mm example

multi_modal_agent_example.py

@@ -0,0 +1,12 @@
+from swarms import MultiModalAgent
+
+node = MultiModalAgent()
+
+text = node.run_text("What is your name? Generate a picture of yourself")
+
+img = node.run_img("/image1", "What is this image about?")
+
+chat = node.chat(
+    "What is your name? Generate a picture of yourself. What is this image about?",
+    streaming=True
+)

swarms/agents/multi_modal_visual_agent.py

@@ -1648,7 +1648,7 @@ class MultiModalAgent:
     def run_text(
         self, 
         text: str = None, 
-        language=None
+        language = "english"
     ):
         """Run text through the model"""
 
@@ -1664,7 +1664,7 @@ class MultiModalAgent:
     def run_img(
         self, 
         image_path: str, 
-        language=None
+        language = "english"
     ):
         """If language is None"""
         if language is None:
@@ -1681,7 +1681,7 @@ class MultiModalAgent:
     def chat(
         self,
         msg: str = None,
-        language: str = None,
+        language: str = "english",
         streaming: bool = False
     ):
         """