feat(community): Support google cloud storage document loader #7740
+219
−4
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| --- | ||
| hide_table_of_contents: true | ||
| sidebar_class_name: node-only | ||
| --- | ||
|
|
||
| # Google Cloud Storage | ||
|
|
||
| :::tip Compatibility | ||
| Only available on Node.js. | ||
| ::: | ||
|
|
||
| This covers how to load a Google Cloud Storage File into LangChain documents. | ||
|
|
||
| ## Setup | ||
|
|
||
| To use this loader, you'll need to have Unstructured already set up and ready to use at an available URL endpoint. It can also be configured to run locally. | ||
|
|
||
| See the docs [here](/docs/integrations/document_loaders/file_loaders/unstructured) for information on how to do that. | ||
|
|
||
| You'll also need to install the official Google Cloud Storage SDK: | ||
|
|
||
| ```bash npm2yarn | ||
| npm install @langchain/community @langchain/core @google-cloud/storage | ||
| ``` | ||
|
|
||
| ## Usage | ||
|
|
||
| Once Unstructured is configured, you can use the Google Cloud Storage loader to load files and then convert them into a Document. | ||
|
|
||
| import CodeBlock from "@theme/CodeBlock"; | ||
| import Example from "@examples/document_loaders/google_cloud_storage.ts"; | ||
|
|
||
| <CodeBlock language="typescript">{Example}</CodeBlock> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,17 @@ | ||
| import { GoogleCloudStorageLoader } from "@langchain/community/document_loaders/web/google_cloud_storage"; | ||
|
|
||
| const loader = new GoogleCloudStorageLoader({ | ||
| bucket: "my-bucket-123", | ||
| file: "path/to/file.pdf", | ||
| storageOptions: { | ||
| keyFilename: "/path/to/keyfile.json", | ||
| }, | ||
| unstructuredLoaderOptions: { | ||
| apiUrl: "http://localhost:8000/general/v0/general", | ||
| apiKey: "", // this will be soon required | ||
| }, | ||
| }); | ||
|
|
||
| const docs = await loader.load(); | ||
|
|
||
| console.log(docs); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,104 @@ | ||
| import { Storage, StorageOptions } from "@google-cloud/storage"; | ||
| import * as os from "node:os"; | ||
| import * as path from "node:path"; | ||
| import * as fsDefault from "node:fs"; | ||
| import { BaseDocumentLoader } from "@langchain/core/document_loaders/base"; | ||
| import { Document } from "@langchain/core/documents"; | ||
| import { | ||
| UnstructuredLoaderOptions, | ||
| UnstructuredLoader, | ||
| } from "../fs/unstructured.js"; | ||
|
|
||
| /** | ||
| * Represents the parameters for the GoogleCloudStorageLoader class. It includes | ||
| * properties such as the GCS bucket, file destination, the options for the UnstructuredLoader and | ||
| * the options for Google Cloud Storage | ||
| */ | ||
| export type GcsLoaderConfig = { | ||
| fs?: typeof fsDefault; | ||
| bucket: string; | ||
| file: string; | ||
| unstructuredLoaderOptions: UnstructuredLoaderOptions; | ||
| storageOptions: StorageOptions; | ||
| }; | ||
|
|
||
| /** | ||
| * A class that extends the BaseDocumentLoader class. It represents a | ||
| * document loader for loading files from a google cloud storage bucket. | ||
| * @example | ||
| * ```typescript | ||
| * const loader = new GoogleCloudStorageLoader({ | ||
| * bucket: "<my-bucket-name>", | ||
| * file: "<file-path>", | ||
| * storageOptions: { | ||
| * keyFilename: "<key-file-name-path>" | ||
| * } | ||
| * unstructuredConfig: { | ||
| * apiUrl: "<unstructured-API-URL>", | ||
| * apiKey: "<unstructured-API-key>" | ||
| * } | ||
| * }); | ||
| * const docs = await loader.load(); | ||
| * ``` | ||
| */ | ||
| export class GoogleCloudStorageLoader extends BaseDocumentLoader { | ||
| private bucket: string; | ||
|
|
||
| private file: string; | ||
|
|
||
| private storageOptions: StorageOptions; | ||
|
|
||
| private _fs: typeof fsDefault; | ||
|
|
||
| private unstructuredLoaderOptions: UnstructuredLoaderOptions; | ||
|
|
||
| constructor({ | ||
| fs = fsDefault, | ||
| file, | ||
| bucket, | ||
| unstructuredLoaderOptions, | ||
| storageOptions, | ||
| }: GcsLoaderConfig) { | ||
| super(); | ||
| this._fs = fs; | ||
| this.bucket = bucket; | ||
| this.file = file; | ||
| this.unstructuredLoaderOptions = unstructuredLoaderOptions; | ||
| this.storageOptions = storageOptions; | ||
| } | ||
|
|
||
| async load(): Promise<Document<Record<string, any>>[]> { | ||
| const tempDir = this._fs.mkdtempSync( | ||
|
There was a problem hiding this comment. nit: could we do this without the filesystem as a passthrough? |
||
| path.join(os.tmpdir(), "googlecloudstoragefileloader-") | ||
| ); | ||
| const filePath = path.join(tempDir, this.file); | ||
|
|
||
| try { | ||
| const storage = new Storage(this.storageOptions); | ||
| const bucket = storage.bucket(this.bucket); | ||
|
|
||
| const [buffer] = await bucket.file(this.file).download(); | ||
| this._fs.mkdirSync(path.dirname(filePath), { recursive: true }); | ||
|
|
||
| this._fs.writeFileSync(filePath, buffer); | ||
| // eslint-disable-next-line @typescript-eslint/no-explicit-any | ||
| } catch (e: any) { | ||
| throw new Error( | ||
| `Failed to download file ${this.file} from google cloud storage bucket ${this.bucket}: ${e.message}` | ||
| ); | ||
| } | ||
|
|
||
| try { | ||
| const unstructuredLoader = new UnstructuredLoader( | ||
| filePath, | ||
| this.unstructuredLoaderOptions | ||
| ); | ||
| const docs = await unstructuredLoader.load(); | ||
| return docs; | ||
| } catch { | ||
| throw new Error( | ||
| `Failed to load file ${filePath} using unstructured loader.` | ||
| ); | ||
| } | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
StorageOptions seems to be used just for authentication. Does this also work with Application Default Credentials? If so - this should be an optional field.