merge

.github/workflows/publish.yml

@@ -25,11 +25,6 @@ jobs:
           pip install build;
         continue-on-error: false
 
-      - name: Setup Node
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
       - name: Build the module
         env:
           PYPI_PASSWORD: ${{ secrets.PYPI_PASSWORD }}

guardrails_api/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.0"
+__version__ = "0.0.0a0"

guardrails_api/app.py

@@ -47,7 +47,7 @@ def register_config(config: Optional[str] = None):
         SourceFileLoader("config", config_file_path).load_module()
 
 
-def create_app(env: Optional[str] = None, config: Optional[str] = None):
+def create_app(env: Optional[str] = None, config: Optional[str] = None, port: Optional[int] = None):
     if os.environ.get("APP_ENVIRONMENT") != "production":
         from dotenv import load_dotenv
 
@@ -56,6 +56,11 @@ def create_app(env: Optional[str] = None, config: Optional[str] = None):
         env_file_path = os.path.abspath(env_file)
         load_dotenv(env_file_path)
 
+    set_port = port or os.environ.get("PORT", 8000)
+    host = os.environ.get("HOST", "http://localhost")
+    self_endpoint = os.environ.get("SELF_ENDPOINT", f"{host}:{set_port}")
+    os.environ["SELF_ENDPOINT"] = self_endpoint
+
     register_config(config)
 
     app = Flask(__name__)

guardrails_api/cli/start.py

@@ -29,12 +29,22 @@ def start(
     env: Optional[str] = typer.Option(
         default="",
         help="An env file to load environment variables from.",
-        prompt=".env file (optional)",
     ),
     config: Optional[str] = typer.Option(
         default="",
         help="A config file to load Guards from.",
-        prompt="config file (optional)",
+    ),
+    timeout: Optional[int] = typer.Option(
+        default=5,
+        help="Gunicorn worker timeout.",
+    ),
+    threads: Optional[int] = typer.Option(
+        default=10,
+        help="Number of Gunicorn worker threads.",
+    ),
+    port: Optional[int] = typer.Option(
+        default=8000,
+        help="The port to run the server on.",
     ),
 ):
     # TODO: If these are empty,
@@ -43,8 +53,8 @@ def start(
     config = config or None
 
     options = {
-        "bind": "0.0.0.0:8000",
-        "timeout": 5,
-        "threads": 10,
+        "bind": f"0.0.0.0:{port}",
+        "timeout": timeout,
+        "threads": threads,
     }
-    StandaloneApplication(create_app(env, config), options).run()
+    StandaloneApplication(create_app(env, config, port), options).run()

guardrails_api/clients/cache_client.py

@@ -15,9 +15,8 @@ def initialize(self, app):
         self.cache = Cache(
             app, 
             config={
-                "CACHE_TYPE": "simple",
+                "CACHE_TYPE": "SimpleCache",
                 "CACHE_DEFAULT_TIMEOUT": 300,
-                "CACHE_NO_NULL_WARNING": True,
                 "CACHE_THRESHOLD": 50
             }
         )

guardrails_api/default.env

@@ -4,5 +4,7 @@ LOGLEVEL="INFO"
 GUARDRAILS_LOG_LEVEL="INFO"
 GUARDRAILS_PROCESS_COUNT=1
 SELF_ENDPOINT=http://localhost:8000
+API_KEY=dapi9b2c2e2e384cce5ba50588dede8b48ae
+HOST=http://localhost
+PORT=8000
 OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES
-API_KEY=dapi9b2c2e2e384cce5ba50588dede8b48ae

pyproject.toml

@@ -10,7 +10,7 @@ readme = "README.md"
 keywords = ["Guardrails", "Guardrails AI", "Guardrails API", "Guardrails API"]
 requires-python = ">= 3.8.1"
 dependencies = [
-    "guardrails-ai@git+https://github.com/guardrails-ai/guardrails.git@0.5.0-dev",
+    "guardrails-ai>=0.5.0a2",
     "flask>=3.0.3,<4",
     "Flask-SQLAlchemy>=3.1.1,<4",
     "Flask-Caching>=2.3.0,<3",

