-
I created an application using `quarkus create app --extension=langchain4j-openai` then I ran `quarkus dev` and browsed to http://localhost:8080/q/dev-ui/io.quarkiverse.langchain4j.quarkus-langchain4j…
-
See https://twitter.com/marcushellberg/status/1775931542881415575?t=ECxBGihAVO03jpzHXCH8BA&s=19
-
If I supply a user message with tokens as an input parameter the tokens are not processed.
```java
@SystemMessage("You are a marvel comics writer, expert in all sorts of super heroes and super vil…
-
Im trying to replace HuggingFaceEmbeddingModel to OnnxEmbeddingModel cause i have ONNX model and there is no reason to cal HF and wait time to model load.
The model loaded from [https://huggingface.c…
-
**Describe the bug**
pass a list of segments with 6 segment to method embedAll, return a list with only on embedding.
when call embeddingStore.addAll(embeddings, segments), exception occur: em…
-
### Description
Due to the high adoption of generative models, an higher level API could be very useful to integrate Quarkus applications to OpenAI services.
The idea is to configure, at least, …
-
**Describe the issue**
I am working with an application compiled against Java 8 and cannot do any upgrades on it. I need to integrate Opensearch serverless with this application but the latest versio…
-
-
Is there an API to load an LLM model from a local GGUF file?
Can we provide the local path of the GGUF file?
-
I found that langchain4j mainly supports client side and has no server side support.
Consider a scenario where multiple personal devices act as server and client.
1. Write a java program to use …