From c3394288bb3e40dd57c05e693203be8be8146cc3 Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Mon, 29 Jun 2026 09:05:54 +0200
Subject: [PATCH] fix: repair Mistral OCR async upload
 (aiohttp.streams.FilePayload removed) (#25779)

_upload_file_async built its multipart body with
`aiohttp.streams.FilePayload(...)`, which no longer exists in aiohttp
(payload classes live in aiohttp.payload, and there is no FilePayload).
The reference sits inside a lazy closure, so import succeeds and only the
async Mistral OCR file-upload path blows up at runtime with
AttributeError on every call.

Mirror the working sync path: open the file in a context manager and let
MultipartWriter.append(file_obj, {...}) build a streaming
BufferedReaderPayload, with the POST issued inside the open() block so
the handle stays valid for the whole upload. Preserves the streaming /
memory-efficiency intent.

Found via the dependency-contract test suite (unit/deps/test_aiohttp.py),
which pins aiohttp.streams.FilePayload as absent.
---
 .../open_webui/retrieval/loaders/mistral.py   | 45 +++++++++----------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/backend/open_webui/retrieval/loaders/mistral.py b/backend/open_webui/retrieval/loaders/mistral.py
index 465ea5d91e..5e30160c47 100644
--- a/backend/open_webui/retrieval/loaders/mistral.py
+++ b/backend/open_webui/retrieval/loaders/mistral.py
@@ -261,33 +261,32 @@ class MistralLoader:
         url = f'{self.base_url}/files'
 
         async def upload_request():
-            # Create multipart writer for streaming upload
-            writer = aiohttp.MultipartWriter('form-data')
+            # Open inside the request so the handle stays valid for the whole
+            # streamed POST and is closed right after.
+            with open(self.file_path, 'rb') as f:
+                writer = aiohttp.MultipartWriter('form-data')
 
-            # Add purpose field
-            purpose_part = writer.append('ocr')
-            purpose_part.set_content_disposition('form-data', name='purpose')
+                # Add purpose field
+                purpose_part = writer.append('ocr')
+                purpose_part.set_content_disposition('form-data', name='purpose')
 
-            # Add file part with streaming
-            file_part = writer.append_payload(
-                aiohttp.streams.FilePayload(
-                    self.file_path,
-                    filename=self.file_name,
-                    content_type='application/pdf',
-                )
-            )
-            file_part.set_content_disposition('form-data', name='file', filename=self.file_name)
+                # Stream the file. aiohttp builds a payload from the file object;
+                # the previous aiohttp.streams.FilePayload was removed upstream
+                # (payloads live in aiohttp.payload and there is no FilePayload),
+                # so this path raised AttributeError on every async OCR upload.
+                file_part = writer.append(f, {'Content-Type': 'application/pdf'})
+                file_part.set_content_disposition('form-data', name='file', filename=self.file_name)
 
-            self._debug_log(f'Uploading file: {self.file_name} ({self.file_size:,} bytes)')
+                self._debug_log(f'Uploading file: {self.file_name} ({self.file_size:,} bytes)')
 
-            async with session.post(
-                url,
-                data=writer,
-                headers=self.headers,
-                timeout=aiohttp.ClientTimeout(total=self.upload_timeout),
-                ssl=AIOHTTP_CLIENT_SESSION_SSL,
-            ) as response:
-                return await self._handle_response_async(response)
+                async with session.post(
+                    url,
+                    data=writer,
+                    headers=self.headers,
+                    timeout=aiohttp.ClientTimeout(total=self.upload_timeout),
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
+                ) as response:
+                    return await self._handle_response_async(response)
 
         response_data = await self._retry_request_async(upload_request)