requirements-lock.txt

@@ -2,96 +2,84 @@ aiohttp==3.9.5
 aiosignal==1.3.1
 annotated-types==0.7.0
 anyio==4.4.0
-asgiref==3.8.1
+arrow==1.3.0
 attrs==23.2.0
 blinker==1.8.2
-boto3==1.34.115
-botocore==1.34.115
-certifi==2024.2.2
+boto3==1.34.132
+botocore==1.34.132
+cachelib==0.9.0
+certifi==2024.6.2
 cffi==1.16.0
 charset-normalizer==3.3.2
 click==8.1.7
 colorama==0.4.6
 coloredlogs==15.0.1
-cryptography==42.0.7
+cryptography==42.0.8
 Deprecated==1.2.14
 distro==1.9.0
-faiss-cpu==1.8.0
-filelock==3.14.0
+Faker==25.9.1
+filelock==3.15.4
 Flask==3.0.3
+Flask-Caching==2.3.0
 Flask-Cors==4.0.1
 Flask-SQLAlchemy==3.1.1
+fqdn==1.5.1
 frozenlist==1.4.1
-fsspec==2024.5.0
-googleapis-common-protos==1.63.0
+fsspec==2024.6.0
+googleapis-common-protos==1.63.2
 griffe==0.36.9
-grpcio==1.64.0
-guardrails-ai @ git+https://github.com/guardrails-ai/guardrails.git@fd77007dfe823f8cb32cd314b78e5f63aea71e9a
+grpcio==1.64.1
+guardrails-ai==0.5.0a2
+guardrails-api @ file:///Users/calebcourier/Projects/gr-mono/guardrails-cdk/guardrails-api
+guardrails-api-client==0.3.8
 gunicorn==22.0.0
 h11==0.14.0
 httpcore==1.0.5
 httpx==0.27.0
-huggingface-hub==0.23.2
+huggingface-hub==0.23.4
 humanfriendly==10.0
 idna==3.7
-importlib-metadata==7.0.0
+ijson==3.3.0
+importlib_metadata==7.1.0
+isoduration==20.11.0
 itsdangerous==2.2.0
 Jinja2==3.1.4
 jmespath==1.0.1
 joblib==1.4.2
 jsonpatch==1.33
-jsonpointer==2.4
+jsonpointer==3.0.0
+jsonref==1.1.0
 jsonschema==4.22.0
 jsonschema-specifications==2023.12.1
 jwt==1.3.1
-langchain-core==0.1.52
-langsmith==0.1.65
-litellm==1.39.3
+langchain-core==0.2.9
+langsmith==0.1.82
+litellm==1.40.25
 lxml==4.9.4
 markdown-it-py==3.0.0
 MarkupSafe==2.1.5
 mdurl==0.1.2
 multidict==6.0.5
 nltk==3.8.1
-numpy==1.26.4
-openai==1.30.5
-opentelemetry-api==1.24.0
-opentelemetry-distro==0.45b0
-opentelemetry-exporter-otlp-proto-common==1.24.0
-opentelemetry-exporter-otlp-proto-grpc==1.24.0
-opentelemetry-exporter-otlp-proto-http==1.24.0
-opentelemetry-instrumentation==0.45b0
-opentelemetry-instrumentation-asgi==0.45b0
-opentelemetry-instrumentation-asyncio==0.45b0
-opentelemetry-instrumentation-aws-lambda==0.45b0
-opentelemetry-instrumentation-boto3sqs==0.45b0
-opentelemetry-instrumentation-botocore==0.45b0
-opentelemetry-instrumentation-dbapi==0.45b0
-opentelemetry-instrumentation-flask==0.45b0
-opentelemetry-instrumentation-grpc==0.45b0
-opentelemetry-instrumentation-httpx==0.45b0
-opentelemetry-instrumentation-jinja2==0.45b0
-opentelemetry-instrumentation-logging==0.45b0
-opentelemetry-instrumentation-requests==0.45b0
-opentelemetry-instrumentation-sqlalchemy==0.45b0
-opentelemetry-instrumentation-sqlite3==0.45b0
-opentelemetry-instrumentation-tortoiseorm==0.45b0
-opentelemetry-instrumentation-urllib==0.45b0
-opentelemetry-instrumentation-urllib3==0.45b0
-opentelemetry-instrumentation-wsgi==0.45b0
-opentelemetry-propagator-aws-xray==1.0.1
-opentelemetry-proto==1.24.0
-opentelemetry-sdk==1.24.0
-opentelemetry-semantic-conventions==0.45b0
-opentelemetry-test-utils==0.45b0
-opentelemetry-util-http==0.45b0
-orjson==3.10.3
-packaging==23.2
+openai==1.35.3
+opentelemetry-api==1.25.0
+opentelemetry-exporter-otlp-proto-common==1.25.0
+opentelemetry-exporter-otlp-proto-grpc==1.25.0
+opentelemetry-exporter-otlp-proto-http==1.25.0
+opentelemetry-instrumentation==0.46b0
+opentelemetry-instrumentation-flask==0.46b0
+opentelemetry-instrumentation-wsgi==0.46b0
+opentelemetry-proto==1.25.0
+opentelemetry-sdk==1.25.0
+opentelemetry-semantic-conventions==0.46b0
+opentelemetry-util-http==0.46b0
+orjson==3.10.5
+packaging==24.1
 protobuf==4.25.3
 psycopg2-binary==2.9.9
 pycparser==2.22
-pydantic==2.7.2
-pydantic_core==2.18.3
+pydantic==2.7.4
+pydantic_core==2.18.4
 pydash==7.0.7
 Pygments==2.18.0
 python-dateutil==2.9.0.post0
@@ -100,23 +88,28 @@ PyYAML==6.0.1
 referencing==0.35.1
 regex==2023.12.25
 requests==2.32.3
+rfc3339-validator==0.1.4
+rfc3987==1.3.8
 rich==13.7.1
 rpds-py==0.18.1
 rstr==3.2.2
-s3transfer==0.10.1
-setuptools==70.0.0
+s3transfer==0.10.2
+setuptools==70.1.0
 shellingham==1.5.4
 six==1.16.0
 sniffio==1.3.1
-SQLAlchemy==2.0.30
-tenacity==8.3.0
+SQLAlchemy==2.0.31
+tenacity==8.4.2
 tiktoken==0.7.0
 tokenizers==0.19.1
 tqdm==4.66.4
 typer==0.9.4
-typing_extensions==4.12.0
-urllib3==2.2.1
+types-python-dateutil==2.9.0.20240316
+typing_extensions==4.12.2
+uri-template==1.3.0
+urllib3==2.2.2
+webcolors==24.6.0
 Werkzeug==3.0.3
 wrapt==1.16.0
 yarl==1.9.4
-zipp==3.19.0
+zipp==3.19.2

