style: misc refs work (#33771)

Author: mdrxy

libs/core/langchain_core/agents.py

@@ -118,12 +118,12 @@ class AgentActionMessageLog(AgentAction):
 
 
 class AgentStep(Serializable):
-    """Result of running an AgentAction."""
+    """Result of running an `AgentAction`."""
 
     action: AgentAction
-    """The AgentAction that was executed."""
+    """The `AgentAction` that was executed."""
     observation: Any
-    """The result of the AgentAction."""
+    """The result of the `AgentAction`."""
 
     @property
     def messages(self) -> Sequence[BaseMessage]:

libs/core/langchain_core/exceptions.py

@@ -16,9 +16,10 @@ class OutputParserException(ValueError, LangChainException):  # noqa: N818
     """Exception that output parsers should raise to signify a parsing error.
 
     This exists to differentiate parsing errors from other code or execution errors
-    that also may arise inside the output parser. `OutputParserException` will be
-    available to catch and handle in ways to fix the parsing error, while other
-    errors will be raised.
+    that also may arise inside the output parser.
+
+    `OutputParserException` will be available to catch and handle in ways to fix the
+    parsing error, while other errors will be raised.
     """
 
     def __init__(
@@ -32,18 +33,19 @@ def __init__(
 
         Args:
             error: The error that's being re-raised or an error message.
-            observation: String explanation of error which can be passed to a
-                model to try and remediate the issue.
+            observation: String explanation of error which can be passed to a model to
+                try and remediate the issue.
             llm_output: String model output which is error-ing.
 
             send_to_llm: Whether to send the observation and llm_output back to an Agent
                 after an `OutputParserException` has been raised.
+
                 This gives the underlying model driving the agent the context that the
                 previous output was improperly structured, in the hopes that it will
                 update the output to the correct format.
 
         Raises:
-            ValueError: If `send_to_llm` is True but either observation or
+            ValueError: If `send_to_llm` is `True` but either observation or
                 `llm_output` are not provided.
         """
         if isinstance(error, str):
@@ -66,11 +68,11 @@ class ErrorCode(Enum):
     """Error codes."""
 
     INVALID_PROMPT_INPUT = "INVALID_PROMPT_INPUT"
-    INVALID_TOOL_RESULTS = "INVALID_TOOL_RESULTS"
+    INVALID_TOOL_RESULTS = "INVALID_TOOL_RESULTS"  # Used in JS; not Py (yet)
     MESSAGE_COERCION_FAILURE = "MESSAGE_COERCION_FAILURE"
-    MODEL_AUTHENTICATION = "MODEL_AUTHENTICATION"
-    MODEL_NOT_FOUND = "MODEL_NOT_FOUND"
-    MODEL_RATE_LIMIT = "MODEL_RATE_LIMIT"
+    MODEL_AUTHENTICATION = "MODEL_AUTHENTICATION"  # Used in JS; not Py (yet)
+    MODEL_NOT_FOUND = "MODEL_NOT_FOUND"  # Used in JS; not Py (yet)
+    MODEL_RATE_LIMIT = "MODEL_RATE_LIMIT"  # Used in JS; not Py (yet)
     OUTPUT_PARSING_FAILURE = "OUTPUT_PARSING_FAILURE"
 
 

libs/core/langchain_core/vectorstores/base.py

@@ -237,8 +237,9 @@ def add_documents(self, documents: list[Document], **kwargs: Any) -> list[str]:
         Args:
             documents: Documents to add to the `VectorStore`.
             **kwargs: Additional keyword arguments.
-                if kwargs contains IDs and documents contain ids,
-                the IDs in the kwargs will receive precedence.
+
+                If kwargs contains IDs and documents contain ids, the IDs in the kwargs
+                will receive precedence.
 
