feat: add File type to preview package (#5873)

* add Blob type

* review feedback

* fix tests and naming

* Update add-blob-type-2a9476a39841f54d.yaml

* removed unused import

---------

Co-authored-by: Stefano Fiorucci <[email protected]>

haystack/preview/dataclasses/__init__.py

@@ -1,4 +1,5 @@
 from haystack.preview.dataclasses.document import Document
 from haystack.preview.dataclasses.answer import ExtractedAnswer, GeneratedAnswer, Answer
+from haystack.preview.dataclasses.byte_stream import ByteStream
 
-__all__ = ["Document", "ExtractedAnswer", "GeneratedAnswer", "Answer"]
+__all__ = ["Document", "ExtractedAnswer", "GeneratedAnswer", "Answer", "ByteStream"]

haystack/preview/dataclasses/byte_stream.py

@@ -0,0 +1,37 @@
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Dict, Any
+
+
+@dataclass(frozen=True)
+class ByteStream:
+    """
+    Base data class representing a binary object in the Haystack API.
+    """
+
+    data: bytes
+    metadata: Dict[str, Any] = field(default_factory=dict, hash=False)
+
+    def to_file(self, destination_path: Path):
+        with open(destination_path, "wb") as fd:
+            fd.write(self.data)
+
+    @classmethod
+    def from_file_path(cls, filepath: Path) -> "ByteStream":
+        """
+        Create a ByteStream from the contents read from a file.
+
+        :param filepath: A valid path to a file.
+        """
+        with open(filepath, "rb") as fd:
+            return cls(data=fd.read())
+
+    @classmethod
+    def from_string(cls, text: str, encoding: str = "utf-8") -> "ByteStream":
+        """
+        Create a ByteStream encoding a string.
+
+        :param text: The string to encode
+        :param encoding: The encoding used to convert the string into bytes
+        """
+        return cls(data=text.encode(encoding))

releasenotes/notes/add-blob-type-2a9476a39841f54d.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Add ByteStream type to send binary raw data across components
+    in a pipeline.

test/preview/dataclasses/test_byte_stream.py

@@ -0,0 +1,33 @@
+import io
+
+from haystack.preview.dataclasses import ByteStream
+
+import pytest
+
+
+@pytest.mark.unit
+def test_from_file_path(tmp_path, request):
+    test_bytes = "Hello, world!\n".encode()
+    test_path = tmp_path / request.node.name
+    with open(test_path, "wb") as fd:
+        assert fd.write(test_bytes)
+
+    b = ByteStream.from_file_path(test_path)
+    assert b.data == test_bytes
+
+
+@pytest.mark.unit
+def test_from_string():
+    test_string = "Hello, world!"
+    b = ByteStream.from_string(test_string)
+    assert b.data.decode() == test_string
+
+
+@pytest.mark.unit
+def test_to_file(tmp_path, request):
+    test_str = "Hello, world!\n"
+    test_path = tmp_path / request.node.name
+
+    ByteStream(test_str.encode()).to_file(test_path)
+    with open(test_path, "rb") as fd:
+        assert fd.read().decode() == test_str