Merge branch 'main' into revisit-content-and-fix-rerank

.github/langchain4j-github-bot.yml

@@ -13,22 +13,30 @@ triage:
         - '*-azure-*/**'
     - id: gemini
       labels: [Gemini]
-      title: "gemini|vertex"
+      title: "gemini|vertex|google"
       notify: [glaforge]
       notifyInPullRequest: true
       files:
         - '*-vertex-*/**'
+        - '*-google-*/**'
     - id: elasticsearch
       labels: [Elasticsearch]
       title: "elasticsearch"
       notify: [dadoonet]
       notifyInPullRequest: true
       files:
-        - '*-elasticsearch-*/**'
+        - 'langchain4j-elasticsearch/**'
     - id: mistral
       labels: [Mistral]
       title: "mistral"
       notify: [czelabueno]
       notifyInPullRequest: true
       files:
-        - '*-mistral-*/**'
+        - 'langchain4j-mistral-ai/**'
+    - id: mcp
+      labels: [MCP]
+      title: "mcp"
+      notify: [jmartisk]
+      notifyInPullRequest: true
+      files:
+        - 'langchain4j-mcp/**'

.github/workflows/comment-pr.yml

@@ -15,6 +15,8 @@ jobs:
     # https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#running-a-workflow-based-on-the-conclusion-of-another-workflow
     if: ${{ github.event.workflow_run.conclusion == 'success' }}
     runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
     env:
       # https://docs.github.com/en/actions/reference/authentication-in-a-workflow#permissions-for-the-github_token
       ACCESS_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/main.yaml

@@ -69,7 +69,8 @@ jobs:
         run: |
           mvn -B -U -T8C test javadoc:aggregate \
             ${{ matrix.mvn_opts }}
-
+      - name: Setup JBang
+        uses: jbangdev/setup-jbang@main
       - name: Integration test with JDK ${{ matrix.java_version }}
         ## The step or job will only run if the `experimental` variable
         ## in the matrix is false (not set to true)

.github/workflows/nightly_jdk17.yaml

@@ -35,6 +35,8 @@ jobs:
           project_id: ${{ secrets.GCP_PROJECT_ID }}
           credentials_json: ${{ secrets.GCP_CREDENTIALS_JSON }}
 
+      - name: Setup JBang
+        uses: jbangdev/setup-jbang@main
       - name: Build with JDK ${{ matrix.java_version }}
         run: |
           ## compile and verify javadocs on ALL modules
@@ -84,7 +86,6 @@ jobs:
           CI_DELAY_SECONDS_AZURE_OPENAI: 1
           CI_DELAY_SECONDS_BEDROCK: 2
           CI_DELAY_SECONDS_GITHUB_MODELS: 7
-          CI_DELAY_SECONDS_GOOGLE_AI_GEMINI: 5
           CI_DELAY_SECONDS_VERTEX_AI_GEMINI: 12
           CI_DELAY_SECONDS_VOYAGE_AI: 22
 

.github/workflows/nightly_jdk21.yaml

@@ -35,6 +35,8 @@ jobs:
           project_id: ${{ secrets.GCP_PROJECT_ID }}
           credentials_json: ${{ secrets.GCP_CREDENTIALS_JSON }}
 
+      - name: Setup JBang
+        uses: jbangdev/setup-jbang@main
       - name: Build with JDK ${{ matrix.java_version }}
         run: |
           ## compile and verify javadocs on ALL modules
@@ -84,7 +86,6 @@ jobs:
           CI_DELAY_SECONDS_AZURE_OPENAI: 1
           CI_DELAY_SECONDS_BEDROCK: 2
           CI_DELAY_SECONDS_GITHUB_MODELS: 7
-          CI_DELAY_SECONDS_GOOGLE_AI_GEMINI: 5
           CI_DELAY_SECONDS_VERTEX_AI_GEMINI: 12
           CI_DELAY_SECONDS_VOYAGE_AI: 22
 

.github/workflows/receive-pr.yml

@@ -43,9 +43,12 @@ jobs:
       # Execute recipes
       - name: Apply OpenRewrite recipes
         run: |
-          mvn --activate-profiles openrewrite \
-            -Dspotless.check.skip=true \
-            org.openrewrite.maven:rewrite-maven-plugin:run
+          mvn --activate-profiles openrewrite -Dspotless.check.skip=true rewrite:run
+
+      # Apply spotless
+      - name: Apply Spotless
+        run: |
+          mvn spotless:apply
 
       # Capture the diff
       - name: Create patch

CONTRIBUTING.md

@@ -2,6 +2,7 @@ Thank you for investing your time and effort in contributing to our project, we
 
 # General guidelines
 
+- For new integrations, please consider adding it in [community repo](https://github.com/langchain4j/langchain4j-community) first.
 - If you want to contribute a bug fix or a new feature that isn't listed in the [issues](https://github.com/langchain4j/langchain4j/issues) yet, please open a new issue for it. We will prioritize is shortly.
 - Follow [Google's Best Practices for Java Libraries](https://jlbp.dev/)
 - Keep the code compatible with Java 17.

