config.yaml

# Model configuration for ModelManager
# You can add or modify model entries as needed
models:
  jina-reranker-v2:
    model_name: jinaai/jina-reranker-v2-base-multilingual
    model_type: sentence_transformers
    description: |
      The Jina Reranker v2 (jina-reranker-v2-base-multilingual) is a transformer-based model that has been fine-tuned for text reranking task, which is a crucial component in many information retrieval systems. It is a cross-encoder model that takes a query and a document pair as input and outputs a score indicating the relevance of the document to the query. The model is trained on a large dataset of query-document pairs and is capable of reranking documents in multiple languages with high accuracy.
    languages: ["multilingual"]
    repository: https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual
  
  bge-reranker-v2:
    model_name: BAAI/bge-reranker-v2-m3
    model_type: sentence_transformers
    description: |
      Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
    languages: ["multilingual"]
    repository: https://huggingface.co/BAAI/bge-reranker-v2-m3

  qwen3-reranker:
    model_name: Qwen/Qwen3-Reranker-0.6B
    model_type: qwen
    description: |
      The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
    languages: ["multilingual"]
    repository: https://huggingface.co/Qwen/Qwen3-Reranker-0.6B

default_model: bge-reranker-v2