mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 06:53:47 +00:00
408 lines
22 KiB
Text
408 lines
22 KiB
Text
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Tool Calling\n",
|
|
"\n",
|
|
"Before you begin, please ensure Llama Stack is installed and set up by following the [Getting Started Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"In this section, we'll explore how to enhance your applications with tool calling capabilities. We'll cover:\n",
|
|
"1. Setting up and using the Brave Search API\n",
|
|
"2. Creating custom tools\n",
|
|
"3. Configuring tool prompts and safety settings"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Set up your connection parameters:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"HOST = \"localhost\" # Replace with your host\n",
|
|
"PORT = 5000 # Replace with your port"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import asyncio\n",
|
|
"import os\n",
|
|
"from typing import Dict, List, Optional\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"\n",
|
|
"from llama_stack_client import LlamaStackClient\n",
|
|
"from llama_stack_client.lib.agents.agent import Agent\n",
|
|
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
|
|
"from llama_stack_client.types.agent_create_params import (\n",
|
|
" AgentConfig,\n",
|
|
" AgentConfigToolSearchToolDefinition,\n",
|
|
")\n",
|
|
"\n",
|
|
"# Load environment variables\n",
|
|
"load_dotenv()\n",
|
|
"\n",
|
|
"# Helper function to create an agent with tools\n",
|
|
"async def create_tool_agent(\n",
|
|
" client: LlamaStackClient,\n",
|
|
" tools: List[Dict],\n",
|
|
" instructions: str = \"You are a helpful assistant\",\n",
|
|
" model: str = \"Llama3.2-11B-Vision-Instruct\",\n",
|
|
") -> Agent:\n",
|
|
" \"\"\"Create an agent with specified tools.\"\"\"\n",
|
|
" print(\"Using the following model: \", model)\n",
|
|
" agent_config = AgentConfig(\n",
|
|
" model=model,\n",
|
|
" instructions=instructions,\n",
|
|
" sampling_params={\n",
|
|
" \"strategy\": \"greedy\",\n",
|
|
" \"temperature\": 1.0,\n",
|
|
" \"top_p\": 0.9,\n",
|
|
" },\n",
|
|
" tools=tools,\n",
|
|
" tool_choice=\"auto\",\n",
|
|
" tool_prompt_format=\"json\",\n",
|
|
" enable_session_persistence=True,\n",
|
|
" )\n",
|
|
"\n",
|
|
" return Agent(client, agent_config)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"First, create a `.env` file in your notebook directory with your Brave Search API key:\n",
|
|
"\n",
|
|
"```\n",
|
|
"BRAVE_SEARCH_API_KEY=your_key_here\n",
|
|
"```\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Using the following model: Llama3.2-11B-Vision-Instruct\n",
|
|
"\n",
|
|
"Query: What are the latest developments in quantum computing?\n",
|
|
"--------------------------------------------------\n",
|
|
"\u001b[30m\u001b[0m\u001b[33minference> \u001b[0m\u001b[33mF\u001b[0m\u001b[33mIND\u001b[0m\u001b[33mINGS\u001b[0m\u001b[33m:\n",
|
|
