
center-for-curriculum-redesign/bge_1-5_query_embeddings
Generate text query embeddings for dense retrieval and semantic search. Accepts an array of short query strings and retu...
Found 10 models (showing 1-10)
Generate text query embeddings for dense retrieval and semantic search. Accepts an array of short query strings and retu...
Rerank a list of candidate documents for a text query. Accepts a text query and a list of documents, and returns the top...
Score relevance between text pairs for reranking search results and retrieval-augmented generation. Takes a JSON list of...
Generates context-based answers from textual prompts, optimized for documentation retrieval and question answering. Fine...
Re-rank documents and passages for retrieval using queryβdocument pairs, returning relevance scores for each pair. Accep...
Score the relevance between query and passage text pairs for retrieval reranking. Accept a JSON string of one or more [q...
Convert text into embeddings for semantic search and retrieval. Accepts a document string and optionally a query and a o...
Convert text to vector embeddings for semantic search, retrieval, clustering, and RAG. Accepts an array of texts and ret...
Rerank passages for a text query. Takes a query and one or more candidate documents (text) and outputs a relevance score...
Convert text into 1024-dimensional embeddings for semantic search and retrieval. Takes a text prompt and returns a dense...