diff --git a/haystack/components/converters/azure.py b/haystack/components/converters/azure.py
index 0907d053c..60b41fd5b 100644
--- a/haystack/components/converters/azure.py
+++ b/haystack/components/converters/azure.py
@@ -185,7 +185,7 @@ class AzureOCRDocumentConverter:
         docs = [*tables, text]
         return docs
 
-    def _convert_tables(self, result: AnalyzeResult, meta: Optional[Dict[str, Any]]) -> List[Document]:
+    def _convert_tables(self, result: "AnalyzeResult", meta: Optional[Dict[str, Any]]) -> List[Document]:
         """
         Converts the tables extracted by Azure's Document Intelligence service into Haystack Documents.
         :param result: The AnalyzeResult Azure object
@@ -294,7 +294,7 @@ class AzureOCRDocumentConverter:
 
         return converted_tables
 
-    def _convert_to_natural_text(self, result: AnalyzeResult, meta: Optional[Dict[str, Any]]) -> Document:
+    def _convert_to_natural_text(self, result: "AnalyzeResult", meta: Optional[Dict[str, Any]]) -> Document:
         """
         This converts the `AnalyzeResult` object into a single Document. We add "\f" separators between to
         differentiate between the text on separate pages. This is the expected format for the PreProcessor.
diff --git a/releasenotes/notes/AnalyzeResult-forward-declaration-5ed1bd9b6dc62c6f.yaml b/releasenotes/notes/AnalyzeResult-forward-declaration-5ed1bd9b6dc62c6f.yaml
new file mode 100644
index 000000000..15986221c
--- /dev/null
+++ b/releasenotes/notes/AnalyzeResult-forward-declaration-5ed1bd9b6dc62c6f.yaml
@@ -0,0 +1,7 @@
+---
+fixes:
+  - |
+    Forward declaration of `AnalyzeResult` type in `AzureOCRDocumentConverter`.
+
+    `AnalyzeResult` is already imported in a lazy import block.
+    The forward declaration avoids issues when `azure-ai-formrecognizer>=3.2.0b2` is not installed.