README.md

@@ -27,7 +27,7 @@ Here's how:
    Since early 2023, the community has been building numerous LLM-powered applications,
    identifying common abstractions, patterns, and techniques. LangChain4j has refined these into practical code.
    Our toolbox includes tools ranging from low-level prompt templating, chat memory management, and function calling
-   to high-level patterns like AI Services and RAG.
+   to high-level patterns like Agents and RAG.
    For each abstraction, we provide an interface along with multiple ready-to-use implementations based on common techniques.
    Whether you're building a chatbot or developing a RAG with a complete pipeline from data ingestion to retrieval,
    LangChain4j offers a wide variety of options.
@@ -50,6 +50,8 @@ the core functionality is in place, allowing you to start building LLM-powered a
 ## Documentation
 Documentation can be found [here](https://docs.langchain4j.dev).
 
+The documentation chatbot (experimental) can be found [here](https://chat.langchain4j.dev/).
+
 
 ## Getting Started
 Getting started guide can be found [here](https://docs.langchain4j.dev/get-started).

code-execution-engines/langchain4j-code-execution-engine-graalvm-polyglot/pom.xml

@@ -7,7 +7,7 @@
     <parent>
         <groupId>dev.langchain4j</groupId>
         <artifactId>langchain4j-parent</artifactId>
-        <version>1.0.0-alpha1</version>
+        <version>1.0.0-alpha2-SNAPSHOT</version>
         <relativePath>../../langchain4j-parent/pom.xml</relativePath>
     </parent>
 

code-execution-engines/langchain4j-code-execution-engine-judge0/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <groupId>dev.langchain4j</groupId>
         <artifactId>langchain4j-parent</artifactId>
-        <version>1.0.0-alpha1</version>
+        <version>1.0.0-alpha2-SNAPSHOT</version>
         <relativePath>../../langchain4j-parent/pom.xml</relativePath>
     </parent>
 

docs/docs/integrations/document-loaders/classpath.md

@@ -0,0 +1,25 @@
+---
+sidebar_position: 3
+---
+
+# Classpath
+
+## Maven Dependency
+
+```xml
+<dependency>
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>langchain4j</artifactId>
+    <version>1.0.0-alpha1</version>
+</dependency>
+```
+
+
+## APIs
+
+- `ClassPathSource` / `ClassPathDocumentLoader`
+
+## Examples
+
+- [ClassPathSourceTests](https://github.com/langchain4j/langchain4j/blob/main/langchain4j/src/test/java/dev/langchain4j/data/document/source/ClassPathSourceTests.java)
+- [ClassPathDocumentLoaderTest](https://github.com/langchain4j/langchain4j/blob/main/langchain4j/src/test/java/dev/langchain4j/data/document/loader/ClassPathDocumentLoaderTest.java)

docs/docs/integrations/document-loaders/file-system.md

@@ -17,7 +17,7 @@ sidebar_position: 3
 
 ## APIs
 
-- `FileSystemDocumentLoader`
+- `FileSystemSource` / `FileSystemDocumentLoader`
 
 
 ## Examples

docs/docs/integrations/embedding-models/dashscope.md

@@ -4,54 +4,74 @@ sidebar_position: 5
 
 # DashScope
 
-https://dashscope.aliyun.com/
+[DashScope](https://dashscope.aliyun.com/) is a platform developed by [Alibaba Cloud](https://www.alibabacloud.com/).
+It provides an interface for model visualization, monitoring, and debugging, particularly when working with AI/ML
+models in production environments. The platform allows users to visualize performance metrics, track model behavior, and
+identify potential issues early on in the deployment cycle.
 
+[Qwen](https://tongyi.aliyun.com/) models are a series of generative AI models developed
+by [Alibaba Cloud](https://www.alibabacloud.com/). The Qwen family of models are specifically designed for tasks like
+text generation, summarization, question answering, and various NLP tasks.
+
+You can refer
+to [DashScope Document](https://help.aliyun.com/zh/model-studio/getting-started/?spm=a2c4g.11186623.help-menu-2400256.d_0.6655453aLIyxGp)
+for more details. LangChain4j integrates with DashScope by
+Using [DashScope Java SDK](https://help.aliyun.com/zh/dashscope/java-sdk-best-practices?spm=a2c4g.11186623.0.0.272a1507Ne69ja)
 
 ## Maven Dependency
 
 :::note
-Since `1.0.0-alpha1`, `langchain4j-dashscope` has migrated to `langchain4j-community` and is renamed to `langchain4j-community-dashscope`.
+Since `1.0.0-alpha1`, `langchain4j-dashscope` has migrated to `langchain4j-community` and is renamed to
+`langchain4j-community-dashscope`.
 :::
 
