feat!: V2 Java client, named vectors

BREAKING

.github/workflows/release.yml

@@ -23,11 +23,11 @@ jobs:
  echo "AUTHOR_EMAIL=$AUTHOR_EMAIL" >> $GITHUB_OUTPUT
  id: author_info
 
- - name: Set up Java 17
+ - name: Set up Java 8
  uses: actions/setup-java@v3
  with:
- distribution: 'oracle'
- java-version: '17'
+ java-version: "8"
+ distribution: temurin
  server-id: ossrh
  server-username: OSSRH_JIRA_USERNAME
  server-password: OSSRH_JIRA_PASSWORD
@@ -51,7 +51,7 @@ jobs:
 
  - name: Semantic Release
  run: |
- bun install @conveyal/maven-semantic-release semantic-release
+ bun install @conveyal/maven-semantic-release semantic-release @semantic-release/git conventional-changelog-conventionalcommits
  bun x semantic-release --prepare @conveyal/maven-semantic-release --publish @semantic-release/github,@conveyal/maven-semantic-release --verify-conditions @semantic-release/github,@conveyal/maven-semantic-release --verify-release @conveyal/maven-semantic-release
  env:
  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test.yml

@@ -16,9 +16,9 @@ jobs:
  - uses: actions/checkout@v4
  - uses: actions/setup-java@v3
  with:
- java-version: "17"
+ java-version: "8"
  distribution: temurin
  - name: Run the Maven tests
  run: mvn test
  - name: Generate assembly fat JAR
- run: mvn clean package -Passembly
+ run: mvn clean package

.releaserc

@@ -0,0 +1,135 @@
+{
+ "branches": [
+ "master"
+ ],
+ "plugins": [
+ [
+ "@semantic-release/commit-analyzer",
+ {
+ "preset": "conventionalcommits",
+ "releaseRules": [
+ {
+ "breaking": true,
+ "release": "major"
+ },
+ {
+ "type": "feat",
+ "release": "minor"
+ },
+ {
+ "type": "fix",
+ "release": "patch"
+ },
+ {
+ "type": "perf",
+ "release": "patch"
+ },
+ {
+ "type": "revert",
+ "release": "patch"
+ },
+ {
+ "type": "docs",
+ "release": "patch"
+ },
+ {
+ "type": "style",
+ "release": "patch"
+ },
+ {
+ "type": "refactor",
+ "release": "patch"
+ },
+ {
+ "type": "test",
+ "release": "patch"
+ },
+ {
+ "type": "build",
+ "release": "patch"
+ },
+ {
+ "type": "ci",
+ "release": "patch"
+ },
+ {
+ "type": "chore",
+ "release": "patch"
+ }
+ ]
+ }
+ ],
+ "@semantic-release/release-notes-generator",
+ [
+ "@semantic-release/release-notes-generator",
+ {
+ "preset": "conventionalcommits",
+ "parserOpts": {
+ "noteKeywords": [
+ "BREAKING CHANGE",
+ "BREAKING CHANGES",
+ "BREAKING"
+ ]
+ },
+ "writerOpts": {
+ "commitsSort": [
+ "subject",
+ "scope"
+ ]
+ },
+ "presetConfig": {
+ "types": [
+ {
+ "type": "feat",
+ "section": "🍕 Features"
+ },
+ {
+ "type": "feature",
+ "section": "🍕 Features"
+ },
+ {
+ "type": "fix",
+ "section": "🐛 Bug Fixes"
+ },
+ {
+ "type": "perf",
+ "section": "🔥 Performance Improvements"
+ },
+ {
+ "type": "revert",
+ "section": "⏩ Reverts"
+ },
+ {
+ "type": "docs",
+ "section": "📝 Documentation"
+ },
+ {
+ "type": "style",
+ "section": "🎨 Styles"
+ },
+ {
+ "type": "refactor",
+ "section": "🧑‍💻 Code Refactoring"
+ },
+ {
+ "type": "test",
+ "section": "✅ Tests"
+ },
+ {
+ "type": "build",
+ "section": "🤖 Build System"
+ },
+ {
+ "type": "ci",
+ "section": "🔁 Continuous Integration"
+ },
+ {
+ "type": "chore",
+ "section": "🧹 Chores"
+ }
+ ]
+ }
+ }
+ ]
+ ]
+}

README.md

@@ -5,19 +5,19 @@
 ## Installation 🚀
 
 > [!IMPORTANT] 
-> Requires Java 17 or above.
+> Requires Java 8 or above.
 
