0.13.0

• 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 24

0.12.0

Hotfix for #23

0.11.0

Added "Dynamic Tools": 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, for code execution. You can subscribe and receive 50 free executions per day.

0.10.0

• Now you can add your custom knowledge base to "AI Services". Relevant information will be automatically retrieved and incorporated into the prompt. This way, the LLM will have a context of the 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.

0.9.0

Added support for Spring Boot 3

0.8.0

• 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 (chat+language) models

0.7.0

Added support for tools (OpenAI functions): https://github.com/langchain4j/langchain4j-examples/blob/main/other-examples/src/main/java/ServiceWithToolsExample.java

0.6.0

• You can now define ChatMemory in AiServices and it will keep history of your interactions
• Added OpenAI moderation model, so you can moderate texts, documents and messages
• Added auto moderation for AiServices. Just put @moderate on top of your method and it will automatically verify that user input does not violates content policy

0.5.0

HuggingFace embedding models are now supported via HF Inference API

0.4.0

• renamed from ai4j to langchain4j
• big design changes
• added "AI Services" (declarative AI facades)
• added more document loaders and splitters
• added in-memory embedding store