chore: import upstream snapshot with attribution

docker/api/Dockerfile

@@ -0,0 +1,13 @@
+# Set base image
+ARG BASE_IMAGE=neuml/txtai-cpu
+FROM $BASE_IMAGE
+
+# Copy configuration
+COPY config.yml .
+
+# Run local API instance to cache models in container
+RUN python -c "from txtai.api import API; API('config.yml', False)"
+
+# Start server and listen on all interfaces
+ENV CONFIG "config.yml"
+ENTRYPOINT ["uvicorn", "--host", "0.0.0.0", "txtai.api:app"]

docker/aws/Dockerfile

@@ -0,0 +1,23 @@
+# Set base image
+ARG BASE_IMAGE=neuml/txtai-cpu
+FROM $BASE_IMAGE
+
+# Application script to copy into image
+ARG APP=api.py
+
+# Install Lambda Runtime Interface Client and Mangum ASGI bindings
+RUN pip install awslambdaric mangum
+
+# Copy configuration
+COPY config.yml .
+
+# Run local API instance to cache models in container
+RUN python -c "from txtai.api import API; API('config.yml', False)"
+
+# Copy application
+COPY $APP ./app.py
+
+# Start runtime client using default application handler
+ENV CONFIG "config.yml"
+ENTRYPOINT ["python", "-m", "awslambdaric"]
+CMD ["app.handler"]

docker/aws/api.py

@@ -0,0 +1,17 @@
+"""
+Lambda handler for a txtai API instance
+"""
+
+from mangum import Mangum
+
+from txtai.api import app, start
+
+# pylint: disable=C0103
+# Create FastAPI application instance wrapped by Mangum
+handler = None
+if not handler:
+    # Start application
+    start()
+
+    # Create handler
+    handler = Mangum(app, lifespan="off")

docker/aws/workflow.py

@@ -0,0 +1,33 @@
+"""
+Lambda handler for txtai workflows
+"""
+
+import json
+
+from txtai.api import API
+
+APP = None
+
+
+# pylint: disable=W0603,W0613
+def handler(event, context):
+    """
+    Runs a workflow using input event parameters.
+
+    Args:
+        event: input event
+        context: input context
+
+    Returns:
+        Workflow results
+    """
+
+    # Create (or get) global app instance
+    global APP
+    APP = APP if APP else API("config.yml")
+
+    # Get parameters from event body
+    event = json.loads(event["body"])
+
+    # Run workflow and return results
+    return {"statusCode": 200, "headers": {"Content-Type": "application/json"}, "body": list(APP.workflow(event["name"], event["elements"]))}

docker/base/Dockerfile

@@ -0,0 +1,38 @@
+# Set base image
+ARG BASE_IMAGE=python:3.10-slim
+FROM $BASE_IMAGE
+
+# Install GPU-enabled version of PyTorch if set
+ARG GPU
+
+# Target CPU architecture
+ARG TARGETARCH
+
+# Set Python version (i.e. 3, 3.10)
+ARG PYTHON_VERSION=3
+
+# List of txtai components to install
+ARG COMPONENTS=[all]
+
+# Locale environment variables
+ENV LC_ALL=C.UTF-8
+ENV LANG=C.UTF-8
+
+RUN \
+    # Install required packages
+    apt-get update && \
+    apt-get -y --no-install-recommends install libgomp1 libportaudio2 libsndfile1 libegl1 libgles2 libvulkan1 git gcc g++ python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python3-pip && \
+    rm -rf /var/lib/apt/lists && \
+    \
+    # Install txtai project and dependencies
+    ln -s /usr/bin/python${PYTHON_VERSION} /usr/bin/python && \
+    python -m pip install --no-cache-dir -U pip wheel setuptools && \
+    if [ -z ${GPU} ]; then pip install --no-cache-dir torch==2.12.1+cpu torchvision==0.27.1+cpu -f https://download.pytorch.org/whl/torch -f https://download.pytorch.org/whl/torchvision; fi && \
+    python -m pip install --no-cache-dir txtai${COMPONENTS} && \
+    python -c "import sys, importlib.util as util; 1 if util.find_spec('nltk') else sys.exit(); import nltk; nltk.download(['punkt', 'punkt_tab', 'averaged_perceptron_tagger_eng'])" && \
+    \
+    # Cleanup build packages
+    apt-get -y purge git gcc g++ python${PYTHON_VERSION}-dev && apt-get -y autoremove
+
+# Set default working directory
+WORKDIR /app

docker/minimal/Dockerfile

@@ -0,0 +1,20 @@
+# Set base image
+ARG BASE_IMAGE=python:3.10-slim
+FROM $BASE_IMAGE
+
+# Target CPU architecture
+ARG TARGETARCH
+
+# Set Python version (i.e. 3, 3.10)
+ARG PYTHON_VERSION=3
+
+# Locale environment variables
+ENV LC_ALL=C.UTF-8
+ENV LANG=C.UTF-8
+
+RUN \
+    # Install minimal txtai project and dependencies
+    MINIMAL=1 python -m pip install --no-cache-dir txtai_minimal
+
+# Set default working directory
+WORKDIR /app

docker/schedule/Dockerfile

@@ -0,0 +1,12 @@
+# Set base image
+ARG BASE_IMAGE=neuml/txtai-cpu
+FROM $BASE_IMAGE
+
+# Copy configuration
+COPY config.yml .
+
+# Run local API instance to cache models in container
+RUN python -c "from txtai.api import API; API('config.yml', False)"
+
+# Start application and wait for completion. Scheduled workflows can run indefinitely. 
+ENTRYPOINT ["python", "-c", "from txtai.api import API; API('config.yml').wait()"]

docker/workflow/Dockerfile

@@ -0,0 +1,13 @@
+# Set base image
+ARG BASE_IMAGE=neuml/txtai-cpu
+FROM $BASE_IMAGE
+
+# Copy configuration
+COPY config.yml .
+
+# Run local API instance to cache models in container
+RUN python -c "from txtai.api import API; API('config.yml', False)"
+
+# Run workflow. Requires two command line arguments: name of workflow and input elements
+ENTRYPOINT ["python", "-c", "import sys; from txtai.api import API\nfor _ in API('config.yml').workflow(sys.argv[1], sys.argv[2:]): pass"]
+CMD ["workflow"]