mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-08 08:38:48 +00:00
bf5193bb99
Upgrade to using a literal for specifying the extra which is the
recommended approach in pydantic 2.
This works correctly also in pydantic v1.
```python
from pydantic.v1 import BaseModel
class Foo(BaseModel, extra="forbid"):
x: int
Foo(x=5, y=1)
```
And
```python
from pydantic.v1 import BaseModel
class Foo(BaseModel):
x: int
class Config:
extra = "forbid"
Foo(x=5, y=1)
```
## Enum -> literal using grit pattern:
```
engine marzano(0.1)
language python
or {
`extra=Extra.allow` => `extra="allow"`,
`extra=Extra.forbid` => `extra="forbid"`,
`extra=Extra.ignore` => `extra="ignore"`
}
```
Resorted attributes in config and removed doc-string in case we will
need to deal with going back and forth between pydantic v1 and v2 during
the 0.3 release. (This will reduce merge conflicts.)
## Sort attributes in Config:
```
engine marzano(0.1)
language python
function sort($values) js {
return $values.text.split(',').sort().join("\n");
}
class_definition($name, $body) as $C where {
$name <: `Config`,
$body <: block($statements),
$values = [],
$statements <: some bubble($values) assignment() as $A where {
$values += $A
},
$body => sort($values),
}
```
34 lines
980 B
Python
34 lines
980 B
Python
from __future__ import annotations
|
|
|
|
import tempfile
|
|
from typing import TYPE_CHECKING, List
|
|
|
|
from langchain_core.documents import Document
|
|
from langchain_core.pydantic_v1 import BaseModel, Field
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
if TYPE_CHECKING:
|
|
from O365.drive import File
|
|
|
|
CHUNK_SIZE = 1024 * 1024 * 5
|
|
|
|
|
|
class OneDriveFileLoader(BaseLoader, BaseModel):
|
|
"""Load a file from `Microsoft OneDrive`."""
|
|
|
|
file: File = Field(...)
|
|
"""The file to load."""
|
|
|
|
class Config:
|
|
arbitrary_types_allowed = True
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load Documents"""
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
file_path = f"{temp_dir}/{self.file.name}"
|
|
self.file.download(to_path=temp_dir, chunk_size=CHUNK_SIZE)
|
|
loader = UnstructuredFileLoader(file_path)
|
|
return loader.load()
|