"\u001b[0m\u001b[33mThe\u001b[0m\u001b[33m latest\u001b[0m\u001b[33m developments\u001b[0m\u001b[33m in\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m computing\u001b[0m\u001b[33m include\u001b[0m\u001b[33m the\u001b[0m\u001b[33m introduction\u001b[0m\u001b[33m of\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m processors\u001b[0m\u001b[33m with\u001b[0m\u001b[33m increasing\u001b[0m\u001b[33m numbers\u001b[0m\u001b[33m of\u001b[0m\u001b[33m q\u001b[0m\u001b[33mubits\u001b[0m\u001b[33m,\u001b[0m\u001b[33m advancements\u001b[0m\u001b[33m in\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m error\u001b[0m\u001b[33m correction\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m the\u001b[0m\u001b[33m development\u001b[0m\u001b[33m of\u001b[0m\u001b[33m new\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m algorithms\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Companies\u001b[0m\u001b[33m such\u001b[0m\u001b[33m as\u001b[0m\u001b[33m IBM\u001b[0m\u001b[33m,\u001b[0m\u001b[33m Google\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m Microsoft\u001b[0m\u001b[33m are\u001b[0m\u001b[33m leading\u001b[0m\u001b[33m the\u001b[0m\u001b[33m charge\u001b[0m\u001b[33m in\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m computing\u001b[0m\u001b[33m research\u001b[0m\u001b[33m and\u001b[0m\u001b[33m development\u001b[0m\u001b[33m.\u001b[0m\u001b[33m For\u001b[0m\u001b[33m example\u001b[0m\u001b[33m,\u001b[0m\u001b[33m IBM\u001b[0m\u001b[33m's\u001b[0m\u001b[33m Quantum\u001b[0m\u001b[33m Experience\u001b[0m\u001b[33m cloud\u001b[0m\u001b[33m-based\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m computer\u001b[0m\u001b[33m has\u001b[0m\u001b[33m \u001b[0m\u001b[33m127\u001b[0m\u001b[33m q\u001b[0m\u001b[33mubits\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mwww\u001b[0m\u001b[33m.ibm\u001b[0m\u001b[33m.com\u001b[0m\u001b[33m/\u001b[0m\u001b[33mquant\u001b[0m\u001b[33mum\u001b[0m\u001b[33m-com\u001b[0m\u001b[33mput\u001b[0m\u001b[33ming\u001b[0m\u001b[33m/\u001b[0m\u001b[33m),\u001b[0m\u001b[33m while\u001b[0m\u001b[33m Google\u001b[0m\u001b[33m's\u001b[0m\u001b[33m S\u001b[0m\u001b[33myc\u001b[0m\u001b[33mam\u001b[0m\u001b[33more\u001b[0m\u001b[33m processor\u001b[0m\u001b[33m has\u001b[0m\u001b[33m \u001b[0m\u001b[33m53\u001b[0m\u001b[33m q\u001b[0m\u001b[33mubits\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33ms\u001b[0m\u001b[33mcai\u001b[0m\u001b[33m.st\u001b[0m\u001b[33manford\u001b[0m\u001b[33m.edu\u001b[0m\u001b[33m/~\u001b[0m\u001b[33mmw\u001b[0m\u001b[33mj\u001b[0m\u001b[33m/s\u001b[0m\u001b[33myc\u001b[0m\u001b[33mam\u001b[0m\u001b[33more\u001b[0m\u001b[33m.html\u001b[0m\u001b[33m).\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[33mQuant\u001b[0m\u001b[33mum\u001b[0m\u001b[33m error\u001b[0m\u001b[33m correction\u001b[0m\u001b[33m is\u001b[0m\u001b[33m also\u001b[0m\u001b[33m a\u001b[0m\u001b[33m major\u001b[0m\u001b[33m area\u001b[0m\u001b[33m of\u001b[0m\u001b[33m research\u001b[0m\u001b[33m,\u001b[0m\u001b[33m with\u001b[0m\u001b[33m scientists\u001b[0m\u001b[33m exploring\u001b[0m\u001b[33m various\u001b[0m\u001b[33m methods\u001b[0m\u001b[33m to\u001b[0m\u001b[33m mitigate\u001b[0m\u001b[33m the\u001b[0m\u001b[33m effects\u001b[0m\u001b[33m of\u001b[0m\u001b[33m deco\u001b[0m\u001b[33mherence\u001b[0m\u001b[33m and\u001b[0m\u001b[33m errors\u001b[0m\u001b[33m in\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m computations\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mar\u001b[0m\u001b[33mxiv\u001b[0m\u001b[33m.org\u001b[0m\u001b[33m/\u001b[0m\u001b[33mabs\u001b[0m\u001b[33m/\u001b[0m\u001b[33m210\u001b[0m\u001b[33m4\u001b[0m\u001b[33m.\u001b[0m\u001b[33m045\u001b[0m\u001b[33m93\u001b[0m\u001b[33m).