Added tika jar into image to avoid downloading

infiniflow · Nov 2, 2024 · ce4d035 · ce4d035
1 parent c7ea7e9
commit ce4d035
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 0 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -104,6 +104,11 @@ RUN --mount=type=bind,source=huggingface.co,target=/huggingface.co \
 # Copy nltk data downloaded via download_deps.py
 COPY nltk_data /root/nltk_data
 
+# https://github.com/chrismattmann/tika-python
+# This is the only way to run python-tika without internet access. Without this set, the default is to check the tika version and pull latest every time from Apache.
+COPY tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 /
+ENV TIKA_SERVER_JAR="file:////tika-server-standard.jar"
+
 # Copy compiled web pages
 COPY --from=builder /ragflow/web/dist /ragflow/web/dist
 

diff --git a/Dockerfile.slim b/Dockerfile.slim
@@ -97,6 +97,11 @@ RUN --mount=type=bind,source=huggingface.co,target=/huggingface.co \
 # Copy nltk data downloaded via download_deps.py
 COPY nltk_data /root/nltk_data
 
+# https://github.com/chrismattmann/tika-python
+# This is the only way to run python-tika without internet access. Without this set, the default is to check the tika version and pull latest every time from Apache.
+COPY tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 /
+ENV TIKA_SERVER_JAR="file:////tika-server-standard.jar"
+
 # Copy compiled web pages
 COPY --from=builder /ragflow/web/dist /ragflow/web/dist
 

diff --git a/download_deps.py b/download_deps.py
@@ -7,6 +7,8 @@
 
 urls = [
     "http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb",
+    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar",
+    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar.md5",
 ]
 
 repos = [