fix: correct spelling mistakes of "seperate, intialise, pre-defined" (#14647)

fix spellings

**seperate -> separate**: found more occurrences, see
https://github.com/langchain-ai/langchain/pull/14602
**initialise -> intialize**: the latter is more common in the repo
**pre-defined > predefined**: adding a comma after a prefix is a
delicate matter, but this is a generally accepted word

also, another word that appears in the repo is "fs" (stands for
filesystem), e.g., in `libs/core/langchain_core/prompts/loading.py`
` """Unified method for loading a prompt from LangChainHub or local
fs."""`
Isn't "filesystem" better?

cookbook/Multi_modal_RAG.ipynb

@@ -46,7 +46,7 @@
     "\n",
     "---\n",
     "\n",
-    "A seperate cookbook highlights `Option 1` [here](https://github.com/langchain-ai/langchain/blob/master/cookbook/multi_modal_RAG_chroma.ipynb).\n",
+    "A separate cookbook highlights `Option 1` [here](https://github.com/langchain-ai/langchain/blob/master/cookbook/multi_modal_RAG_chroma.ipynb).\n",
     "\n",
     "And option `Option 2` is appropriate for cases when a multi-modal LLM cannot be used for answer synthesis (e.g., cost, etc).\n",
     "\n",

docs/docs/modules/model_io/prompts/prompt_templates/index.ipynb

@@ -16,7 +16,7 @@
    "id": "2d98412d-fc53-42c1-aed8-f1f8eb9ada58",
    "metadata": {},
    "source": [
-    "Prompt templates are pre-defined recipes for generating prompts for language models.\n",
+    "Prompt templates are predefined recipes for generating prompts for language models.\n",
     "\n",
     "A template may include instructions, few-shot examples, and specific context and\n",
     "questions appropriate for a given task.\n",

libs/community/langchain_community/document_loaders/gcs_file.py

@@ -58,7 +58,7 @@ class GCSFileLoader(BaseLoader):
                 "Please install it with `pip install google-cloud-storage`."
             )
 
-        # Initialise a client
+        # initialize a client
         storage_client = storage.Client(
             self.project_name, client_info=get_client_info("google-cloud-storage")
         )

libs/community/langchain_community/document_loaders/html_bs.py

@@ -18,7 +18,7 @@ class BSHTMLLoader(BaseLoader):
         bs_kwargs: Union[dict, None] = None,
         get_text_separator: str = "",
     ) -> None:
-        """Initialise with path, and optionally, file encoding to use, and any kwargs
+        """initialize with path, and optionally, file encoding to use, and any kwargs
         to pass to the BeautifulSoup object.
 
         Args:

libs/community/langchain_community/document_loaders/mhtml.py

@@ -19,7 +19,7 @@ class MHTMLLoader(BaseLoader):
         bs_kwargs: Union[dict, None] = None,
         get_text_separator: str = "",
     ) -> None:
-        """Initialise with path, and optionally, file encoding to use, and any kwargs
+        """initialize with path, and optionally, file encoding to use, and any kwargs
         to pass to the BeautifulSoup object.
 
         Args:

libs/community/langchain_community/document_loaders/rspace.py

@@ -66,7 +66,7 @@ class RSpaceLoader(BaseLoader):
 
         except Exception:
             raise Exception(
-                f"Unable to initialise client - is url {self.url} or "
+                f"Unable to initialize client - is url {self.url} or "
                 f"api key  correct?"
             )
 

libs/community/langchain_community/document_loaders/tencent_cos_file.py

@@ -34,7 +34,7 @@ class TencentCOSFileLoader(BaseLoader):
                 "Please install it with `pip install cos-python-sdk-v5`."
             )
 
-        # Initialise a client
+        # initialize a client
         client = CosS3Client(self.conf)
         with tempfile.TemporaryDirectory() as temp_dir:
             file_path = f"{temp_dir}/{self.bucket}/{self.key}"

libs/community/langchain_community/embeddings/embaas.py

@@ -30,11 +30,11 @@ class EmbaasEmbeddings(BaseModel, Embeddings):
     Example:
         .. code-block:: python
 
-            # Initialise with default model and instruction
+            # initialize with default model and instruction
             from langchain_community.embeddings import EmbaasEmbeddings
             emb = EmbaasEmbeddings()
 
-            # Initialise with custom model and instruction
+            # initialize with custom model and instruction
             from langchain_community.embeddings import EmbaasEmbeddings
             emb_model = "instructor-large"
             emb_inst = "Represent the Wikipedia document for retrieval"

libs/community/langchain_community/vectorstores/semadb.py

@@ -36,7 +36,7 @@ class SemaDB(VectorStore):
         distance_strategy: DistanceStrategy = DistanceStrategy.EUCLIDEAN_DISTANCE,
         api_key: str = "",
     ):
-        """Initialise the SemaDB vector store."""
+        """initialize the SemaDB vector store."""
         self.collection_name = collection_name
         self.vector_size = vector_size
         self.api_key = api_key or get_from_env("api_key", "SEMADB_API_KEY")

libs/langchain/langchain/agents/agent_iterator.py

@@ -210,7 +210,7 @@ class AgentExecutorIterator:
 
     async def __aiter__(self) -> AsyncIterator[AddableDict]:
         """
-        N.B. __aiter__ must be a normal method, so need to initialise async run manager
+        N.B. __aiter__ must be a normal method, so need to initialize async run manager
         on first __anext__ call where we can await it
         """
         logger.debug("Initialising AgentExecutorIterator (async)")

libs/langchain/langchain/chains/api/news_docs.py

@@ -10,7 +10,7 @@ Request parameters
 
     country | The 2-letter ISO 3166-1 code of the country you want to get headlines for. Possible options: ae ar at au be bg br ca ch cn co cu cz de eg fr gb gr hk hu id ie il in it jp kr lt lv ma mx my ng nl no nz ph pl pt ro rs ru sa se sg si sk th tr tw ua us ve za. Note: you can't mix this param with the sources param.
     category | The category you want to get headlines for. Possible options: business entertainment general health science sports technology. Note: you can't mix this param with the sources param.
-    sources | A comma-seperated string of identifiers for the news sources or blogs you want headlines from. Use the /top-headlines/sources endpoint to locate these programmatically or look at the sources index. Note: you can't mix this param with the country or category params.
+    sources | A comma-separated string of identifiers for the news sources or blogs you want headlines from. Use the /top-headlines/sources endpoint to locate these programmatically or look at the sources index. Note: you can't mix this param with the country or category params.
     q | Keywords or a phrase to search for.
     pageSize | int | The number of results to return per page (request). 20 is the default, 100 is the maximum.
     page | int | Use this to page through the results if the total results found is greater than the page size.

libs/langchain/langchain/evaluation/criteria/__init__.py

@@ -11,7 +11,7 @@ chain against specified criteria.
 
 Examples
 --------
-Using a pre-defined criterion:
+Using a predefined criterion:
 >>> from langchain.llms import OpenAI
 >>> from langchain.evaluation.criteria import CriteriaEvalChain
 

libs/langchain/langchain/output_parsers/format_instructions.py

@@ -50,7 +50,7 @@ Make sure to always enclose the YAML output in triple backticks (```)"""
 
 PANDAS_DATAFRAME_FORMAT_INSTRUCTIONS = """The output should be formatted as a string as the operation, followed by a colon, followed by the column or row to be queried on, followed by optional array parameters.
 1. The column names are limited to the possible columns below.
-2. Arrays must either be a comma-seperated list of numbers formatted as [1,3,5], or it must be in range of numbers formatted as [0..4].
+2. Arrays must either be a comma-separated list of numbers formatted as [1,3,5], or it must be in range of numbers formatted as [0..4].
 3. Remember that arrays are optional and not necessarily required.
 4. If the column is not in the possible columns or the operation is not a valid Pandas DataFrame operation, return why it is invalid as a sentence starting with either "Invalid column" or "Invalid operation".
 

libs/langchain/tests/unit_tests/agents/test_agent_iterator.py

@@ -361,7 +361,7 @@ def test_agent_iterator_failing_tool() -> None:
 
     agent_iter = agent.iter(inputs="when was langchain made")
     assert isinstance(agent_iter, AgentExecutorIterator)
-    # initialise iterator
+    # initialize iterator
     iterator = iter(agent_iter)
 
     with pytest.raises(ZeroDivisionError):