Document intelligence

.gitignore

@@ -0,0 +1,178 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# MacOS files
+.DS_Store
+.DS_Store/

README.md

@@ -1,2 +1,13 @@
 # spark-symbiota-ml
 Source code for models developed by BU Spark to enable plant specimen recognition for Symbiota
+
+## Directories
+1. transcription: Contains the transcription scripts for performing ocr.
+2. backend: Contains a simple api implementation with one route to receive the url of an image, downloads and verifies the image, and then calls the transcription scripts to perform ocr on the downloaded image.
+3. docker: Contains a docker compose implementation of the backend server.
+
+## Running the ocr service
+1. Put the `.env` file containing the required variables (see the [transcription README](/transcription/README.md))in the transcription directory.
+2. To do a minimal installation of only the Azure pipeline, install the packages in `transcription/requirements-doc-int.txt` and then `backend/requirements-backend.txt` in order. Otherwise, you can install the root `requirements.txt` and then `backend/requirements-backend.txt`. 
+3. If the docker network `symbiota-network` has not been created yet, run `docker network create symbiota-network` to create the network. The ocr service and the ocr middleware can be hosted on this network together. Change this in `docker/docker-compose.yaml` according to your hosting preferences.
+4. Navigate to the `docker` directory and run `docker compose up -d`.

backend/__init__.py

@@ -0,0 +1 @@
+# Let Python treat this directory as a package for importing functions

backend/main.py

@@ -0,0 +1,48 @@
+import requests
+from PIL import Image
+import os
+from fastapi import FastAPI, HTTPException, Query
+from transcription.doc_intelligence import run_doc_intell_pipeline
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+    return {"message": "OCR service is running"}
+
+@app.post("/azure")
+async def evaluate(url: str = Query(...)):
+    # Create a temporary file
+    temp_filename = 'temp.jpg'
+
+    # Download the image
+    def download_image():
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download image")
+        with open(temp_filename, "wb") as f:
+            f.write(response.content)
+
+    try:
+        download_image()
+    except Exception as e:
+        os.remove(temp_filename)
+        raise HTTPException(status_code=400, detail=str(e))
+
+    # Verify that the downloaded file is a valid image
+    try:
+        with Image.open(temp_filename) as img:
+            img.verify()
+    except Exception:
+        os.remove(temp_filename)
+        raise HTTPException(status_code=400, detail="Downloaded file is not a valid image")
+
+    # Downloaded file path
+    print("Downloaded image path:", temp_filename)
+
+    azure_result = run_doc_intell_pipeline(temp_filename)
+
+    # Clean up by deleting the temporary file
+    os.remove(temp_filename)
+
+    return azure_result

docker/Dockerfile

@@ -0,0 +1,20 @@
+# Dockerfile for running the ocr service
+FROM python:3.11.5-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install dependencies
+COPY transcription/requirements-doc-int.txt transcription/
+RUN pip install --no-cache-dir -r transcription/requirements-doc-int.txt
+COPY backend/requirements-backend.txt backend/
+RUN pip install --no-cache-dir -r backend/requirements-backend.txt
+
+# Copy code into the container
+COPY . .
+
+# Expose port 8080 for FastAPI
+EXPOSE 8080
+
+# Run FastAPI
+CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8080"]

docker/docker-compose.yaml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  ocr_service:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile
+    ports:
+      - "8080:8080"
+    networks:
+      - symbiota-network
+
+networks:
+  symbiota-network:
+    external: true