gemini-docs-dbfiles / docstore /014d1118-fffc-4f45-bacf-d5ff55838bf4
arshjaved's picture
Upload all project files and folders
2e9b585 verified
state-of-the-art performance. Text embeddings are used to measure the relatedness of strings and are widely used in many AI applications. text-embedding-004 achieves a stronger retrieval performance and outperforms existing models with comparable dimensions, on the standard MTEB embedding benchmarks. Model details Property Description id_card Model code Gemini API models/text-embedding-004 save Supported data types Input Text Output Text embeddings token_auto Token limits [*] Input token limit 2,048 Output dimension size 768 swap_driving_apps_wheel Rate limits [**] 1,500 requests per minute encrypted Adjustable safety settings Not supported calendar_month Latest update April 2024 Embedding Note: Text Embedding is the newer version of the Embedding model. If you're creating a new project, use Text Embedding. You can use the Embedding model to generate text embeddings for input text. The Embedding model is optimized for creating embeddings with 768 dimensions for text of up to 2,048 tokens. Embedding model details Property Description id_card Model code models/embedding-001 save Supported data types Input Text Output Text embeddings token_auto Token limits [*] Input token limit 2,048 Output dimension size 768 swap_driving_apps_wheel Rate limits [**] 1,500 requests per minute encrypted Adjustable safety settings Not supported calendar_month Latest update December 2023 AQA You can use the AQA model to perform Attributed Question-Answering (AQA)–related tasks over a document, corpus, or a set of passages. The AQA model returns answers to questions that are grounded in provided sources, along with estimating answerable probability. Model details Property Description id_card Model code models/aqa save Supported data types Input Text Output Text language Supported language English token_auto Token limits [*] Input token limit 7,168 Output token limit 1,024 swap_driving_apps_wheel Rate limits [**] 1,500 requests per minute encrypted Adjustable safety settings Supported