chown -R user /home/user/

RUN git lfs install

COPY comps /root/comps
#RUN chown -R user /home/user/comps/text2cypher

#RUN rm -rf /etc/ssh/ssh_host*

ARG uvpip='uv pip install --system --no-cache-dir'
RUN pip install --no-cache-dir --upgrade pip setuptools uv && \
    pip install --no-cache-dir accelerate \
    huggingface_hub \
    json_repair \
    langchain_experimental \
    llama-index \
    llama-index-embeddings-huggingface \
    llama-index-embeddings-langchain \
    llama-index-graph-stores-neo4j \
    llama-index-llms-huggingface \
    llama-index-llms-huggingface-api \
    neo4j \
    peft \
    pydub \
    pyprojroot \
    sentence-transformers \
    unstructured \
    urllib3 \
    optimum-habana==1.17.0 && \
    $uvpip git+https://github.com/HabanaAI/DeepSpeed.git@1.19.0

RUN git clone --depth 1 --branch ${REPO_VER} ${REPO}

WORKDIR /root/comps/text2query/src
RUN $uvpip -r requirements-cpu.txt && \
    $uvpip --upgrade --force-reinstall pydantic numpy==1.26.3 transformers==4.49.0

# Set environment variables
ENV PYTHONPATH=/root:/usr/lib/habanalabs/:/root/optimum-habana
ENV HABANA_VISIBLE_DEVICES=all
ENV OMPI_MCA_btl_vader_single_copy_mechanism=none
ENV DEBIAN_FRONTEND="noninteractive"  TZ=Etc/UTC

#USER user
WORKDIR /root/comps/text2query/src

ENTRYPOINT ["python", "opea_text2query_microservice.py"]