mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 21:33:31 -04:00
Lance Martin
6e69bfbb28
Many cities have open data portals for events like crime, traffic, etc. Socrata provides an API for many, including SF (e.g., see [here](https://dev.socrata.com/foundry/data.sfgov.org/tmnf-yvry)). This is a new data loader for city data that uses Socrata API.
37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
from typing import Iterator, List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
class AirtableLoader(BaseLoader):
|
|
"""Loader for Airtable tables."""
|
|
|
|
def __init__(self, api_token: str, table_id: str, base_id: str):
|
|
"""Initialize with API token and the IDs for table and base"""
|
|
self.api_token = api_token
|
|
self.table_id = table_id
|
|
self.base_id = base_id
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Lazy load records from table."""
|
|
|
|
from pyairtable import Table
|
|
|
|
table = Table(self.api_token, self.base_id, self.table_id)
|
|
records = table.all()
|
|
for record in records:
|
|
# Need to convert record from dict to str
|
|
yield Document(
|
|
page_content=str(record),
|
|
metadata={
|
|
"source": self.base_id + "_" + self.table_id,
|
|
"base_id": self.base_id,
|
|
"table_id": self.table_id,
|
|
},
|
|
)
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load Table."""
|
|
return list(self.lazy_load())
|