Embeddings

Users have a few options to choose from when it comes to embeddings.

  • OpenAIEmbedding: the default embedding class. Defaults to β€œtext-embedding-ada-002”

  • LangchainEmbedding: a wrapper around Langchain’s embedding models.

OpenAI embeddings file.

llama_index.embeddings.openai.OAEMM

alias of OpenAIEmbeddingModeModel

llama_index.embeddings.openai.OAEMT

alias of OpenAIEmbeddingModelType

class llama_index.embeddings.openai.OpenAIEmbedding(mode: str = OpenAIEmbeddingMode.TEXT_SEARCH_MODE, model: str = OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002, deployment_name: Optional[str] = None, **kwargs: Any)

OpenAI class for embeddings.

Parameters

  • mode (str) –

    Mode for embedding. Defaults to OpenAIEmbeddingMode.TEXT_SEARCH_MODE. Options are:

    • OpenAIEmbeddingMode.SIMILARITY_MODE

    • OpenAIEmbeddingMode.TEXT_SEARCH_MODE

  • model (str) –

    Model for embedding. Defaults to OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002. Options are:

    • OpenAIEmbeddingModelType.DAVINCI

    • OpenAIEmbeddingModelType.CURIE

    • OpenAIEmbeddingModelType.BABBAGE

    • OpenAIEmbeddingModelType.ADA

    • OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002

  • deployment_name (Optional[str]) – Optional deployment of model. Defaults to None. If this value is not None, mode and model will be ignored. Only available for using AzureOpenAI.

async aget_queued_text_embeddings(text_queue: List[Tuple[str, str]]) → Tuple[List[str], List[List[float]]]

Asynchronously get a list of text embeddings.

Call async embedding API to get embeddings for all queued texts in parallel. Argument text_queue must be passed in to avoid updating it async.

get_agg_embedding_from_queries(queries: List[str], agg_fn: Optional[Callable[[...], List[float]]] = None) → List[float]

Get aggregated embedding from multiple queries.

get_query_embedding(query: str) → List[float]

Get query embedding.

get_queued_text_embeddings() → Tuple[List[str], List[List[float]]]

Get queued text embeddings.

Call embedding API to get embeddings for all queued texts.

get_text_embedding(text: str) → List[float]

Get text embedding.

property last_token_usage: int

Get the last token usage.

queue_text_for_embedding(text_id: str, text: str) → None

Queue text for embedding.

Used for batching texts during embedding calls.

similarity(embedding1: List, embedding2: List, mode: SimilarityMode = SimilarityMode.DEFAULT) → float

Get embedding similarity.

property total_tokens_used: int

Get the total tokens used so far.

class llama_index.embeddings.openai.OpenAIEmbeddingModeModel(value)

OpenAI embedding mode model.

class llama_index.embeddings.openai.OpenAIEmbeddingModelType(value)

OpenAI embedding model type.

async llama_index.embeddings.openai.aget_embedding(text: str, engine: Optional[str] = None) → List[float]

Asynchronously get embedding.

NOTE: Copied from OpenAI’s embedding utils: https://github.com/openai/openai-python/blob/main/openai/embeddings_utils.py

Copied here to avoid importing unnecessary dependencies like matplotlib, plotly, scipy, sklearn.

async llama_index.embeddings.openai.aget_embeddings(list_of_text: List[str], engine: Optional[str] = None) → List[List[float]]

Asynchronously get embeddings.

NOTE: Copied from OpenAI’s embedding utils: https://github.com/openai/openai-python/blob/main/openai/embeddings_utils.py

Copied here to avoid importing unnecessary dependencies like matplotlib, plotly, scipy, sklearn.

llama_index.embeddings.openai.get_embedding(text: str, engine: Optional[str] = None) → List[float]

Get embedding.

NOTE: Copied from OpenAI’s embedding utils: https://github.com/openai/openai-python/blob/main/openai/embeddings_utils.py

Copied here to avoid importing unnecessary dependencies like matplotlib, plotly, scipy, sklearn.

llama_index.embeddings.openai.get_embeddings(list_of_text: List[str], engine: Optional[str] = None) → List[List[float]]

Get embeddings.

NOTE: Copied from OpenAI’s embedding utils: https://github.com/openai/openai-python/blob/main/openai/embeddings_utils.py

Copied here to avoid importing unnecessary dependencies like matplotlib, plotly, scipy, sklearn.

We also introduce a LangchainEmbedding class, which is a wrapper around Langchain’s embedding models. A full list of embeddings can be found here.

Langchain Embedding Wrapper Module.

class llama_index.embeddings.langchain.LangchainEmbedding(langchain_embedding: Embeddings, **kwargs: Any)

External embeddings (taken from Langchain).

Parameters

langchain_embedding (langchain.embeddings.Embeddings) – Langchain embeddings class.

async aget_queued_text_embeddings(text_queue: List[Tuple[str, str]]) → Tuple[List[str], List[List[float]]]

Asynchronously get a list of text embeddings.

Call async embedding API to get embeddings for all queued texts in parallel. Argument text_queue must be passed in to avoid updating it async.

get_agg_embedding_from_queries(queries: List[str], agg_fn: Optional[Callable[[...], List[float]]] = None) → List[float]

Get aggregated embedding from multiple queries.

get_query_embedding(query: str) → List[float]

Get query embedding.

get_queued_text_embeddings() → Tuple[List[str], List[List[float]]]

Get queued text embeddings.

Call embedding API to get embeddings for all queued texts.

get_text_embedding(text: str) → List[float]

Get text embedding.

property last_token_usage: int

Get the last token usage.

queue_text_for_embedding(text_id: str, text: str) → None

Queue text for embedding.

Used for batching texts during embedding calls.

similarity(embedding1: List, embedding2: List, mode: SimilarityMode = SimilarityMode.DEFAULT) → float

Get embedding similarity.

property total_tokens_used: int

Get the total tokens used so far.