 ### GitHub Releases 📦
 
-The packaged `jar` file releases can be found [here](https://github.com/qdrant/qdrant-spark/releases).
+The packaged `jar` file can be found [here](https://github.com/qdrant/qdrant-spark/releases).
 
 ### Building from source 🛠️
 
-To build the `jar` from source, you need [JDK@17](https://www.oracle.com/java/technologies/javase/jdk17-archive-downloads.html) and [Maven](https://maven.apache.org/) installed.
+To build the `jar` from source, you need [JDK@18](https://www.azul.com/downloads/#zulu) and [Maven](https://maven.apache.org/) installed.
 Once the requirements have been satisfied, run the following command in the project root. 🛠️
 
 ```bash
-mvn package -P assembly
+mvn package
 ```
 
 This will build and store the fat JAR in the `target` directory by default.
@@ -30,7 +30,7 @@ For use with Java and Scala projects, the package can be found [here](https://ce
 <dependency>
  <groupId>io.qdrant</groupId>
  <artifactId>spark</artifactId>
- <version>1.12.1</version>
+ <version>2.0</version>
 </dependency>
 ```
 
@@ -43,7 +43,7 @@ from pyspark.sql import SparkSession
 
 spark = SparkSession.builder.config(
  "spark.jars",
- "spark-1.12.1-jar-with-dependencies.jar", # specify the downloaded JAR file
+ "spark-2.0.jar", # specify the downloaded JAR file
  )
  .master("local[*]")
  .appName("qdrant")
@@ -58,7 +58,7 @@ To load data into Qdrant, a collection has to be created beforehand with the app
  <pyspark.sql.DataFrame>
  .write
  .format("io.qdrant.spark.Qdrant")
- .option("qdrant_url", <QDRANT_URL>)
+ .option("qdrant_url", <QDRANT_GRPC_URL>)
  .option("collection_name", <QDRANT_COLLECTION_NAME>)
  .option("embedding_field", <EMBEDDING_FIELD_NAME>) # Expected to be a field of type ArrayType(FloatType)
  .option("schema", <pyspark.sql.DataFrame>.schema.json())
@@ -70,31 +70,32 @@ To load data into Qdrant, a collection has to be created beforehand with the app
 - An API key can be set using the `api_key` option to make authenticated requests.
 
 ## Databricks
+
 You can use the `qdrant-spark` connector as a library in Databricks to ingest data into Qdrant.
+
 - Go to the `Libraries` section in your cluster dashboard.
 - Select `Install New` to open the library installation modal.
-- Search for `io.qdrant:spark:1.12.1` in the Maven packages and click `Install`.
+- Search for `io.qdrant:spark:2.0` in the Maven packages and click `Install`.
 
 <img width="1064" alt="Screenshot 2024-01-05 at 17 20 01 (1)" src="https://github.com/qdrant/qdrant-spark/assets/46051506/d95773e0-c5c6-4ff2-bf50-8055bb08fd1b">
 
-
 ## Datatype support 📋
 
-Qdrant supports all the Spark data types, and the appropriate types are mapped based on the provided `schema`.
+Qdrant supports all the Spark data types. The appropriate types are mapped based on the provided `schema`.
 
 ## Options and Spark types 🛠️
 
 | Option | Description | DataType | Required |
 | :---------------- | :------------------------------------------------------------------------ | :--------------------- | :------- |
-| `qdrant_url` | REST URL of the Qdrant instance  | `StringType` | ✅ |
+| `qdrant_url` | GRPC URL of the Qdrant instance. Eg: <http://localhost:6334> | `StringType` | ✅ |
 | `collection_name` | Name of the collection to write data into | `StringType` | ✅ |
 | `embedding_field` | Name of the field holding the embeddings | `ArrayType(FloatType)` | ✅ |
 | `schema` | JSON string of the dataframe schema | `StringType` | ✅ |
-| `mode` | Write mode of the dataframe. Supports "append". | `StringType` | ✅ |
 | `id_field` | Name of the field holding the point IDs. Default: Generates a random UUId | `StringType` | ❌ |
 | `batch_size` | Max size of the upload batch. Default: 100 | `IntType` | ❌ |
 | `retries` | Number of upload retries. Default: 3 | `IntType` | ❌ |
 | `api_key` | Qdrant API key to be sent in the header. Default: null | `StringType` | ❌ |
+| `vector_name` | Name of the vector in the collection. Default: null | `StringType` | ❌ |
 
 ## LICENSE 📜