langchain-core 1.0.0rc3__py3-none-any.whl → 1.0.2__py3-none-any.whl

langchain_core/example_selectors/semantic_similarity.py

@@ -41,7 +41,7 @@ class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
     """Optional keys to filter input to. If provided, the search is based on
     the input variables instead of all variables."""
     vectorstore_kwargs: dict[str, Any] | None = None
-    """Extra arguments passed to similarity_search function of the vectorstore."""
+    """Extra arguments passed to similarity_search function of the `VectorStore`."""
 
     model_config = ConfigDict(
         arbitrary_types_allowed=True,
@@ -159,7 +159,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
             vectorstore_kwargs: Extra arguments passed to similarity_search function
-                of the vectorstore.
+                of the `VectorStore`.
             vectorstore_cls_kwargs: optional kwargs containing url for vector store
 
         Returns:
@@ -203,7 +203,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
             vectorstore_kwargs: Extra arguments passed to similarity_search function
-                of the vectorstore.
+                of the `VectorStore`.
             vectorstore_cls_kwargs: optional kwargs containing url for vector store
 
         Returns:
@@ -286,12 +286,12 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
             k: Number of examples to select.
-            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
+            fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
             vectorstore_kwargs: Extra arguments passed to similarity_search function
-                of the vectorstore.
+                of the `VectorStore`.
             vectorstore_cls_kwargs: optional kwargs containing url for vector store
 
         Returns:
@@ -333,12 +333,12 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
             embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
             vectorstore_cls: A vector store DB interface class, e.g. FAISS.
             k: Number of examples to select.
-            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
+            fetch_k: Number of `Document` objects to fetch to pass to MMR algorithm.
             input_keys: If provided, the search is based on the input variables
                 instead of all variables.
             example_keys: If provided, keys to filter examples to.
             vectorstore_kwargs: Extra arguments passed to similarity_search function
-                of the vectorstore.
+                of the `VectorStore`.
             vectorstore_cls_kwargs: optional kwargs containing url for vector store
 
         Returns:

langchain_core/exceptions.py

@@ -86,6 +86,6 @@ def create_message(*, message: str, error_code: ErrorCode) -> str:
     """
     return (
         f"{message}\n"
-        "For troubleshooting, visit: https://python.langchain.com/docs/"
-        f"troubleshooting/errors/{error_code.value} "
+        "For troubleshooting, visit: https://docs.langchain.com/oss/python/langchain"
+        f"/errors/{error_code.value} "
     )

langchain_core/indexing/__init__.py

@@ -1,7 +1,7 @@
 """Code to help indexing data into a vectorstore.
 
 This package contains helper logic to help deal with indexing data into
-a vectorstore while avoiding duplicated content and over-writing content
+a `VectorStore` while avoiding duplicated content and over-writing content
 if it's unchanged.
 """
 

langchain_core/indexing/api.py

@@ -304,42 +304,42 @@ def index(
     !!! warning
 
         * In full mode, the loader should be returning
-          the entire dataset, and not just a subset of the dataset.
-          Otherwise, the auto_cleanup will remove documents that it is not
-          supposed to.
+            the entire dataset, and not just a subset of the dataset.
+            Otherwise, the auto_cleanup will remove documents that it is not
+            supposed to.
         * In incremental mode, if documents associated with a particular
-          source id appear across different batches, the indexing API
-          will do some redundant work. This will still result in the
-          correct end state of the index, but will unfortunately not be
-          100% efficient. For example, if a given document is split into 15
-          chunks, and we index them using a batch size of 5, we'll have 3 batches
-          all with the same source id. In general, to avoid doing too much
-          redundant work select as big a batch size as possible.
+            source id appear across different batches, the indexing API
+            will do some redundant work. This will still result in the
+            correct end state of the index, but will unfortunately not be
+            100% efficient. For example, if a given document is split into 15
+            chunks, and we index them using a batch size of 5, we'll have 3 batches
+            all with the same source id. In general, to avoid doing too much
+            redundant work select as big a batch size as possible.
         * The `scoped_full` mode is suitable if determining an appropriate batch size
-          is challenging or if your data loader cannot return the entire dataset at
-          once. This mode keeps track of source IDs in memory, which should be fine
-          for most use cases. If your dataset is large (10M+ docs), you will likely
-          need to parallelize the indexing process regardless.
+            is challenging or if your data loader cannot return the entire dataset at
+            once. This mode keeps track of source IDs in memory, which should be fine
+            for most use cases. If your dataset is large (10M+ docs), you will likely
+            need to parallelize the indexing process regardless.
 
