Skip to main content

Python SDK for AgentRPC

Project description

AgentRPC Python SDK

A universal RPC layer for AI agents. Connect to any function, any language, any framework, in minutes.

⚠️ The AgentRPC Python SDK does not currently support registering tools.

Installation

pip install agentrpc

Registering Tools

Creating an AgentRPC Client

from agentrpc import AgentRPC

agentrpc = AgentRPC(
  # Get your API secret from https://app.agentrpc.com
  api_secret="YOUR_API_SECRET"
)

OpenAI Tools

AgentRPC provides integration with OpenAI's function calling capabilities, allowing you to expose your registered RPC functions as tools for OpenAI models to use.

Agents SDK

rpc.openai.agents.get_tools()

The get_tools() method returns your registered AgentRPC functions as OpenAI Agent tools.

# First register your functions with AgentRPC (Locally or on another machine)

# Attach the tools to the Agent
agent = Agent(name="AgentRPC Agent", tools=agentrpc.openai.agents.get_tools())

result = await Runner.run(
    agent,
    input="What is the weather in Melbourne?",
)

print(result.final_output)

Completions SDK

rpc.openai.completions.get_tools()

The get_tools() method returns your registered AgentRPC functions formatted as OpenAI tools, ready to be passed to OpenAI's API.

# First register your functions with AgentRPC (Locally or on another machine)

# Then get the tools formatted for OpenAI
tools = agentrpc.openai.get_tools()

# Pass these tools to OpenAI
chat_completion = openai.chat.completions.create(
  model="gpt-4-1106-preview",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

rpc.OpenAI.completions.execute_tool(tool_call)

The execute_tool() method executes an OpenAI tool call against your registered AgentRPC functions.

# Process tool calls from OpenAI's response
if chat_completion.choices[0].tool_calls:
  for tool_call in response_message.tool_calls:
    rpc.openai.execute_tool(tool_call)

API

AgentRPC(options?)

Creates a new AgentRPC client.

Options:

Option Type Default Description
api_secret str Required The API secret key.
endpoint str https://api.agentrpc.com Custom API endpoint.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentrpc-0.0.8.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentrpc-0.0.8-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file agentrpc-0.0.8.tar.gz.

File metadata

  • Download URL: agentrpc-0.0.8.tar.gz
  • Upload date:
  • Size: 7.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.2

File hashes

Hashes for agentrpc-0.0.8.tar.gz
Algorithm Hash digest
SHA256 5a37bdac464c04c076234a77c43bf31dbbacf6d26bb13c6132ff35d2cdc96195
MD5 54b2a78eabd7c64f73c559c42de4911a
BLAKE2b-256 9be9662c4a28bf5a54f02ead78bc33020b9e3a7d68b60f61a8c1ff825ecd47f1

See more details on using hashes here.

File details

Details for the file agentrpc-0.0.8-py3-none-any.whl.

File metadata

  • Download URL: agentrpc-0.0.8-py3-none-any.whl
  • Upload date:
  • Size: 6.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.2

File hashes

Hashes for agentrpc-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 68d59eb77581483b7a39b522c19bab215817fa8cd182b7b19f53d8c20e35929a
MD5 44335f7eb954ba216bba12feda14bc34
BLAKE2b-256 88e08d68a8a6675376faddc248e36c8cd3c9ecdf548d980191583557e63fd3f7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page