Create Airtable loader (#5958)

Create document loader for Airtable

docs/modules/indexes/document_loaders.rst

@@ -30,6 +30,7 @@ For detailed instructions on how to get set up with Unstructured, see installati
    :maxdepth: 1
    :glob:
 
+   ./document_loaders/examples/airtable.ipynb
    ./document_loaders/examples/audio.ipynb
    ./document_loaders/examples/conll-u.ipynb
    ./document_loaders/examples/copypaste.ipynb

docs/modules/indexes/document_loaders/examples/airtable.ipynb

@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ae421e6",
+   "metadata": {},
+   "source": [
+    "# Airtable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98aea00d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install pyairtable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "592483eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import AirtableLoader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "637e1205",
+   "metadata": {},
+   "source": [
+    "* Get your API key [here](https://support.airtable.com/docs/creating-and-using-api-keys-and-access-tokens).\n",
+    "* Get ID of your base [here](https://airtable.com/developers/web/api/introduction).\n",
+    "* Get your table ID from the table url as shown [here](https://www.highviewapps.com/kb/where-can-i-find-the-airtable-base-id-and-table-id/#:~:text=Both%20the%20Airtable%20Base%20ID,URL%20that%20begins%20with%20tbl)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c12a7aff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "api_key=\"xxx\"\n",
+    "base_id=\"xxx\"\n",
+    "table_id=\"xxx\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ccddd5a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = AirtableLoader(api_key,table_id,base_id)\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae76c25c",
+   "metadata": {},
+   "source": [
+    "Returns each table row as `dict`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7abec7ce",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "403c95da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'id': 'recF3GbGZCuh9sXIQ',\n",
+       " 'createdTime': '2023-06-09T04:47:21.000Z',\n",
+       " 'fields': {'Priority': 'High',\n",
+       "  'Status': 'In progress',\n",
+       "  'Name': 'Document Splitters'}}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "eval(docs[0].page_content)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/document_loaders/__init__.py

@@ -1,6 +1,7 @@
 """All different types of document loaders."""
 
 from langchain.document_loaders.airbyte_json import AirbyteJSONLoader
+from langchain.document_loaders.airtable import AirtableLoader
 from langchain.document_loaders.apify_dataset import ApifyDatasetLoader
 from langchain.document_loaders.arxiv import ArxivLoader
 from langchain.document_loaders.azlyrics import AZLyricsLoader
@@ -135,6 +136,7 @@ TelegramChatLoader = TelegramChatFileLoader
 __all__ = [
     "AZLyricsLoader",
     "AirbyteJSONLoader",
+    "AirtableLoader",
     "ApifyDatasetLoader",
     "ArxivLoader",
     "AzureBlobStorageContainerLoader",

langchain/document_loaders/airtable.py

@@ -0,0 +1,36 @@
+from typing import Iterator, List
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+
+
+class AirtableLoader(BaseLoader):
+    """Loader that loads local airbyte json files."""
+
+    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]:
+        """Load 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())