Update pydantic compatibility

docs/docs/versions/v0_3/overview.mdx

@@ -0,0 +1,128 @@
+# LangChain Update Announcement
+
+We are excited to announce the 0.3 release of LangChain.
+
+This release was primarily aimed at upgrading LangChain to use Pydantic 2 internally
+which resolves a [number of usability issues](
+https://python.langchain.com/v0.2/docs/how_to/pydantic_compatibility/
+) faced by users that have already migrated to Pydantic 2.
+
+## Context
+
+LangChain has been providing pseudo support for [Pydantic 2 since langchain >= 0.0.267 (August of 2023)](https://github.com/langchain-ai/langchain/discussions/9337)
+via the Pydantic v1 namespace.
+
+Since the `0.0.267` release of LangChain, users have been able to install either Pydantic 1 or Pydantic 2 in their environment and interact with LangChain APIs via Pydantic models constructed using v1 functionality.
+
+Given that Pydantic 1 has reached EOL, we have decided to transition to Pydantic 2 officially in this release. This means that users will no longer be able to install Pydantic 1 or use Pydantic.v1 namespace objects when interacting with LangChain APIs. Users will need to update their code to use only Pydantic 2 features when interacting with LangChain.
+
+
+## Breaking Changes
+
+The breaking changes include:
+
+* Breaking changes arising from the Pydantic 1 to Pydantic 2 transition.
+* Deprecated functionality that was to be removed in the 0.3 release.
+
+## Pydantic Migration guidelines
+
+We refer users to Pydantic's [migration guide](https://docs.pydantic.dev/latest/migration/) for more information on how to transition their own code from Pydantic 1 to Pydantic 2.
+
+In addition, we have provided a list of common issues that users may encounter when using LangChain with Pydantic 2:
+
+### 1. Passing Pydantic objects to LangChain APIs
+
+Users using the following APIs:
+
+* `BaseChatModel.bind_tools`
+* `BaseChatModel.with_structured_output`
+* `Tool.from_function`
+* `StructuredTool.from_function`
+
+should ensure that they are passing Pydantic 2 objects to these APIs rather than
+Pydantic 1 objects (created via the `pydantic.v1` namespace of pydantic 2).
+
+:::caution
+While `v1` objets may be accepted by some of these APIs, users are strongly to
+use Pydantic 2 objects to avoid any potential issues.
+:::
+
+### 2. Sub-classing LangChain models
+
+Any sub-classing from existing LangChain models (e.g., `BaseTool`, `BaseChatModel`, `LLM`)
+should upgrade to use Pydantic 2 features.
+
+For example, any user code that's relying on Pydantic 1 features (e.g., `validator`) should
+be updated to the Pydantic 2 equivalent (e.g., `field_validator`), and any references to
+`pydantic.v1`, `langchain_core.pydantic_v1`, `langchain.pydantic_v1` should be replaced
+with imports from `pydantic`.
+
+```python
+from pydantic.v1 import validator, Field # if pydantic 2 is installed
+# from pydantic import validator, Field # if pydantic 1 is installed
+# from langchain_core.pydantic_v1 import validator, Field
+# from langchain.pydantic_v1 import validator, Field
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @validator('x') # v1 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+```
+
+Should change to:
+
+```python
+from pydantic import Field, field_validator # pydantic v2
+from langchain_core.pydantic_v1 import BaseTool
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @field_validator('x') # v2 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+
+
+CustomTool(
+    name='custom_tool',
+    description="hello",
+    x=1,
+)
+```
+
+### 3. model_rebuild()
+
+When sub-classing from LangChain models, users may need to add relevant imports
+to the file and rebuild the model.
+
+```python
+from langchain_core.output_parsers import BaseOutputParser
+
+
+class FooParser(BaseOutputParser):
+    ...
+```
+
+New code:
+
+```python
+from typing import Optional as Optional
+
+from langchain_core.output_parsers import BaseOutputParser
+
+class FooParser(BaseOutputParser):
+    ...
+
+FooParser.model_rebuild()
+```
+