Fix subclassing OpenAIEmbeddings (#4500)

# Fix subclassing OpenAIEmbeddings

Fixes #4498 

## Before submitting

- Problem: Due to annotated type `Tuple[()]`.
- Fix: Change the annotated type to "Iterable[str]". Even though
tiktoken use
[Collection[str]](https://github.com/openai/tiktoken/blob/095924e02c85617df6889698d94515f91666c7ea/tiktoken/core.py#L80)
type annotation, but pydantic doesn't support Collection type, and
[Iterable](https://docs.pydantic.dev/latest/usage/types/#typing-iterables)
is the closest to Collection.

langchain/embeddings/openai.py

@@ -9,6 +9,7 @@ from typing import (
     List,
     Literal,
     Optional,
+    Sequence,
     Set,
     Tuple,
     Union,
@@ -115,7 +116,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     openai_api_key: Optional[str] = None
     openai_organization: Optional[str] = None
     allowed_special: Union[Literal["all"], Set[str]] = set()
-    disallowed_special: Union[Literal["all"], Set[str], Tuple[()]] = "all"
+    disallowed_special: Union[Literal["all"], Set[str], Sequence[str]] = "all"
     chunk_size: int = 1000
     """Maximum number of texts to embed in each batch"""
     max_retries: int = 6