I have a question about Quarkus Langchain4j. I have made this Quarkus (Java 25) project with the purpose of exposing an API that receives a search text, processes it with an "extractor” AI ...

I use Gemini to get information about historical figures : public interface Historian { @UserMessage(""" You are a historian who is collecting information about ...

How does langhchain4j know how to generate the arguments for MCP tool calling? I have implemented an chatAgent with MessageWindowChatMemory.withMaxMessages(50). The tools are added dynamically from an ...

When using rag and memory, multiple identical copies of the same information is sent to the ai, when asking related questions. I have import java.util.ArrayList; import java.util.List; import dev....

I'm using LangChain4j to define prompts using @UserMessage annotations, like this: @UserMessage( "The alert is described as follows: {{description}}\n\n" + "HTTP response evidence:...

I have a liveOrdersTool in langchain4j, my chat looks something like this : get live orders and tell me about them good response ... 1hr later ... get live orders and tell me about them, it ...

I tried to develop a basic assistant and expose it as a tool in Kotlin, following the examples shown in: quarkus agentic ai step by step. However, when I try to use the @Tool annotation in my Kotlin ...

Im using the code below to generate an answer from Anthropic's Sonnet 3-7. When I add a tools/toolProvider to my streamAssistant, the code breaks every time I run a prompt that depends on a tool call. ...

I want to know if there are any other settings required for pgvector or what content needs to be set in the code to enable pgvector to support higher vector dimensions. I found on the official website ...

Tonight I received the following from openAI via email: Web search delivers accurate and clearly-cited answers from the web. Using the same tool as search in ChatGPT, it’s great at conversation and ...

I'll use a synthetic example - the real one is more complex. Consider trying to validate a freeform address. You want to be sure the user provided all the information needed and if not prompt them to ...

I am developing an AI-assisted interface using LangChain4j and injecting OllamaChatModel, but I am encountering an issue where the application fails to start due to a NullPointerException related to @...

In vanilla langchain4j we can provide tools programatically https://docs.langchain4j.dev/tutorials/tools#specifying-tools-programmatically I don't seem to find a way to do the same with quarkus-...

I am trying to use Langchain4J to connect to Open AI models and Anthropic model that are hosted behind my organization's base URL. The OpenAI Model is working fine. However, the Anthropic Model always ...

I am trying to integrate LangChain4j to my spring boot app that, by the way, is using Spring Data mongo. One of the things I realize (obviously) is that I dont want to use an in memory store bur ...