Add Weaviate Destination airbytehq#20012

airbyte-integrations/connectors/destination-weaviate/.dockerignore

@@ -0,0 +1,5 @@
+*
+!Dockerfile
+!main.py
+!destination_weaviate
+!setup.py

airbyte-integrations/connectors/destination-weaviate/Dockerfile

@@ -0,0 +1,38 @@
+FROM python:3.9.11-alpine3.15 as base
+
+# build and load all requirements
+FROM base as builder
+WORKDIR /airbyte/integration_code
+
+# upgrade pip to the latest version
+RUN apk --no-cache upgrade \
+    && pip install --upgrade pip \
+    && apk --no-cache add tzdata build-base
+
+
+COPY setup.py ./
+# install necessary packages to a temporary folder
+RUN pip install --prefix=/install .
+
+# build a clean environment
+FROM base
+WORKDIR /airbyte/integration_code
+
+# copy all loaded and built libraries to a pure basic image
+COPY --from=builder /install /usr/local
+# add default timezone settings
+COPY --from=builder /usr/share/zoneinfo/Etc/UTC /etc/localtime
+RUN echo "Etc/UTC" > /etc/timezone
+
+# bash is installed for more convenient debugging.
+RUN apk --no-cache add bash
+
+# copy payload code only
+COPY main.py ./
+COPY destination_weaviate ./destination_weaviate
+
+ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
+ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
+
+LABEL io.airbyte.version=0.1.0
+LABEL io.airbyte.name=airbyte/destination-weaviate

airbyte-integrations/connectors/destination-weaviate/README.md

@@ -0,0 +1,123 @@
+# Weaviate Destination
+
+This is the repository for the Weaviate destination connector, written in Python.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/destinations/weaviate).
+
+## Local development
+
+### Prerequisites
+**To iterate on this connector, make sure to complete this prerequisites section.**
+
+#### Minimum Python version required `= 3.7.0`
+
+#### Build & Activate Virtual Environment and install dependencies
+From this connector directory, create a virtual environment:
+```
+python -m venv .venv
+```
+
+This will generate a virtualenv for this module in `.venv/`. Make sure this venv is active in your
+development environment of choice. To activate it from the terminal, run:
+```
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+If you are in an IDE, follow your IDE's instructions to activate the virtualenv.
+
+Note that while we are installing dependencies from `requirements.txt`, you should only edit `setup.py` for your dependencies. `requirements.txt` is
+used for editable installs (`pip install -e`) to pull in Python dependencies from the monorepo and will call `setup.py`.
+If this is mumbo jumbo to you, don't worry about it, just put your deps in `setup.py` but install using `pip install -r requirements.txt` and everything
+should work as you expect.
+
+#### Building via Gradle
+From the Airbyte repository root, run:
+```
+./gradlew :airbyte-integrations:connectors:destination-weaviate:build
+```
+
+#### Create credentials
+**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.io/integrations/destinations/weaviate)
+to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `destination_weaviate/spec.json` file.
+Note that the `secrets` directory is gitignored by default, so there is no danger of accidentally checking in sensitive information.
+See `integration_tests/sample_config.json` for a sample config file.
+
+**If you are an Airbyte core member**, copy the credentials in Lastpass under the secret name `destination weaviate test creds`
+and place them into `secrets/config.json`.
+
+### Locally running the connector
+```
+python main.py spec
+python main.py check --config secrets/config.json
+python main.py discover --config secrets/config.json
+python main.py read --config secrets/config.json --catalog integration_tests/configured_catalog.json
+```
+
+### Locally running the connector docker image
+
+#### Build
+First, make sure you build the latest Docker image:
+```
+docker build . -t airbyte/destination-weaviate:dev
+```
+
+You can also build the connector image via Gradle:
+```
+./gradlew :airbyte-integrations:connectors:destination-weaviate:airbyteDocker
+```
+When building via Gradle, the docker image name and tag, respectively, are the values of the `io.airbyte.name` and `io.airbyte.version` `LABEL`s in
+the Dockerfile.
+
+#### Run
+Then run any of the connector commands as follows:
+```
+docker run --rm airbyte/destination-weaviate:dev spec
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/destination-weaviate:dev check --config /secrets/config.json
+# messages.jsonl is a file containing line-separated JSON representing AirbyteMessages
+cat messages.jsonl | docker run --rm -v $(pwd)/secrets:/secrets -v $(pwd)/integration_tests:/integration_tests airbyte/destination-weaviate:dev write --config /secrets/config.json --catalog /integration_tests/configured_catalog.json
+```
+## Testing
+   Make sure to familiarize yourself with [pytest test discovery](https://docs.pytest.org/en/latest/goodpractices.html#test-discovery) to know how your test files and methods should be named.
+First install test dependencies into your virtual environment:
+```
+pip install .[tests]
+```
+### Unit Tests
+To run unit tests locally, from the connector directory run:
+```
+python -m pytest unit_tests
+```
+
+### Integration Tests
+There are two types of integration tests: Acceptance Tests (Airbyte's test suite for all destination connectors) and custom integration tests (which are specific to this connector).
+#### Custom Integration tests
+Place custom tests inside `integration_tests/` folder, then, from the connector root, run
+```
+python -m pytest integration_tests
+```
+#### Acceptance Tests
+Coming soon: 
+
+### Using gradle to run tests
+All commands should be run from airbyte project root.
+To run unit tests:
+```
+./gradlew :airbyte-integrations:connectors:destination-weaviate:unitTest
+```
+To run acceptance and custom integration tests:
+```
+./gradlew :airbyte-integrations:connectors:destination-weaviate:integrationTest
+```
+
+## Dependency Management
+All of your dependencies should go in `setup.py`, NOT `requirements.txt`. The requirements file is only used to connect internal Airbyte dependencies in the monorepo for local development.
+We split dependencies between two groups, dependencies that are:
+* required for your connector to work need to go to `MAIN_REQUIREMENTS` list.
+* required for the testing need to go to `TEST_REQUIREMENTS` list
+
+### Publishing a new version of the connector
+You've checked out the repo, implemented a million dollar feature, and you're ready to share your changes with the world. Now what?
+1. Make sure your changes are passing unit and integration tests.
+1. Bump the connector version in `Dockerfile` -- just increment the value of the `LABEL io.airbyte.version` appropriately (we use [SemVer](https://semver.org/)).
+1. Create a Pull Request.
+1. Pat yourself on the back for being an awesome contributor.
+1. Someone from Airbyte will take a look at your PR and iterate with you to merge it into master.

