langchain_openai.embeddings.base.OpenAIEmbeddings

class langchain_openai.embeddings.base.OpenAIEmbeddings

Bases: BaseModel, Embeddings

OpenAI embedding models.

To use, you should have the environment variable OPENAI_API_KEY set with your API key or pass it as a named parameter to the constructor.

In order to use the library with Microsoft Azure endpoints, use AzureOpenAIEmbeddings.

Example

from langchain_openai import OpenAIEmbeddings

model = OpenAIEmbeddings(model="text-embedding-3-large")

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param allowed_special: Optional[Union[Literal['all'], Set[str]]] = None

param check_embedding_ctx_length: bool = True

Whether to check the token length of inputs and automatically split inputs longer than embedding_ctx_length.

param chunk_size: int = 1000

Maximum number of texts to embed in each batch

param default_headers: Optional[Mapping[str, str]] = None

param default_query: Optional[Mapping[str, object]] = None

param deployment: Optional[str] = 'text-embedding-ada-002'

param dimensions: Optional[int] = None

The number of dimensions the resulting output embeddings should have.

Only supported in text-embedding-3 and later models.

param disallowed_special: Optional[Union[Literal['all'], Set[str], Sequence[str]]] = None

param embedding_ctx_length: int = 8191

The maximum number of tokens to embed at once.

param headers: Any = None

param http_async_client: Optional[Any] = None

Optional httpx.AsyncClient. Only used for async invocations. Must specify http_client as well if you’d like a custom client for sync invocations.

param http_client: Optional[Any] = None

Optional httpx.Client. Only used for sync invocations. Must specify http_async_client as well if you’d like a custom client for async invocations.

param max_retries: int = 2

Maximum number of retries to make when generating.

param model: str = 'text-embedding-ada-002'

param model_kwargs: Dict[str, Any] [Optional]

Holds any model parameters valid for create call not explicitly specified.

param openai_api_base: Optional[str] = None (alias 'base_url')

Base URL path for API requests, leave blank if not using a proxy or service emulator.

param openai_api_key: Optional[SecretStr] = None (alias 'api_key')

Automatically inferred from env var OPENAI_API_KEY if not provided.

Constraints

• type = string

• writeOnly = True

• format = password

param openai_api_type: Optional[str] = None

param openai_api_version: Optional[str] = None (alias 'api_version')

Automatically inferred from env var OPENAI_API_VERSION if not provided.

param openai_organization: Optional[str] = None (alias 'organization')

Automatically inferred from env var OPENAI_ORG_ID if not provided.

param openai_proxy: Optional[str] = None

param request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None (alias 'timeout')

Timeout for requests to OpenAI completion API. Can be float, httpx.Timeout or None.

param retry_max_seconds: int = 20

Max number of seconds to wait between retries

param retry_min_seconds: int = 4

Min number of seconds to wait between retries

param show_progress_bar: bool = False

Whether to show a progress bar when embedding.

param skip_empty: bool = False

Whether to skip empty strings when embedding or raise an error. Defaults to not skipping.

param tiktoken_enabled: bool = True

Set this to False for non-OpenAI implementations of the embeddings API, e.g. the –extensions openai extension for text-generation-webui

param tiktoken_model_name: Optional[str] = None

The model name to pass to tiktoken when using this class. Tiktoken is used to count the number of tokens in documents to constrain them to be under a certain limit. By default, when set to None, this will be the same as the embedding model name. However, there are some cases where you may want to use this Embedding class with a model name not supported by tiktoken. This can include when using Azure embeddings or when using one of the many model providers that expose an OpenAI-like API but with different models. In those cases, in order to avoid erroring when tiktoken is called, you can specify a model name to use here.

async aembed_documents(texts: List[str], chunk_size: Optional[int] = 0) → List[List[float]]

Call out to OpenAI’s embedding endpoint async for embedding search docs.

Parameters

• texts (List[str]) – The list of texts to embed.

• chunk_size (Optional[int]) – The chunk size of embeddings. If None, will use the chunk size specified by the class.

Returns

List of embeddings, one for each text.

Return type

List[List[float]]

async aembed_query(text: str) → List[float]

Call out to OpenAI’s embedding endpoint async for embedding query text.

Parameters

text (str) – The text to embed.

Returns

Embedding for the text.

Return type

List[float]

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

Parameters

• _fields_set (Optional[SetStr]) –

• values (Any) –

Return type

Model

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

• include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to include in new model

• exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to exclude from new model, as with values this takes precedence over include

• update (Optional[DictStrAny]) – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep (bool) – set to True to make a deep copy of the model

• self (Model) –

Returns

new model instance

Return type

Model

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters

• include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

• exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

• by_alias (bool) –

• skip_defaults (Optional[bool]) –

• exclude_unset (bool) –

• exclude_defaults (bool) –

• exclude_none (bool) –

Return type

DictStrAny

embed_documents(texts: List[str], chunk_size: Optional[int] = 0) → List[List[float]]

Call out to OpenAI’s embedding endpoint for embedding search docs.

Parameters

• texts (List[str]) – The list of texts to embed.

• chunk_size (Optional[int]) – The chunk size of embeddings. If None, will use the chunk size specified by the class.

Returns

List of embeddings, one for each text.

Return type

List[List[float]]

embed_query(text: str) → List[float]

Call out to OpenAI’s embedding endpoint for embedding query text.

Parameters

text (str) – The text to embed.

Returns

Embedding for the text.

