# Embeddings > langchain_nvidia_ai_endpoints → Embeddings ## Classes - [`Model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model) - [`inference_priority`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/decorators/inference_priority) - [`Ranking`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/Ranking) - [`NVIDIARerank`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank) - [`NVIDIARAGError`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGError) - [`NVIDIARAGConnectionError`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGConnectionError) - [`NVIDIARAGServerError`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGServerError) - [`NVIDIARAGValidationError`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGValidationError) - [`NVIDIARAGRetriever`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever) - [`ChatNVIDIADynamo`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo) - [`NVIDIAEmbeddings`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings) - [`NVIDIA`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm/NVIDIA) - [`UsageCallbackHandler`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler) - [`ChatNVIDIA`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA) ## Functions - [`register_model()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/register_model) - [`lookup_model()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/lookup_model) - [`determine_model()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/determine_model) - [`get_inference_priority()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/decorators/get_inference_priority) - [`convert_message_to_dict()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_utils/convert_message_to_dict) - [`standardize_model_name()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/standardize_model_name) - [`get_token_cost_for_model()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/get_token_cost_for_model) - [`get_usage_callback()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/get_usage_callback) - [`parse_thinking_content()`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/parse_thinking_content) ## Modules - [`langchain_nvidia_ai_endpoints`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/langchain_nvidia_ai_endpoints) - [`decorators`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/decorators) - [`reranking`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking) - [`retrievers`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers) - [`chat_models_dynamo`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo) - [`embeddings`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings) - [`llm`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm) - [`callbacks`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks) - [`chat_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models) - [`data`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/data) ## Constants - [`logger`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/logger) - [`default_hosted_model_name`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/default_hosted_model_name) - [`mdl_name`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/mdl_name) - [`model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/model) - [`is_hosted`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/is_hosted) - [`cls`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/cls) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/base_url) - [`infer_path`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/infer_path) - [`listing_path`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/listing_path) - [`polling_url_tmpl`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/polling_url_tmpl) - [`get_session_fn`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/get_session_fn) - [`verify_ssl`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/verify_ssl) - [`api_key`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/api_key) - [`timeout`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/timeout) - [`interval`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/interval) - [`last_inputs`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/last_inputs) - [`last_response`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/last_response) - [`headers_tmpl`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/headers_tmpl) - [`lc_secrets`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/lc_secrets) - [`lc_attributes`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/lc_attributes) - [`infer_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/infer_url) - [`available_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIABaseClient/available_models) - [`get_async_session_fn`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_common/_NVIDIAAsyncClient/get_async_session_fn) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/model_config) - [`id`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/id) - [`model_type`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/model_type) - [`client`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/client) - [`endpoint`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/endpoint) - [`aliases`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/aliases) - [`supports_tools`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/supports_tools) - [`supports_structured_output`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/supports_structured_output) - [`supports_thinking`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/supports_thinking) - [`thinking_prefix`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/thinking_prefix) - [`no_thinking_prefix`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/no_thinking_prefix) - [`thinking_param_enable`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/thinking_param_enable) - [`thinking_param_disable`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/thinking_param_disable) - [`base_model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/base_model) - [`deprecated`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/Model/deprecated) - [`CHAT_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/CHAT_MODEL_TABLE) - [`QA_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/QA_MODEL_TABLE) - [`VLM_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/VLM_MODEL_TABLE) - [`EMBEDDING_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/EMBEDDING_MODEL_TABLE) - [`RANKING_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/RANKING_MODEL_TABLE) - [`RANKING_VLM_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/RANKING_VLM_MODEL_TABLE) - [`COMPLETION_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/COMPLETION_MODEL_TABLE) - [`OPENAI_MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/OPENAI_MODEL_TABLE) - [`MODEL_TABLE`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_statics/MODEL_TABLE) - [`F`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/decorators/F) - [`index`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/Ranking/index) - [`logit`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/Ranking/logit) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/base_url) - [`top_n`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/top_n) - [`model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/model) - [`truncate`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/truncate) - [`max_batch_size`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/max_batch_size) - [`default_headers`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/default_headers) - [`extra_headers`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/extra_headers) - [`available_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/reranking/NVIDIARerank/available_models) - [`status_code`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGServerError/status_code) - [`body`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGServerError/body) - [`body`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGValidationError/body) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/base_url) - [`k`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/k) - [`collection_names`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/collection_names) - [`vdb_top_k`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/vdb_top_k) - [`vdb_endpoint`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/vdb_endpoint) - [`enable_reranker`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/enable_reranker) - [`enable_query_rewriting`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/enable_query_rewriting) - [`enable_filter_generator`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/enable_filter_generator) - [`enable_citations`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/enable_citations) - [`filter_expr`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/filter_expr) - [`confidence_threshold`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/confidence_threshold) - [`embedding_model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/embedding_model) - [`embedding_endpoint`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/embedding_endpoint) - [`reranker_model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/reranker_model) - [`reranker_endpoint`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/reranker_endpoint) - [`messages`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/messages) - [`timeout`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/retrievers/NVIDIARAGRetriever/timeout) - [`osl`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo/osl) - [`iat`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo/iat) - [`latency_sensitivity`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo/latency_sensitivity) - [`priority`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo/priority) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/base_url) - [`model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/model) - [`truncate`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/truncate) - [`dimensions`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/dimensions) - [`max_batch_size`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/max_batch_size) - [`default_headers`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/default_headers) - [`available_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/embeddings/NVIDIAEmbeddings/available_models) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm/NVIDIA/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm/NVIDIA/base_url) - [`model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm/NVIDIA/model) - [`available_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/llm/NVIDIA/available_models) - [`logger`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/_utils/logger) - [`logger`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/logger) - [`DEFAULT_MODEL_COST_PER_1K_TOKENS`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/DEFAULT_MODEL_COST_PER_1K_TOKENS) - [`llm_output`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/llm_output) - [`price_map`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/price_map) - [`total_tokens`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/total_tokens) - [`prompt_tokens`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/prompt_tokens) - [`completion_tokens`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/completion_tokens) - [`successful_requests`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/successful_requests) - [`total_cost`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/total_cost) - [`model_usage`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/model_usage) - [`always_verbose`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/UsageCallbackHandler/always_verbose) - [`usage_callback_var`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/callbacks/usage_callback_var) - [`T_Parser`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/T_Parser) - [`logger`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/logger) - [`model_config`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/model_config) - [`base_url`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/base_url) - [`model`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/model) - [`temperature`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/temperature) - [`max_tokens`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/max_tokens) - [`top_p`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/top_p) - [`seed`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/seed) - [`stop`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/stop) - [`stream_options`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/stream_options) - [`default_headers`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/default_headers) - [`model_kwargs`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/model_kwargs) - [`profile`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/profile) - [`available_models`](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models/ChatNVIDIA/available_models)