{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "995f4d22", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/zonca/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n" ] } ], "source": [ "from smolagents import LiteLLMModel\n", "from dotenv import load_dotenv\n", "import os\n", "\n", "load_dotenv()\n", "\n", "# Replace all calls to HfApiModel\n", "llm_model = LiteLLMModel(\n", " model_id=\"gemini/gemini-2.0-flash\", # you can see other model names here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models. It is important to prefix the name with \"gemini/\"\n", " api_key=os.getenv(\"GEMINI_API_KEY\"),\n", " max_tokens=8192\n", ")" ] }, { "cell_type": "code", "execution_count": 2, "id": "38e0f80a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The capital of France is **Paris**.\n", "\n" ] } ], "source": [ "response = llm_model([\n", " {\"role\": \"user\", \"content\": \"What is the capital of France?\"}\n", "])\n", "print(response.content)" ] }, { "cell_type": "code", "execution_count": 7, "id": "939309dd", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
╭──────────────────────────────────────────────────── New run ────────────────────────────────────────────────────╮\n",
       "│                                                                                                                 │\n",
       "│ Call echo with 'hello'                                                                                          │\n",
       "│                                                                                                                 │\n",
       "╰─ HfApiModel - Qwen/Qwen2.5-Coder-32B-Instruct ──────────────────────────────────────────────────────────────────╯\n",
       "
\n" ], "text/plain": [ "\u001b[38;2;212;183;2m╭─\u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[1;38;2;212;183;2mNew run\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╮\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mCall echo with 'hello'\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-Coder-32B-Instruct \u001b[0m\u001b[38;2;212;183;2m─────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Step 1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n",
       "
\n" ], "text/plain": [ "\u001b[38;2;212;183;2m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ \u001b[0m\u001b[1mStep \u001b[0m\u001b[1;36m1\u001b[0m\u001b[38;2;212;183;2m ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
Error in generating model output:\n",
       "InferenceClient.chat_completion() got an unexpected keyword argument 'repo_id'\n",
       "
\n" ], "text/plain": [ "\u001b[1;31mError in generating model output:\u001b[0m\n", "\u001b[1;35mInferenceClient.chat_completion\u001b[0m\u001b[1;31m(\u001b[0m\u001b[1;31m)\u001b[0m\u001b[1;31m got an unexpected keyword argument \u001b[0m\u001b[32m'repo_id'\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
[Step 1: Duration 0.01 seconds]\n",
       "
\n" ], "text/plain": [ "\u001b[2m[Step 1: Duration 0.01 seconds]\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "ename": "AgentGenerationError", "evalue": "Error in generating model output:\nInferenceClient.chat_completion() got an unexpected keyword argument 'repo_id'", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mTypeError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:1266\u001b[39m, in \u001b[36mCodeAgent.step\u001b[39m\u001b[34m(self, memory_step)\u001b[39m\n\u001b[32m 1265\u001b[39m additional_args = {\u001b[33m\"\u001b[39m\u001b[33mgrammar\u001b[39m\u001b[33m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m.grammar} \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.grammar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m {}\n\u001b[32m-> \u001b[39m\u001b[32m1266\u001b[39m chat_message: ChatMessage = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1267\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43minput_messages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1268\u001b[39m \u001b[43m \u001b[49m\u001b[43mstop_sequences\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mObservation:\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mCalling tools:\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1269\u001b[39m \u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43madditional_args\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1270\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1271\u001b[39m memory_step.model_output_message = chat_message\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/models.py:1090\u001b[39m, in \u001b[36mInferenceClientModel.__call__\u001b[39m\u001b[34m(self, messages, stop_sequences, grammar, tools_to_call_from, **kwargs)\u001b[39m\n\u001b[32m 1081\u001b[39m completion_kwargs = \u001b[38;5;28mself\u001b[39m._prepare_completion_kwargs(\n\u001b[32m 1082\u001b[39m messages=messages,\n\u001b[32m 1083\u001b[39m stop_sequences=stop_sequences,\n\u001b[32m (...)\u001b[39m\u001b[32m 1088\u001b[39m **kwargs,\n\u001b[32m 1089\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m1090\u001b[39m response = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mclient\u001b[49m\u001b[43m.