support data: in URL for memory. Add ootb support for pdfs

llama_toolchain/memory/api/api.py

@@ -8,7 +8,9 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-
+import base64
+import mimetypes
+import os
 from typing import List, Optional, Protocol
 
 from llama_models.schema_utils import json_schema_type, webmethod
@@ -23,10 +25,25 @@ from llama_models.llama3.api.datatypes import *  # noqa: F403
 class MemoryBankDocument(BaseModel):
     document_id: str
     content: InterleavedTextMedia | URL
-    mime_type: str
+    mime_type: str | None = None
     metadata: Dict[str, Any] = Field(default_factory=dict)
 
 
+def data_url_from_file(file_path: str) -> URL:
+    if not os.path.exists(file_path):
+        raise FileNotFoundError(f"File not found: {file_path}")
+
+    with open(file_path, "rb") as file:
+        file_content = file.read()
+
+    base64_content = base64.b64encode(file_content).decode("utf-8")
+    mime_type, _ = mimetypes.guess_type(file_path)
+
+    data_url = f"data:{mime_type};base64,{base64_content}"
+
+    return URL(uri=data_url)
+
+
 @json_schema_type
 class MemoryBankType(Enum):
     vector = "vector"