mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-04 22:23:50 +00:00
236e957abb
After this PR chat models will correctly handle pydantic 2 with
bind_tools and with_structured_output.
```python
import pydantic
print(pydantic.__version__)
```
2.8.2
```python
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field
class Add(BaseModel):
x: int
y: int
model = ChatOpenAI().bind_tools([Add])
print(model.invoke('2 + 5').tool_calls)
model = ChatOpenAI().with_structured_output(Add)
print(type(model.invoke('2 + 5')))
```
```
[{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_PNUFa4pdfNOYXxIMHc6ps2Do', 'type': 'tool_call'}]
<class '__main__.Add'>
```
```python
from langchain_openai import ChatOpenAI
from pydantic.v1 import BaseModel, Field
class Add(BaseModel):
x: int
y: int
model = ChatOpenAI().bind_tools([Add])
print(model.invoke('2 + 5').tool_calls)
model = ChatOpenAI().with_structured_output(Add)
print(type(model.invoke('2 + 5')))
```
```python
[{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_hhiHYP441cp14TtrHKx3Upg0', 'type': 'tool_call'}]
<class '__main__.Add'>
```
Addresses issues: https://github.com/langchain-ai/langchain/issues/22782
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
|
||
|---|---|---|
| .. | ||
| _api | ||
| caches | ||
| callbacks | ||
| chat_history | ||
| data | ||
| dependencies | ||
| document_loaders | ||
| documents | ||
| embeddings | ||
| example_selectors | ||
| examples | ||
| fake | ||
| indexing | ||
| language_models | ||
| load | ||
| messages | ||
| output_parsers | ||
| outputs | ||
| prompts | ||
| runnables | ||
| stores | ||
| tracers | ||
| utils | ||
| vectorstores | ||
| __init__.py | ||
| conftest.py | ||
| prompt_file.txt | ||
| stubs.py | ||
| test_globals.py | ||
| test_graph_vectorstores.py | ||
| test_imports.py | ||
| test_messages.py | ||
| test_outputs.py | ||
| test_sys_info.py | ||
| test_tools.py | ||