docs: Spell check fixes (#24217)

**Description:** Spell check fixes for docs, comments, and a couple of
strings. No code change e.g. variable names.
**Issue:** none
**Dependencies:** none
**Twitter handle:** hmartin

docs/api_reference/create_api_rst.py

@@ -78,7 +78,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            # The clasification of the class is used to select a template
+            # The type of the class is used to select a template
             # for the object when rendering the documentation.
             # See `templates` directory for defined templates.
             # This is a hacky solution to distinguish between different

docs/docs/concepts.mdx

@@ -821,7 +821,7 @@ We recommend this method as a starting point when working with structured output
 - If multiple underlying techniques are supported, you can supply a `method` parameter to
 [toggle which one is used](/docs/how_to/structured_output/#advanced-specifying-the-method-for-structuring-outputs).
 
-You may want or need to use other techiniques if:
+You may want or need to use other techniques if:
 
 - The chat model you are using does not support tool calling.
 - You are working with very complex schemas and the model is having trouble generating outputs that conform.

docs/docs/how_to/index.mdx

@@ -84,7 +84,7 @@ These are the core building blocks you can use when building applications.
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: stream tool calls](/docs/how_to/tool_streaming)
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
-- [How to: bind model-specific formated tools](/docs/how_to/tools_model_specific)
+- [How to: bind model-specific formatted tools](/docs/how_to/tools_model_specific)
 - [How to: force a specific tool call](/docs/how_to/tool_choice)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 

docs/docs/integrations/providers/nvidia.mdx

@@ -61,7 +61,7 @@ When ready to deploy, you can self-host models with NVIDIA NIM—which is includ
 ```python
 from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings, NVIDIARerank
 
-# connect to an chat NIM running at localhost:8000, specifyig a specific model
+# connect to a chat NIM running at localhost:8000, specifying a model
 llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta/llama3-8b-instruct")
 
 # connect to an embedding NIM running at localhost:8080

docs/docs/integrations/providers/premai.md

@@ -202,7 +202,7 @@ Prem Templates are also available for Streaming too.
 
 ## Prem Embeddings
 
-In this section we are going to dicuss how we can get access to different embedding model using `PremEmbeddings` with LangChain. Lets start by importing our modules and setting our API Key. 
+In this section we cover how we can get access to different embedding models using `PremEmbeddings` with LangChain. Let's start by importing our modules and setting our API Key.
 
 ```python
 import os

libs/community/langchain_community/cross_encoders/huggingface.py

@@ -60,7 +60,7 @@ class HuggingFaceCrossEncoder(BaseModel, BaseCrossEncoder):
             List of scores, one for each pair.
         """
         scores = self.client.predict(text_pairs)
-        # Somes models e.g bert-multilingual-passage-reranking-msmarco
+        # Some models e.g bert-multilingual-passage-reranking-msmarco
         # gives two score not_relevant and relevant as compare with the query.
         if len(scores.shape) > 1:  # we are going to get the relevant scores
             scores = map(lambda x: x[1], scores)

libs/community/langchain_community/embeddings/ascend.py

@@ -60,7 +60,7 @@ class AscendEmbeddings(Embeddings, BaseModel):
             raise ValueError("model_path is required")
         if not os.access(values["model_path"], os.F_OK):
             raise FileNotFoundError(
-                f"Unabled to find valid model path in [{values['model_path']}]"
+                f"Unable to find valid model path in [{values['model_path']}]"
             )
         try:
             import torch_npu

libs/community/langchain_community/storage/sql.py

@@ -72,7 +72,7 @@ class SQLStore(BaseStore[str, bytes]):
             from langchain_rag.storage import SQLStore
 
             # Instantiate the SQLStore with the root path
-            sql_store = SQLStore(namespace="test", db_url="sqllite://:memory:")
+            sql_store = SQLStore(namespace="test", db_url="sqlite://:memory:")
 
             # Set values for keys
             sql_store.mset([("key1", b"value1"), ("key2", b"value2")])

libs/community/tests/integration_tests/tools/zenguard/test_zenguard.py

@@ -9,7 +9,7 @@ from langchain_community.tools.zenguard.tool import Detector, ZenGuardTool
 @pytest.fixture()
 def zenguard_tool() -> ZenGuardTool:
     if os.getenv("ZENGUARD_API_KEY") is None:
-        raise ValueError("ZENGUARD_API_KEY is not set in environment varibale")
+        raise ValueError("ZENGUARD_API_KEY is not set in environment variable")
     return ZenGuardTool()
 
 

libs/community/tests/unit_tests/graph_vectorstores/extractors/test_html_link_extractor.py

@@ -12,7 +12,7 @@ PAGE_1 = """
 Hello.
 <a href="relative">Relative</a>
 <a href="/relative-base">Relative base.</a>
-<a href="http://cnn.com">Aboslute</a>
+<a href="http://cnn.com">Absolute</a>
 <a href="//same.foo">Test</a>
 </body>
 </html>

libs/core/langchain_core/documents/base.py

@@ -15,7 +15,7 @@ PathLike = Union[str, PurePath]
 class BaseMedia(Serializable):
     """Use to represent media content.
 
-    Media objets can be used to represent raw data, such as text or binary data.
+    Media objects can be used to represent raw data, such as text or binary data.
 
     LangChain Media objects allow associating metadata and an optional identifier
     with the content.

libs/core/tests/unit_tests/language_models/chat_models/test_cache.py

@@ -279,7 +279,7 @@ class CustomChat(GenericFakeChatModel):
 async def test_can_swap_caches() -> None:
     """Test that we can use a different cache object.
 
-    This test verifies that when we fetch teh llm_string representation
+    This test verifies that when we fetch the llm_string representation
     of the chat model, we can swap the cache object and still get the same
     result.
     """

libs/text-splitters/langchain_text_splitters/character.py

@@ -345,7 +345,7 @@ class RecursiveCharacterTextSplitter(TextSplitter):
             ]
         elif language == Language.ELIXIR:
             return [
-                # Split along method function and module definiton
+                # Split along method function and module definition
                 "\ndef ",
                 "\ndefp ",
                 "\ndefmodule ",