Metadata-Version: 2.4
Name: langchain-humanod
Version: 0.1.0
Summary: LangChain integration for delegating tasks to real humans via the Humanod API.
Home-page: https://github.com/humanod/langchain-humanod
Author: Humanod
Author-email: hello@humanod.app
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: humanod>=0.1.0
Requires-Dist: langchain-core>=0.1.0
Requires-Dist: pydantic>=2.0.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# LangChain Humanod Toolkit

Allows LangChain agents to securely interact with the physical world by hiring real humans through the [Humanod API](https://humanod.app).

## Installation

```bash
pip install langchain-humanod
```

## Quick Start (with LangGraph or traditional Agents)

```python
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.
