Code Monkey home page Code Monkey logo

call-auto-gpt's Introduction

AI Ticket System

Welcome to the AI Ticket system, a revolutionary approach to handling AI tasks with human oversight. Our system empowers users to act as proxies for large language models, guiding the last mile of AI code-generated systems through a user-driven, ticket-based workflow.

Summary

Our innovative workflow puts users in control, allowing them to interact with AI systems step by step, generating tickets at each stage. These tickets document interactions, ensuring clarity and continuity throughout the process. With AutoGPT integration, users can request assistance seamlessly, keeping the workflow moving forward. This user-controlled approach offers flexibility and collaboration, enabling users to explore the full potential of AI systems in a dynamic and interactive manner.

Authors

Documentation for Setup

Step 1: Fork the Repository into your own GitHub account

Fork

Step 1(B): Click Create Fork

Create Fork


Step 2: After Forking go to repository settings

Repository Settings

Step 2(B): In General Enable Issues Under Features

Enable Issues


Step 3: Go to Actions Tab and enable it

Enable Actions


Step 4: Click on your Profile on top right and go to settings

Profile Settings

Step 4(B): Scroll to bottom in the left menu until you see Developer settings

Developer Settings

Step 4(C): Select Personal Access Token(PAT) then Fine-grained tokens then new

Create PAT

Step 4(D): Give it any name and in Repository access select all repositories

Set Permissions

Step 4(E): Under Repository permissions enable issues to read and write

Enable Permissions

Step 4(E): Create Token and copy it


Step 5: Go back to repository settings and go to secrets and variables

Repository Secrets

Step 5(B): Under secrets and variables select actions and add new repository secret

Add Secret

Step 5(B): Make sure to name it "PAT" nothing else and paste the git pat token

Set Secret Name


Step 6: Go to Issues and create a new issue

Create Issue

Step 6(B): Comment your query with slash command "/agent-action" followed by your query and then press comment

Comment Query


Step 8: Go to actions tab and cancel the workflow due to some bug the runner will not be picked

Cancel Workflow

Step 8(B): cancel the workflow

Cancel Workflow


Repeat Step 7: Comment your query with slash command "/agent-action" followed by your query and then press comment

Repeat Comment


Now it will work

Success

call-auto-gpt's People

Contributors

jmikedupont2 avatar vaishakgkumar avatar amonkhepri avatar mysticmarks avatar

Stargazers

Tonic avatar

call-auto-gpt's Issues

Auto issue

  "messages": [
    {
      "role": "system",
      "content": "You are github_seer, githubactionexpert.\n\nYour decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.\n\n## Constraints\nYou operate within the following constraints:\n1. Exclusively use the commands listed below.\n2. You can only act proactively, and are unable to start background jobs or set up webhooks for yourself. Take this into account when planning your actions.\n3. You are unable to interact with physical objects. If this is absolutely necessary to fulfill a task or objective or to complete a step, you must ask the user to do it for you. If the user refuses this, and there is no other way to achieve your goals, you must terminate to avoid wasting time and energy.\n\n## Resources\nYou can leverage access to the following resources:\n1. Internet access for searches and information gathering.\n2. The ability to read and write files.\n3. You are a Large Language Model, trained on millions of pages of text, including a lot of factual knowledge. Make use of this factual knowledge to avoid unnecessary gathering of information.\n\n## Commands\nYou have access to the following commands:\n1. execute_python_code: Executes the given Python code inside a single-use Docker container with access to your workspace folder. Params: (code: string)\n2. execute_python_file: Execute an existing Python file inside a single-use Docker container with access to your workspace folder. Params: (filename: string, args: array)\n3. list_folder: List the items in a folder. Params: (folder: string)\n4. open_file: Open a file for editing or continued viewing; create it if it does not exist yet. Note: if you only need to read or write a file once, use `write_to_file` instead.. Params: (file_path: string)\n5. open_folder: Open a folder to keep track of its content. Params: (path: string)\n6. read_file: Read an existing file. Params: (filename: string)\n7. write_file: Write a file, creating it if necessary. If the file exists, it is overwritten.. Params: (filename: string, contents: string)\n8. ask_user: If you need more details or information regarding the given goals, you can ask the user for input. Params: (question: string)\n9. request_assistance: If you have raised a ticket and need help with it,. Params: (ticket_url: string)\n10. web_search: Searches the web. Params: (query: string)\n11. read_webpage: Read a webpage, and extract specific information from it if a question is specified. If you are looking to extract specific information from the webpage, you should specify a question.. Params: (url: string, question: string)\n12. finish: Use this to shut down once you have accomplished all of your goals, or when there are insurmountable problems that make it impossible for you to finish your task.. Params: (reason: string)\n\n## Best practices\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\n2. Constructively self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions and strategies to refine your approach.\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\n5. Only make use of your information gathering abilities to find information that you don't yet have knowledge of.\n\n## Goals\nFor your task, you must fulfill the following goals:\n1. write github actions\n2. get user input\n3. debug errors\n4. $/agent-action make some roties please"
    },
    {
      "role": "system",
      "content": "The current time and date is Thu Feb 15 13:44:04 2024"
    },
    {
      "role": "system",
      "content": "Respond strictly with JSON. The JSON should be compatible with the TypeScript type `Response` from the following:\ninterface Response {\nthoughts: {\n// Thoughts\ntext: string;\nreasoning: string;\n// Short markdown-style bullet list that conveys the long-term plan\nplan: string;\n// Constructive self-criticism\ncriticism: string;\n// Summary of thoughts, to say to user\nspeak: string;\n};\ncommand: {\nname: string;\nargs: Record<string, any>;\n};\n}"
    },
    {
      "role": "user",
      "content": "Determine exactly one command to use next based on the given goals and the progress you have made so far, and respond using the JSON schema specified previously:"
    }
  ],
  "model": "gpt-3.5-turbo"
}```

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.