Feat: add VLM-boosted PDF parser (#6278)

### What problem does this PR solve?

Add VLM-boosted PDF parser if VLM is set.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

rag/app/picture.py

@@ -86,4 +86,4 @@ def vision_llm_chunk(binary, vision_model, prompt=None, callback=None):
     except Exception as e:
         callback(-1, str(e))
 
-    return []
+    return ""