refactor(medcat-service): Add pydantic. Add types to Health and Info APIs (#51)

* refactor(medcat-service): Add pydantic. Add types to Health and Info APIs

* refactor(medcat-service): Fix types to not be global. Add port to test functions to make easier to use

Author: alhendrickson

.devcontainer/devcontainer.json

@@ -29,7 +29,8 @@
 	"workspaceMount": "source=${localWorkspaceFolder},target=${localWorkspaceFolder},type=bind",
 	"mounts": [
 		"source=${localEnv:HOME}/.cache/pip,target=/home/vscode/.cache/pip,type=bind",
-		"source=${localEnv:HOME}/.cache/uv,target=/home/vscode/.cache/uv,type=bind"
+		"source=${localEnv:HOME}/.cache/uv,target=/home/vscode/.cache/uv,type=bind",
+		"source=${localEnv:HOME}/.cache/huggingface,target=/home/vscode/.cache/huggingface,type=bind",
 	],
 	"customizations": {
 		"vscode": {

.gitignore

@@ -0,0 +1,212 @@
+
+# Python gitignore https://github.com/github/gitignore/blob/main/Python.gitignore
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

medcat-service/medcat_service/api/api.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 import logging
 import os
@@ -9,6 +8,7 @@
 from flask import Blueprint, Response, request
 
 from medcat_service.nlp_service import NlpService
+from medcat_service.types import HealthCheckResponseContainer, ServiceInfo
 
 log = logging.getLogger("API")
 log.setLevel(level=os.getenv("APP_LOG_LEVEL", logging.INFO))
@@ -29,8 +29,8 @@ def info(nlp_service: NlpService) -> Response:
     :param nlp_service: NLP Service provided by dependency injection
     :return: Flask Response
     """
-    app_info = nlp_service.nlp.get_app_info()
-    return Response(response=json.dumps(app_info), status=200, mimetype="application/json")
+    app_info: ServiceInfo = nlp_service.nlp.get_app_info()
+    return Response(response=app_info.model_dump_json(), status=200, mimetype="application/json")
 
 
 @api.route('/process', methods=['POST'])
@@ -48,10 +48,12 @@ def process(nlp_service: NlpService) -> Response:
     meta_anns_filters = payload.get('meta_anns_filters', None)
 
     try:
-        result = nlp_service.nlp.process_content(payload['content'], meta_anns_filters=meta_anns_filters)
-        app_info = nlp_service.nlp.get_app_info()
-        response = {'result': result, 'medcat_info': app_info}
-        return Response(response=json.dumps(response, iterable_as_array=True), status=200, mimetype="application/json")
+        result = nlp_service.nlp.process_content(
+            payload['content'], meta_anns_filters=meta_anns_filters)
+        app_info: ServiceInfo = nlp_service.nlp.get_app_info()
+        response = {'result': result, 'medcat_info': app_info.model_dump()}
+        return Response(response=json.dumps(response, iterable_as_array=True, default=str),
+                        status=200, mimetype="application/json")
 
     except Exception as e:
         log.error(traceback.format_exc())
@@ -71,10 +73,12 @@ def process_bulk(nlp_service: NlpService) -> Response:
 
     try:
         result = nlp_service.nlp.process_content_bulk(payload['content'])
-        app_info = nlp_service.nlp.get_app_info()
+        app_info: ServiceInfo = nlp_service.nlp.get_app_info()
 
-        response = {'result': result, 'medcat_info': app_info}
-        return Response(response=json.dumps(response, iterable_as_array=True), status=200, mimetype="application/json")
+        response = {'result': result,
+                    'medcat_info': app_info.model_dump()}
+        return Response(response=json.dumps(response, iterable_as_array=True, default=str),
+                        status=200, mimetype="application/json")
 
     except Exception as e:
         log.error(traceback.format_exc())
@@ -91,7 +95,8 @@ def retrain_medcat(nlp_service: NlpService) -> Response:
     try:
         result = nlp_service.nlp.retrain_medcat(payload['content'], payload['replace_cdb'])
         app_info = nlp_service.nlp.get_app_info()
-        response = {'result': result, 'annotations': payload['content'], 'medcat_info': app_info}
+        response = {'result': result,
+                    'annotations': payload['content'], 'medcat_info': app_info}
         return Response(response=json.dumps(response), status=200, mimetype="application/json")
 
     except Exception as e:
@@ -104,8 +109,8 @@ def liveness():
     """
     Liveness API checks if the application is running.
     """
-    response = {"status": "UP", "checks": []}
-    return Response(response=json.dumps(response), status=200)
+    response = HealthCheckResponseContainer(status="UP", checks=[])
+    return Response(response=response.model_dump_json(), status=200)
 
 
 @api.route('/health/ready')
@@ -115,9 +120,11 @@ def readiness(nlp_service: NlpService) -> Response:
     """
     medcat_is_ready = nlp_service.get_processor().is_ready()
 
-    if medcat_is_ready["status"] == "UP":
-        response = {"status": "UP", "checks": [medcat_is_ready]}
-        return Response(response=json.dumps(response), status=200)
+    if medcat_is_ready.status == "UP":
+        response = HealthCheckResponseContainer(
+            status="UP", checks=[medcat_is_ready])
+        return Response(response=response.model_dump_json(), status=200)
     else:
-        response = {"status": "DOWN", "checks": [medcat_is_ready]}
-        return Response(response=json.dumps(response), status=503)
+        response = HealthCheckResponseContainer(
+            status="DOWN", checks=[medcat_is_ready])
+        return Response(response=response.model_dump_json(), status=503)