refac: audio file handling

backend/open_webui/routers/files.py

@@ -16,6 +16,7 @@ from open_webui.models.files import (
     Files,
 )
 from open_webui.routers.retrieval import ProcessFileForm, process_file
+from open_webui.routers.audio import transcribe
 from open_webui.storage.provider import Storage
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from pydantic import BaseModel
@@ -67,7 +68,22 @@ def upload_file(
         )
 
         try:
-            process_file(request, ProcessFileForm(file_id=id), user=user)
+            if file.content_type in [
+                "audio/mpeg",
+                "audio/wav",
+                "audio/ogg",
+                "audio/x-m4a",
+            ]:
+                file_path = Storage.get_file(file_path)
+                result = transcribe(request, file_path)
+                process_file(
+                    request,
+                    ProcessFileForm(file_id=id, content=result.get("text", "")),
+                    user=user,
+                )
+            else:
+                process_file(request, ProcessFileForm(file_id=id), user=user)
+
             file_item = Files.get_file_by_id(id=id)
         except Exception as e:
             log.exception(e)

backend/open_webui/routers/retrieval.py

@@ -913,7 +913,12 @@ def process_file(
             # Update the content in the file
             # Usage: /files/{file_id}/data/content/update
 
-            VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+            try:
+                # /files/{file_id}/data/content/update
+                VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+            except:
+                # Audio file upload pipeline
+                pass
 
             docs = [
                 Document(

src/lib/components/channel/MessageInput.svelte

@@ -157,22 +157,6 @@
 		}
 
 		files = [...files, fileItem];
-		// Check if the file is an audio file and transcribe/convert it to text file
-		if (['audio/mpeg', 'audio/wav', 'audio/ogg', 'audio/x-m4a'].includes(file['type'])) {
-			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
-				toast.error(`${error}`);
-				return null;
-			});
-
-			if (res) {
-				console.log(res);
-				const blob = new Blob([res.text], { type: 'text/plain' });
-				file = blobToFile(blob, `${file.name}.txt`);
-
-				fileItem.name = file.name;
-				fileItem.size = file.size;
-			}
-		}
 
 		try {
 			// During the file upload, file content is automatically extracted.

src/lib/components/chat/MessageInput.svelte

@@ -174,22 +174,6 @@
 		}
 
 		files = [...files, fileItem];
-		// Check if the file is an audio file and transcribe/convert it to text file
-		if (['audio/mpeg', 'audio/wav', 'audio/ogg', 'audio/x-m4a'].includes(file['type'])) {
-			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
-				toast.error(`${error}`);
-				return null;
-			});
-
-			if (res) {
-				console.log(res);
-				const blob = new Blob([res.text], { type: 'text/plain' });
-				file = blobToFile(blob, `${file.name}.txt`);
-
-				fileItem.name = file.name;
-				fileItem.size = file.size;
-			}
-		}
 
 		try {
 			// During the file upload, file content is automatically extracted.

src/lib/components/workspace/Knowledge/KnowledgeBase.svelte

@@ -133,20 +133,6 @@
 
 		knowledge.files = [...(knowledge.files ?? []), fileItem];
 
-		// Check if the file is an audio file and transcribe/convert it to text file
-		if (['audio/mpeg', 'audio/wav', 'audio/ogg', 'audio/x-m4a'].includes(file['type'])) {
-			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
-				toast.error(`${error}`);
-				return null;
-			});
-
-			if (res) {
-				console.log(res);
-				const blob = new Blob([res.text], { type: 'text/plain' });
-				file = blobToFile(blob, `${file.name}.txt`);
-			}
-		}
-
 		try {
 			const uploadedFile = await uploadFile(localStorage.token, file).catch((e) => {
 				toast.error(`${e}`);