\u001b[49m\u001b[43mchat_completion\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mcompletion_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1092\u001b[39m \u001b[38;5;28mself\u001b[39m.last_input_token_count = response.usage.prompt_tokens\n", "\u001b[31mTypeError\u001b[39m: InferenceClient.chat_completion() got an unexpected keyword argument 'repo_id'", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[31mAgentGenerationError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[7]\u001b[39m\u001b[32m, line 28\u001b[39m\n\u001b[32m 25\u001b[39m agent = CodeAgent(tools=[echo], model=model)\n\u001b[32m 27\u001b[39m \u001b[38;5;66;03m# Run the agent with a prompt\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m28\u001b[39m response = \u001b[43magent\u001b[49m\u001b[43m.\u001b[49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mCall echo with \u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mhello\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m 29\u001b[39m \u001b[38;5;28mprint\u001b[39m(response)\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:341\u001b[39m, in \u001b[36mMultiStepAgent.run\u001b[39m\u001b[34m(self, task, stream, reset, images, additional_args, max_steps)\u001b[39m\n\u001b[32m 339\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m._run(task=\u001b[38;5;28mself\u001b[39m.task, max_steps=max_steps, images=images)\n\u001b[32m 340\u001b[39m \u001b[38;5;66;03m# Outputs are returned only at the end. We only look at the last step.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m341\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdeque\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_run\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_steps\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmax_steps\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimages\u001b[49m\u001b[43m=\u001b[49m\u001b[43mimages\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxlen\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m1\u001b[39;49m\u001b[43m)\u001b[49m[\u001b[32m0\u001b[39m].final_answer\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:365\u001b[39m, in \u001b[36mMultiStepAgent._run\u001b[39m\u001b[34m(self, task, max_steps, images)\u001b[39m\n\u001b[32m 362\u001b[39m final_answer = \u001b[38;5;28mself\u001b[39m._execute_step(task, action_step)\n\u001b[32m 363\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentGenerationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 364\u001b[39m \u001b[38;5;66;03m# Agent generation errors are not caused by a Model error but an implementation error: so we should raise them and exit.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m365\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[32m 366\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 367\u001b[39m \u001b[38;5;66;03m# Other AgentError types are caused by the Model, so we should log them and iterate.\u001b[39;00m\n\u001b[32m 368\u001b[39m action_step.error = e\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:362\u001b[39m, in \u001b[36mMultiStepAgent._run\u001b[39m\u001b[34m(self, task, max_steps, images)\u001b[39m\n\u001b[32m 360\u001b[39m action_step = \u001b[38;5;28mself\u001b[39m._create_action_step(step_start_time, images)\n\u001b[32m 361\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m362\u001b[39m final_answer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_execute_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maction_step\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 363\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentGenerationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 364\u001b[39m \u001b[38;5;66;03m# Agent generation errors are not caused by a Model error but an implementation error: so we should raise them and exit.\u001b[39;00m\n\u001b[32m 365\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m e\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:385\u001b[39m, in \u001b[36mMultiStepAgent._execute_step\u001b[39m\u001b[34m(self, task, memory_step)\u001b[39m\n\u001b[32m 383\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m_execute_step\u001b[39m(\u001b[38;5;28mself\u001b[39m, task: \u001b[38;5;28mstr\u001b[39m, memory_step: ActionStep) -> Union[\u001b[38;5;28;01mNone\u001b[39;00m, Any]:\n\u001b[32m 384\u001b[39m \u001b[38;5;28mself\u001b[39m.logger.log_rule(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mStep \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.step_number\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m, level=LogLevel.INFO)\n\u001b[32m--> \u001b[39m\u001b[32m385\u001b[39m final_answer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstep\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmemory_step\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 386\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m final_answer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m.final_answer_checks:\n\u001b[32m 387\u001b[39m \u001b[38;5;28mself\u001b[39m._validate_final_answer(final_answer)\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:1282\u001b[39m, in \u001b[36mCodeAgent.step\u001b[39m\u001b[34m(self, memory_step)\u001b[39m\n\u001b[32m 1280\u001b[39m memory_step.model_output = model_output\n\u001b[32m 1281\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m-> \u001b[39m\u001b[32m1282\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m AgentGenerationError(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mError in generating model output:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m, \u001b[38;5;28mself\u001b[39m.logger) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01me\u001b[39;00m\n\u001b[32m 1284\u001b[39m \u001b[38;5;28mself\u001b[39m.logger.log_markdown(\n\u001b[32m 1285\u001b[39m content=model_output,\n\u001b[32m 1286\u001b[39m title=\u001b[33m\"\u001b[39m\u001b[33mOutput message of the LLM:\u001b[39m\u001b[33m\"\u001b[39m,\n\u001b[32m 1287\u001b[39m level=LogLevel.DEBUG,\n\u001b[32m 1288\u001b[39m )\n\u001b[32m 1290\u001b[39m \u001b[38;5;66;03m# Parse\u001b[39;00m\n", "\u001b[31mAgentGenerationError\u001b[39m: Error in generating model output:\nInferenceClient.chat_completion() got an unexpected keyword argument 'repo_id'" ] } ], "source": [ "import os\n", "from smolagents import CodeAgent, HfApiModel, tool\n", "\n", "# Set your Hugging Face API token\n", "os.environ[\"HF_API_TOKEN\"] = \"\"\n", "\n", "# Define a simple tool\n", "@tool\n", "def echo(text: str) -> str:\n", " \"\"\"\n", " Echo the input text.\n", "\n", " Args:\n", " text (str): The text to echo.\n", "\n", " Returns:\n", " str: The same text that was input.\n", " \"\"\"\n", " return text\n", "\n", "# Initialize the model\n", "model = HfApiModel(repo_id=\"HuggingFaceH4/zephyr-7b-beta\") # or another supported model\n", "\n", "# Create the agent with the tool\n", "agent = CodeAgent(tools=[echo], model=model)\n", "\n", "# Run the agent with a prompt\n", "response = agent.run(\"Call echo with 'hello'\")\n", "print(response)" ] }, { "cell_type": "code", "execution_count": 8, "id": "9f94c824", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
╭──────────────────────────────────────────────────── New run ────────────────────────────────────────────────────╮\n",
       "│                                                                                                                 │\n",
       "│ How many seconds would it take for a leopard at full speed to run through Pont des Arts?                        │\n",
       "│                                                                                                                 │\n",
       "╰─ InferenceClientModel - Qwen/Qwen2.5-Coder-32B-Instruct ────────────────────────────────────────────────────────╯\n",
       "
\n" ], "text/plain": [ "\u001b[38;2;212;183;2m╭─\u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[1;38;2;212;183;2mNew run\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╮\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mHow many seconds would it take for a leopard at full speed to run through Pont des Arts?\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-Coder-32B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Step 1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n",
       "
\n" ], "text/plain": [ "\u001b[38;2;212;183;2m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ \u001b[0m\u001b[1mStep \u001b[0m\u001b[1;36m1\u001b[0m\u001b[38;2;212;183;2m ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
Error in generating model output:\n",
       "404 Client Error: Not Found for url: \n",
       "https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: \n",
       "Root=1-681045d9-038c834f3e57cf572c3f9c02;195ac9a0-e49e-48f8-a238-84c03d4c9606)\n",
       "
\n" ], "text/plain": [ "\u001b[1;31mError in generating model output:\u001b[0m\n", "\u001b[1;36m404\u001b[0m\u001b[1;31m Client Error: Not Found for url: \u001b[0m\n", "\u001b[4;94mhttps://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m(\u001b[0m\u001b[1;31mRequest ID: \u001b[0m\n", "\u001b[1;33mRoot\u001b[0m\u001b[1;31m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;31m-681045d9-038c834f3e57cf572c3f9c02;\u001b[0m\u001b[93m195ac9a0-e49e-48f8-a238-84c03d4c9606\u001b[0m\u001b[1;31m)\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
[Step 1: Duration 0.57 seconds]\n",
       "
\n" ], "text/plain": [ "\u001b[2m[Step 1: Duration 0.57 seconds]\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "ename": "AgentGenerationError", "evalue": "Error in generating model output:\n404 Client Error: Not Found for url: https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: Root=1-681045d9-038c834f3e57cf572c3f9c02;195ac9a0-e49e-48f8-a238-84c03d4c9606)", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mHTTPError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/huggingface_hub/utils/_http.py:409\u001b[39m, in \u001b[36mhf_raise_for_status\u001b[39m\u001b[34m(response, endpoint_name)\u001b[39m\n\u001b[32m 408\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m409\u001b[39m \u001b[43mresponse\u001b[49m\u001b[43m.