updated smol agents app

Gradio_UI.py

@@ -265,7 +265,7 @@ class GradioUI:
             stored_messages = gr.State([])
             file_uploads_log = gr.State([])
             chatbot = gr.Chatbot(
-                label="Agent",
+                label="Post Card Generator Agent",
                 type="messages",
                 avatar_images=(
                     None,

README.md

@@ -1,8 +1,8 @@
 ---
-title: First Agent Template
-emoji: ⚡
-colorFrom: pink
-colorTo: yellow
+title: Post Card Generator
+emoji: ✉️
+colorFrom: orange
+colorTo: green
 sdk: gradio
 sdk_version: 5.15.0
 app_file: app.py

app.py

@@ -1,22 +1,30 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
 import datetime
-import requests
+
 import pytz
 import yaml
-from tools.final_answer import FinalAnswerTool
+from huggingface_hub import InferenceClient
+from smolagents import CodeAgent, HfApiModel, tool, Tool
 
 from Gradio_UI import GradioUI
+from tools.final_answer import FinalAnswerTool
+
+
+class TextToImageTool(Tool):
+    description = "This tool creates an image according to a prompt, which is a text description."
+    name = "image_generator"
+    inputs = {"prompt":
+                  {"type": "string",
+                   "description": "The image generator prompt. Don't hesitate to add details in the prompt to make the image look better, like 'high-res, photorealistic', etc."}
+              }
+    output_type = "image"
+    model_sdxl = "black-forest-labs/FLUX.1-schnell"
+    client = InferenceClient(model_sdxl)
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
-@tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
-    Args:
-        arg1: the first argument
-        arg2: the second argument
-    """
-    return "What magic will you build ?"
+
+    def forward(self, prompt):
+        updated_prompt = prompt + ". Don't use duplicate or overlapping texts. Make sure words used in the image are correctly spelled."
+        print(updated_prompt)
+        return self.client.text_to_image(updated_prompt)
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
@@ -41,21 +49,21 @@ final_answer = FinalAnswerTool()
 
 model = HfApiModel(
 max_tokens=2096,
-temperature=0.5,
+temperature=0.1,
 model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
 custom_role_conversions=None,
 )
 
 
 # Import tool from Hub
-image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
-
+# image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
+image_generation_tool = TextToImageTool()
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[image_generation_tool,final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,