Renamed OpenAiEmbeddingConfig dataclass (#2546)

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.12.5-dev4
+## 0.12.5-dev5
 
 ### Enhancements
 
@@ -12,6 +12,7 @@
 * **Fix don't treat plain text files with double quotes as JSON ** If a file can be deserialized as JSON but it deserializes as a string, treat it as plain text even though it's valid JSON.
 * **Fix `check_connection` in opensearch, databricks, postgres, azure connectors **
 * **Fix cluster of bugs in `partition_xlsx()` that dropped content.** Algorithm for detecting "subtables" within a worksheet dropped table elements for certain patterns of populated cells such as when a trailing single-cell row appeared in a contiguous block of populated cells.
+* **Rename `OpenAiEmbeddingConfig` to `OpenAIEmbeddingConfig`.
 
 ## 0.12.4
 

docs/source/core/embedding.rst

@@ -43,10 +43,10 @@ To obtain an api key, visit: https://platform.openai.com/account/api-keys
     import os
 
     from unstructured.documents.elements import Text
-    from unstructured.embed.openai import OpenAiEmbeddingConfig, OpenAIEmbeddingEncoder
+    from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
 
     # Initialize the encoder with OpenAI credentials
-    embedding_encoder = OpenAIEmbeddingEncoder(config=OpenAiEmbeddingConfig(api_key=os.environ["OPENAI_API_KEY"]))
+    embedding_encoder = OpenAIEmbeddingEncoder(config=OpenAIEmbeddingConfig(api_key=os.environ["OPENAI_API_KEY"]))
 
     # Embed a list of Elements
     elements = embedding_encoder.embed_documents(

examples/embed/example_openai.py

@@ -1,10 +1,10 @@
 import os
 
 from unstructured.documents.elements import Text
-from unstructured.embed.openai import OpenAiEmbeddingConfig, OpenAIEmbeddingEncoder
+from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
 
 embedding_encoder = OpenAIEmbeddingEncoder(
-    config=OpenAiEmbeddingConfig(api_key=os.environ["OPENAI_API_KEY"])
+    config=OpenAIEmbeddingConfig(api_key=os.environ["OPENAI_API_KEY"])
 )
 elements = embedding_encoder.embed_documents(
     elements=[Text("This is sentence 1"), Text("This is sentence 2")],

test_unstructured/embed/test_openai.py

@@ -1,5 +1,5 @@
 from unstructured.documents.elements import Text
-from unstructured.embed.openai import OpenAiEmbeddingConfig, OpenAIEmbeddingEncoder
+from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
 
 
 def test_embed_documents_does_not_break_element_to_dict(mocker):
@@ -10,7 +10,7 @@ def test_embed_documents_does_not_break_element_to_dict(mocker):
     # Mock create_client to return our mock_client
     mocker.patch.object(OpenAIEmbeddingEncoder, "create_client", return_value=mock_client)
 
-    encoder = OpenAIEmbeddingEncoder(config=OpenAiEmbeddingConfig(api_key="api_key"))
+    encoder = OpenAIEmbeddingEncoder(config=OpenAIEmbeddingConfig(api_key="api_key"))
     elements = encoder.embed_documents(
         elements=[Text("This is sentence 1"), Text("This is sentence 2")],
     )

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.12.5-dev4"  # pragma: no cover
+__version__ = "0.12.5-dev5"  # pragma: no cover

unstructured/embed/openai.py

@@ -15,14 +15,14 @@ if TYPE_CHECKING:
 
 
 @dataclass
-class OpenAiEmbeddingConfig(EmbeddingConfig):
+class OpenAIEmbeddingConfig(EmbeddingConfig):
     api_key: str
     model_name: str = "text-embedding-ada-002"
 
 
 @dataclass
 class OpenAIEmbeddingEncoder(BaseEmbeddingEncoder):
-    config: OpenAiEmbeddingConfig
+    config: OpenAIEmbeddingConfig
     _client: Optional["OpenAIEmbeddings"] = field(init=False, default=None)
     _exemplary_embedding: Optional[List[float]] = field(init=False, default=None)
 

unstructured/ingest/interfaces.py

@@ -196,9 +196,9 @@ class EmbeddingConfig(BaseConfig):
             kwargs["model_name"] = self.model_name
         # TODO make this more dynamic to map to encoder configs
         if self.provider == "langchain-openai":
-            from unstructured.embed.openai import OpenAiEmbeddingConfig, OpenAIEmbeddingEncoder
+            from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
 
-            return OpenAIEmbeddingEncoder(config=OpenAiEmbeddingConfig(**kwargs))
+            return OpenAIEmbeddingEncoder(config=OpenAIEmbeddingConfig(**kwargs))
         elif self.provider == "langchain-huggingface":
             from unstructured.embed.huggingface import (
                 HuggingFaceEmbeddingConfig,