Package dev.langchain4j.data.document.loader.gcs

Class GoogleCloudStorageDocumentLoader

java.lang.Object

dev.langchain4j.data.document.loader.gcs.GoogleCloudStorageDocumentLoader

public class GoogleCloudStorageDocumentLoader
extends Object

Google Cloud Storage Document Loader to load documents from Google Cloud Storage buckets.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	GoogleCloudStorageDocumentLoader.Builder

Method Summary

Modifier and Type	Method	Description
static GoogleCloudStorageDocumentLoader.Builder	builder()
Document	loadDocument(String bucket, String objectName, DocumentParser parser)	Loads a single document from the specified Google Cloud Storage bucket based on the specified object key.
List<Document>	loadDocuments(String bucket, DocumentParser parser)	Loads all documents from an GCS bucket.
List<Document>	loadDocuments(String bucket, String globPattern, DocumentParser parser)	Load a list of documents from the specified bucket, filtered with a glob pattern.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

loadDocument

public Document loadDocument(String bucket,
 String objectName,
 DocumentParser parser)

Loads a single document from the specified Google Cloud Storage bucket based on the specified object key.

Parameters:

bucket - GCS bucket to load from.

objectName - The key of the GCS object which should be loaded.

parser - The parser to be used for parsing text from the object.

Returns:

A document containing the content of the GCS object.

loadDocuments

public List<Document> loadDocuments(String bucket,
 String globPattern,
 DocumentParser parser)

Load a list of documents from the specified bucket, filtered with a glob pattern.

Parameters:

bucket - the bucket to load files from

globPattern - filter only files matching the glob pattern, see https://cloud.google.com/storage/docs/json_api/v1/objects/list#list-object-glob

parser - the parser to use to parse the document

Returns:

A list of documents from the bucket that match the glob pattern.

loadDocuments

public List<Document> loadDocuments(String bucket,
 DocumentParser parser)

Loads all documents from an GCS bucket.

Parameters:

bucket - the bucket to load from.

parser - The parser to be used for parsing text from the object.

Returns:

A list of documents.

builder

public static GoogleCloudStorageDocumentLoader.Builder builder()