Add Iugu document loader (#5162)

Create IUGU loader
---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>

docs/modules/indexes/document_loaders.rst

@@ -40,6 +40,8 @@ For detailed instructions on how to get set up with Unstructured, see installati
    ./document_loaders/examples/file_directory.ipynb
    ./document_loaders/examples/html.ipynb
    ./document_loaders/examples/image.ipynb
+   ./document_loaders/examples/iugu.ipynb
+   ./document_loaders/examples/jupyter_notebook.ipynb
    ./document_loaders/examples/json.ipynb
    ./document_loaders/examples/markdown.ipynb
    ./document_loaders/examples/microsoft_powerpoint.ipynb

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

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Iugu\n",
+    "\n",
+    ">[Iugu](https://www.iugu.com/) is a Brazilian services and software as a service (SaaS) company. It offers payment-processing software and application programming interfaces for e-commerce websites and mobile applications.\n",
+    "\n",
+    "This notebook covers how to load data from the `Iugu REST API` into a format that can be ingested into LangChain, along with example usage for vectorization."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "\n",
+    "from langchain.document_loaders import IuguLoader\n",
+    "from langchain.indexes import VectorstoreIndexCreator"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The Iugu API requires an access token, which can be found inside of the Iugu dashboard.\n",
+    "\n",
+    "This document loader also requires a `resource` option which defines what data you want to load.\n",
+    "\n",
+    "Following resources are available:\n",
+    "\n",
+    "`Documentation` [Documentation](https://dev.iugu.com/reference/metadados)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iugu_loader = IuguLoader(\"charges\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a vectorstore retriver from the loader\n",
+    "# see https://python.langchain.com/en/latest/modules/indexes/getting_started.html for more details\n",
+    "\n",
+    "index = VectorstoreIndexCreator().from_loaders([iugu_loader])\n",
+    "iugu_doc_retriever = index.vectorstore.as_retriever()"
+   ]
+  }
+ ],
+ "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": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

langchain/document_loaders/iugu.py

@@ -0,0 +1,41 @@
+"""Loader that fetches data from IUGU"""
+import json
+import urllib.request
+from typing import List, Optional
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+from langchain.utils import get_from_env, stringify_dict
+
+IUGU_ENDPOINTS = {
+    "invoices": "https://api.iugu.com/v1/invoices",
+    "customers": "https://api.iugu.com/v1/customers",
+    "charges": "https://api.iugu.com/v1/charges",
+    "subscriptions": "https://api.iugu.com/v1/subscriptions",
+    "plans": "https://api.iugu.com/v1/plans",
+}
+
+
+class IuguLoader(BaseLoader):
+    def __init__(self, resource: str, api_token: Optional[str] = None) -> None:
+        self.resource = resource
+        api_token = api_token or get_from_env("api_token", "IUGU_API_TOKEN")
+        self.headers = {"Authorization": f"Bearer {api_token}"}
+
+    def _make_request(self, url: str) -> List[Document]:
+        request = urllib.request.Request(url, headers=self.headers)
+
+        with urllib.request.urlopen(request) as response:
+            json_data = json.loads(response.read().decode())
+            text = stringify_dict(json_data)
+            metadata = {"source": url}
+            return [Document(page_content=text, metadata=metadata)]
+
+    def _get_resource(self) -> List[Document]:
+        endpoint = IUGU_ENDPOINTS.get(self.resource)
+        if endpoint is None:
+            return []
+        return self._make_request(endpoint)
+
+    def load(self) -> List[Document]:
+        return self._get_resource()