LangChain开源大型语言模型（LLM）框架

# LangChain for Java: Supercharge your Java application with the power of LLMs ## Project goals The goal of this project is to simplify the integration of AI/LLM capabilities into your Java application. This can be achieved thanks to: - **A simple and coherent layer of abstractions**, designed to ensure that your code does not depend on concrete implementations such as LLM providers, embedding store providers, etc. This allows for easy swapping of components. - **Numerous implementations of the above-mentioned abstractions**, providing you with a variety of LLMs and embedding stores to choose from. - **Range of in-demand features on top of LLMs, such as:** - The capability to **ingest your own data** (documentation, codebase, etc.), allowing the LLM to act and respond based on your data. - **Autonomous agents** for delegating tasks (defined on the fly) to the LLM, which will strive to complete them. - **Prompt templates** to help you achieve the highest possible quality of LLM responses. - **Memory** to provide context to the LLM for your current and past conversations. - **Structured outputs** for receiving responses from the LLM with a desired structure as Java POJOs. - **"AI Services"** for declaratively defining complex AI behavior behind a simple API. - **Chains** to reduce the need for extensive boilerplate code in common use-cases. - **Auto-moderation** to ensure that all inputs and outputs to/from the LLM are not harmful. ## Code examples Please see examples of how LangChain4j can be used in `langchain4j-examples` repo: - [Examples in plain Java](https://github.com/langchain4j/langchain4j-examples/tree/main/other-examples/src/main/java) - [Example with Spring Boot](https://github.com/langchain4j/langchain4j-examples/blob/main/spring-boot-example/src/test/java/dev/example/CustomerSupportApplicationTest.java) ## News 29 September: - Updates to models API: return `Response<T>` instead of `T`. `Response<T>` contains token usage and finish reason. - All model and embedding store integrations now live in their own modules - Integration with [Vespa](https://vespa.ai/) by [@Heezer](https://github.com/Heezer) - Integration with [Elasticsearch](https://www.elastic.co/) by [@Martin7-1](https://github.com/Martin7-1) - Integration with [Redis](https://redis.io/) by [@Martin7-1](https://github.com/Martin7-1) - Integration with [Milvus](https://milvus.io/) by [@IuriiKoval](https://github.com/IuriiKoval) - Integration with [Astra DB](https://www.datastax.com/products/datastax-astra) and [Cassandra](https://cassandra.apache.org/) by [@clun](https://github.com/clun) - Added support for overlap in document splitters - Some bugfixes and smaller improvements 29 August: - Offline [text classification with embeddings](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/embedding/classification/EmbeddingModelTextClassifierExample.java) - Integration with [Google Vertex AI](https://cloud.google.com/vertex-ai) by [@kuraleta](https://github.com/kuraleta) - Reworked [document splitters](https://github.com/langchain4j/langchain4j/blob/main/langchain4j/src/main/java/dev/langchain4j/data/document/splitter/DocumentSplitters.java) - In-memory embedding store can now be easily persisted - [And more](https://github.com/langchain4j/langchain4j/releases/tag/0.22.0) 19 August: - Integration with [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) by [@kuraleta](https://github.com/kuraleta) - Integration with Qwen models (DashScope) by [@jiangsier-xyz](https://github.com/jiangsier-xyz) - [Integration with Chroma](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/embedding/store/ChromaEmbeddingStoreExample.java) by [@kuraleta](https://github.com/kuraleta) - [Support for persistent ChatMemory](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithPersistentMemoryForEachUserExample.java) 10 August: - [Integration with Weaviate](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/embedding/store/WeaviateEmbeddingStoreExample.java) by [@Heezer](https://github.com/Heezer) - [Support for DOC, XLS and PPT document types](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/DocumentLoaderExamples.java) by [@oognuyh](https://github.com/oognuyh) - [Separate chat memory for each user](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithMemoryForEachUserExample.java) - [Custom in-process embedding models](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/embedding/model/InProcessEmbeddingModelExamples.java) - Added lots of Javadoc - [And more](https://github.com/langchain4j/langchain4j/releases/tag/0.19.0) 26 July: - We've added integration with [LocalAI](https://localai.io/). Now, you can use LLMs hosted locally! - Added support for [response streaming in AI Services](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithStreamingExample.java). 21 July: - Now, you can do [text embedding inside your JVM](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/embedding/model/InProcessEmbeddingModelExamples.java). 17 July: - You can now try out OpenAI's `gpt-3.5-turbo` and `text-embedding-ada-002` models with LangChain4j for free, without needing an OpenAI account and keys! Simply use the API key "demo". 15 July: - Added EmbeddingStoreIngestor - Redesigned document loaders (see FileSystemDocumentLoader) - Simplified ConversationalRetrievalChain - Renamed DocumentSegment into TextSegment - Added output parsers for numeric types - Added @UserName for AI Services - Fixed [23](https://github.com/langchain4j/langchain4j/issues/23) and [24](https://github.com/langchain4j/langchain4j/issues/24) 11 July: - Added ["Dynamic Tools"](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithDynamicToolsExample.java): Now, the LLM can generate code for tasks that require precise calculations, such as math and string manipulation. This will be dynamically executed in a style akin to GPT-4's code interpreter! We use [Judge0, hosted by Rapid API](https://rapidapi.com/judge0-official/api/judge0-ce/pricing), for code execution. You can subscribe and receive 50 free executions per day. 5 July: - Now you can [add your custom knowledge base to "AI Services"](https://github.com/langchain4j/langchain4j-examples/blob/main/spring-boot-example/src/test/java/dev/example/CustomerSupportApplicationTest.java). Relevant information will be automatically retrieved and injected into the prompt. This way, the LLM will have a context of your data and will answer based on it! - The current date and time can now be automatically injected into the prompt using special `{{current_date}}`, `{{current_time}}` and `{{current_date_time}}` placeholders. 3 July: - Added support for Spring Boot 3 2 July: - [Added Spring Boot Starter](https://github.com/langchain4j/langchain4j-examples/blob/main/spring-boot-example/src/test/java/dev/example/CustomerSupportApplicationTest.java) - Added support for HuggingFace models 1 July: - [Added "Tools"](https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithToolsExample.java) (support for OpenAI functions) ## Highlights You can declaratively define concise "AI Services" that are powered by LLMs: ```java interface Assistant { String chat(String userMessage); } Assistant assistant = AiServices.create(Assistant.class, model); String answer = assistant.chat("Hello"); System.out.println(answer); // Hello! How can I assist you today? ``` You can use LLM as a classifier: ```java enum Sentiment { POSITIVE, NEUTRAL, NEGATIVE } in