Update the operator.

Signed-off-by: jinlingxu06 <jinling.xu@zilliz.com>

README.md

@@ -1,2 +1,86 @@
-# azure-openai
+# Sentence Embedding with OpenAI
+
+*author: Junjie, Jael*
+
+<br />
+
+## Description
+
+A sentence embedding operator generates one embedding vector in ndarray for each input text.
+The embedding represents the semantic information of the whole input text as one vector.
+This operator is implemented with embedding models from [OpenAI](https://platform.openai.com/docs/guides/embeddings).
+Please note you need an [OpenAI API key](https://platform.openai.com/account/api-keys) to access OpenAI.
+
+<br />
+
+## Code Example
+
+Use the pre-trained model ''
+to generate an embedding for the sentence "Hello, world.".
+
+*Write a pipeline with explicit inputs/outputs name specifications:*
+
+```python
+from towhee import pipe, ops, DataCollection
+
+p = (
+    pipe.input('text')
+        .map('text', 'vec', 
+             ops.sentence_embedding.openai(model_name='text-embedding-ada-002', api_key=OPENAI_API_KEY))
+        .output('text', 'vec')
+)
+
+DataCollection(p('Hello, world.')).show()
+```
+
+<br />
+
+## Factory Constructor
+
+Create the operator via the following factory method:
+
+***sentence_embedding.openai(model_name='text-embedding-ada-002')***
+
+**Parameters:**
+
+***model_name***: *str*
+
+The model name in string, defaults to 'text-embedding-ada-002'. Supported model names:
+- text-embedding-ada-002
+- text-similarity-davinci-001
+- text-similarity-curie-001
+- text-similarity-babbage-001
+- text-similarity-ada-001
+
+***api_key***: *str=None*
+
+The OpenAI API key in string, defaults to None.
+
+<br />
+
+## Interface
+
+The operator takes a piece of text in string as input.
+It returns a text emabedding in numpy.ndarray.
+
+***\_\_call\_\_(txt)***
+
+**Parameters:**
+
+***text***: *str*
+
+​	The text in string.
+
+**Returns**:
+
+*numpy.ndarray or list*
+
+​	The text embedding extracted by model.
+
+<br />
+
+***supported_model_names()***
+
+Get a list of supported model names.
+
 

__init__.py

@@ -0,0 +1,4 @@
+from .azure_openai_embedding import AzureOpenaiEmbeding
+
+def azure_openai(*args, **kwargs):
+    return AzureOpenaiEmbeding(*args, **kwargs)

azure_openai_embedding.py

@@ -0,0 +1,61 @@
+# Copyright 2021 Zilliz. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from openai import Embedding
+from tenacity import retry, stop_after_attempt, wait_random_exponential
+from towhee.operator.base import PyOperator
+
+
+class AzureOpenaiEmbeding(PyOperator):
+    def __init__(self,
+                 engine='text-embedding-ada-002',
+                 api_type: str = 'azure',
+                 api_version: str = '2023-07-01-preview',
+                 api_key=None, 
+                 api_base=None):
+        self._engine = engine
+        self._api_type = api_type
+        self._api_version = api_version
+        self._api_key = api_key
+        self._api_base = api_base
+
+
+
+    @retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
+    def _call(self, text):
+        text = text.replace("\n", " ")
+        return Embedding.create(input=[text],
+                                engine=self._engine,
+                                api_key=self._api_key,
+                                api_type=self._api_type,
+                                api_version=self._api_version,
+                                api_base=self._api_base
+        )["data"][0]["embedding"]
+
+    def __call__(self, text):
+        return self._call(text)
+
+    @staticmethod
+    def supported_model_names():
+        model_list = [
+            'text-embedding-ada-002',
+            'text-similarity-davinci-001',
+            'text-similarity-curie-001',
+            'text-similarity-babbage-001',
+            'text-similarity-ada-001'
+        ]
+        model_list.sort()
+        return model_list
+

requirements.txt

@@ -0,0 +1 @@
+openai