         Returns:
             List of IDs of the added texts.
@@ -421,7 +422,7 @@ def similarity_search_with_score(
             **kwargs: Arguments to pass to the search method.
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`.
+            List of tuples of `(doc, similarity_score)`.
         """
         raise NotImplementedError
 
@@ -435,7 +436,7 @@ async def asimilarity_search_with_score(
             **kwargs: Arguments to pass to the search method.
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`.
+            List of tuples of `(doc, similarity_score)`.
         """
         # This is a temporary workaround to make the similarity search
         # asynchronous. The proper solution is to make the similarity search
@@ -465,7 +466,7 @@ def _similarity_search_with_relevance_scores(
                 to filter the resulting set of retrieved docs
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`
+            List of tuples of `(doc, similarity_score)`
         """
         relevance_score_fn = self._select_relevance_score_fn()
         docs_and_scores = self.similarity_search_with_score(query, k, **kwargs)
@@ -492,7 +493,7 @@ async def _asimilarity_search_with_relevance_scores(
                 to filter the resulting set of retrieved docs
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`
+            List of tuples of `(doc, similarity_score)`
         """
         relevance_score_fn = self._select_relevance_score_fn()
         docs_and_scores = await self.asimilarity_search_with_score(query, k, **kwargs)
@@ -516,7 +517,7 @@ def similarity_search_with_relevance_scores(
                 to filter the resulting set of retrieved docs
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`.
+            List of tuples of `(doc, similarity_score)`.
         """
         score_threshold = kwargs.pop("score_threshold", None)
 
@@ -565,7 +566,7 @@ async def asimilarity_search_with_relevance_scores(
                 to filter the resulting set of retrieved docs
 
         Returns:
-            List of Tuples of `(doc, similarity_score)`
+            List of tuples of `(doc, similarity_score)`
         """
         score_threshold = kwargs.pop("score_threshold", None)
 
@@ -667,7 +668,7 @@ def max_marginal_relevance_search(
             k: Number of `Document` objects to return.
             fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             lambda_mult: Number between `0` and `1` that determines the degree
-                of diversity among the results with 0 corresponding
+                of diversity among the results with `0` corresponding
                 to maximum diversity and `1` to minimum diversity.
             **kwargs: Arguments to pass to the search method.
 
@@ -694,7 +695,7 @@ async def amax_marginal_relevance_search(
             k: Number of `Document` objects to return.
             fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             lambda_mult: Number between `0` and `1` that determines the degree
-                of diversity among the results with 0 corresponding
+                of diversity among the results with `0` corresponding
                 to maximum diversity and `1` to minimum diversity.
             **kwargs: Arguments to pass to the search method.
 
@@ -732,7 +733,7 @@ def max_marginal_relevance_search_by_vector(
             k: Number of `Document` objects to return.
             fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             lambda_mult: Number between `0` and `1` that determines the degree
-                of diversity among the results with 0 corresponding
+                of diversity among the results with `0` corresponding
                 to maximum diversity and `1` to minimum diversity.
             **kwargs: Arguments to pass to the search method.
 
@@ -759,7 +760,7 @@ async def amax_marginal_relevance_search_by_vector(
             k: Number of `Document` objects to return.
             fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             lambda_mult: Number between `0` and `1` that determines the degree
-                of diversity among the results with 0 corresponding
+                of diversity among the results with `0` corresponding
                 to maximum diversity and `1` to minimum diversity.
             **kwargs: Arguments to pass to the search method.
 

libs/langchain/langchain_classic/agents/agent.py

@@ -403,8 +403,8 @@ class RunnableAgent(BaseSingleActionAgent):
     """Whether to stream from the runnable or not.
 
     If `True` then underlying LLM is invoked in a streaming fashion to make it possible
-        to get access to the individual LLM tokens when using stream_log with the Agent
-        Executor. If `False` then LLM is invoked in a non-streaming fashion and
+        to get access to the individual LLM tokens when using stream_log with the
+        `AgentExecutor`. If `False` then LLM is invoked in a non-streaming fashion and
         individual LLM tokens will not be available in stream_log.
     """
 