Return type

List[float]

classmethod from_orm(obj: Any) → Model

Parameters

obj (Any) –

Return type

Model

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

Parameters

• include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

• exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

• by_alias (bool) –

• skip_defaults (Optional[bool]) –

• exclude_unset (bool) –

• exclude_defaults (bool) –

• exclude_none (bool) –

• encoder (Optional[Callable[[Any], Any]]) –

• models_as_dict (bool) –

• dumps_kwargs (Any) –

Return type

unicode

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model

Parameters

• path (Union[str, Path]) –

• content_type (unicode) –

• encoding (unicode) –

• proto (Protocol) –

• allow_pickle (bool) –

Return type

Model

classmethod parse_obj(obj: Any) → Model

Parameters

obj (Any) –

Return type

Model

classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model

Parameters

• b (Union[str, bytes]) –

• content_type (unicode) –

• encoding (unicode) –

• proto (Protocol) –

• allow_pickle (bool) –

Return type

Model

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny

Parameters

• by_alias (bool) –

• ref_template (unicode) –

Return type

DictStrAny

classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) → unicode

Parameters

• by_alias (bool) –

• ref_template (unicode) –

• dumps_kwargs (Any) –

Return type

unicode

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

Parameters

localns (Any) –

Return type

None

classmethod validate(value: Any) → Model

Parameters

value (Any) –

Return type

Model

Examples using OpenAIEmbeddings

• # activeloop token is needed if you are not signed in using CLI: `activeloop login -u <USERNAME> -p <PASSWORD>`

• # if you plan to use bson serialization, install also:

• %pip install -qU langchain langchain-community langchain-openai faker langchain-chroma

• %pip install -qU langchain langchain-community langchain-openai langchain-chroma

• %pip install -qU langchain langchain-community langchain-openai youtube-transcript-api pytube langchain-chroma

• 1. Vanilla RAG {#vanilla-rag-1}

• > ChatPromptValue(messages=[HumanMessage(content=’tell me a short joke about ice cream’)])

• Adding values to chain state {#adding-values-to-chain-state}

• Backed by a Vector Store

• Build a sample vectorDB

• Clean up KDB.AI “documents” table and index for similarity search

• Define your embedding model

• DocumentDB connection string

• Download the content

• Dynamically route logic based on input {#dynamically-route-logic-based-on-input}

• Establishing a connection to the database is facilitated through the singlestoredb Python connector.

• Examples of a pretend task of creating antonyms.

• Formatting inputs & output {#formatting-inputs-output}

• Get 3 diff embeddings.

• Get an OpenAI token: https://platform.openai.com/account/api-keys

• Get openAI api key by reading local .env file

• Helper function for printing docs

• Here we useimport getpass

• Here we want to make sure the answer is minimally relevant

• If using the default Docker installation, use this instantiation instead:

• Install all needed libraries

• Javelin AI Gateway

• Load in document to retrieve over

• Metadata {#metadata}

• OR

• OR (depending on Python version)

• OpenAI

• Option 1: use an OpenAI account

• PDF

• Passing data through {#passing-data-through}

• Pip install necessary package

• Pip install necessary package {#pip-install-necessary-package}

• Pip install necessary packages

• QA with private data protection {#qa-with-private-data-protection}

• Quickstart

• Quickstart {#quickstart}

• Retrievers

• Select the most similar example to the input.

• Self-querying

• Set env var OPENAI_API_KEY or load from a .env file

• Set env var OPENAI_API_KEY or load from a .env file:

• Set up the OpenAI Environment Variables

• Setup {#setup}

• Streaming With LangChain {#streaming-with-langchain}

• Swapping the `ByteStore` {#swapping-the-bytestore}

• Text embedding models

• The input schema of the chain is the input schema of its first part, the prompt.

• The vectorstore to use to index the child chunks

• This example only specifies a filter

• This example only specifies a relevant query

• This is a long document we can split up.

• This is a prompt template used to format each individual example.

• This text splitter is used to create the child documents

• This will only get documents for Ankush

• To make the caching really obvious, lets use a slower model.

• Uncomment if you want to log to LangSmith

• Uncomment the below to use LangSmith. Not required.

• Uncomment this to install psychicapi if you don’t already have it installed

• Use Meilisearch vector store to store texts & associated embeddings as vector

• Vector stores

• Wait until the cluster is ready for use.

• You need the dgml-utils package to use the DocugamiLoader (run pip install directly without “poetry run” if you are not using poetry)

• adding_memory_chain_multiple_inputs.md

• analyticdb.md

• astradb.md

• azure_ai_search.md

• cassandra.md

• clickhouse.md

• connection to redis standalone at localhost, db 0, no password

• conversational_retrieval_agents.md

• cosine: distance metric

• create new index

• create the index

• databricks_vector_search.md

• document_comparison_toolkit.md

• duckdb.md

• ecloud_vector_search.md

• epsilla.md

• fleet_context.md

• for example

• from langchain_community.embeddings.openai import OpenAIEmbeddings

• hologres.md

• import

• import dotenv

• import os

• in case if some queries fail consider installing libdeeplake manually

• indexing.md

• initialize MongoDB python client

• initialize the bm25 retriever and faiss retriever

• initialize the index

• inspect.md

• install package

• knn.md

• lancedb.md

• load text splitter and split docs into snippets of text

• openai

• openai.md

• or install latest:

• or shorter

• os.environ[“LANGCHAIN_TRACING_V2”] = “true”

• os.environ[“OPENAI_API_KEY”] = getpass.getpass()

• output length: 4

• pinecone.md

• qdrant.md

• ragatouille.md

• re_phrase.md

• replace

• set a flag to switch between local and remote parsing

• set the environment variables needed for openai package to know to reach out to azure

• svm.md

• tigris.md

• typesense.md

• use directly a `where_str` to delete

• usearch.md

• vectorstore.md

• vikingdb.md

• with pip

• xata.md

• xata_chat_message_history.md