tests/blueprints/test_guards.py

@@ -44,8 +44,8 @@ def test_route_setup(mocker):
 
     from guardrails_api.blueprints.guards import guards_bp
 
-    assert guards_bp.route_call_count == 3
-    assert guards_bp.routes == ["/", "/<guard_name>", "/<guard_name>/validate"]
+    assert guards_bp.route_call_count == 4
+    assert guards_bp.routes == ["/", "/<guard_name>", "/<guard_name>/validate", "/<guard_name>/history/<call_id>"]
 
 
 def test_guards__get(mocker):
@@ -362,6 +362,7 @@ def test_validate__raises_bad_request__num_reasks(mocker):
 def test_validate__parse(mocker):
     os.environ["PGHOST"] = "localhost"
     mock_outcome = ValidationOutcome(
+        call_id="mock-call-id",
         raw_llm_output="Hello world!",
         validated_output="Hello world!",
         validation_passed=True,
@@ -386,6 +387,10 @@ def test_validate__parse(mocker):
         "guardrails_api.blueprints.guards.guard_client.get_guard",
         return_value=mock_guard,
     )
+
+    mocker.patch(
+        "guardrails_api.blueprints.guards.CacheClient.set"
+    )
 
     # mocker.patch("guardrails_api.blueprints.guards.get_tracer", return_value=mock_tracer)
 
@@ -430,6 +435,7 @@ def test_validate__parse(mocker):
     # set_attribute_spy.assert_has_calls(expected_calls)
 
     assert response == {
+        "callId": "mock-call-id",
         "validatedOutput": "Hello world!",
         "validationPassed": True,
         "rawLlmOutput": "Hello world!",
@@ -442,7 +448,10 @@ def test_validate__call(mocker):
     os.environ["PGHOST"] = "localhost"
     mock_guard = MockGuardStruct()
     mock_outcome = ValidationOutcome(
-        raw_llm_output="Hello world!", validated_output=None, validation_passed=False
+        call_id="mock-call-id",
+        raw_llm_output="Hello world!",
+        validated_output=None,
+        validation_passed=False
     )
 
     mock___call__ = mocker.patch.object(MockGuardStruct, "__call__")
@@ -475,6 +484,12 @@ def test_validate__call(mocker):
         "guardrails_api.blueprints.guards.get_llm_callable",
         return_value="openai.Completion.create",
     )
+
+    mocker.patch(
+        "guardrails_api.blueprints.guards.CacheClient.set"
+    )
+
+
 
     # mocker.patch("guardrails_api.blueprints.guards.get_tracer", return_value=mock_tracer)
 
@@ -523,6 +538,7 @@ def test_validate__call(mocker):
     # set_attribute_spy.assert_has_calls(expected_calls)
 
     assert response == {
+        "callId": "mock-call-id",
         "validationPassed": False,
         "validatedOutput": None,
         "rawLlmOutput": "Hello world!",

tests/cli/test_start.py

@@ -9,7 +9,7 @@ def test_start(mocker):
 
     from guardrails_api.cli.start import start
 
-    start("env", "config")
+    start("env", "config", 5, 10, 8000)
 
     mock_gunicorn.assert_called_once_with(
         mock_flask_app,
@@ -20,4 +20,4 @@ def test_start(mocker):
         },
     )
 
-    mock_create_app.assert_called_once_with("env", "config")
+    mock_create_app.assert_called_once_with("env", "config", 8000)