\u001b[49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 410\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/requests/models.py:1024\u001b[39m, in \u001b[36mResponse.raise_for_status\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m 1023\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m http_error_msg:\n\u001b[32m-> \u001b[39m\u001b[32m1024\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m HTTPError(http_error_msg, response=\u001b[38;5;28mself\u001b[39m)\n", "\u001b[31mHTTPError\u001b[39m: 404 Client Error: Not Found for url: https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[31mHfHubHTTPError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:1266\u001b[39m, in \u001b[36mCodeAgent.step\u001b[39m\u001b[34m(self, memory_step)\u001b[39m\n\u001b[32m 1265\u001b[39m additional_args = {\u001b[33m\"\u001b[39m\u001b[33mgrammar\u001b[39m\u001b[33m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m.grammar} \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.grammar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m {}\n\u001b[32m-> \u001b[39m\u001b[32m1266\u001b[39m chat_message: ChatMessage = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1267\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43minput_messages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1268\u001b[39m \u001b[43m \u001b[49m\u001b[43mstop_sequences\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mObservation:\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mCalling tools:\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1269\u001b[39m \u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43madditional_args\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1270\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1271\u001b[39m memory_step.model_output_message = chat_message\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/models.py:1090\u001b[39m, in \u001b[36mInferenceClientModel.__call__\u001b[39m\u001b[34m(self, messages, stop_sequences, grammar, tools_to_call_from, **kwargs)\u001b[39m\n\u001b[32m 1081\u001b[39m completion_kwargs = \u001b[38;5;28mself\u001b[39m._prepare_completion_kwargs(\n\u001b[32m 1082\u001b[39m messages=messages,\n\u001b[32m 1083\u001b[39m stop_sequences=stop_sequences,\n\u001b[32m (...)\u001b[39m\u001b[32m 1088\u001b[39m **kwargs,\n\u001b[32m 1089\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m1090\u001b[39m response = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mclient\u001b[49m\u001b[43m.\u001b[49m\u001b[43mchat_completion\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mcompletion_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1092\u001b[39m \u001b[38;5;28mself\u001b[39m.last_input_token_count = response.usage.prompt_tokens\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/huggingface_hub/inference/_client.py:992\u001b[39m, in \u001b[36mInferenceClient.chat_completion\u001b[39m\u001b[34m(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream_options, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p, extra_body)\u001b[39m\n\u001b[32m 985\u001b[39m request_parameters = provider_helper.prepare_request(\n\u001b[32m 986\u001b[39m inputs=messages,\n\u001b[32m 987\u001b[39m parameters=parameters,\n\u001b[32m (...)\u001b[39m\u001b[32m 990\u001b[39m api_key=\u001b[38;5;28mself\u001b[39m.token,\n\u001b[32m 991\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m992\u001b[39m data = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_inner_post\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest_parameters\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 994\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m stream:\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/huggingface_hub/inference/_client.py:357\u001b[39m, in \u001b[36mInferenceClient._inner_post\u001b[39m\u001b[34m(self, request_parameters, stream)\u001b[39m\n\u001b[32m 356\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m357\u001b[39m \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 358\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m response.iter_lines() \u001b[38;5;28;01mif\u001b[39;00m stream \u001b[38;5;28;01melse\u001b[39;00m response.content\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/huggingface_hub/utils/_http.py:482\u001b[39m, in \u001b[36mhf_raise_for_status\u001b[39m\u001b[34m(response, endpoint_name)\u001b[39m\n\u001b[32m 480\u001b[39m \u001b[38;5;66;03m# Convert `HTTPError` into a `HfHubHTTPError` to display request information\u001b[39;00m\n\u001b[32m 481\u001b[39m \u001b[38;5;66;03m# as well (request id and/or server error message)\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m482\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m _format(HfHubHTTPError, \u001b[38;5;28mstr\u001b[39m(e), response) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01me\u001b[39;00m\n", "\u001b[31mHfHubHTTPError\u001b[39m: 404 Client Error: Not Found for url: https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: Root=1-681045d9-038c834f3e57cf572c3f9c02;195ac9a0-e49e-48f8-a238-84c03d4c9606)", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[31mAgentGenerationError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[8]\u001b[39m\u001b[32m, line 6\u001b[39m\n\u001b[32m 3\u001b[39m model = InferenceClientModel()\n\u001b[32m 4\u001b[39m agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)\n\u001b[32m----> \u001b[39m\u001b[32m6\u001b[39m \u001b[43magent\u001b[49m\u001b[43m.\u001b[49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mHow many seconds would it take for a leopard at full speed to run through Pont des Arts?\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:341\u001b[39m, in \u001b[36mMultiStepAgent.run\u001b[39m\u001b[34m(self, task, stream, reset, images, additional_args, max_steps)\u001b[39m\n\u001b[32m 339\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m._run(task=\u001b[38;5;28mself\u001b[39m.task, max_steps=max_steps, images=images)\n\u001b[32m 340\u001b[39m \u001b[38;5;66;03m# Outputs are returned only at the end. We only look at the last step.