langchain_community.embeddings.openai
.OpenAIEmbeddings¶
- class langchain_community.embeddings.openai.OpenAIEmbeddings[source]¶
Bases:
BaseModel
,Embeddings
[Deprecated] OpenAI嵌入模型。
要使用,请确保已安装``openai`` Python包,并将环境变量``OPENAI_API_KEY``设置为您的API密钥,或将其作为构造函数的命名参数传递。
- 示例:
from langchain_community.embeddings import OpenAIEmbeddings openai = OpenAIEmbeddings(openai_api_key="my-api-key")
要使用Microsoft Azure端点的库,需要设置OPENAI_API_TYPE、OPENAI_API_BASE、OPENAI_API_KEY和OPENAI_API_VERSION。 OPENAI_API_TYPE必须设置为’azure’,其他属性与您的端点属性相对应。 另外,部署名称必须作为model参数传递。
- 示例:
import os os.environ["OPENAI_API_TYPE"] = "azure" os.environ["OPENAI_API_BASE"] = "https://<your-endpoint.openai.azure.com/" os.environ["OPENAI_API_KEY"] = "your AzureOpenAI key" os.environ["OPENAI_API_VERSION"] = "2023-05-15" os.environ["OPENAI_PROXY"] = "http://your-corporate-proxy:8080" from langchain_community.embeddings.openai import OpenAIEmbeddings embeddings = OpenAIEmbeddings( deployment="your-embeddings-deployment-name", model="your-embeddings-model-name", openai_api_base="https://your-endpoint.openai.azure.com/", openai_api_type="azure", ) text = "This is a test query." query_result = embeddings.embed_query(text)
Notes
Deprecated since version 0.0.9.
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: Union[Literal['all'], Set[str]] = {}¶
- param chunk_size: int = 1000¶
每个批次中嵌入的最大文本数量
- 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 disallowed_special: Union[Literal['all'], Set[str], Sequence[str]] = 'all'¶
- param embedding_ctx_length: int = 8191¶
一次嵌入的最大令牌数。
- param headers: Any = None¶
- param http_client: Optional[Any] = None¶
可选的 httpx.Client。
- param max_retries: int = 2¶
生成时最大的重试次数。
- param model: str = 'text-embedding-ada-002'¶
- param model_kwargs: Dict[str, Any] [Optional]¶
保存任何在`create`调用中有效但未明确指定的模型参数。
- param openai_api_base: Optional[str] = None (alias 'base_url')¶
API请求的基本URL路径,如果不使用代理或服务模拟器,请留空。
- param openai_api_key: Optional[str] = None (alias 'api_key')¶
如果未提供,将自动从环境变量`OPENAI_API_KEY`中推断。
- param openai_api_type: Optional[str] = None¶
- param openai_api_version: Optional[str] = None (alias 'api_version')¶
如果未提供,将自动从环境变量`OPENAI_API_VERSION`中推断。
- param openai_organization: Optional[str] = None (alias 'organization')¶
如果未提供,将自环境变量`OPENAI_ORG_ID`自动推断。
- param openai_proxy: Optional[str] = None¶
- param request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None (alias 'timeout')¶
请求到OpenAI完成API的超时时间。可以是浮点数、httpx.Timeout或None。
- param retry_max_seconds: int = 20¶
重试之间等待的最大秒数
- param retry_min_seconds: int = 4¶
重试之间等待的最短秒数
- param show_progress_bar: bool = False¶
在嵌入时是否显示进度条。
- param skip_empty: bool = False¶
是否在嵌入时跳过空字符串或引发错误。 默认情况下不跳过。
- param tiktoken_enabled: bool = True¶
将此设置为False,用于嵌入API的非OpenAI实现,例如`text-generation-webui`的`–extensions openai`扩展。
- param tiktoken_model_name: Optional[str] = None¶
在使用这个类时,传递给tiktoken的模型名称。 Tiktoken用于计算文档中令牌的数量,以限制它们在某个特定限制之下。默认情况下,当设置为None时,这将与嵌入模型名称相同。然而,在一些情况下,您可能希望使用这个嵌入类与tiktoken不支持的模型名称一起使用。这可能包括使用Azure嵌入或使用许多提供类似OpenAI API但具有不同模型的模型提供商之一。在这些情况下,为了避免在调用tiktoken时出错,您可以在这里指定要使用的模型名称。
- async aembed_documents(texts: List[str], chunk_size: Optional[int] = 0) List[List[float]] [source]¶
调用OpenAI的嵌入端点异步进行嵌入搜索文档。
- 参数:
texts:要嵌入的文本列表。 chunk_size:嵌入的块大小。如果为None,则将使用类别指定的块大小。
- 返回:
每个文本的嵌入列表。
- Parameters
texts (List[str]) –
chunk_size (Optional[int]) –
- Return type
List[List[float]]
- async aembed_query(text: str) List[float] [source]¶
调用OpenAI的嵌入端点异步地为嵌入查询文本。
- 参数:
text:要嵌入的文本。
- 返回:
文本的嵌入。
- Parameters
text (str) –
- 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]] [source]¶
调用OpenAI的嵌入端点以获取嵌入搜索文档。
- 参数:
texts:要嵌入的文本列表。 chunk_size:嵌入的块大小。如果为None,将使用类指定的块大小。
- 返回:
每个文本的嵌入列表。
- Parameters
texts (List[str]) –
chunk_size (Optional[int]) –
- Return type
List[List[float]]
- embed_query(text: str) List[float] [source]¶
调用OpenAI的嵌入端点来嵌入查询文本。
- 参数:
text:要嵌入的文本。
- 返回:
文本的嵌入。
- Parameters
text (str) –
- 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¶
%pip install -qU langchain langchain-community langchain-openai faker langchain-chroma
%pip install -qU langchain langchain-community langchain-openai langchain-chroma
> ChatPromptValue(messages=[HumanMessage(content=’tell me a short joke about ice cream’)])
Adding values to chain state {#adding-values-to-chain-state}
Clean up KDB.AI “documents” table and index for similarity search
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.
Get an OpenAI token: https://platform.openai.com/account/api-keys
If using the default Docker installation, use this instantiation instead:
Pip install necessary package {#pip-install-necessary-package}
QA with private data protection {#qa-with-private-data-protection}
The input schema of the chain is the input schema of its first part, the prompt.
This is a prompt template used to format each individual example.
To make the caching really obvious, lets use a slower model.
Uncomment this to install psychicapi if you don’t already have it installed
Use Meilisearch vector store to store texts & associated embeddings as vector
connection to redis standalone at localhost, db 0, no password
from langchain_community.embeddings.openai import OpenAIEmbeddings
in case if some queries fail consider installing libdeeplake manually
set the environment variables needed for openai package to know to reach out to azure