     Args:
         docs_source: Data loader or iterable of documents to index.
         record_manager: Timestamped set to keep track of which documents were
             updated.
-        vector_store: VectorStore or DocumentIndex to index the documents into.
+        vector_store: `VectorStore` or DocumentIndex to index the documents into.
         batch_size: Batch size to use when indexing.
         cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
-              that are associated with source ids that were seen during indexing.
-              Clean up is done continuously during indexing helping to minimize the
-              probability of users seeing duplicated content.
+                that are associated with source IDs that were seen during indexing.
+                Clean up is done continuously during indexing helping to minimize the
+                probability of users seeing duplicated content.
             - full: Delete all documents that have not been returned by the loader
-              during this run of indexing.
-              Clean up runs after all documents have been indexed.
-              This means that users may see duplicated content during indexing.
+                during this run of indexing.
+                Clean up runs after all documents have been indexed.
+                This means that users may see duplicated content during indexing.
             - scoped_full: Similar to Full, but only deletes all documents
-              that haven't been updated AND that are associated with
-              source ids that were seen during indexing.
+                that haven't been updated AND that are associated with
+                source IDs that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
             of the document.
@@ -363,7 +363,7 @@ def index(
             When changing the key encoder, you must change the
             index as well to avoid duplicated documents in the cache.
         upsert_kwargs: Additional keyword arguments to pass to the add_documents
-            method of the VectorStore or the upsert method of the DocumentIndex.
+            method of the `VectorStore` or the upsert method of the DocumentIndex.
             For example, you can use this to specify a custom vector_field:
             upsert_kwargs={"vector_field": "embedding"}
             !!! version-added "Added in version 0.3.10"
@@ -375,10 +375,10 @@ def index(
     Raises:
         ValueError: If cleanup mode is not one of 'incremental', 'full' or None
         ValueError: If cleanup mode is incremental and source_id_key is None.
-        ValueError: If vectorstore does not have
+        ValueError: If `VectorStore` does not have
             "delete" and "add_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If `vectorstore` is not a VectorStore or a DocumentIndex.
+        TypeError: If `vectorstore` is not a `VectorStore` or a DocumentIndex.
         AssertionError: If `source_id` is None when cleanup mode is incremental.
             (should be unreachable code).
     """
@@ -415,7 +415,7 @@ def index(
                 raise ValueError(msg)
 
         if type(destination).delete == VectorStore.delete:
-            # Checking if the vectorstore has overridden the default delete method
+            # Checking if the VectorStore has overridden the default delete method
             # implementation which just raises a NotImplementedError
             msg = "Vectorstore has not implemented the delete method"
             raise ValueError(msg)
@@ -466,11 +466,11 @@ def index(
         ]
 
         if cleanup in {"incremental", "scoped_full"}:
-            # source ids are required.
+            # Source IDs are required.
             for source_id, hashed_doc in zip(source_ids, hashed_docs, strict=False):
                 if source_id is None:
                     msg = (
-                        f"Source ids are required when cleanup mode is "
+                        f"Source IDs are required when cleanup mode is "
                         f"incremental or scoped_full. "
                         f"Document that starts with "
                         f"content: {hashed_doc.page_content[:100]} "
@@ -479,7 +479,7 @@ def index(
                     raise ValueError(msg)
                 if cleanup == "scoped_full":
                     scoped_full_cleanup_source_ids.add(source_id)
-            # source ids cannot be None after for loop above.
+            # Source IDs cannot be None after for loop above.
             source_ids = cast("Sequence[str]", source_ids)
 
         exists_batch = record_manager.exists(
@@ -538,7 +538,7 @@ def index(
         # If source IDs are provided, we can do the deletion incrementally!
         if cleanup == "incremental":
             # Get the uids of the documents that were not returned by the loader.
-            # mypy isn't good enough to determine that source ids cannot be None
+            # mypy isn't good enough to determine that source IDs cannot be None
             # here due to a check that's happening above, so we check again.
             for source_id in source_ids:
                 if source_id is None:
@@ -642,42 +642,42 @@ async def aindex(
     !!! warning
 
         * In full mode, the loader should be returning
-          the entire dataset, and not just a subset of the dataset.
-          Otherwise, the auto_cleanup will remove documents that it is not
-          supposed to.
+            the entire dataset, and not just a subset of the dataset.
+            Otherwise, the auto_cleanup will remove documents that it is not
+            supposed to.
         * In incremental mode, if documents associated with a particular
-          source id appear across different batches, the indexing API
-          will do some redundant work. This will still result in the
-          correct end state of the index, but will unfortunately not be
-          100% efficient. For example, if a given document is split into 15
-          chunks, and we index them using a batch size of 5, we'll have 3 batches
-          all with the same source id. In general, to avoid doing too much
-          redundant work select as big a batch size as possible.
+            source id appear across different batches, the indexing API
+            will do some redundant work. This will still result in the
+            correct end state of the index, but will unfortunately not be
+            100% efficient. For example, if a given document is split into 15
+            chunks, and we index them using a batch size of 5, we'll have 3 batches
+            all with the same source id. In general, to avoid doing too much
+            redundant work select as big a batch size as possible.
         * The `scoped_full` mode is suitable if determining an appropriate batch size
-          is challenging or if your data loader cannot return the entire dataset at
-          once. This mode keeps track of source IDs in memory, which should be fine
-          for most use cases. If your dataset is large (10M+ docs), you will likely
-          need to parallelize the indexing process regardless.
+            is challenging or if your data loader cannot return the entire dataset at
+            once. This mode keeps track of source IDs in memory, which should be fine
+            for most use cases. If your dataset is large (10M+ docs), you will likely
+            need to parallelize the indexing process regardless.
 
     Args:
         docs_source: Data loader or iterable of documents to index.
         record_manager: Timestamped set to keep track of which documents were
             updated.
-        vector_store: VectorStore or DocumentIndex to index the documents into.
+        vector_store: `VectorStore` or DocumentIndex to index the documents into.
         batch_size: Batch size to use when indexing.
         cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
-              that are associated with source ids that were seen during indexing.
-              Clean up is done continuously during indexing helping to minimize the
-              probability of users seeing duplicated content.
+                that are associated with source IDs that were seen during indexing.
+                Clean up is done continuously during indexing helping to minimize the
+                probability of users seeing duplicated content.
             - full: Delete all documents that have not been returned by the loader
-              during this run of indexing.
-              Clean up runs after all documents have been indexed.
-              This means that users may see duplicated content during indexing.
+                during this run of indexing.
+                Clean up runs after all documents have been indexed.
+                This means that users may see duplicated content during indexing.
             - scoped_full: Similar to Full, but only deletes all documents
-              that haven't been updated AND that are associated with
-              source ids that were seen during indexing.
+                that haven't been updated AND that are associated with
+                source IDs that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
             of the document.
@@ -701,7 +701,7 @@ async def aindex(
             When changing the key encoder, you must change the
             index as well to avoid duplicated documents in the cache.
         upsert_kwargs: Additional keyword arguments to pass to the add_documents
-            method of the VectorStore or the upsert method of the DocumentIndex.
+            method of the `VectorStore` or the upsert method of the DocumentIndex.
             For example, you can use this to specify a custom vector_field:
             upsert_kwargs={"vector_field": "embedding"}
             !!! version-added "Added in version 0.3.10"
@@ -713,10 +713,10 @@ async def aindex(
     Raises:
         ValueError: If cleanup mode is not one of 'incremental', 'full' or None
         ValueError: If cleanup mode is incremental and source_id_key is None.
-        ValueError: If vectorstore does not have
+        ValueError: If `VectorStore` does not have
             "adelete" and "aadd_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If `vector_store` is not a VectorStore or DocumentIndex.
+        TypeError: If `vector_store` is not a `VectorStore` or DocumentIndex.
         AssertionError: If `source_id_key` is None when cleanup mode is
             incremental or `scoped_full` (should be unreachable).
     """
@@ -757,7 +757,7 @@ async def aindex(
             type(destination).adelete == VectorStore.adelete
             and type(destination).delete == VectorStore.delete
         ):
-            # Checking if the vectorstore has overridden the default adelete or delete
+            # Checking if the VectorStore has overridden the default adelete or delete
             # methods implementation which just raises a NotImplementedError
             msg = "Vectorstore has not implemented the adelete or delete method"
             raise ValueError(msg)
@@ -815,11 +815,11 @@ async def aindex(
         ]
 
         if cleanup in {"incremental", "scoped_full"}:
-            # If the cleanup mode is incremental, source ids are required.
+            # If the cleanup mode is incremental, source IDs are required.
             for source_id, hashed_doc in zip(source_ids, hashed_docs, strict=False):
                 if source_id is None:
                     msg = (
-                        f"Source ids are required when cleanup mode is "
+                        f"Source IDs are required when cleanup mode is "
                         f"incremental or scoped_full. "
                         f"Document that starts with "
                         f"content: {hashed_doc.page_content[:100]} "
@@ -828,7 +828,7 @@ async def aindex(
                     raise ValueError(msg)
                 if cleanup == "scoped_full":
                     scoped_full_cleanup_source_ids.add(source_id)
-            # source ids cannot be None after for loop above.
+            # Source IDs cannot be None after for loop above.
             source_ids = cast("Sequence[str]", source_ids)
 
         exists_batch = await record_manager.aexists(
@@ -888,7 +888,7 @@ async def aindex(
         if cleanup == "incremental":
             # Get the uids of the documents that were not returned by the loader.
 
-            # mypy isn't good enough to determine that source ids cannot be None
+            # mypy isn't good enough to determine that source IDs cannot be None
             # here due to a check that's happening above, so we check again.
             for source_id in source_ids:
                 if source_id is None:

langchain_core/indexing/base.py

@@ -25,7 +25,7 @@ class RecordManager(ABC):
     The record manager abstraction is used by the langchain indexing API.
 
     The record manager keeps track of which documents have been
-    written into a vectorstore and when they were written.
+    written into a `VectorStore` and when they were written.
 
     The indexing API computes hashes for each document and stores the hash
     together with the write time and the source id in the record manager.
@@ -37,7 +37,7 @@ class RecordManager(ABC):
     already been indexed, and to only index new documents.
 
     The main benefit of this abstraction is that it works across many vectorstores.
-    To be supported, a vectorstore needs to only support the ability to add and
+    To be supported, a `VectorStore` needs to only support the ability to add and
     delete documents by ID. Using the record manager, the indexing API will
     be able to delete outdated documents and avoid redundant indexing of documents
     that have already been indexed.
@@ -45,13 +45,13 @@ class RecordManager(ABC):
     The main constraints of this abstraction are:
 
     1. It relies on the time-stamps to determine which documents have been
-       indexed and which have not. This means that the time-stamps must be
-       monotonically increasing. The timestamp should be the timestamp
-       as measured by the server to minimize issues.
+        indexed and which have not. This means that the time-stamps must be
+        monotonically increasing. The timestamp should be the timestamp
+        as measured by the server to minimize issues.
     2. The record manager is currently implemented separately from the
-       vectorstore, which means that the overall system becomes distributed
-       and may create issues with consistency. For example, writing to
-       record manager succeeds, but corresponding writing to vectorstore fails.
+        vectorstore, which means that the overall system becomes distributed
+        and may create issues with consistency. For example, writing to
+        record manager succeeds, but corresponding writing to `VectorStore` fails.
     """
 
     def __init__(
@@ -460,7 +460,7 @@ class UpsertResponse(TypedDict):
 class DeleteResponse(TypedDict, total=False):
     """A generic response for delete operation.
 
-    The fields in this response are optional and whether the vectorstore
+    The fields in this response are optional and whether the `VectorStore`
     returns them or not is up to the implementation.
     """
 
@@ -508,8 +508,6 @@ class DocumentIndex(BaseRetriever):
     1. Storing document in the index.
     2. Fetching document by ID.
     3. Searching for document using a query.
-
-    !!! version-added "Added in version 0.2.29"
     """
 
     @abc.abstractmethod
@@ -520,40 +518,40 @@ class DocumentIndex(BaseRetriever):
         if it is provided. If the ID is not provided, the upsert method is free
         to generate an ID for the content.
 
-        When an ID is specified and the content already exists in the vectorstore,
+        When an ID is specified and the content already exists in the `VectorStore`,
         the upsert method should update the content with the new data. If the content
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **kwargs: Additional keyword arguments.
 
         Returns:
             A response object that contains the list of IDs that were
-            successfully added or updated in the vectorstore and the list of IDs that
+            successfully added or updated in the `VectorStore` and the list of IDs that
             failed to be added or updated.
         """
 
     async def aupsert(
         self, items: Sequence[Document], /, **kwargs: Any
     ) -> UpsertResponse:
-        """Add or update documents in the vectorstore. Async version of upsert.
+        """Add or update documents in the `VectorStore`. Async version of `upsert`.
 
         The upsert functionality should utilize the ID field of the item
         if it is provided. If the ID is not provided, the upsert method is free
         to generate an ID for the item.
 
-        When an ID is specified and the item already exists in the vectorstore,
+        When an ID is specified and the item already exists in the `VectorStore`,
         the upsert method should update the item with the new data. If the item
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **kwargs: Additional keyword arguments.
 
         Returns:
             A response object that contains the list of IDs that were
-            successfully added or updated in the vectorstore and the list of IDs that
+            successfully added or updated in the `VectorStore` and the list of IDs that
             failed to be added or updated.
         """
         return await run_in_executor(
@@ -570,7 +568,7 @@ class DocumentIndex(BaseRetriever):
         Calling delete without any input parameters should raise a ValueError!
 
         Args:
-            ids: List of ids to delete.
+            ids: List of IDs to delete.
             **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index,
                 or else issue a non-blocking delete etc.
@@ -588,7 +586,7 @@ class DocumentIndex(BaseRetriever):
         Calling adelete without any input parameters should raise a ValueError!
 
         Args:
-            ids: List of ids to delete.
+            ids: List of IDs to delete.
             **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index.
 

langchain_core/indexing/in_memory.py

@@ -23,8 +23,6 @@ class InMemoryDocumentIndex(DocumentIndex):
 
     It provides a simple search API that returns documents by the number of
     counts the given query appears in the document.
-
-    !!! version-added "Added in version 0.2.29"
     """
 
     store: dict[str, Document] = Field(default_factory=dict)
@@ -64,10 +62,10 @@ class InMemoryDocumentIndex(DocumentIndex):
         """Delete by IDs.
 
         Args:
-            ids: List of ids to delete.
+            ids: List of IDs to delete.
 
         Raises:
-            ValueError: If ids is None.
+            ValueError: If IDs is None.
 
         Returns:
             A response object that contains the list of IDs that were successfully

langchain_core/language_models/__init__.py

@@ -6,12 +6,13 @@ LangChain has two main classes to work with language models: chat models and
 **Chat models**
 
 Language models that use a sequence of messages as inputs and return chat messages
-as outputs (as opposed to using plain text). Chat models support the assignment of
-distinct roles to conversation messages, helping to distinguish messages from the AI,
-users, and instructions such as system messages.
+as outputs (as opposed to using plain text).
 
-The key abstraction for chat models is `BaseChatModel`. Implementations
-should inherit from this class.
+Chat models support the assignment of distinct roles to conversation messages, helping
+to distinguish messages from the AI, users, and instructions such as system messages.
+
+The key abstraction for chat models is `BaseChatModel`. Implementations should inherit
+from this class.
 
 See existing [chat model integrations](https://docs.langchain.com/oss/python/integrations/chat).
 

langchain_core/language_models/base.py

@@ -200,14 +200,14 @@ class BaseLanguageModel(
                 pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             **kwargs: Arbitrary additional keyword arguments. These are usually passed
                 to the model provider API call.
 
         Returns:
             An `LLMResult`, which contains a list of candidate `Generation` objects for
-            each input prompt and additional model provider-specific output.
+                each input prompt and additional model provider-specific output.
 
         """
 
@@ -237,14 +237,14 @@ class BaseLanguageModel(
                 pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
-            callbacks: Callbacks to pass through. Used for executing additional
+            callbacks: `Callbacks` to pass through. Used for executing additional
                 functionality, such as logging or streaming, throughout generation.
             **kwargs: Arbitrary additional keyword arguments. These are usually passed
                 to the model provider API call.
 
         Returns:
             An `LLMResult`, which contains a list of candidate `Generation` objects for
-            each input prompt and additional model provider-specific output.
+                each input prompt and additional model provider-specific output.
 
         """
 
@@ -262,15 +262,14 @@ class BaseLanguageModel(
         return self.lc_attributes
 
     def get_token_ids(self, text: str) -> list[int]:
-        """Return the ordered ids of the tokens in a text.
+        """Return the ordered IDs of the tokens in a text.
 
         Args:
             text: The string input to tokenize.
 
         Returns:
-            A list of ids corresponding to the tokens in the text, in order they occur
-            in the text.
-
+            A list of IDs corresponding to the tokens in the text, in order they occur
+                in the text.
         """
         if self.custom_get_token_ids is not None:
             return self.custom_get_token_ids(text)