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m341\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdeque\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_run\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_steps\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmax_steps\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimages\u001b[49m\u001b[43m=\u001b[49m\u001b[43mimages\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxlen\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m1\u001b[39;49m\u001b[43m)\u001b[49m[\u001b[32m0\u001b[39m].final_answer\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:365\u001b[39m, in \u001b[36mMultiStepAgent._run\u001b[39m\u001b[34m(self, task, max_steps, images)\u001b[39m\n\u001b[32m 362\u001b[39m final_answer = \u001b[38;5;28mself\u001b[39m._execute_step(task, action_step)\n\u001b[32m 363\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentGenerationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 364\u001b[39m \u001b[38;5;66;03m# Agent generation errors are not caused by a Model error but an implementation error: so we should raise them and exit.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m365\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[32m 366\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 367\u001b[39m \u001b[38;5;66;03m# Other AgentError types are caused by the Model, so we should log them and iterate.\u001b[39;00m\n\u001b[32m 368\u001b[39m action_step.error = e\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:362\u001b[39m, in \u001b[36mMultiStepAgent._run\u001b[39m\u001b[34m(self, task, max_steps, images)\u001b[39m\n\u001b[32m 360\u001b[39m action_step = \u001b[38;5;28mself\u001b[39m._create_action_step(step_start_time, images)\n\u001b[32m 361\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m362\u001b[39m final_answer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_execute_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maction_step\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 363\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m AgentGenerationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 364\u001b[39m \u001b[38;5;66;03m# Agent generation errors are not caused by a Model error but an implementation error: so we should raise them and exit.\u001b[39;00m\n\u001b[32m 365\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m e\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:385\u001b[39m, in \u001b[36mMultiStepAgent._execute_step\u001b[39m\u001b[34m(self, task, memory_step)\u001b[39m\n\u001b[32m 383\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m_execute_step\u001b[39m(\u001b[38;5;28mself\u001b[39m, task: \u001b[38;5;28mstr\u001b[39m, memory_step: ActionStep) -> Union[\u001b[38;5;28;01mNone\u001b[39;00m, Any]:\n\u001b[32m 384\u001b[39m \u001b[38;5;28mself\u001b[39m.logger.log_rule(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mStep \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.step_number\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m, level=LogLevel.INFO)\n\u001b[32m--> \u001b[39m\u001b[32m385\u001b[39m final_answer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mstep\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmemory_step\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 386\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m final_answer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m.final_answer_checks:\n\u001b[32m 387\u001b[39m \u001b[38;5;28mself\u001b[39m._validate_final_answer(final_answer)\n", "\u001b[36mFile \u001b[39m\u001b[32m~/p/software/Final_Assignment_Template/.venv/lib/python3.13/site-packages/smolagents/agents.py:1282\u001b[39m, in \u001b[36mCodeAgent.step\u001b[39m\u001b[34m(self, memory_step)\u001b[39m\n\u001b[32m 1280\u001b[39m memory_step.model_output = model_output\n\u001b[32m 1281\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m-> \u001b[39m\u001b[32m1282\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m AgentGenerationError(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mError in generating model output:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m, \u001b[38;5;28mself\u001b[39m.logger) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01me\u001b[39;00m\n\u001b[32m 1284\u001b[39m \u001b[38;5;28mself\u001b[39m.logger.log_markdown(\n\u001b[32m 1285\u001b[39m content=model_output,\n\u001b[32m 1286\u001b[39m title=\u001b[33m\"\u001b[39m\u001b[33mOutput message of the LLM:\u001b[39m\u001b[33m\"\u001b[39m,\n\u001b[32m 1287\u001b[39m level=LogLevel.DEBUG,\n\u001b[32m 1288\u001b[39m )\n\u001b[32m 1290\u001b[39m \u001b[38;5;66;03m# Parse\u001b[39;00m\n", "\u001b[31mAgentGenerationError\u001b[39m: Error in generating model output:\n404 Client Error: Not Found for url: https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: Root=1-681045d9-038c834f3e57cf572c3f9c02;195ac9a0-e49e-48f8-a238-84c03d4c9606)" ] } ], "source": [ "from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel\n", "\n", "model = InferenceClientModel()\n", "agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)\n", "\n", "agent.run(\"How many seconds would it take for a leopard at full speed to run through Pont des Arts?\")" ] }, { "cell_type": "code", "execution_count": null, "id": "9b9fc943", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.1" } }, "nbformat": 4, "nbformat_minor": 5 }