Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEATURE] Configure Embedding Model #523

Open
rafgitdz opened this issue Feb 20, 2025 · 1 comment
Open

[FEATURE] Configure Embedding Model #523

rafgitdz opened this issue Feb 20, 2025 · 1 comment

Comments

@rafgitdz
Copy link

Description

Currently, the embedding model used by Devoxx Genie is fixed and cannot be configured dynamically. This feature aims to provide flexible configuration options for the embedding model, allowing users to select and adjust the model based on their specific needs.

Proposed Solution

  • Add a configuration parameter to specify the embedding model to be used.
  • Support multiple configuration options:
    • Via environment variables (DEVOXX_GENIE_EMBEDDING_MODEL)
    • Via the UI (if applicable)
  • Implement dynamic model loading at application startup.
  • Add error handling to prevent failures if the specified model is unavailable.

Benefits

  • Greater flexibility for users.
  • Ability to experiment with different embedding models without modifying the code.
  • Improved adaptability to specific application needs.
@stephanj
Copy link
Collaborator

I assume you're referring to the RAG embedding using nomic-embed-text ?

com.devoxx.genie.service.chromadb.ChromaEmbeddingService.java

private void initEmbeddingModel() {
        this.embeddingModel = OllamaEmbeddingModel.builder()
                .baseUrl(stateService.getOllamaModelUrl())
                .modelName("nomic-embed-text")
                .build();
    }

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants