embeddings
#
Embedding models are wrappers around embedding models from different APIs and services.
Embedding models can be LLMs or not.
Class hierarchy:
Embeddings --> <name>Embeddings # Examples: OpenAIEmbeddings, HuggingFaceEmbeddings
Classes
|
Aleph Alpha's asymmetric semantic embedding. |
Symmetric version of the Aleph Alpha's semantic embeddings. |
|
Anyscale Embeddings API. |
|
Ascend NPU accelerate Embedding model |
|
Embedding documents and queries with Awa DB. |
|
Baichuan Text Embedding models. |
|
Baidu Qianfan Embeddings embedding models. |
|
Bookend AI sentence_transformers embedding models. |
|
Clarifai embedding models. |
|
|
Cloudflare Workers AI embedding model. |
DashScope embedding models. |
|
Deep Infra's embedding inference service. |
|
EdenAI embedding. |
|
Embaas's embedding service. |
|
Payload for the Embaas embeddings API. |
|
Fake embedding model that always returns the same embedding vector for the same text. |
|
Fake embedding model. |
|
Qdrant FastEmbedding models. |
|
Google's PaLM Embeddings APIs. |
|
GPT4All embedding models. |
|
Gradient.ai Embedding models. |
|
|
Deprecated, TinyAsyncGradientEmbeddingClient was removed. |
Embed texts using the HuggingFace API. |
|
Wrapper around sentence_transformers embedding models. |
|
Tencent Hunyuan embedding models API by Tencent. |
|
Self-hosted embedding models for infinity package. |
|
|
Helper tool to embed Infinity. |
Optimized Infinity embedding models. |
|
Wrapper around the BGE embedding model with IPEX-LLM optimizations on Intel CPUs and GPUs. |
|
Leverage Itrex runtime to unlock the performance of compressed NLP models. |
|
Javelin AI Gateway embeddings. |
|
Jina embedding models. |
|
JohnSnowLabs embedding models |
|
LASER Language-Agnostic SEntence Representations. |
|
llama.cpp embedding models. |
|
Llamafile lets you distribute and run large language models with a single file. |
|
LLMRails embedding models. |
|
LocalAI embedding models. |
|
MiniMax embedding model integration. |
|
Cohere embedding LLMs in MLflow. |
|
Embedding LLMs in MLflow. |
|
MLflow AI Gateway embeddings. |
|
Model2Vec embedding models. |
|
ModelScopeHub embedding models. |
|
MosaicML embedding service. |
|
NCP ClovaStudio Embedding API. |
|
NLP Cloud embedding models. |
|
OCI authentication types as enumerator. |
|
OCI embedding models. |
|
OctoAI Compute Service embedding models. |
|
OpenVNO BGE embedding models. |
|
OpenVINO embedding models. |
|
Quantized bi-encoders embedding models. |
|
Get Embeddings |
|
OVHcloud AI Endpoints Embeddings. |
|
Prem's Embedding APIs |
|
Content handler for LLM class. |
|
Custom Sagemaker Inference Endpoints. |
|
SambaNova embedding models. |
|
Custom embedding models on self-hosted remote hardware. |
|
|
HuggingFace embedding models on self-hosted remote hardware. |
|
HuggingFace InstructEmbedding models on self-hosted remote hardware. |
Embeddings by spaCy models. |
|
Exception raised for errors in the header assembly. |
|
SparkLLM embedding model integration. |
|
|
URL class for parsing the URL. |
TensorflowHub embedding models. |
|
text2vec embedding models. |
|
|
A client to handle synchronous and asynchronous requests to the TextEmbed API. |
A class to handle embedding requests to the TextEmbed API. |
|
|
Device to use for inference, cuda or cpu. |
Exception raised when no consumer group is provided on initialization of TitanTakeoffEmbed or in embed request. |
|
Configuration for the reader to be deployed in Takeoff. |
|
Custom exception for interfacing with Takeoff Embedding class. |
|
Interface with Takeoff Inference API for embedding models. |
|
Volcengine Embeddings embedding models. |
|
Xinference embedding models. |
|
YandexGPT Embeddings models. |
|
ZhipuAI embedding model integration. |
Functions
Use tenacity to retry the embedding call. |
|
Use tenacity to retry the completion call. |
|
|
Get the bytes string of a file. |
Check if a URL is a local file. |
|
Use tenacity to retry the embedding call. |
|
Use tenacity to retry the embedding call. |
|
Use tenacity to retry the completion call. |
|
|
Check if an endpoint is live by sending a GET request to the specified URL. |
Use tenacity to retry the embedding call. |
|
Use tenacity to retry the embedding call. |
|
Create a retry decorator for PremAIEmbeddings. |
|
|
Using tenacity for retry in embedding calls |
|
Load the embedding model. |
Use tenacity to retry the completion call. |
|
Use tenacity to retry the embedding call. |
Deprecated classes