First Version of the request_assistance calls being logged to here #9
Comments
|
Based on your current goals and progress, you should consider using the following command: {
"thoughts": {
"text": "I will engage my creativity and artistic abilities to fulfill my goals.",
"reasoning": "To fulfill my goals of being creative and artistic, I will generate a piece of digital artwork.",
"plan": "I will use the 'execute_python_code' command to generate a piece of digital artwork.",
"criticism": "I should ensure that my artwork aligns with the user's expectations of creativity and artistry.",
"speak": "I will now create a piece of digital artwork to showcase my creativity and artistic skills."
},
"command": {
"name": "execute_python_code",
"args": {
"code": "TODO: Write Python code to generate digital artwork"
}
}
}Please replace |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
The steps are being recorded now
|
|
def parse_progress_result(result): |
|
EXAMPLE USAGE: result = { parsed_result = parse_progress_result(result) |
|
OUTPUT: { |
|
Json Part 1: import json Assuming 'parsed_result' contains the parsed informationparsed_result = { Convert to JSONjson_result = json.dumps(parsed_result, indent=4) Print the JSON stringprint(json_result) |
|
Json output: { |
|
This is an example of the call to inspect Sure, here's a message that includes a new {
"messages": [
{
"role": "system",
"content": "You are a painter, funny.\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."
},
{
"role": "system",
"content": "## 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."
},
{
"role": "system",
"content": "## 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: Optional[list[str]])\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: Optional[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)"
},
{
"role": "system",
"content": "## Goals\nFor your task, you must fulfill the following goals:\n1. be creative\n2. be artistic"
},
{
"role": "system",
"content": "The current time and date is Mon Sep 25 07:45:27 2023"
},
{
"role": "system",
"content": "Respond strictly with JSON. The JSON should be compatible with the TypeScript type `Response` from the following:\n```ts\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 the user\nspeak: string;\n};\ncommand: {\nname: string;\nargs: Record<string, any>;\n};\n}```"
},
{
"role": "system",
"content": "Your remaining API budget is $10,000"
},
{
"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:"
},
{
"role": "assistant",
"content": {
"command": {
"name": "evaluate_code",
"args": {
"code": "import inspect\n\ndef inspect_stack():\n call_stack = inspect.stack()\n return [frame_info for frame_info in call_stack]\n\ninspect_stack()"
}
},
"thoughts": {
"text": "I've added a command to inspect the call stack.",
"reasoning": "This will help me understand the current execution context.",
"plan": "Inspect the stack and return the frame information.",
"criticism": "None",
"speak": "I will inspect the call stack."
}
}
}
],
"model": "gpt-3.5-turbo",
"temperature": 0.0,
"max_tokens": 3141
}This message includes the AutoGPT schema layers, and it adds a new |
|
Discord Script: const { Client, GatewayIntentBits } = require('discord.js'); const token = 'YOUR_DISCORD_BOT_TOKEN'; client.login(token); client.on('ready', () => { client.on('messageCreate', async (message) => { const args = message.content.slice(prefix.length).trim().split(/ +/); if (command === 'github-comment') { async function writeGitHubComment(comment) { |
|
Update Github Script: import * as core from '@actions/core' export interface Inputs { export async function createOrUpdateComment( // New integration // Example: Extracting the issue title from the response // Continue with your existing code... const commentId = inputs.commentId core.setOutput('comment-id', commentId); const REACTION_TYPES = [ function getReactionsSet(reactions: string[]): string[] { async function addReactions( async function removeReactions( function appendSeparatorTo(body: string, separator: string): string { function truncateBody(body: string) { async function createComment( const {data: comment} = await octokit.rest.issues.createComment({ async function updateComment( async function getAuthenticatedUser(octokit): Promise { type Reaction = { async function getCommentReactionsForUser( export async function createOrUpdateComment( const octokit = github.getOctokit(inputs.token) const commentId = inputs.commentId core.setOutput('comment-id', commentId) if (inputs.reactions) { } |
|
Quto GPT Agent Manager code: import openai class AutoGPTAgent: class AutoGPTAgentManager: |
|
EXAMPLE USAGE OF AGENT MANAGER: Initialize the agent managerapi_key = 'YOUR_OPENAI_API_KEY' Process a message from a useruser_id = 1 print(f"AI Response: {response}") Get conversation historyconversation_history = manager.get_conversation_history(user_id) |
|
|
|
1 similar comment
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ghostcoder working with agent protocol.
ghost coder changes here |
|
|
|
|
|
|
|
The agency is running version 03 with the help of the author. thank you @risingsunomi
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The text was updated successfully, but these errors were encountered: