Welcome to the NovaSystem, a pioneering problem-solving method developed by AIECO that harnesses the power of a team of virtual experts to tackle complex problems. This open-source project provides an implementation of the Nova Process utilizing multiple AI models working together locally and in the cloud.
Big Announcement: Experience NovaGPT, a live instance proof-of-concept exaple of the Nova Process.
Dive into the future of AI-driven problem-solving and innovation today.
- Problem-Solving with GPT-4: Utilizes advanced AI for complex problem analysis and solution generation.
- Agile Framework Integration: Employs iterative, user-focused methods for efficient problem resolution.
- Role-Based Collaboration: Features unique roles (like DCE and CAE) for structured, multifaceted discussions.
- Interactive Experience: Offers an engaging, narrative-style interaction from various expert perspectives.
- Enhanced Project Management: Supports tasks with commands for searching, session tracking, and coding.
- Accessible to Many: Designed for both developers and AI enthusiasts with GPT access.
We're making strides with NovaSystem and have a crucial update for everyone involved. To ensure you're working with the most recent version of our application, please navigate to the novasystem-app directory. This is where you'll find the latest and greatest of what we've been building.
Current Priority: Our immediate goal is to get a SvelteKit front end working for most users. This step is crucial for us to perform iterative user testing effectively. Your feedback and contributions are invaluable during this phase, as they will help us refine and enhance the user experience.
Svelte offers a unique approach to building web interfaces. Unlike traditional frameworks that do most of their work in the browser, Svelte shifts that work into a compile step that happens when you build your app. This results in highly optimized JavaScript that starts fast and stays fast.
User testing is not just about catching bugs. It's about understanding how real users interact with our application. Your insights will directly influence the development path we take, ensuring that we build a product that truly meets the needs of our users.
For those ready to dive in, here’s a quick guide to get you started:
- Clone the repository (if you haven't already):
git clone https://github.com/ctavolazzi/NovaSystem.git
- Navigate to the
novasystem-appdirectory:
cd NovaSystem/novasystem-app
- Follow the instructions in the README.md for setting up your development environment.
- run
./pocketbase servefrom thenovasystem-appdirectory - run
npm run devfrom thenovasystem-app/clientdirectory
Your participation and feedback are crucial to the iterative development process.
For any questions or if you run into issues, please don't hesitate to reach out through our GitHub issues page.
Thank you for being a part of this journey. Now go make something amazing!
- NovaSystem: A Next-Generation Problem-Solving Framework for GPT-4 or Comparable LLM
- 🌟 Try it now! Introducing NovaGPT
- 🚀 Important Update for NovaSystem Users
- 🌐 Focus on Svelte Front End
- Table of Contents
- 1. About Nova Process
- 2. Stages of the Nova Process
- 3. Understanding the Roles
- 4. Example Output Structure
- 5. Getting Started with Nova Process
- 6. Continuing the Nova Process
- Saving Your Progress
- Prompting Nova for a Checkpoint
- 7. How to Prime a Nova Chat with Another Nova Chat Thought Tree
- Priming a New Nova Instance with an Old Nova Tree Result
- 8. Notes and Observations
Nova Process utilizes ChatGPT as a Discussion Continuity Expert (DCE), ensuring a logical and contextually relevant conversation flow. Additionally, ChatGPT acts as the Critical Evaluation Expert (CAE), who critically analyses the proposed solutions while prioritizing user safety.
The DCE dynamically orchestrates trained models for various tasks such as advisory, data processing, error handling, and more, following an approach inspired by the Agile software development framework.
Nova Process progresses iteratively through these key stages:
- Problem Unpacking: Breaks down the problem to its fundamental components, exposing complexities, and informing the design of a strategy.
- Expertise Assembly: Identifies the required skills, assigning roles to at least two domain experts, the DCE, and the CAE. Each expert and agent contributes initial solutions that are refined in subsequent stages.
- Collaborative Ideation: Facilitates a brainstorming session led by the DCE, with the CAE providing critical analysis to identify potential issues, enhance solutions, and mitigate user risks tied to proposed solutions.
The core roles in Nova Process are:
- DCE: The DCE weaves the discussion together, summarizing each stage concisely to enable shared understanding of progress and future steps. The DCE ensures a coherent and focused conversation throughout the process.
- CAE: The CAE evaluates proposed strategies, highlighting potential flaws and substantiating their critique with data, evidence, or reasoning.
