Openai embedding
OpenAIEmbedding
¶
Bases: Embedding
The openai embedding class.
Source code in agentuniverse/agent/action/knowledge/embedding/openai_embedding.py
Python
class OpenAIEmbedding(Embedding):
"""The openai embedding class."""
openai_client_args: Optional[dict] = None
openai_api_key: Optional[str] = Field(default_factory=lambda: get_from_env("OPENAI_API_KEY"))
client: Any = None
async_client: Any = None
dimensions: Optional[int] = None
def get_embeddings(self, texts: List[str]) -> List[List[float]]:
"""Get the OpenAI embeddings.
Note:
The `embedding_model_name` parameter of the openai embedding class must be provided.
The `dimensions` parameter of the openai embedding class is optional.
Args:
texts (List[str]): A list of texts that need to be embedded.
Returns:
List[List[float]]: Each text gets a float list, and the result is a list of the results for each text.
Raises:
ValueError: If texts exceed the embedding model token limit or missing some required parameters.
"""
self.client = OpenAI(api_key=self.openai_api_key, **self.openai_client_args or {})
if self.embedding_model_name is None:
raise ValueError("Must provide `embedding_model_name`")
try:
if self.dimensions:
response = self.client.embeddings.create(input=texts, model=self.embedding_model_name,
dimensions=self.dimensions)
else:
response = self.client.embeddings.create(input=texts, model=self.embedding_model_name)
# Extract the embedding data from the response
data = response.data
# Return the embeddings as a list of lists of floats
return [embedding.embedding for embedding in data]
except BadRequestError as e:
raise ValueError(e.message)
async def async_get_embeddings(self, texts: List[str]) -> List[List[float]]:
"""Asynchronously get the OpenAI embeddings.
Note:
The `embedding_model_name` parameter of the openai embedding class must be provided.
The `dimensions` parameter of the openai embedding class is optional.
Args:
texts (List[str]): A list of texts that need to be embedded.
Returns:
List[List[float]]: Each text gets a float list, and the result is a list of the results for each text.
Raises:
ValueError: If texts exceed the embedding model token limit or missing some required parameters.
"""
self.async_client = AsyncOpenAI(api_key=self.openai_api_key, **self.openai_client_args or {})
if self.embedding_model_name is None:
raise ValueError("Must provide `embedding_model_name`")
try:
if self.dimensions:
response = await self.async_client.embeddings.create(input=texts, model=self.embedding_model_name,
dimensions=self.dimensions)
else:
response = await self.async_client.embeddings.create(input=texts, model=self.embedding_model_name)
# Extract the embedding data from the response
data = response.data
# Return the embeddings as a list of lists of floats
return [embedding.embedding for embedding in data]
except BadRequestError as e:
raise ValueError(e.message)
def as_langchain(self) -> OpenAIEmbeddings:
"""Convert the agentUniverse(aU) openai embedding class to the langchain openai embedding class."""
return OpenAIEmbeddings(openai_api_key=self.openai_api_key,
client=self.client.embeddings, async_client=self.async_client.embeddings)
as_langchain()
¶
Convert the agentUniverse(aU) openai embedding class to the langchain openai embedding class.
Source code in agentuniverse/agent/action/knowledge/embedding/openai_embedding.py
async_get_embeddings(texts)
async
¶
Asynchronously get the OpenAI embeddings.
Note
The embedding_model_name parameter of the openai embedding class must be provided.
The dimensions parameter of the openai embedding class is optional.
Returns: List[List[float]]: Each text gets a float list, and the result is a list of the results for each text. Raises: ValueError: If texts exceed the embedding model token limit or missing some required parameters.
Source code in agentuniverse/agent/action/knowledge/embedding/openai_embedding.py
Python
async def async_get_embeddings(self, texts: List[str]) -> List[List[float]]:
"""Asynchronously get the OpenAI embeddings.
Note:
The `embedding_model_name` parameter of the openai embedding class must be provided.
The `dimensions` parameter of the openai embedding class is optional.
Args:
texts (List[str]): A list of texts that need to be embedded.
Returns:
List[List[float]]: Each text gets a float list, and the result is a list of the results for each text.
Raises:
ValueError: If texts exceed the embedding model token limit or missing some required parameters.
"""
self.async_client = AsyncOpenAI(api_key=self.openai_api_key, **self.openai_client_args or {})
if self.embedding_model_name is None:
raise ValueError("Must provide `embedding_model_name`")
try:
if self.dimensions:
response = await self.async_client.embeddings.create(input=texts, model=self.embedding_model_name,
dimensions=self.dimensions)
else:
response = await self.async_client.embeddings.create(input=texts, model=self.embedding_model_name)
# Extract the embedding data from the response
data = response.data
# Return the embeddings as a list of lists of floats
return [embedding.embedding for embedding in data]
except BadRequestError as e:
raise ValueError(e.message)
get_embeddings(texts)
¶
Get the OpenAI embeddings.
Note
The embedding_model_name parameter of the openai embedding class must be provided.
The dimensions parameter of the openai embedding class is optional.
Returns: List[List[float]]: Each text gets a float list, and the result is a list of the results for each text.
Raises: ValueError: If texts exceed the embedding model token limit or missing some required parameters.
Source code in agentuniverse/agent/action/knowledge/embedding/openai_embedding.py
Python
def get_embeddings(self, texts: List[str]) -> List[List[float]]:
"""Get the OpenAI embeddings.
Note:
The `embedding_model_name` parameter of the openai embedding class must be provided.
The `dimensions` parameter of the openai embedding class is optional.
Args:
texts (List[str]): A list of texts that need to be embedded.
Returns:
List[List[float]]: Each text gets a float list, and the result is a list of the results for each text.
Raises:
ValueError: If texts exceed the embedding model token limit or missing some required parameters.
"""
self.client = OpenAI(api_key=self.openai_api_key, **self.openai_client_args or {})
if self.embedding_model_name is None:
raise ValueError("Must provide `embedding_model_name`")
try:
if self.dimensions:
response = self.client.embeddings.create(input=texts, model=self.embedding_model_name,
dimensions=self.dimensions)
else:
response = self.client.embeddings.create(input=texts, model=self.embedding_model_name)
# Extract the embedding data from the response
data = response.data
# Return the embeddings as a list of lists of floats
return [embedding.embedding for embedding in data]
except BadRequestError as e:
raise ValueError(e.message)