\u001b[0m\u001b[33m New\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m algorithms\u001b[0m\u001b[33m,\u001b[0m\u001b[33m such\u001b[0m\u001b[33m as\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m simulation\u001b[0m\u001b[33m and\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m machine\u001b[0m\u001b[33m learning\u001b[0m\u001b[33m,\u001b[0m\u001b[33m are\u001b[0m\u001b[33m also\u001b[0m\u001b[33m being\u001b[0m\u001b[33m developed\u001b[0m\u001b[33m to\u001b[0m\u001b[33m take\u001b[0m\u001b[33m advantage\u001b[0m\u001b[33m of\u001b[0m\u001b[33m the\u001b[0m\u001b[33m unique\u001b[0m\u001b[33m properties\u001b[0m\u001b[33m of\u001b[0m\u001b[33m quantum\u001b[0m\u001b[33m computing\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mar\u001b[0m\u001b[33mxiv\u001b[0m\u001b[33m.org\u001b[0m\u001b[33m/\u001b[0m\u001b[33mabs\u001b[0m\u001b[33m/\u001b[0m\u001b[33m210\u001b[0m\u001b[33m2\u001b[0m\u001b[33m.\u001b[0m\u001b[33m081\u001b[0m\u001b[33m83\u001b[0m\u001b[33m).\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[33mS\u001b[0m\u001b[33mOURCES\u001b[0m\u001b[33m:\n",
|
|
"\u001b[0m\u001b[33m-\u001b[0m\u001b[33m IBM\u001b[0m\u001b[33m Quantum\u001b[0m\u001b[33m Experience\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mwww\u001b[0m\u001b[33m.ibm\u001b[0m\u001b[33m.com\u001b[0m\u001b[33m/\u001b[0m\u001b[33mquant\u001b[0m\u001b[33mum\u001b[0m\u001b[33m-com\u001b[0m\u001b[33mput\u001b[0m\u001b[33ming\u001b[0m\u001b[33m/)\n",
|
|
"\u001b[0m\u001b[33m-\u001b[0m\u001b[33m Google\u001b[0m\u001b[33m's\u001b[0m\u001b[33m S\u001b[0m\u001b[33myc\u001b[0m\u001b[33mam\u001b[0m\u001b[33more\u001b[0m\u001b[33m processor\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33ms\u001b[0m\u001b[33mcai\u001b[0m\u001b[33m.st\u001b[0m\u001b[33manford\u001b[0m\u001b[33m.edu\u001b[0m\u001b[33m/~\u001b[0m\u001b[33mmw\u001b[0m\u001b[33mj\u001b[0m\u001b[33m/s\u001b[0m\u001b[33myc\u001b[0m\u001b[33mam\u001b[0m\u001b[33more\u001b[0m\u001b[33m.html\u001b[0m\u001b[33m)\n",
|
|
"\u001b[0m\u001b[33m-\u001b[0m\u001b[33m \"\u001b[0m\u001b[33mQuant\u001b[0m\u001b[33mum\u001b[0m\u001b[33m error\u001b[0m\u001b[33m correction\u001b[0m\u001b[33m with\u001b[0m\u001b[33m encoded\u001b[0m\u001b[33m cat\u001b[0m\u001b[33m codes\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mar\u001b[0m\u001b[33mxiv\u001b[0m\u001b[33m.org\u001b[0m\u001b[33m/\u001b[0m\u001b[33mabs\u001b[0m\u001b[33m/\u001b[0m\u001b[33m210\u001b[0m\u001b[33m4\u001b[0m\u001b[33m.\u001b[0m\u001b[33m045\u001b[0m\u001b[33m93\u001b[0m\u001b[33m)\n",
|
|
"\u001b[0m\u001b[33m-\u001b[0m\u001b[33m \"\u001b[0m\u001b[33mQuant\u001b[0m\u001b[33mum\u001b[0m\u001b[33m simulation\u001b[0m\u001b[33m of\u001b[0m\u001b[33m many\u001b[0m\u001b[33m-body\u001b[0m\u001b[33m systems\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m (\u001b[0m\u001b[33mhttps\u001b[0m\u001b[33m://\u001b[0m\u001b[33mar\u001b[0m\u001b[33mxiv\u001b[0m\u001b[33m.org\u001b[0m\u001b[33m/\u001b[0m\u001b[33mabs\u001b[0m\u001b[33m/\u001b[0m\u001b[33m210\u001b[0m\u001b[33m2\u001b[0m\u001b[33m.\u001b[0m\u001b[33m081\u001b[0m\u001b[33m83\u001b[0m\u001b[33m)\u001b[0m\u001b[97m\u001b[0m\n",
|
|
"\u001b[30m\u001b[0m"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"async def create_search_agent(client: LlamaStackClient) -> Agent:\n",