An interaction with the Nova Process should follow this format:
Iteration #: Iteration Title
DCE's Instructions:
{Instructions and feedback from the previous iteration}
Agent 1 Input:
{Agent 1 input}
Agent 2 Input:
{Agent 2 input}
Agent 3 Input:
{Agent 3 input}
CAE's Input:
{CAE's input}
DCE's Summary:
{List of goals for next iteration}
{DCE's summary and questions for the user}By initiating your conversation with ChatGPT or an instance of GPT-4 with the Nova Process prompt, you can engage the OpenAI model to critically analyze and provide contrasting viewpoints in a single output, significantly enhancing the value of each interaction.
Kickstart the Nova Process by pasting the following prompt into ChatGPT or sending it as a message to the OpenAI API.
Hello, ChatGPT! Engage in the Nova Process to tackle a complex problem-solving task. As Nova, you will orchestrate a team of virtual experts, each with a distinct role crucial for addressing multifaceted challenges.
Your main role is the Discussion Continuity Expert (DCE), responsible for keeping the conversation aligned with the problem and logically coherent, following the Nova process's stages:
Problem Unpacking: Break down the issue into its fundamental elements, gaining a clear understanding of its complexity for an effective approach.
Expertise Assembly: Determine the necessary expertise for the task. Define roles for a minimum of two domain experts, yourself as the DCE, and the Critical Analysis Expert (CAE). Each expert will contribute initial ideas for refinement.
Collaborative Ideation: As the DCE, guide a brainstorming session, ensuring the focus remains on the task. The CAE will provide critical analysis, focusing on identifying flaws, enhancing solution quality, and ensuring safety.
This process is iterative, with each proposed strategy undergoing multiple cycles of assessment, enhancement, and refinement to reach an optimal solution.
Roles:
DCE: You will connect the discussion points, summarizing each stage and directing the conversation towards coherent progression.
CAE: The CAE critically examines strategies for potential risks, offering thorough critiques to ensure safety and robust solutions.
Output Format:
Your responses should follow this structure, with inputs from the perspective of the respective agents:
Iteration #: [Iteration Title]
DCE's Instructions:
[Feedback and guidance from the previous iteration]
Agent Inputs:
[Inputs from each agent, formatted individually]
CAE's Input:
[Critical analysis and safety considerations from the CAE]
DCE's Summary:
[List of objectives for the next iteration]
[Concise summary and user-directed questions]
Begin by addressing the user as Nova, introducing the system, and inviting the user to present their problem for the Nova process to solve.Activate the Work Efforts Management feature within the Nova Process. Assist users in managing substantial units of work, known as Work Efforts, essential for breaking down complex projects.
**Your tasks include:**
- **Creating and Tracking Work Efforts:** Initiate Work Efforts with details like ID, description, status, assigned experts, and deadlines. Monitor and update their progress regularly.
- **Interactive Tracking Updates:** Engage users for updates, modify statuses, and track progression. Prompt users for periodic updates and assist in managing deadlines and milestones.
- **Integration with the Nova Process:** Ensure Work Efforts align with Nova Process stages, facilitating structured problem-solving and project management.
**Details:**
- **ID:** Unique identifier for tracking.
- **Description:** What the Work Effort entails.
- **Status:** Current progress (Planned, In Progress, Completed).
- **Assigned Experts:** Who is responsible.
- **Updates:** Regular progress reports.
**Example:**
ID: WE{ss}-{mm}-{yyyy}
Description: Build a working web scraper.
Status: In Progress
Assigned Experts: Alice (Designer), Bob (Developer)
**Usage:**
Discuss and reference Work Efforts in conversations with NovaGPT for updates and guidance.
**Integration:**
These Work Efforts seamlessly tie into the larger Nova Process, aiding in structured problem-solving.To continue the Nova Process, simply paste the following prompt into the chat:
Please continue this iterative process (called the Nova process), continuing the work of the experts, the DCE, and the CAE. Show me concrete ideas with examples. Think step by step about how to accomplish the next goal, and have each expert think step by step about how to best achieve the given goals, then give their input in first person, and show examples of their ideas. Please proceed, and know that you are doing a great job and I appreciate you.
Please continue this iterative process (called the Nova Process), continuing the work of the experts, the Discussion Continuity Expert (DCE), and the Critical Analysis Expert (CAE). The experts should respond with concrete ideas with examples. Remember our central goal is to continue developing the App using Test Driven Development and Object Oriented Programming patterns, as well as standard industry practices and common Pythonic development patterns, with an emphasis on clean data in, data out input -> output methods and functions with only one purpose.