@@ -445,7 +445,7 @@ def plan(
             # Use streaming to make sure that the underlying LLM is invoked in a
             # streaming
             # fashion to make it possible to get access to the individual LLM tokens
-            # when using stream_log with the Agent Executor.
+            # when using stream_log with the AgentExecutor.
             # Because the response from the plan is not a generator, we need to
             # accumulate the output into final output and return that.
             for chunk in self.runnable.stream(inputs, config={"callbacks": callbacks}):
@@ -481,7 +481,7 @@ async def aplan(
             # Use streaming to make sure that the underlying LLM is invoked in a
             # streaming
             # fashion to make it possible to get access to the individual LLM tokens
-            # when using stream_log with the Agent Executor.
+            # when using stream_log with the AgentExecutor.
             # Because the response from the plan is not a generator, we need to
             # accumulate the output into final output and return that.
             async for chunk in self.runnable.astream(
@@ -511,8 +511,8 @@ class RunnableMultiActionAgent(BaseMultiActionAgent):
     """Whether to stream from the runnable or not.
 
     If `True` then underlying LLM is invoked in a streaming fashion to make it possible
-        to get access to the individual LLM tokens when using stream_log with the Agent
-        Executor. If `False` then LLM is invoked in a non-streaming fashion and
+        to get access to the individual LLM tokens when using stream_log with the
+        `AgentExecutor`. If `False` then LLM is invoked in a non-streaming fashion and
         individual LLM tokens will not be available in stream_log.
     """
 
@@ -557,7 +557,7 @@ def plan(
             # Use streaming to make sure that the underlying LLM is invoked in a
             # streaming
             # fashion to make it possible to get access to the individual LLM tokens
-            # when using stream_log with the Agent Executor.
+            # when using stream_log with the AgentExecutor.
             # Because the response from the plan is not a generator, we need to
             # accumulate the output into final output and return that.
             for chunk in self.runnable.stream(inputs, config={"callbacks": callbacks}):
@@ -593,7 +593,7 @@ async def aplan(
             # Use streaming to make sure that the underlying LLM is invoked in a
             # streaming
             # fashion to make it possible to get access to the individual LLM tokens
-            # when using stream_log with the Agent Executor.
+            # when using stream_log with the AgentExecutor.
             # Because the response from the plan is not a generator, we need to
             # accumulate the output into final output and return that.
             async for chunk in self.runnable.astream(

libs/langchain/langchain_classic/agents/agent_iterator.py

@@ -53,9 +53,9 @@ def __init__(
         include_run_info: bool = False,
         yield_actions: bool = False,
     ):
-        """Initialize the AgentExecutorIterator.
+        """Initialize the `AgentExecutorIterator`.
 
-        Initialize the AgentExecutorIterator with the given AgentExecutor,
+        Initialize the `AgentExecutorIterator` with the given `AgentExecutor`,
         inputs, and optional callbacks.
 
         Args:
@@ -91,7 +91,7 @@ def __init__(
 
     @property
     def inputs(self) -> dict[str, str]:
-        """The inputs to the AgentExecutor."""
+        """The inputs to the `AgentExecutor`."""
         return self._inputs
 
     @inputs.setter
@@ -100,7 +100,7 @@ def inputs(self, inputs: Any) -> None:
 
     @property
     def agent_executor(self) -> AgentExecutor:
-        """The AgentExecutor to iterate over."""
+        """The `AgentExecutor` to iterate over."""
         return self._agent_executor
 
     @agent_executor.setter
@@ -171,7 +171,7 @@ def make_final_outputs(
         return prepared_outputs
 
     def __iter__(self: AgentExecutorIterator) -> Iterator[AddableDict]:
-        """Create an async iterator for the AgentExecutor."""
+        """Create an async iterator for the `AgentExecutor`."""
         logger.debug("Initialising AgentExecutorIterator")
         self.reset()
         callback_manager = CallbackManager.configure(
@@ -235,7 +235,7 @@ def __iter__(self: AgentExecutorIterator) -> Iterator[AddableDict]:
         yield self._stop(run_manager)
 
     async def __aiter__(self) -> AsyncIterator[AddableDict]:
-        """Create an async iterator for the AgentExecutor.
+        """Create an async iterator for the `AgentExecutor`.
 
