Fixed sts region issue. Added some references to pyinstaller exe creation.

.dockerignore

@@ -7,9 +7,11 @@
 *.pkl
 *.env
 *.zip
+*.pth
 test/*
 deprecated_models/*
 experiments/*
+build_deps/*
 .ipynb_checkpoints/*
 orchestration/*
 .vscode/*

.gitignore

@@ -7,9 +7,11 @@
 *.pkl
 *.env
 *.zip
+*.pth
 test/*
 deprecated_models/*
 .ipynb_checkpoints/*
 orchestration/*
 experiments/*
+build_deps/*
 .vscode/*

AddressMatcher_0.1.spec

@@ -0,0 +1,46 @@
+# -*- mode: python ; coding: utf-8 -*-
+from PyInstaller.utils.hooks import collect_data_files
+
+datas = []
+datas += collect_data_files('gradio_client')
+datas += collect_data_files('gradio')
+
+
+a = Analysis(
+    ['app.py'],
+    pathex=[],
+    binaries=[],
+    datas=datas,
+    hiddenimports=['pyarrow.vendored.version'],
+    hookspath=['build_deps\\\\'],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+    module_collection_mode={
+        'gradio': 'py',  # Collect gradio package as source .py files
+    }
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    a.binaries,
+    a.datas,
+    [],
+    name='AddressMatcher_0.1',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)

Dockerfile

@@ -14,8 +14,8 @@ RUN useradd -m -u 1000 user
 # Change ownership of /home/user directory
 RUN chown -R user:user /home/user
 
-# Create the output files directory and set its permissions
-RUN mkdir -p /home/user/output && chown -R user:user /home/user/output
+# Make output folder
+RUN mkdir -p /home/user/app/output && chown -R user:user /home/user/app/output
 
 # Switch to the "user" user
 USER user

how_to_create_exe_dist.txt

@@ -0,0 +1,35 @@
+1. Create minimal environment to run the app in conda. E.g. 'conda create --name new_env'
+
+2. Activate the environment 'conda activate new_env'
+
+3. cd to this folder. Install packages from requirements.txt using 'pip install -r requirements.txt' 
+
+NOTE: for ensuring that spaCy models are loaded into the program correctly in requirements.txt, follow this guide: https://spacy.io/usage/models#models-download
+
+6. If necessary, create hook- files to tell pyinstaller to include specific packages in the exe build. Examples are provided for gradio and en_core_web_sm (a spaCy model). Put these in the build_deps\ subfolder
+
+7. pip install pyinstaller
+
+8. In command line, cd to the folder that contains app.py. 
+
+9.Run the following, assuming you want to make one single .exe file (This helped me: https://github.com/pyinstaller/pyinstaller/issues/8108):
+
+a) In command line: pyi-makespec --additional-hooks-dir="build_deps\\" --collect-data=gradio_client --collect-data=gradio --hidden-import pyarrow.vendored.version --onefile --name AddressMatcher_0.1 app.py
+
+b) Open the created spec file in Notepad. Add the following to the end of the Analysis section then save:
+
+a = Analysis(
+    ...
+    module_collection_mode={
+        'gradio': 'py',  # Collect gradio package as source .py files
+    }
+)
+
+c) Back in command line, run this: pyinstaller --clean --noconfirm AddressMatcher_0.1.spec
+
+
+9. A 'dist' folder will be created with the executable inside along with all dependencies('dist\data_text_search'). 
+
+10. In 'dist\data_text_search' try double clicking on the .exe file. After a short delay, the command prompt should inform you about the IP address of the app that is now running. Copy the IP address. **Do not close this window!**
+
+11. In an Internet browser, navigate to the indicated IP address. The app should now be running in your browser window.

tools/aws_functions.py

@@ -24,7 +24,7 @@ except Exception as e:
 
 
 def get_assumed_role_info():
-    sts = boto3.client('sts')
+    sts = boto3.client('sts', region_name='eu-west-2')
     response = sts.get_caller_identity()
 
     # Extract ARN of the assumed role