From 56e5aa4dd9fbd5efcf7836e7323a42867cdad3fc Mon Sep 17 00:00:00 2001
From: Brandon Sharp <8883217+Reverendheat@users.noreply.github.com>
Date: Mon, 3 Jun 2024 16:05:56 -0400
Subject: [PATCH] community[patch]: Airtable to allow for addtl params (#22092)

- [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>
---
 .../document_loaders/airtable.ipynb           |  5 ++-
 .../document_loaders/airtable.py              | 42 +++++++++++--------
 2 files changed, 28 insertions(+), 19 deletions(-)

diff --git a/docs/docs/integrations/document_loaders/airtable.ipynb b/docs/docs/integrations/document_loaders/airtable.ipynb
index 48080be9ffb..fb59c3bbb0a 100644
--- a/docs/docs/integrations/document_loaders/airtable.ipynb
+++ b/docs/docs/integrations/document_loaders/airtable.ipynb
@@ -47,7 +47,8 @@
    "source": [
     "api_key = \"xxx\"\n",
     "base_id = \"xxx\"\n",
-    "table_id = \"xxx\""
+    "table_id = \"xxx\"\n",
+    "view = \"xxx\"  # optional"
    ]
   },
   {
@@ -57,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = AirtableLoader(api_key, table_id, base_id)\n",
+    "loader = AirtableLoader(api_key, table_id, base_id, view=view)\n",
     "docs = loader.load()"
    ]
   },
diff --git a/libs/community/langchain_community/document_loaders/airtable.py b/libs/community/langchain_community/document_loaders/airtable.py
index c39ed1fe630..45487ba2431 100644
--- a/libs/community/langchain_community/document_loaders/airtable.py
+++ b/libs/community/langchain_community/document_loaders/airtable.py
@@ -1,21 +1,29 @@
-from typing import Iterator
+from typing import Any, Iterator
 
+from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 
-from langchain_community.document_loaders.base import BaseLoader
-
 
 class AirtableLoader(BaseLoader):
     """Load the `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"""
+    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
-        """Airtable API token."""
         self.table_id = table_id
-        """Airtable table ID."""
         self.base_id = base_id
-        """Airtable base ID."""
+        self.kwargs = kwargs
 
     def lazy_load(self) -> Iterator[Document]:
         """Lazy load Documents from table."""
@@ -23,14 +31,14 @@ class AirtableLoader(BaseLoader):
         from pyairtable import Table
 
         table = Table(self.api_token, self.base_id, self.table_id)
-        records = table.all()
+        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={
-                    "source": self.base_id + "_" + self.table_id,
-                    "base_id": self.base_id,
-                    "table_id": self.table_id,
-                },
-            )
+            yield Document(page_content=str(record), metadata=metadata)