[BUG] Introduce parser supplier support in FileSystemDocumentLoader#l…

KaisNeffati · Apr 28, 2024 · 154782e · 154782e
1 parent 608f55b
commit 154782e
Show file tree

Hide file tree

Showing 3 changed files with 278 additions and 14 deletions.
diff --git a/docs/docs/tutorials/7-rag.md b/docs/docs/tutorials/7-rag.md
@@ -181,12 +181,20 @@ List<Document> documents = FileSystemDocumentLoader.loadDocuments("/home/langcha
 List<Document> documents = FileSystemDocumentLoader.loadDocumentsRecursively("/home/langchain4j", new TextDocumentParser());
 ```
 
+The `FileSystemDocumentLoader` supports stateful parsers (ex: `ApacheTikaDocumentParser `), facilitating parser reusability across multiple documents. Users can specify a Supplier for on-demand parser instantiation, ensuring that each document is processed with a fresh instance of the parser.
+
+Here is an example:
+```java
+// Load a single document
+Document document = FileSystemDocumentLoader.loadDocument("/home/langchain4j/file.txt", ApacheTikaDocumentParser::new);
+```
+
+
 You can also load documents without explicitly specifying a `DocumentParser`.
 In this case, a default `DocumentParser` will be used.
 The default one is loaded through SPI (e.g. from `langchain4j-document-parser-apache-tika` or `langchain4j-easy-rag`).
 If no `DocumentParser`s are found through SPI, a `TextDocumentParser` is used as a fallback.
 
-
 ### Document Transformer
 `DocumentTransformer` implementations can perform a variety of tasks such as transforming documents,
 cleaning them, filtering, enriching, etc.