center-for-curriculum-redesign/bge_1-5_query_embeddings
Generate query embeddings from short English text for passage retrieval and semantic search. Accepts an array of query s...
Found 12 models (showing 1-12)
Generate query embeddings from short English text for passage retrieval and semantic search. Accepts an array of query s...
Rerank documents for a text query, returning the top-k most relevant texts with relevance scores. Accepts a text query a...
Re-rank query–candidate text pairs for search and RAG by returning a relevance score per pair. Takes a JSON-encoded list...
Generates context-based answers from textual prompts, optimized for documentation retrieval and question answering. Fine...
Rerank text passages for a query by scoring text pairs and returning relevance scores. Accept a JSON list of (query, doc...
Score relevance between queries and passages for retrieval re-ranking. Accept a JSON string containing one or many [quer...
Generate instruction-tuned text embeddings for documents and queries, with an optional relevance score for query–documen...
Convert text into dense vector embeddings for semantic search and retrieval. Generate sentence and paragraph embeddings...
Rerank query–document pairs for information retrieval and RAG. Accepts text inputs as one or many [query, passage] pairs...
Embed text into 1024-dimensional vectors for semantic search, dense retrieval, and RAG pipelines. Takes a text prompt an...
Convert text into vector embeddings for semantic search, retrieval-augmented generation, clustering, and classification....
Convert English text into embeddings for semantic search and long‑document retrieval. Accepts English text and returns d...