|
|
" \"\"\"Create an agent with Brave Search capability.\"\"\"\n",
|
|
" search_tool = AgentConfigToolSearchToolDefinition(\n",
|
|
" type=\"brave_search\",\n",
|
|
" engine=\"brave\",\n",
|
|
" api_key=\"dummy_value\"#os.getenv(\"BRAVE_SEARCH_API_KEY\"),\n",
|
|
" )\n",
|
|
"\n",
|
|
" models_response = client.models.list()\n",
|
|
" for model in models_response:\n",
|
|
" if model.identifier.endswith(\"Instruct\"):\n",
|
|
" model_name = model.llama_model\n",
|
|
"\n",
|
|
"\n",
|
|
" return await create_tool_agent(\n",
|
|
" client=client,\n",
|
|
" tools=[search_tool],\n",
|
|
" model = model_name,\n",
|
|
" instructions=\"\"\"\n",
|
|
" You are a research assistant that can search the web.\n",
|
|
" Always cite your sources with URLs when providing information.\n",
|
|
" Format your responses as:\n",
|
|
"\n",
|
|
" FINDINGS:\n",
|
|
" [Your summary here]\n",
|
|
"\n",
|
|
" SOURCES:\n",
|
|
" - [Source title](URL)\n",
|
|
" \"\"\"\n",
|
|
" )\n",
|
|
"\n",
|
|
"# Example usage\n",
|
|
"async def search_example():\n",
|
|
" client = LlamaStackClient(base_url=f\"http://{HOST}:{PORT}\")\n",
|
|
" agent = await create_search_agent(client)\n",
|
|
"\n",
|
|
" # Create a session\n",
|
|
" session_id = agent.create_session(\"search-session\")\n",
|
|
"\n",
|
|
" # Example queries\n",
|
|
" queries = [\n",
|
|
" \"What are the latest developments in quantum computing?\",\n",
|
|
" #\"Who won the most recent Super Bowl?\",\n",
|
|
" ]\n",
|
|
"\n",
|
|
" for query in queries:\n",
|
|
" print(f\"\\nQuery: {query}\")\n",
|
|
" print(\"-\" * 50)\n",
|
|
"\n",
|
|
" response = agent.create_turn(\n",
|
|
" messages=[{\"role\": \"user\", \"content\": query}],\n",
|
|
" session_id=session_id,\n",
|
|
" )\n",
|
|
"\n",
|
|
" async for log in EventLogger().log(response):\n",
|
|
" log.print()\n",
|
|
"\n",
|
|
"# Run the example (in Jupyter, use asyncio.run())\n",
|
|
"await search_example()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 3. Custom Tool Creation\n",
|
|
"\n",
|
|
"Let's create a custom weather tool:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"Query: What's the weather like in San Francisco?\n",
|
|
"--------------------------------------------------\n",
|
|
"\u001b[30m\u001b[0m\u001b[33minference> \u001b[0m\u001b[33m{\n",
|
|
"\u001b[0m\u001b[33m \u001b[0m\u001b[33m \"\u001b[0m\u001b[33mtype\u001b[0m\u001b[33m\":\u001b[0m\u001b[33m \"\u001b[0m\u001b[33mfunction\u001b[0m\u001b[33m\",\n",
|
|
"\u001b[0m\u001b[33m \u001b[0m\u001b[33m \"\u001b[0m\u001b[33mname\u001b[0m\u001b[33m\":\u001b[0m\u001b[33m \"\u001b[0m\u001b[33mget\u001b[0m\u001b[33m_weather\u001b[0m\u001b[33m\",\n",
|
|
"\u001b[0m\u001b[33m \u001b[0m\u001b[33m \"\u001b[0m\u001b[33mparameters\u001b[0m\u001b[33m\":\u001b[0m\u001b[33m {\n",
|
|
"\u001b[0m\u001b[33m \u001b[0m\u001b[33m \"\u001b[0m\u001b[33mlocation\u001b[0m\u001b[33m\":\u001b[0m\u001b[33m \"\u001b[0m\u001b[33mSan\u001b[0m\u001b[33m Francisco\u001b[0m\u001b[33m\"\n",
|
|
"\u001b[0m\u001b[33m \u001b[0m\u001b[33m }\n",
|
|
"\u001b[0m\u001b[33m}\u001b[0m\u001b[97m\u001b[0m\n",
|
|
"\u001b[32mCustomTool> {\"temperature\": 72.5, \"conditions\": \"partly cloudy\", \"humidity\": 65.0}\u001b[0m\n",
|
|
"\n",
|
|
"Query: Tell me the weather in Tokyo tomorrow\n",
|
|
"--------------------------------------------------\n",
