Complete Alfred smolagents

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+import random
+from smolagents import CodeAgent, DuckDuckGoSearchTool, LiteLLMModel
+from langchain_ollama import ChatOllama
+
+# Import our custom tools from their modules
+from tools import WeatherInfoTool, HubStatsTool
+from retriever import load_guest_dataset
+
+# Initialize the Hugging Face model
+model = LiteLLMModel(
+    model_id="ollama_chat/qwen2.5-coder:7b", 
+    api_base="http://localhost:xxxx",
+    temperature=0
+)
+
+# Initialize the web search tool
+search_tool = DuckDuckGoSearchTool()
+
+# Initialize the weather tool
+weather_info_tool = WeatherInfoTool()
+
+# Initialize the Hub stats tool
+hub_stats_tool = HubStatsTool()
+
+# Load the guest dataset and initialize the guest info tool
+guest_info_tool = load_guest_dataset()
+
+# Create Alfred with all the tools
+alfred = CodeAgent(tools=[guest_info_tool, search_tool, hub_stats_tool, weather_info_tool], model=model)
+
+if __name__ == "__main__":
+    # query = "Tell me about 'Lady Ada Lovelace'"
+    # query = "What's the weather like in Paris tonight? Will it be suitable for our fireworks display?"
+    # query = "One of our guests is from Qwen. What can you tell me about their most popular model?"
+    query = "I need to speak with Dr. Nikola Tesla about recent advancements in wireless energy. Can you help me prepare for this conversation?"
+
+    # First interaction
+    # response1 = alfred_with_memory.run("Tell me about Lady Ada Lovelace.")
+    # print("🎩 Alfred's First Response:")
+    # print(response1)
+
+    # # Second interaction (referencing the first)
+    # response2 = alfred_with_memory.run("What projects is she currently working on?", reset=False)
+    # print("🎩 Alfred's Second Response:")
+    # print(response2)
+
+    response = alfred.run(query)
+    print("🎩 Alfred's Response:")
+    print(response)
+    

retriever.py

@@ -0,0 +1,43 @@
+from smolagents import Tool
+import datasets
+
+class GuestInfoRetrieverTool(Tool):
+    name = "guest_info_retriever"
+    description = "Retrieves detailed information about gala guests based on their name or relation."
+    inputs = {
+        "query": {
+            "type": "string",
+            "description": "The name or relation of the guest you want information about."
+        }
+    }
+    output_type = "string"
+
+    def __init__(self, guest_list, **kwargs):
+        super().__init__(**kwargs)
+        self.guest_list = guest_list
+
+    def forward(self, query: str):
+        query = query.lower()
+        # Busca simples por correspondência de texto em qualquer campo
+        results = []
+        for guest in self.guest_list:
+            # Verifica se a query está no nome ou na descrição
+            if query in guest['name'].lower() or query in guest['description'].lower() or query in guest['relation'].lower():
+                info = (f"Name: {guest['name']}\n"
+                        f"Relation: {guest['relation']}\n"
+                        f"Description: {guest['description']}\n"
+                        f"Email: {guest['email']}")
+                results.append(info)
+        
+        if results:
+            # Retorna os 3 primeiros matches
+            return "\n\n---\n\n".join(results[:3])
+        else:
+            return "No matching guest information found."
+
+def load_guest_dataset():
+    # Carrega o dataset da Hugging Face
+    dataset = datasets.load_dataset("agents-course/unit3-invitees", split="train")
+    
+    # Passamos a lista crua de dicionários para a Tool
+    return GuestInfoRetrieverTool(guest_list=list(dataset))

tools.py

@@ -0,0 +1,47 @@
+import random
+from smolagents import Tool
+from huggingface_hub import list_models
+
+class WeatherInfoTool(Tool):
+    name = "weather_info"
+    description = "Fetches dummy weather information for a given location."
+    inputs = {
+        "location": {
+            "type": "string",
+            "description": "The location to get weather information for."
+        }
+    }
+    output_type = "string"
+
+    def forward(self, location: str):
+        weather_conditions = [
+            {"condition": "Rainy", "temp_c": 15},
+            {"condition": "Clear", "temp_c": 25},
+            {"condition": "Windy", "temp_c": 20}
+        ]
+        data = random.choice(weather_conditions)
+        return f"Weather in {location}: {data['condition']}, {data['temp_c']}°C"
+
+class HubStatsTool(Tool):
+    name = "hub_stats"
+    description = "Fetches the most downloaded model from a specific author on the Hugging Face Hub."
+    inputs = {
+        "author": {
+            "type": "string",
+            "description": "The username of the model author/organization to find models from."
+        }
+    }
+    output_type = "string"
+
+    def forward(self, author: str):
+        try:
+            models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))
+            if models:
+                model = models[0]
+                # Usando format para números grandes
+                downloads = getattr(model, 'downloads', 0)
+                return f"The most downloaded model by {author} is {model.id} with {downloads:,} downloads."
+            else:
+                return f"No models found for author {author}."
+        except Exception as e:
+            return f"Error fetching models for {author}: {str(e)}"