Dataprep | PGVector : Added support for new changes in utils.py (#269)

* Added support for new changes in utils.py Signed-off-by: Yogesh <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * trigger GitHub actions Signed-off-by: Yogesh <[email protected]> --------- Signed-off-by: Yogesh <[email protected]> Co-authored-by: Yogesh <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: lvliang-intel <[email protected]>
opea-project · Jul 9, 2024 · 54eb7ab · 54eb7ab
1 parent 9ecc5c3
commit 54eb7ab
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 0 deletions.
diff --git a/comps/dataprep/pgvector/langchain/docker/Dockerfile b/comps/dataprep/pgvector/langchain/docker/Dockerfile
@@ -6,10 +6,13 @@ FROM python:3.11-slim
 
 ENV LANG C.UTF-8
 
+ARG ARCH="cpu"
+
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     build-essential \
     libgl1-mesa-glx \
     libjemalloc-dev \
+    default-jre \
     vim
 
 RUN useradd -m -s /bin/bash user && \
@@ -21,6 +24,7 @@ USER user
 COPY comps /home/user/comps
 
 RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    if [ ${ARCH} = "cpu" ]; then pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
     pip install --no-cache-dir -r /home/user/comps/dataprep/pgvector/langchain/requirements.txt
 
 ENV PYTHONPATH=$PYTHONPATH:/home/user

diff --git a/comps/dataprep/pgvector/langchain/requirements.txt b/comps/dataprep/pgvector/langchain/requirements.txt
@@ -1,11 +1,14 @@
 beautifulsoup4
+cairosvg
 docarray[full]
+docx2txt
 easyocr
 fastapi
 huggingface_hub
 langchain
 langchain-community
 langsmith
+markdown
 numpy
 opentelemetry-api
 opentelemetry-exporter-otlp
@@ -17,5 +20,6 @@ prometheus-fastapi-instrumentator==7.0.0
 psycopg2-binary
 pymupdf
 python-docx
+python-pptx
 sentence_transformers
 shortuuid