This is an automated email from the ASF dual-hosted git repository.
potiuk pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push:
new acb9458d09 Refine Type Handling in OpenAI Embedding Operator to Match
OpenAI Typings (#35547)
acb9458d09 is described below
commit acb9458d096f956b319c2b121cbcd01489492491
Author: Yoel <[email protected]>
AuthorDate: Wed Nov 15 02:50:35 2023 +0700
Refine Type Handling in OpenAI Embedding Operator to Match OpenAI Typings
(#35547)
---
airflow/providers/openai/hooks/openai.py | 5 ++++-
airflow/providers/openai/operators/openai.py | 27 +++++++++++++++----------
tests/providers/openai/operators/test_openai.py | 12 +++++++++++
3 files changed, 32 insertions(+), 12 deletions(-)
diff --git a/airflow/providers/openai/hooks/openai.py
b/airflow/providers/openai/hooks/openai.py
index ee21b5a3c3..fac725b5be 100644
--- a/airflow/providers/openai/hooks/openai.py
+++ b/airflow/providers/openai/hooks/openai.py
@@ -74,7 +74,10 @@ class OpenAIHook(BaseHook):
return conn.host
def create_embeddings(
- self, text: str | list[Any], model: str = "text-embedding-ada-002",
**kwargs: Any
+ self,
+ text: str | list[str] | list[int] | list[list[int]],
+ model: str = "text-embedding-ada-002",
+ **kwargs: Any,
) -> list[float]:
"""Generate embeddings for the given text using the given model.
diff --git a/airflow/providers/openai/operators/openai.py
b/airflow/providers/openai/operators/openai.py
index 1e585b5d0a..1697e88b98 100644
--- a/airflow/providers/openai/operators/openai.py
+++ b/airflow/providers/openai/operators/openai.py
@@ -31,16 +31,17 @@ class OpenAIEmbeddingOperator(BaseOperator):
"""
Operator that accepts input text to generate OpenAI embeddings using the
specified model.
+ :param conn_id: The OpenAI connection ID to use.
+ :param input_text: The text to generate OpenAI embeddings for. This can be
a string, a list of strings,
+ a list of integers, or a list of lists of integers.
+ :param model: The OpenAI model to be used for generating the embeddings.
+ :param embedding_kwargs: Additional keyword arguments to pass to the
OpenAI `create_embeddings` method.
+
.. seealso::
For more information on how to use this operator, take a look at the
guide:
:ref:`howto/operator:OpenAIEmbeddingOperator`
-
- :param conn_id: The OpenAI connection.
- :param input_text: The text to generate OpenAI embeddings on. Either
input_text or input_callable
- should be provided.
- :param model: The OpenAI model to be used for generating the embeddings.
- :param embedding_kwargs: For possible option check
- .. seealso::
https://platform.openai.com/docs/api-reference/embeddings/create
+ For possible options for `embedding_kwargs`, see:
+ https://platform.openai.com/docs/api-reference/embeddings/create
"""
template_fields: Sequence[str] = ("input_text",)
@@ -48,16 +49,16 @@ class OpenAIEmbeddingOperator(BaseOperator):
def __init__(
self,
conn_id: str,
- input_text: str | list[Any],
+ input_text: str | list[str] | list[int] | list[list[int]],
model: str = "text-embedding-ada-002",
embedding_kwargs: dict | None = None,
**kwargs: Any,
):
- self.embedding_kwargs = embedding_kwargs or {}
super().__init__(**kwargs)
self.conn_id = conn_id
self.input_text = input_text
self.model = model
+ self.embedding_kwargs = embedding_kwargs or {}
@cached_property
def hook(self) -> OpenAIHook:
@@ -65,7 +66,11 @@ class OpenAIEmbeddingOperator(BaseOperator):
return OpenAIHook(conn_id=self.conn_id)
def execute(self, context: Context) -> list[float]:
- self.log.info("Input text: %s", self.input_text)
+ if not self.input_text or not isinstance(self.input_text, (str, list)):
+ raise ValueError(
+ "The 'input_text' must be a non-empty string, list of strings,
list of integers, or list of lists of integers."
+ )
+ self.log.info("Generating embeddings for the input text of length:
%d", len(self.input_text))
embeddings = self.hook.create_embeddings(self.input_text,
model=self.model, **self.embedding_kwargs)
- self.log.info("Embeddings: %s", embeddings)
+ self.log.info("Generated embeddings for %d items", len(embeddings))
return embeddings
diff --git a/tests/providers/openai/operators/test_openai.py
b/tests/providers/openai/operators/test_openai.py
index 11a6483802..12b1cf0b13 100644
--- a/tests/providers/openai/operators/test_openai.py
+++ b/tests/providers/openai/operators/test_openai.py
@@ -18,6 +18,8 @@ from __future__ import annotations
from unittest.mock import Mock
+import pytest
+
from airflow.providers.openai.operators.openai import OpenAIEmbeddingOperator
from airflow.utils.context import Context
@@ -34,3 +36,13 @@ def test_execute_with_input_text():
embeddings = operator.execute(context)
assert embeddings == [1.0, 2.0, 3.0]
+
+
[email protected]("invalid_input", ["", None, 123])
+def test_execute_with_invalid_input(invalid_input):
+ with pytest.raises(ValueError):
+ operator = OpenAIEmbeddingOperator(
+ task_id="TaskId", conn_id="test_conn_id", model="test_model",
input_text=invalid_input
+ )
+ context = Context()
+ operator.execute(context)
