mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
56e5aa4dd9
- [X] **PR title**: "community: added optional params to Airtable table.all()" - [X] **PR message**: - **Description:** Add's **kwargs to AirtableLoader to allow for kwargs: https://pyairtable.readthedocs.io/en/latest/api.html#pyairtable.Table.all - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** parakoopa88 - [X] **Add tests and docs**: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [X] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
from typing import Any, Iterator
|
|
|
|
from langchain_core.document_loaders import BaseLoader
|
|
from langchain_core.documents import Document
|
|
|
|
|
|
class AirtableLoader(BaseLoader):
|
|
"""Load the `Airtable` tables."""
|
|
|
|
def __init__(
|
|
self, api_token: str, table_id: str, base_id: str, **kwargs: Any
|
|
) -> None:
|
|
"""Initialize with API token and the IDs for table and base.
|
|
|
|
Args:
|
|
api_token: Airtable API token.
|
|
table_id: Airtable table ID.
|
|
base_id:
|
|
**kwargs: Additional parameters to pass to Table.all(). Refer to the
|
|
pyairtable documentation for available options:
|
|
https://pyairtable.readthedocs.io/en/latest/api.html#pyairtable.Table.all
|
|
""" # noqa: E501
|
|
self.api_token = api_token
|
|
self.table_id = table_id
|
|
self.base_id = base_id
|
|
self.kwargs = kwargs
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Lazy load Documents from table."""
|
|
|
|
from pyairtable import Table
|
|
|
|
table = Table(self.api_token, self.base_id, self.table_id)
|
|
records = table.all(**self.kwargs)
|
|
for record in records:
|
|
metadata = {
|
|
"source": self.base_id + "_" + self.table_id,
|
|
"base_id": self.base_id,
|
|
"table_id": self.table_id,
|
|
}
|
|
if "view" in self.kwargs:
|
|
metadata["view"] = self.kwargs["view"]
|
|
# Need to convert record from dict to str
|
|
yield Document(page_content=str(record), metadata=metadata)
|