-
I first want to say that I love JLama! It makes it very accessible to use AI. First time I toyed around with it because of JLama. Many people and companies (including me) do not like using external pa…
-
Consider how Quarkus Authentication and LLM API Keys will work together.
I'm assuming, if I start a demo with an API key, in prod, it will be more like a company's API key.
Depending on the nature…
-
[This](https://www.rungalileo.io/blog/mastering-rag-how-to-architect-an-enterprise-rag-system) article makes a very good case for adding observability to RAG.
We should probably head the advice an…
-
Description:
When attempting to serialize the Embedding and TextSegment classes for Redis caching, serialization continuously fails due to the absence of getter and setter methods. I have tried usi…
-
**Is your feature request related to a problem? Please describe.**
Currently, ChromaDBEmbeddedStore doesn't support authentication.
**Describe the solution you'd like**
Add support for basic …
-
The starter dependency provided by this project is quite convenient for setting up a local development workflow based on Testcontainers, thank you for that!
I'd like to share some suggestions to a…
-
Could you please add support for GitHub Copilot to generate commit messages.
[langchain4j](https://github.com/langchain4j/langchain4j) should since the latest version support the GitHub model.
T…
-
**Describe the bug**
If a search results in an empty pagemap (an expected result from `com.google.api.services.customsearch.v1.model.Result`) then https://github.com/langchain4j/langchain4j/blob/…
-
The current RAG model for pgvector is to store the documents in their own table.
In my application my source documents already have a table:
```java
@Entity
public class Talk extends PanacheEn…
-
The new Advanced RAG provides the `ReRankingContentAggregator` which can re-rank results based on a `ScoringModel` (e.g. the `CohereScoringModel`).
this works great, the re-ranked list of results i…