only for Image to Text

app.py

@@ -12,7 +12,7 @@ if not _omp_threads.isdigit() or int(_omp_threads) < 1:
 
 import torch
 from dotenv import load_dotenv
-from fastapi import FastAPI, File, UploadFile
+from fastapi import FastAPI, Request, UploadFile
 from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 from PIL import Image, UnidentifiedImageError
@@ -354,17 +354,26 @@ def insert_record(collection, payload: dict) -> str:
 
 
 @app.post("/generate-caption")
-async def generate_caption(
-    file: UploadFile | None = File(default=None),
-    files: list[UploadFile] | None = File(default=None),
-):
+async def generate_caption(request: Request):
     _ensure_db_ready()
 
-    uploads = []
-    if files:
-        uploads.extend(files)
-    if file is not None:
-        uploads.append(file)
+    try:
+        form = await request.form()
+    except Exception as exc:
+        raise AppError("Invalid request payload.", 422) from exc
+
+    uploads: list[UploadFile] = []
+    for key in ("files", "files[]", "file"):
+        for value in form.getlist(key):
+            if isinstance(value, UploadFile):
+                uploads.append(value)
+
+    # Fallback for clients that send non-standard multipart keys.
+    if not uploads:
+        for _, value in form.multi_items():
+            if isinstance(value, UploadFile):
+                uploads.append(value)
+
     if not uploads:
         raise AppError("At least one image is required.", 400)
     if len(uploads) > MAX_IMAGES: