Add dependency for pdf2image and OCR processing (#421)

opea-project · Aug 21, 2024 · 9397522 · 9397522
1 parent 3c29fb4
commit 9397522
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 3 deletions.
diff --git a/comps/dataprep/redis/langchain/docker/Dockerfile b/comps/dataprep/redis/langchain/docker/Dockerfile
@@ -13,7 +13,9 @@ RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missin
     libgl1-mesa-glx \
     libjemalloc-dev \
     default-jre \
-    vim
+    vim \
+    poppler-utils \
+    tesseract-ocr
 
 RUN useradd -m -s /bin/bash user && \
     mkdir -p /home/user && \

diff --git a/comps/dataprep/redis/langchain_ray/docker/Dockerfile b/comps/dataprep/redis/langchain_ray/docker/Dockerfile
@@ -13,7 +13,9 @@ RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missin
     libgl1-mesa-glx \
     libjemalloc-dev \
     vim \
-    libcairo2
+    libcairo2 \
+    poppler-utils \
+    tesseract-ocr
 
 RUN useradd -m -s /bin/bash user && \
     mkdir -p /home/user && \

diff --git a/comps/dataprep/redis/llama_index/docker/Dockerfile b/comps/dataprep/redis/llama_index/docker/Dockerfile
@@ -13,7 +13,9 @@ RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missin
     libgl1-mesa-glx \
     libjemalloc-dev \
     vim \
-    libcairo2
+    libcairo2 \
+    poppler-utils \
+    tesseract-ocr
 
 RUN useradd -m -s /bin/bash user && \
     mkdir -p /home/user && \