Update Dockerfile to new package structure, and fix streaming bugs.

.dockerignore

@@ -1,5 +1,2 @@
 *
-!src/
+!packages/
-!tests/
-!pyproject.toml
-!README.md

Dockerfile

@@ -1,22 +1,28 @@
 FROM python:3.13-slim-bullseye
 
 ENV DEBIAN_FRONTEND=noninteractive
-
+ENV EXIFTOOL_PATH=/usr/bin/exiftool
-ARG INSTALL_GIT=false
+ENV FFMPEG_PATH=/usr/bin/ffmpeg
-RUN if [ "$INSTALL_GIT" = "true" ]; then \
-    apt-get update && apt-get install -y --no-install-recommends \
-    git \
-    && rm -rf /var/lib/apt/lists/*; \
-    fi
 
 # Runtime dependency
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ffmpeg \
-    && rm -rf /var/lib/apt/lists/*
+    exiftool
+
+ARG INSTALL_GIT=false
+RUN if [ "$INSTALL_GIT" = "true" ]; then \
+    apt-get install -y --no-install-recommends \
+    git; \
+    fi
+
+# Cleanup
+RUN rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 COPY . /app
-RUN pip --no-cache-dir install .
+RUN pip --no-cache-dir install \
+    /app/packages/markitdown[all] \
+    /app/packages/markitdown-sample-plugin
 
 # Default USERID and GROUPID
 ARG USERID=nobody

packages/markitdown/src/markitdown/_markitdown.py

@@ -327,6 +327,17 @@ class MarkItDown:
         elif base_guess.extension is not None:
             placeholder_filename = "placeholder" + base_guess.extension
 
+        # Check if we have a seekable stream. If not, load the entire stream into memory.
+        if not stream.seekable():
+            buffer = io.BytesIO()
+            while True:
+                chunk = stream.read(4096)
+                if not chunk:
+                    break
+                buffer.write(chunk)
+            buffer.seek(0)
+            stream = buffer
+
         # Add guesses based on stream content
         for guess in _guess_stream_info_from_stream(
             file_stream=stream, filename_hint=placeholder_filename

packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py

@@ -7,6 +7,7 @@ from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
 # Try loading optional (but in this case, required) dependencies
 # Save reporting of any exceptions for later
 _dependency_exc_info = None
+olefile = None
 try:
     import olefile
 except ImportError:
@@ -48,7 +49,7 @@ class OutlookMsgConverter(DocumentConverter):
         # Brute force, check if we have an OLE file
         cur_pos = file_stream.tell()
         try:
-            if not olefile.isOleFile(file_stream):
+            if olefile and not olefile.isOleFile(file_stream):
                 return False
         finally:
             file_stream.seek(cur_pos)