airbyte-integrations/connectors/destination-weaviate/build.gradle

@@ -0,0 +1,8 @@
+plugins {
+    id 'airbyte-python'
+    id 'airbyte-docker'
+}
+
+airbytePython {
+    moduleDirectory 'destination_weaviate'
+}

airbyte-integrations/connectors/destination-weaviate/destination_weaviate/__init__.py

@@ -0,0 +1,8 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+
+from .destination import DestinationWeaviate
+
+__all__ = ["DestinationWeaviate"]

airbyte-integrations/connectors/destination-weaviate/destination_weaviate/client.py

@@ -0,0 +1,41 @@
+import weaviate
+
+from typing import Any, Mapping
+import uuid
+
+
+class Client:
+    def __init__(self, config: Mapping[str, Any]):
+        self.client = self.get_weaviate_client(config)
+        self.config = config
+        self.batch_size = 100
+
+    def queue_write_operation(self, stream_name: str, record: Mapping):
+        # TODO need to handle case where original DB ID is not a UUID
+        id = ""
+        if record.get('id'):
+            id = record.get("id")
+            del record["id"]
+        else:
+            id = uuid.uuid4()
+
+        self.client.batch.add_data_object(record, stream_name, id)
+        if self.client.batch.num_objects() >= self.batch_size:
+            self.client.batch.create_objects()
+
+    def flush(self):
+        self.client.batch.create_objects()
+
+    @staticmethod
+    def get_weaviate_client(config: Mapping[str, Any]) -> weaviate.Client:
+        url, username, password = config.get("url"), config.get("username"), config.get("password")
+
+        if username and not password:
+            raise Exception("Password is required when username is set")
+        if password and not username:
+            raise Exception("Username is required when password is set")
+
+        if username and password:
+            credentials = weaviate.auth.AuthClientPassword(username, password)
+            return weaviate.Client(url=url, auth_client_secret=credentials)
+        return weaviate.Client(url=url, timeout_config=(2, 2))

airbyte-integrations/connectors/destination-weaviate/destination_weaviate/destination.py

