update the tutorial 2

T2_tools_define/random_fact.py

@@ -0,0 +1,53 @@
+from typing import Optional
+import requests
+
+from smolagents.agents import ToolCallingAgent
+from smolagents import CodeAgent, HfApiModel, tool
+from huggingface_hub import login
+from smolagents import LiteLLMModel
+
+from dotenv import load_dotenv
+import os
+
+# load .env file
+load_dotenv()
+
+api_key = os.environ.get('API_KEY')
+
+#print(api_key)
+login(api_key)
+
+
+# Select LLM engine to use!
+model = HfApiModel()
+# model = LiteLLMModel(
+#         model_id="ollama_chat/llama3.1",
+#         api_base="http://localhost:11434",  # replace with remote open-ai compatible server if necessary
+#         #api_key="your-api-key",  # replace with API key if necessary
+#         #num_ctx=8192,  # ollama default is 2048 which will often fail horribly. 8192 works for easy tasks, more is better. Check https://huggingface.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator to calculate how much VRAM this will need for the selected model.
+#     )
+
+
+@tool
+def get_random_fact() -> str:
+    """
+    Fetches a random fact from the "uselessfacts.jsph.pl" API.
+    Returns:
+        str: A string containing the random fact or an error message if the request fails.
+    """
+    url = "https://uselessfacts.jsph.pl/random.json?language=en"
+
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+
+        data = response.json()
+
+        return f"Random Fact: {data['text']}"
+    except requests.exceptions.RequestException as e:
+        return f"Error fetching random fact: {str(e)}"
+
+agent = ToolCallingAgent(tools=[get_random_fact], model=model)
+# agent = CodeAgent(tools=[get_weather], model=model)
+
+agent.run("Tell me a random fact!")

T2_tools_define/wiki_tools.py

@@ -0,0 +1,61 @@
+from typing import Optional
+import requests
+
+from smolagents.agents import ToolCallingAgent
+from smolagents import CodeAgent, HfApiModel, tool
+from huggingface_hub import login
+from smolagents import LiteLLMModel
+
+from dotenv import load_dotenv
+import os
+
+# load .env file
+load_dotenv()
+
+api_key = os.environ.get('API_KEY')
+
+#print(api_key)
+login(api_key)
+
+
+# Select LLM engine to use!
+model = HfApiModel()
+# model = LiteLLMModel(
+#         model_id="ollama_chat/llama3.1",
+#         api_base="http://localhost:11434",  # replace with remote open-ai compatible server if necessary
+#         #api_key="your-api-key",  # replace with API key if necessary
+#         #num_ctx=8192,  # ollama default is 2048 which will often fail horribly. 8192 works for easy tasks, more is better. Check https://huggingface.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator to calculate how much VRAM this will need for the selected model.
+#     )
+
+
+@tool
+def search_wikipedia(query: str) -> str:
+    """
+    Fetches a summary of a Wikipedia page for a given query.
+    Args:
+        query: The search term to look up on Wikipedia.
+    Returns:
+        str: A summary of the Wikipedia page if successful, or an error message if the request fails.
+    Raises:
+        requests.exceptions.RequestException: If there is an issue with the HTTP request.
+    """
+    url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{query}"
+
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+
+        data = response.json()
+        title = data["title"]
+        extract = data["extract"]
+
+        return f"Summary for {title}: {extract}"
+    
+    except requests.exceptions.RequestException as e:
+        return f"Error fetching Wikipedia data: {str(e)}"
+    
+
+agent = ToolCallingAgent(tools=[search_wikipedia], model=model)
+# agent = CodeAgent(tools=[get_weather], model=model)
+
+agent.run("who is the director of the movie inception?")