Human Use

Human Use

What is Human Use about?

Human Use provides a bridge between AI agents and actual humans by exposing Rapidata’s human‑in‑the‑loop API. It lets agents request short free‑text answers, image classifications, image rankings, and textual comparisons that are performed by real users.

How to use Human Use?

1. Clone the repository and install dependencies (UV or pip).
2. Configure credentials in a .env file (copy from .env.example).
3. Run the Streamlit app with streamlit run app.py to interact via a web UI.
4. Integrate the MCP server into tools like Cursor by adding the provided mcpServers entry to ~/.cursor/mcp.json.
5. Call the exposed endpoints (get_free_text_responses, get_human_image_classification, get_human_image_ranking, get_human_text_comparison) from your AI code.

Key features

• Free‑text response: Collect short answers from humans.
• Image classification: Obtain human labels for images in a directory.
• Image ranking: Ask humans to order images by preference.
• Text comparison: Have humans pick the better of two text snippets.
• Streamlit UI: Ready‑to‑use web interface for manual testing.
• Cursor MCP integration: Simple configuration to use within the Cursor development environment.

Use cases

• Creative brainstorming: Generate slogans, taglines, or design ideas with human feedback.
• Model evaluation: Validate AI‑generated content (texts, images) through real‑user judgments.
• Data labeling: Acquire high‑quality human labels for training or fine‑tuning models.
• Human‑in‑the‑loop pipelines: Deploy AI agents that defer ambiguous decisions to humans.

FAQ

• Do I need a Rapidata account? Yes, an API key from Rapidata is required and should be placed in the .env file.
• Can I run the server locally? Absolutely; the MCP server runs via UV (uv run rapidata_human_api.py).
• Is there a hosted version? A hosted UI is available at chat.rapidata.ai for quick testing without setup.
• What languages are supported? The API is language‑agnostic; you can call it from Python, JavaScript, or any environment that can make HTTP requests.
• How are payments handled? Usage is billed through Rapidata according to their pricing model.

🤖 Human Use is the easiest way to connect your AI agents with human intelligence via the Rapidata API.

Hosted Version

We now offer a hosted version of Human Use at chat.rapidata.ai - access all the features without setting up your own environment!

Human Use in Action

Coming up with a cool car design

https://github.com/user-attachments/assets/0d4c5c8f-4177-4fcf-8028-800dab16b009

Finding the best slogan

Function Naming

Ranking different image generation models.

MCP Server

Overview

The MCP server is a tool that allows you to connect your AI agents with human intelligence via the Rapidata API.

Tools

1. get_free_text_responses
   • Will ask actual humans to provide some short free text responses to the question.
2. get_human_image_classification
   • Will ask actual humans to classify the images in the directory.
3. get_human_image_ranking
   • Will ask actual humans to rank the images in the directory.
4. get_human_text_comparison
   • Will ask actual humans to compare two texts and select which one is better.

Configuration

Cursor

add the following to your cursor mcp.json file (usually in ~/.cursor/mcp.json)

{
    "mcpServers": {
        "human-use": {
            "command": "uv",
            "args": [
                "--directory",
                "YOUR_ABSOLUTE_PATH_HERE",
                "run",
                "rapidata_human_api.py"
            ]
        }
    }
}

You should now be able to see the human-use server in Cursor settings.

App

Overview

The app is a custom Streamlit app that allows you to use the MCP server. We have built because of issues with other clients. Namely the Claude desktop app.

App Setup

Clone Repository

git clone https://github.com/RapidataAI/human-use.git

Environment Configuration

Copy the .env.example file to .env and fill it in with your own credentials/settings

Note: paths should be ABSOLUTE paths

Installation with UV

Prerequisites

Install uv if you haven't already:

# For MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# For Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Setup Instructions (in the human-use repository)

1. Create and activate a virtual environment:

   uv venv
   
   # On Unix/macOS
   source .venv/bin/activate
   
   # On Windows
   .venv\Scripts\activate
   

2. Install dependencies:

   uv sync
   

Run the application

streamlit run app.py

Troubleshooting

If you encounter issues, with the dependencies make sure that "which python" and "which streamlit" are the same path. If they are not the same path, run "python -m streamlit run app.py" instead of "streamlit run app.py".

If UV is not found, make sure you close all terminals and editors, then re-open a new one and try again.

Contact

If you have any questions or need further assistance, please contact us at info@rapidata.ai.