@@ -0,0 +1,78 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+
+from typing import Any, Iterable, Mapping
+
+from airbyte_cdk import AirbyteLogger
+from airbyte_cdk.destinations import Destination
+from airbyte_cdk.models import AirbyteConnectionStatus, AirbyteMessage, ConfiguredAirbyteCatalog, DestinationSyncMode, Status, Type
+
+
+from .client import Client
+
+
+class DestinationWeaviate(Destination):
+    def write(
+            self, config: Mapping[str, Any], configured_catalog: ConfiguredAirbyteCatalog, input_messages: Iterable[AirbyteMessage]
+    ) -> Iterable[AirbyteMessage]:
+
+        """
+        TODO
+        Reads the input stream of messages, config, and catalog to write data to the destination.
+
+        This method returns an iterable (typically a generator of AirbyteMessages via yield) containing state messages received
+        in the input message stream. Outputting a state message means that every AirbyteRecordMessage which came before it has been
+        successfully persisted to the destination. This is used to ensure fault tolerance in the case that a sync fails before fully completing,
+        then the source is given the last state message output from this method as the starting point of the next sync.
+
+        :param config: dict of JSON configuration matching the configuration declared in spec.json
+        :param configured_catalog: The Configured Catalog describing the schema of the data being received and how it should be persisted in the
+                                    destination
+        :param input_messages: The stream of input messages received from the source
+        :return: Iterable of AirbyteStateMessages wrapped in AirbyteMessage structs
+        """
+        client = Client(config)
+        # TODO add support for overwrite mode
+        #for configured_stream in configured_catalog.streams:
+        #    if configured_stream.destination_sync_mode == DestinationSyncMode.overwrite:
+        #        client.delete_stream_entries(configured_stream.stream.name)
+
+        for message in input_messages:
+            if message.type == Type.STATE:
+                # Emitting a state message indicates that all records which came before it have been written to the destination. So we flush
+                # the queue to ensure writes happen, then output the state message to indicate it's safe to checkpoint state
+                client.flush()
+                yield message
+            elif message.type == Type.RECORD:
+                record = message.record
+                client.queue_write_operation(record.stream, record.data)
+            else:
+                # ignore other message types for now
+                continue
+
+        # Make sure to flush any records still in the queue
+        client.flush()
+
+    def check(self, logger: AirbyteLogger, config: Mapping[str, Any]) -> AirbyteConnectionStatus:
+        """
+        Tests if the input configuration can be used to successfully connect to the destination with the needed permissions
+            e.g: if a provided API token or password can be used to connect and write to the destination.
+
+        :param logger: Logging object to display debug/info/error to the logs
+            (logs will not be accessible via airbyte UI if they are not passed to this logger)
+        :param config: Json object containing the configuration of this destination, content of this json is as specified in
+        the properties of the spec.json file
+
+        :return: AirbyteConnectionStatus indicating a Success or Failure
+        """
+        try:
+            client = Client.get_weaviate_client(config)
+            ready = client.is_ready()
+            if not ready:
+                return AirbyteConnectionStatus(status=Status.FAILED,
+                                              message=f"Weaviate server {config.get('url')} not ready")
+            return AirbyteConnectionStatus(status=Status.SUCCEEDED)
+        except Exception as e:
+            return AirbyteConnectionStatus(status=Status.FAILED, message=f"An exception occurred: {repr(e)}")

airbyte-integrations/connectors/destination-weaviate/destination_weaviate/spec.json

@@ -0,0 +1,39 @@
+{
+  "documentationUrl" : "https://docs.airbyte.com/integrations/destinations/weaviate",
+  "supported_destination_sync_modes" : [
+    "append"
+  ],
+  "supportsIncremental" : true,
+  "supportsDBT" : false,
+  "supportsNormalization" : false,
+  "connectionSpecification" : {
+    "$schema" : "http://json-schema.org/draft-07/schema#",
+    "title" : "Destination Weaviate",
+    "type" : "object",
+    "required" : [
+      "url"
+    ],
+    "additionalProperties" : false,
+    "properties" : {
+      "url" : {
+        "type" : "string",
+        "description" : "The URL to the weaviate instance",
+        "examples" : [
+          "http://localhost:8080",
+          "https://your-instance.semi.network"
+        ]
+      },
+      "username" : {
+        "type" : "string",
+        "description" : "Username used with OIDC authentication",
+        "examples" : [
+          "xyz@weaviate.io"
+        ]
+      },
+      "password" : {
+        "type" : "string",
+        "description" : "Password used with OIDC authentication"
+      }
+    }
+  }
+}

airbyte-integrations/connectors/destination-weaviate/integration_tests/example-config.json

@@ -0,0 +1 @@
+{ "url": "http://localhost:8080"}