|
|
"\u001b[30m\u001b[0m\u001b[33minference> \u001b[0m\u001b[36m\u001b[0m\u001b[36m{\"\u001b[0m\u001b[36mtype\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mfunction\u001b[0m\u001b[36m\",\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mname\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mget\u001b[0m\u001b[36m_weather\u001b[0m\u001b[36m\",\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mparameters\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m {\"\u001b[0m\u001b[36mlocation\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mTok\u001b[0m\u001b[36myo\u001b[0m\u001b[36m\",\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mdate\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m \"\u001b[0m\u001b[36mtom\u001b[0m\u001b[36morrow\u001b[0m\u001b[36m\"}}\u001b[0m\u001b[97m\u001b[0m\n",
|
|
"\u001b[32mCustomTool> {\"temperature\": 90.1, \"conditions\": \"sunny\", \"humidity\": 40.0}\u001b[0m\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from typing import TypedDict, Optional, Dict, Any\n",
|
|
"from datetime import datetime\n",
|
|
"import json\n",
|
|
"from llama_stack_client.types.tool_param_definition_param import ToolParamDefinitionParam\n",
|
|
"from llama_stack_client.types import CompletionMessage,ToolResponseMessage\n",
|
|
"from llama_stack_client.lib.agents.custom_tool import CustomTool\n",
|
|
"\n",
|
|
"class WeatherTool(CustomTool):\n",
|
|
" \"\"\"Example custom tool for weather information.\"\"\"\n",
|
|
"\n",
|
|
" def get_name(self) -> str:\n",
|
|
" return \"get_weather\"\n",
|
|
"\n",
|
|
" def get_description(self) -> str:\n",
|
|
" return \"Get weather information for a location\"\n",
|
|
"\n",
|
|
" def get_params_definition(self) -> Dict[str, ToolParamDefinitionParam]:\n",
|
|
" return {\n",
|
|
" \"location\": ToolParamDefinitionParam(\n",
|
|
" param_type=\"str\",\n",
|
|
" description=\"City or location name\",\n",
|
|
" required=True\n",
|
|
" ),\n",
|
|
" \"date\": ToolParamDefinitionParam(\n",
|
|
" param_type=\"str\",\n",
|
|
" description=\"Optional date (YYYY-MM-DD)\",\n",
|
|
" required=False\n",
|
|
" )\n",
|
|
" }\n",
|
|
" async def run(self, messages: List[CompletionMessage]) -> List[ToolResponseMessage]:\n",
|
|
" assert len(messages) == 1, \"Expected single message\"\n",
|
|
"\n",
|
|
" message = messages[0]\n",
|
|
"\n",
|
|
" tool_call = message.tool_calls[0]\n",
|
|
" # location = tool_call.arguments.get(\"location\", None)\n",
|
|
" # date = tool_call.arguments.get(\"date\", None)\n",
|
|
" try:\n",
|
|
" response = await self.run_impl(**tool_call.arguments)\n",
|
|
" response_str = json.dumps(response, ensure_ascii=False)\n",
|
|
" except Exception as e:\n",
|
|
" response_str = f\"Error when running tool: {e}\"\n",
|
|
"\n",
|
|
" message = ToolResponseMessage(\n",
|
|
" call_id=tool_call.call_id,\n",
|
|
" tool_name=tool_call.tool_name,\n",
|
|
" content=response_str,\n",
|
|
" role=\"ipython\",\n",
|
|
" )\n",
|
|
" return [message]\n",
|
|
"\n",
|
|
" async def run_impl(self, location: str, date: Optional[str] = None) -> Dict[str, Any]:\n",
|
|
" \"\"\"Simulate getting weather data (replace with actual API call).\"\"\"\n",
|
|
" # Mock implementation\n",
|
|
" if date:\n",
|
|
" return {\n",
|
|
" \"temperature\": 90.1,\n",
|
|
" \"conditions\": \"sunny\",\n",
|
|
" \"humidity\": 40.0\n",
|
|
" }\n",
|
|
" return {\n",
|
|
" \"temperature\": 72.5,\n",
|
|
" \"conditions\": \"partly cloudy\",\n",
|
|
" \"humidity\": 65.0\n",
|
|
" }\n",
|
|
"\n",
|
|
"\n",
|
|
"async def create_weather_agent(client: LlamaStackClient) -> Agent:\n",
|
|
" \"\"\"Create an agent with weather tool capability.\"\"\"\n",
|
|
" models_response = client.models.list()\n",
|
|
" for model in models_response:\n",
|
|
" if model.identifier.endswith(\"Instruct\"):\n",
|
|
" model_name = model.llama_model\n",
|
|
" agent_config = AgentConfig(\n",
|
|
" model=model_name,\n",
|
|
" instructions=\"\"\"\n",
|
|
" You are a weather assistant that can provide weather information.\n",
|
|
" Always specify the location clearly in your responses.\n",
|
|
" Include both temperature and conditions in your summaries.\n",
|
|
" \"\"\",\n",
|
|
" sampling_params={\n",
|
|
" \"strategy\": \"greedy\",\n",
|
|
" \"temperature\": 1.0,\n",
|
|
" \"top_p\": 0.9,\n",
|
|
" },\n",
|
|
" tools=[\n",
|
|
" {\n",
|
|
" \"function_name\": \"get_weather\",\n",
|
|
" \"description\": \"Get weather information for a location\",\n",
|
|
" \"parameters\": {\n",
|
|
" \"location\": {\n",
|
|
" \"param_type\": \"str\",\n",
|
|
" \"description\": \"City or location name\",\n",
|
|
" \"required\": True,\n",
|
|
" },\n",
|
|
" \"date\": {\n",
|
|
" \"param_type\": \"str\",\n",
|
|
" \"description\": \"Optional date (YYYY-MM-DD)\",\n",
|
|
" \"required\": False,\n",
|
|
" },\n",
|
|
" },\n",
|
|
" \"type\": \"function_call\",\n",
|
|
" }\n",
|
|
" ],\n",
|
|
" tool_choice=\"auto\",\n",
|
|
" tool_prompt_format=\"json\",\n",
|
|
" input_shields=[],\n",
|
|
" output_shields=[],\n",
|
|
" enable_session_persistence=True\n",
|
|
" )\n",
|
|
"\n",
|
|
" # Create the agent with the tool\n",
|
|
" weather_tool = WeatherTool()\n",
|
|
" agent = Agent(\n",
|
|
" client=client,\n",
|
|
" agent_config=agent_config,\n",
|
|
" custom_tools=[weather_tool]\n",
|
|
" )\n",
|
|
"\n",
|
|
" return agent\n",
|
|
"\n",
|
|
"# Example usage\n",
|
|
"async def weather_example():\n",
|
|
" client = LlamaStackClient(base_url=f\"http://{HOST}:{PORT}\")\n",
|
|
" agent = await create_weather_agent(client)\n",
|
|
" session_id = agent.create_session(\"weather-session\")\n",
|
|
"\n",
|
|
" queries = [\n",
|
|
" \"What's the weather like in San Francisco?\",\n",
|
|
" \"Tell me the weather in Tokyo tomorrow\",\n",
|
|
" ]\n",
|
|
"\n",
|
|
" for query in queries:\n",
|
|
" print(f\"\\nQuery: {query}\")\n",
|
|
" print(\"-\" * 50)\n",
|
|
"\n",
|
|
" response = agent.create_turn(\n",
|
|
" messages=[{\"role\": \"user\", \"content\": query}],\n",
|
|
" session_id=session_id,\n",
|
|
" )\n",
|
|
"\n",
|
|
" async for log in EventLogger().log(response):\n",
|
|
" log.print()\n",
|
|
"\n",
|
|
"# For Jupyter notebooks\n",
|
|
"import nest_asyncio\n",
|
|
"nest_asyncio.apply()\n",
|
|
"\n",
|
|
"# Run the example\n",
|
|
"await weather_example()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Thanks for checking out this tutorial, hopefully you can now automate everything with Llama! :D\n",
|
|
"\n",
|
|
"Next up, we learn another hot topic of LLMs: Memory and Rag. Continue learning [here](./04_Memory101.ipynb)!"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.10.15"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|