         N.B. __aiter__ must be a normal method, so need to initialize async run manager
         on first __anext__ call where we can await it.

libs/langchain/langchain_classic/agents/openai_assistant/base.py

@@ -231,15 +231,15 @@ def execute_agent(agent, tools, input):
     """
 
     client: Any = Field(default_factory=_get_openai_client)
-    """OpenAI or AzureOpenAI client."""
+    """`OpenAI` or `AzureOpenAI` client."""
     async_client: Any = None
-    """OpenAI or AzureOpenAI async client."""
+    """`OpenAI` or `AzureOpenAI` async client."""
     assistant_id: str
     """OpenAI assistant id."""
     check_every_ms: float = 1_000.0
     """Frequency with which to check run progress in ms."""
     as_agent: bool = False
-    """Use as a LangChain agent, compatible with the AgentExecutor."""
+    """Use as a LangChain agent, compatible with the `AgentExecutor`."""
 
     @model_validator(mode="after")
     def _validate_async_client(self) -> Self:

libs/partners/nomic/langchain_nomic/embeddings.py

@@ -11,7 +11,7 @@
 
 
 class NomicEmbeddings(Embeddings):
-    """NomicEmbeddings embedding model.
+    """`NomicEmbeddings` embedding model.
 
     Example:
         ```python
@@ -66,8 +66,8 @@ def __init__(
         """Initialize `NomicEmbeddings` model.
 
         Args:
-            model: model name
-            nomic_api_key: optionally, set the Nomic API key. Uses the `NOMIC_API_KEY`
+            model: Model name
+            nomic_api_key: Optionally, set the Nomic API key. Uses the `NOMIC_API_KEY`
                 environment variable by default.
             dimensionality: The embedding dimension, for use with Matryoshka-capable
                 models. Defaults to full-size.
@@ -76,7 +76,12 @@ def __init__(
             device: The device to use for local embeddings. Choices include
                 `'cpu'`, `'gpu'`, `'nvidia'`, `'amd'`, or a specific device
                 name. See the docstring for `GPT4All.__init__` for more info.
-                Typically defaults to `'cpu'`. Do not use on macOS.
+
+                Typically defaults to `'cpu'`.
+
+                !!! warning
+
+                    Do not use on macOS.
             vision_model: The vision model to use for image embeddings.
 
         """
@@ -93,8 +98,8 @@ def embed(self, texts: list[str], *, task_type: str) -> list[list[float]]:
         """Embed texts.
 
         Args:
-            texts: list of texts to embed
-            task_type: the task type to use when embedding. One of `'search_query'`,
+            texts: List of texts to embed
+            task_type: The task type to use when embedding. One of `'search_query'`,
                 `'search_document'`, `'classification'`, `'clustering'`
 
         """
@@ -112,7 +117,7 @@ def embed_documents(self, texts: list[str]) -> list[list[float]]:
         """Embed search docs.
 
         Args:
-            texts: list of texts to embed as documents
+            texts: List of texts to embed as documents
 
         """
         return self.embed(
@@ -124,7 +129,7 @@ def embed_query(self, text: str) -> list[float]:
         """Embed query text.
 
         Args:
-            text: query text
+            text: Query text
 
         """
         return self.embed(
@@ -136,7 +141,7 @@ def embed_image(self, uris: list[str]) -> list[list[float]]:
         """Embed images.
 
         Args:
-            uris: list of image URIs to embed
+            uris: List of image URIs to embed
         """
         return embed.image(
             images=uris,

libs/partners/ollama/tests/integration_tests/chat_models/test_chat_models.py

@@ -40,7 +40,7 @@ def test_init_model_not_found(mock_list: MagicMock) -> None:
 
 @patch("langchain_ollama.chat_models.Client.list")
 def test_init_connection_error(mock_list: MagicMock) -> None:
-    """Test that a ValidationError is raised on connect failure during init."""
+    """Test that a `ValidationError` is raised on connect failure during init."""
     mock_list.side_effect = ConnectError("Test connection error")
 
     with pytest.raises(ValidationError) as excinfo: