Harrison/add roam loader (#939)

2025-10-11 18:43:25 +00:00 · 2023-02-08 00:35:33 -08:00
parent bc7e56e8df
commit 44ecec3896
15 changed files with 876 additions and 1 deletions
--- a/docs/modules/document_loaders/examples/gcs_directory.ipynb
+++ b/docs/modules/document_loaders/examples/gcs_directory.ipynb
@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0ef41fd4",
+   "metadata": {},
+   "source": [
+    "# GCS Directory\n",
+    "\n",
+    "This covers how to load document objects from an Google Cloud Storage (GCS) directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5cfb25c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GCSDirectoryLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "93a4d0f1",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install google-cloud-storage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "633dc839",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GCSDirectoryLoader(project_name=\"aist\", bucket=\"testing-hwc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a863467d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n",
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpz37njh7u/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17c0dcbb",
+   "metadata": {},
+   "source": [
+    "## Specifying a prefix\n",
+    "You can also specify a prefix for more finegrained control over what files to load."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b3143c89",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = GCSDirectoryLoader(project_name=\"aist\", bucket=\"testing-hwc\", prefix=\"fake\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "226ac6f5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n",
+      "/Users/harrisonchase/workplace/langchain/.venv/lib/python3.10/site-packages/google/auth/_default.py:83: UserWarning: Your application has authenticated using end user credentials from Google Cloud SDK without a quota project. You might receive a \"quota exceeded\" or \"API not enabled\" error. We recommend you rerun `gcloud auth application-default login` and make sure a quota project is added. Or you can use service accounts instead. For more information about service accounts, see https://cloud.google.com/docs/authentication/\n",
+      "  warnings.warn(_CLOUD_SDK_CREDENTIALS_WARNING)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpylg6291i/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9c0734f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}