Chasm Inference Scout Setup Guide

Introduction

Welcome to the Inference Scout documentation. This guide will help you set up and run Inference Scout on your server, whether you are a first-time user or a seasoned developer.

Inference Scout is a tool that runs inference tasks given by Chasm's Orchestrator. It allows you to leverage powerful language models and contribute to Chasm Network.

Prerequisites

API Keys

  • Obtain a Groq API key from the Groq Console

  • (Optional) Obtain an Openrouter API key from Openrouter

  • Obtain SCOUT_UID and WEBHOOK_API_KEY from the Chasm Website

Server Specifications

Minimum Requirements:

  • 1 vCPU

  • 1GB RAM

  • 20GB Disk

  • Static IP

Suggested Requirements:

  • 2 vCPU

  • 4GB RAM

  • 50GB SSD

  • Static IP

Obtaining your SCOUT_UID and WEBHOOK_API_KEY

  1. Click _mint(scout)

  2. Log in to the website and retrieve your webhook API key and UID as the first step.

Software Requirements

  1. Install Docker: Follow the Docker Installation Guide

  2. Make a new folder and enter the folder: Do a mkdir chasm-scoutand cd chasm-scout

  3. Set up the environment file: Use nano .env or vim .env to create a file with the following content:

PORT=3001
LOGGER_LEVEL=debug

# Chasm
ORCHESTRATOR_URL=https://orchestrator.chasm.net
SCOUT_NAME=
SCOUT_UID=
WEBHOOK_API_KEY=
# Scout Webhook Url, update based on your server's IP and Port
# e.g. http://123.123.123.123:3001/
WEBHOOK_URL=

# Chosen Provider (groq, openai)
PROVIDERS=groq
MODEL=gemma2-9b-it
GROQ_API_KEY=

# Optional
OPENROUTER_API_KEY=
OPENAI_API_KEY=

Do not use single quotes (') or double quotes (") in your .env file, as Docker has issues with them.

Setup Guide

  1. Get Required Credentials from Chasm

  2. Prepare the .env File (as shown above)

  3. Pull the Docker Image:

    docker pull chasmtech/chasm-scout:latest
  4. Run the Docker Container:

    docker run -d --restart=always --env-file ./.env -p 3001:3001 --name scout chasmtech/chasm-scout
  5. Verify Server Status:

    docker logs scout
  6. Test Server Response:

    curl localhost:3001

    Expected response: OK

  7. Test LLM Functionality:

    source ./.env
    curl -X POST \
         -H "Content-Type: application/json" \
         -H "Authorization: Bearer $WEBHOOK_API_KEY" \
         -d '{"body":"{\"model\":\"gemma2-9b-it\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"}]}"}' \
         $WEBHOOK_URL
  8. Restart Docker Container (if needed):

    docker stop scout
    docker rm scout
    docker run -d --restart=always --env-file ./.env -p 3001:3001 --name scout johnsonchasm/chasm-scout
  9. Verify Scout Ranking:

    Check your scout ranking at the Leaderboard. Note: The node status may take up to an hour to update.

  10. Monitor Scout Performance:

    docker stats scout

Troubleshooting

Environment Variables

Double-check that all required environment variables are correctly set in the .env file.

Additional Resources

This guide should help you set up and run the Chasm Scout server effectively. For more detailed instructions and troubleshooting, refer to the original repository and additional resources provided.

Last updated