feat: Add example script about routing metadata to converters in inde…

…xing pipelines (#6702)

* support single metadata dict in markdown2document

* reno

* unwrap list

* direct key access

* typing

* add example of indexing pipeline using Multiplexer

* reno

examples/pipelines/indexing_pipeline_with_meta.py

@@ -0,0 +1,43 @@
+from typing import Dict, Any
+from pathlib import Path
+from datetime import datetime
+
+from haystack import Pipeline
+from haystack.components.others import Multiplexer
+from haystack.components.converters import PyPDFToDocument, TextFileToDocument
+from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
+from haystack.components.routers import FileTypeRouter, DocumentJoiner
+from haystack.components.writers import DocumentWriter
+from haystack.document_stores import InMemoryDocumentStore
+
+
+document_store = InMemoryDocumentStore()
+
+p = Pipeline()
+p.add_component(instance=FileTypeRouter(mime_types=["text/plain", "application/pdf"]), name="file_type_router")
+p.add_component(instance=Multiplexer(Dict[str, Any]), name="metadata_multiplexer")
+p.add_component(instance=TextFileToDocument(), name="text_file_converter")
+p.add_component(instance=PyPDFToDocument(), name="pdf_file_converter")
+p.add_component(instance=DocumentJoiner(), name="joiner")
+p.add_component(instance=DocumentCleaner(), name="cleaner")
+p.add_component(instance=DocumentSplitter(split_by="sentence", split_length=250, split_overlap=30), name="splitter")
+p.add_component(instance=DocumentWriter(document_store=document_store), name="writer")
+
+p.connect("file_type_router.text/plain", "text_file_converter.sources")
+p.connect("file_type_router.application/pdf", "pdf_file_converter.sources")
+p.connect("metadata_multiplexer", "text_file_converter.meta")
+p.connect("metadata_multiplexer", "pdf_file_converter.meta")
+p.connect("text_file_converter.documents", "joiner.documents")
+p.connect("pdf_file_converter.documents", "joiner.documents")
+p.connect("joiner.documents", "cleaner.documents")
+p.connect("cleaner.documents", "splitter.documents")
+p.connect("splitter.documents", "writer.documents")
+
+result = p.run(
+    {
+        "file_type_router": {"sources": list(Path(".").iterdir())},
+        "metadata_multiplexer": {"value": {"date_added": datetime.now().isoformat()}},
+    }
+)
+
+assert all("date_added" in doc.meta for doc in document_store.filter_documents())

releasenotes/notes/route-meta-to-converters-ed85acc43b5aa96a.yaml

@@ -0,0 +1,3 @@
+---
+enhancements:
+  - Add example script about how to use Multiplexer to route meta to file converters.