-`0.36.2` and previous:
+Before `1.0.0-alpha1`:
 
 ```xml
+
 <dependency>
     <groupId>dev.langchain4j</groupId>
     <artifactId>langchain4j-dashscope</artifactId>
-    <version>1.0.0-alpha1</version>
+    <version>${previous version here}</version>
 </dependency>
 ```
 
 `1.0.0-alpha1` and later:
 
 ```xml
+
 <dependency>
     <groupId>dev.langchain4j</groupId>
     <artifactId>langchain4j-community-dashscope</artifactId>
-    <version>1.0.0-alpha1</version>
+    <version>${latest version here}</version>
 </dependency>
 ```
 
 Or, you can use BOM to manage dependencies consistently:
 
 ```xml
+
 <dependencyManagement>
     <dependency>
         <groupId>dev.langchain4j</groupId>
         <artifactId>langchain4j-community-bom</artifactId>
-        <version>1.0.0-alpha1</version>
+        <version>${latest version here}</version>
         <typ>pom</typ>
         <scope>import</scope>
     </dependency>
 </dependencyManagement>
 ```
 
-## APIs
+## Configurable Parameters
 
-- `QwenEmbeddingModel`
+`QwenEmbeddingModel` has following parameters to configure when you initialize it:
 
+| Property  | Description                                                                  | Default Value                                                                           |
+|-----------|------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------|
+| baseUrl   | The URL to connect to. You can use HTTP or websocket to connect to DashScope | https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding |
+| apiKey    | The API Key                                                                  |                                                                                         |
+| modelName | The model to use.                                                            | text-embedding-v2                                                                       |
 
 ## Examples
 
-- [QwenEmbeddingModelIT](https://github.com/langchain4j/langchain4j/blob/main/langchain4j-dashscope/src/test/java/dev/langchain4j/model/dashscope/QwenEmbeddingModelIT.java)
+- [QwenEmbeddingModelIT](https://github.com/langchain4j/langchain4j-community/blob/main/models/langchain4j-community-dashscope/src/test/java/dev/langchain4j/community/model/dashscope/QwenEmbeddingModelIT.java)

docs/docs/integrations/embedding-models/qianfan.md

@@ -4,21 +4,88 @@ sidebar_position: 16
 
 # Qianfan
 
+[百度智能云千帆大模型](https://console.bce.baidu.com/qianfan/ais/console/applicationConsole/application)
+![image](https://github.com/langchain4j/langchain4j/assets/95265298/600f8006-4484-4a75-829c-c8c16a3130c2)
+
 ## Maven Dependency
 
+You can use DashScope with LangChain4j in plain Java or Spring Boot applications.
+
+### Plain Java
+
+:::note
+Since `1.0.0-alpha1`, `langchain4j-qianfan` has migrated to `langchain4j-community` and is renamed to `langchain4j-community-qianfan`.
+:::
+
+Before `1.0.0-alpha1`:
+
 ```xml
 <dependency>
     <groupId>dev.langchain4j</groupId>
     <artifactId>langchain4j-qianfan</artifactId>
-    <version>1.0.0-alpha1</version>
+    <version>${previous version here}</version>
+</dependency>
+```
+
+`1.0.0-alpha1` and later:
+
+```xml
+<dependency>
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>langchain4j-community-qianfan</artifactId>
+    <version>${latest version here}</version>
 </dependency>
 ```
 
+### Spring Boot
+
+:::note
+Since `1.0.0-alpha1`, `langchain4j-qianfan-spring-boot-starter` has migrated to `langchain4j-community` and is renamed
+to `langchain4j-community-qianfan-spring-boot-starter`.
+:::
+
+Before `1.0.0-alpha1`:
+
+```xml
+
+<dependency>
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>langchain4j-qianfan-spring-boot-starter</artifactId>
+    <version>${previous version here}</version>
+</dependency>
+```
+
+`1.0.0-alpha1` and later:
+
+```xml
+
+<dependency>
+    <groupId>dev.langchain4j</groupId>
+    <artifactId>langchain4j-community-qianfan-spring-boot-starter</artifactId>
+    <version>${latest version here}</version>
+</dependency>
+```
+
+Or, you can use BOM to manage dependencies consistently:
+
+```xml
+
+<dependencyManagement>
+    <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-community-bom</artifactId>
+        <version>${latest version here}</version>
+        <typ>pom</typ>
+        <scope>import</scope>
+    </dependency>
+</dependencyManagement>
+```
+
 ## APIs
 
 - `QianfanEmbeddingModel`
 
 
 ## Examples
 
-- [QianfanEmbeddingModelIT](https://github.com/langchain4j/langchain4j/blob/main/langchain4j-qianfan/src/test/java/dev/langchain4j/model/qianfan/QianfanEmbeddingModelIT.java)
+- [QianfanEmbeddingModelIT](https://github.com/langchain4j/langchain4j-community/blob/main/models/langchain4j-community-qianfan/src/test/java/dev/langchain4j/community/model/qianfan/QianfanEmbeddingModelIT.java)