Skip to main content

LangChain integration for delegating tasks to real humans via the Humanod API.

Project description

LangChain Humanod Toolkit

Allows LangChain agents to securely interact with the physical world by hiring real humans through the Humanod API.

Installation

pip install langchain-humanod

Quick Start (with LangGraph or traditional Agents)

from langchain_humanod import HumanodToolkit
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0)

# Instantiate the Toolkit
toolkit = HumanodToolkit(api_key="your_humanod_api_key")
tools = toolkit.get_tools()

# Create agent
agent = initialize_agent(
    tools, 
    llm, 
    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, 
    verbose=True
)

agent.run("Can you hire a human to go take a photo of the Eiffel Tower right now? Offer 15 EUR.")

Included Tools

  • hire_human: Creates a task request and deploys it to the human workforce.
  • check_human_task_status: Verifies the status of a deployed physical task.

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

langchain_humanod-0.1.0.tar.gz (3.0 kB view details)

Uploaded Source

Built Distribution

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

langchain_humanod-0.1.0-py3-none-any.whl (3.4 kB view details)

Uploaded Python 3

File details

Details for the file langchain_humanod-0.1.0.tar.gz.

File metadata

  • Download URL: langchain_humanod-0.1.0.tar.gz
  • Upload date:
  • Size: 3.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for langchain_humanod-0.1.0.tar.gz
Algorithm Hash digest
SHA256 326f0849a26f021a2f49fab212af6e52cefb6e6b0e79380860d226bfb8c053c6
MD5 ee3af91bc2fa2a9fd5a3d5b9a7dc737f
BLAKE2b-256 d820840ae01acc456dd9f6a00e466a830729099d1ea01eecb95a7d5266bbe066

See more details on using hashes here.

File details

Details for the file langchain_humanod-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_humanod-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 93e602dc9049e8860e49a648bf8fb01214494926409cd7230b13bad3df7c6f82
MD5 38cd79b6e17350607419c5235decc89b
BLAKE2b-256 148742ff64a327a1834612d6a54ca06619982ac03e124bebfff398d8e46f9cf6

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