docs: format oai embeddings docstring (#25448)

libs/partners/openai/langchain_openai/embeddings/base.py

@@ -95,83 +95,83 @@ def _process_batched_chunked_embeddings(
 class OpenAIEmbeddings(BaseModel, Embeddings):
     """OpenAI embedding model integration.
 
-     Setup:
+    Setup:
-         Install ``langchain_openai`` and set environment variable ``OPENAI_API_KEY``.
+        Install ``langchain_openai`` and set environment variable ``OPENAI_API_KEY``.
 
-         .. code-block:: bash
+        .. code-block:: bash
 
-             pip install -U langchain_openai
+            pip install -U langchain_openai
-             export OPENAI_API_KEY="your-api-key"
+            export OPENAI_API_KEY="your-api-key"
 
-     Key init args — embedding params:
+    Key init args — embedding params:
-         model: str
+        model: str
-             Name of OpenAI model to use.
+            Name of OpenAI model to use.
-         dimensions: Optional[int] = None
+        dimensions: Optional[int] = None
-             The number of dimensions the resulting output embeddings should have.
+            The number of dimensions the resulting output embeddings should have.
-             Only supported in `text-embedding-3` and later models.
+            Only supported in `text-embedding-3` and later models.
 
     Key init args — client params:
-         api_key: Optional[SecretStr] = None
+        api_key: Optional[SecretStr] = None
-             OpenAI API key.
+            OpenAI API key.
-         organization: Optional[str] = None
+        organization: Optional[str] = None
-             OpenAI organization ID. If not passed in will be read
+            OpenAI organization ID. If not passed in will be read
-             from env var OPENAI_ORG_ID.
+            from env var OPENAI_ORG_ID.
-         max_retries: int = 2
+        max_retries: int = 2
-             Maximum number of retries to make when generating.
+            Maximum number of retries to make when generating.
-         request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None
+        request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None
-             Timeout for requests to OpenAI completion API
+            Timeout for requests to OpenAI completion API
 
-     See full list of supported init args and their descriptions in the params section.
+    See full list of supported init args and their descriptions in the params section.
 
-     Instantiate:
+    Instantiate:
-         .. code-block:: python
+        .. code-block:: python
 
-             from langchain_openai import OpenAIEmbeddings
+            from langchain_openai import OpenAIEmbeddings
 
-             embed = OpenAIEmbeddings(
+            embed = OpenAIEmbeddings(
-                 model="text-embedding-3-large"
+                model="text-embedding-3-large"
-                 # With the `text-embedding-3` class
+                # With the `text-embedding-3` class
-                 # of models, you can specify the size
+                # of models, you can specify the size
-                 # of the embeddings you want returned.
+                # of the embeddings you want returned.
-                 # dimensions=1024
+                # dimensions=1024
-             )
+            )
 
-     Embed single text:
+    Embed single text:
-         .. code-block:: python
+        .. code-block:: python
 
-             input_text = "The meaning of life is 42"
+            input_text = "The meaning of life is 42"
-             vector = embeddings.embed_query("hello")
+            vector = embeddings.embed_query("hello")
-             print(vector[:3])
+            print(vector[:3])
 
-         .. code-block:: python
+        .. code-block:: python
 
-             [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]
+            [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]
 
-     Embed multiple texts:
+    Embed multiple texts:
-         .. code-block:: python
+        .. code-block:: python
 
-             vectors = embeddings.embed_documents(["hello", "goodbye"])
+            vectors = embeddings.embed_documents(["hello", "goodbye"])
-             # Showing only the first 3 coordinates
+            # Showing only the first 3 coordinates
-             print(len(vectors))
+            print(len(vectors))
-             print(vectors[0][:3])
+            print(vectors[0][:3])
 
-         .. code-block:: python
+        .. code-block:: python
 
-             2
+            2
-             [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]
+            [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]
 
-     Async:
+    Async:
-         .. code-block:: python
+        .. code-block:: python
 
-             await embed.aembed_query(input_text)
+            await embed.aembed_query(input_text)
-             print(vector[:3])
+            print(vector[:3])
 
-             # multiple:
+            # multiple:
-             # await embed.aembed_documents(input_texts)
+            # await embed.aembed_documents(input_texts)
 
-         .. code-block:: python
+        .. code-block:: python
 
-             [-0.009100092574954033, 0.005071679595857859, -0.0029193938244134188]
+            [-0.009100092574954033, 0.005071679595857859, -0.0029193938244134188]
     """
 
     client: Any = Field(default=None, exclude=True)  #: :meta private: