wehub-resource-sync
113 lines
2.9 KiB
Plaintext
113 lines
2.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!curl -LsSf https://astral.sh/uv/install.sh | sh\n",
|
|
"!uv pip install python-a2a"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# open a terminal and run: python agent1.py\n",
|
|
"# open another terminal and run: python agent2.py\n",
|
|
"# open another terminal and run: python agent3.py\n",
|
|
"\n",
|
|
"# after that, run the following cells"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from python_a2a import AgentNetwork, A2AClient, AIAgentRouter\n",
|
|
"\n",
|
|
"# Create an agent network\n",
|
|
"network = AgentNetwork(name=\"Math Assistant Network\")\n",
|
|
"\n",
|
|
"# Add agents to the network\n",
|
|
"network.add(\"Sine\", \"http://localhost:4737\")\n",
|
|
"network.add(\"Cosine\", \"http://localhost:4738\")\n",
|
|
"network.add(\"Tangent\", \"http://localhost:4739\")\n",
|
|
"\n",
|
|
"# Create a router to intelligently direct queries to the best agent\n",
|
|
"router = AIAgentRouter(\n",
|
|
" llm_client=A2AClient(\"http://localhost:5000/openai\"), # LLM for making routing decisions\n",
|
|
" agent_network=network\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Route a query to the appropriate agent\n",
|
|
"query = \"Tan of 0.78545\"\n",
|
|
"agent_name, confidence = router.route_query(query)\n",
|
|
"print(f\"Routing to {agent_name} with {confidence:.2f} confidence\")\n",
|
|
"\n",
|
|
"# Get the selected agent and ask the question\n",
|
|
"agent = network.get_agent(agent_name)\n",
|
|
"response = agent.ask(query)\n",
|
|
"print(f\"Response: {response}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Route a query to the appropriate agent\n",
|
|
"query = \"Sine of 3.14159\"\n",
|
|
"agent_name, confidence = router.route_query(query)\n",
|
|
"print(f\"Routing to {agent_name} with {confidence:.2f} confidence\")\n",
|
|
"\n",
|
|
"# Get the selected agent and ask the question\n",
|
|
"agent = network.get_agent(agent_name)\n",
|
|
"response = agent.ask(query)\n",
|
|
"print(f\"Response: {response}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "base",
|
|
"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": "3.12.2"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|