Add new supported file types to ToMarkdown (cloudflare#25344)

* Add new supported file formats to ToMarkdown documentation

* Added changelog entries for new supported types

* Removed changelog entry for Workers AI, added release not for AutoRAG

* Use active voice in release notes

Author: Naapperas

src/content/partials/workers-ai/markdown-conversion-support.mdx

@@ -62,24 +62,26 @@
 				Microsoft Office Documents
 			</td>
 			<td colspan="5" rowspan="1">
-				`.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.et`
+				`.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.et`, `.docx`
 			</td>
 			<td colspan="5" rowspan="1">
 				`application/vnd.openxmlformats-officedocument.spreadsheetml.sheet`,
 				`application/vnd.ms-excel.sheet.macroenabled.12`,
 				`application/vnd.ms-excel.sheet.binary.macroenabled.12`,
-				`application/vnd.ms-excel`
+				`application/vnd.ms-excel`,
+				`application/vnd.openxmlformats-officedocument.wordprocessingml.document`
 			</td>
 		</tr>
 		<tr>
 			<td colspan="5" rowspan="1">
 				Open Document Format
 			</td>
 			<td colspan="5" rowspan="1">
-				`.ods`
+				`.ods`, `.odt`
 			</td>
 			<td colspan="5" rowspan="1">
-				`application/vnd.oasis.opendocument.spreadsheet`
+				`application/vnd.oasis.opendocument.spreadsheet`,
+				`application/vnd.oasis.opendocument.text`
 			</td>
 		</tr>
 		<tr>

src/content/release-notes/ai-search.yaml

@@ -7,6 +7,10 @@ entries:
     title: AI Search (formerly AutoRAG) now supports more models
     description: |-
       Connect your provider keys through AI Gateway to use models like from OpenAI and Anthropic for both embeddings and inference. API updates to align with the new name are coming soon, with existing APIs still supported.
+  - publish_date: "2025-09-23"
+    title: Support document file types in AutoRAG
+    description: |-
+      Our [conversion utility](/workers-ai/features/markdown-conversion/) can now convert `.docx` and `.odt` files to Markdown, making these files available to index inside your AutoRAG instance.
   - publish_date: "2025-08-20"
     title: Increased maximum query results to 50
     description: |-

src/content/release-notes/workers-ai.yaml

@@ -10,6 +10,10 @@ entries:
       - [`@cf/pfnet/plamo-embedding-1b`](/workers-ai/models/plamo-embedding-1b) creates embeddings from Japanese text.
       - [`@cf/aisingapore/gemma-sea-lion-v4-27b-it`](/workers-ai/models/gemma-sea-lion-v4-27b-it) is a fine-tuned model that supports multiple South East Asian languages, including Burmese, English, Indonesian, Khmer, Lao, Malay, Mandarin, Tagalog, Tamil, Thai, and Vietnamese.
       - [`@cf/ai4bharat/indictrans2-en-indic-1B`](/workers-ai/models/indictrans2-en-indic-1B) is a translation model that can translate between 22 indic languages, including Bengali, Gujarati, Hindi, Tamil, Sanskrit and even traditionally low-resourced languages like Kashmiri, Manipuri and Sindhi. 
+  - publish_date: "2025-09-23"
+    title: 'New document formats supported by Markdown conversion utility'
+    description: |-
+      - Our [Markdown conversion utility](/workers-ai/features/markdown-conversion/) now supports converting `.docx` and `.odt` files.
   - publish_date: "2025-09-18"
     title: Model Catalog updates (types, EmbeddingGemma, model deprecation)
     description: |-