from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

model = pc.inference.get_model(model_name="llama-text-embed-v2")

print(model)

{'default_dimension': 1024,
 'max_batch_size': 96,
 'max_sequence_length': 2048,
 'modality': 'text',
 'model': 'llama-text-embed-v2',
 'provider_name': 'NVIDIA',
 'short_description': 'A high performance dense embedding model optimized for '
                      'multilingual and cross-lingual text question-answering '
                      'retrieval with support for long documents (up to 2048 '
                      'tokens) and dynamic embedding size (Matryoshka '
                      'Embeddings).',
 'supported_dimensions': [384, 512, 768, 1024, 2048],
 'supported_metrics': [cosine, dotproduct],
 'supported_parameters': [{'allowed_values': ['query', 'passage'],
                           'parameter': 'input_type',
                           'required': True,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': ['END', 'NONE', 'START'],
                           'default': 'END',
                           'parameter': 'truncate',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': [384, 512, 768, 1024, 2048],
                           'default': 1024,
                           'parameter': 'dimension',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'integer'}],
 'type': 'embed',
 'vector_type': 'dense'}