feat: Allow setting metadata for ByteStream when created from file or from string

haystack/dataclasses/byte_stream.py

@@ -3,7 +3,7 @@
 from typing import Optional, Dict, Any
 
 
-@dataclass(frozen=True)
+@dataclass
 class ByteStream:
     """
     Base data class representing a binary object in the Haystack API.
@@ -14,25 +14,38 @@ class ByteStream:
     mime_type: Optional[str] = field(default=None)
 
     def to_file(self, destination_path: Path):
+        """
+        Write the ByteStream to a file. Note: the metadata will be lost.
+
+        :param destination_path: The path to write the ByteStream to.
+        """
         with open(destination_path, "wb") as fd:
             fd.write(self.data)
 
     @classmethod
-    def from_file_path(cls, filepath: Path, mime_type: Optional[str] = None) -> "ByteStream":
+    def from_file_path(
+        cls, filepath: Path, mime_type: Optional[str] = None, meta: Optional[Dict[str, Any]] = None
+    ) -> "ByteStream":
         """
         Create a ByteStream from the contents read from a file.
 
         :param filepath: A valid path to a file.
+        :param mime_type: The mime type of the file.
+        :param meta: Additional metadata to be stored with the ByteStream.
         """
         with open(filepath, "rb") as fd:
-            return cls(data=fd.read(), mime_type=mime_type)
+            return cls(data=fd.read(), mime_type=mime_type, meta=meta or {})
 
     @classmethod
-    def from_string(cls, text: str, encoding: str = "utf-8", mime_type: Optional[str] = None) -> "ByteStream":
+    def from_string(
+        cls, text: str, encoding: str = "utf-8", mime_type: Optional[str] = None, meta: Optional[Dict[str, Any]] = None
+    ) -> "ByteStream":
         """
         Create a ByteStream encoding a string.
 
         :param text: The string to encode
         :param encoding: The encoding used to convert the string into bytes
+        :param mime_type: The mime type of the file.
+        :param meta: Additional metadata to be stored with the ByteStream.
         """
-        return cls(data=text.encode(encoding), mime_type=mime_type)
+        return cls(data=text.encode(encoding), mime_type=mime_type, meta=meta or {})

releasenotes/notes/meta-in-bytestream-a29816c919c0be5a.yaml

@@ -0,0 +1,3 @@
+---
+enhancements:
+  - Add meta parameter to `ByteStream.from_file_path()` and `ByteStream.from_string()`.

test/dataclasses/test_byte_stream.py

@@ -1,9 +1,5 @@
-import io
-
 from haystack.dataclasses import ByteStream
 
-import pytest
-
 
 def test_from_file_path(tmp_path, request):
     test_bytes = "Hello, world!\n".encode()
@@ -19,6 +15,10 @@ def test_from_file_path(tmp_path, request):
     assert b.data == test_bytes
     assert b.mime_type == "text/plain"
 
+    b = ByteStream.from_file_path(test_path, meta={"foo": "bar"})
+    assert b.data == test_bytes
+    assert b.meta == {"foo": "bar"}
+
 
 def test_from_string():
     test_string = "Hello, world!"
@@ -30,6 +30,10 @@ def test_from_string():
     assert b.data.decode() == test_string
     assert b.mime_type == "text/plain"
 
+    b = ByteStream.from_string(test_string, meta={"foo": "bar"})
+    assert b.data.decode() == test_string
+    assert b.meta == {"foo": "bar"}
+
 
 def test_to_file(tmp_path, request):
     test_str = "Hello, world!\n"