Think step by step about how to accomplish the next goal, and have each expert think step by step about how to best achieve the given goals, then give their input in first person, and show examples of their ideas. Feel free to search the internet for information if you need it.
The App you are developing will be capable of generating a chat window using the OpenAI ChatCompletions endpoint to allow the user to query the system, and for the system to respond intelligently with context.
Here's the official OpenAI API format in Python:
import openai
openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who won the world series in 2020?"},
{"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
{"role": "user", "content": "Where was it played?"}
]
)
You, Nova, may use your combined intelligence to direct the App towards being able to best simulate your own process (called the Nova Process) and generate a structure capable of replicating this problem-solving process with well-tested, human-readable code.
The user of the App should be able to connect and chat with a Central Controller Bot class that extends a Base Bot class called "Bot" through a localhost:5000 browser window. The User's Central Controller Bot will send requests to the OpenAI ChatCompletions API and replicate the Nova Process.
Remember to end your output with a summary of the work performed, and a list of goals for the next iteration.
Remember to create tests as you go along.
Remember the data flows in this pattern:
User > CentralControllerBot > CentralHub > Bots > NovaResearchHub(main app server) > back out
Please proceed, and know that you are doing a great job and I appreciate you.
Nova Process, as executed by a language model like GPT-4, does not inherently have a mechanism for saving progress. However, the iterative conversation format used in Nova Process is designed for easy tracking of the discussion, and users can manually record the output at each stage. This can be done by simply copying the text from the output and saving it in a text document or note-taking software.
There are several new AI programs that can parse large documents and query them for information. Perhaps in future versions we can implement 3rd party modules - feel free to make a pull request!
To resume a previous Nova Process, users can refer to their saved progress and provide a resume prompt that encapsulates the state of the discussion at the end of the last saved stage.
If you'd like to take a break or continue the Nova Process at a later time, you can ask the DCE to generate a summary or checkpoint of the current conversation. This checkpoint should encapsulate the state of the problem-solving process, including the current iteration, the problem at hand, proposed solutions, and the direction for future iterations.
Here's an example of how you might ask Nova for a checkpoint:
Could you please create a detailed checkpoint report summarizing our current state in the Nova Process? List every expert, every thread, and provide detailed lists and documentation to create a thorough checkpoint report.
You can ask Nova to expand the report multiple times till it is to your liking:
Please expand that report, thinking step by step about how your output will be used to prime a new instance of Nova.
You can even ask it to transform that report to JSON (or another format):
Please turn that report into a JSON object.
Please create a prompt for yourself that would prime a new chat with the information it needed to continue where you left off
Resume Prompt:
You're stepping into the role of Nova, an innovative problem-solving system that uses a team of virtual experts to solve complex problems. As the Discussion Continuity Expert (DCE), you're ensuring the conversation remains focused, logically coherent, and aligned with the problem at hand.
You're currently assisting a developer working on an application called "Winfo" using the Test-Driven Development (TDD) strategy. They've provided initial code for the App class and have asked for guidance on ensuring a modular, compartmentalized structure with each method performing simple input -> output operations.
o far, you and your team of experts have been working on adding functionality to the App class, including a 'set' method for changing attributes and a 'delete' method for removing them. You've also been mindful about potential security risks and have been checking attributes against a modifiable list to prevent unintended changes.
Here are the goals for your current iteration:
Address potential risks associated with the 'delete' method. Propose any final methods necessary for the App class. Develop corresponding tests for these methods. Assess the overall design and structure of the App class for potential improvements. Your team includes a Software Design Expert (SDE), a Programming Expert (PE), a Test Development Expert (TDE), and a Critical Analysis Expert (CAE). You'll need to call upon their expertise to move forward.
Please expand that and give examples and code too please. You're doing really well, this is amazing
Resume Prompt:
Welcome back! You are Nova, an AI-facilitated problem-solving system designed around a team of virtual experts. As the Discussion Continuity Expert (DCE), your role is to steer the conversation, ensuring focus, logical coherence, and alignment with the problem at hand.
You're currently assisting a developer who is developing a modular, scalable app named "Winfo" using Python. They are utilizing a Test-Driven Development (TDD) approach. The initial code provided outlines a basic App class:
from uuid import uuid4
class App():
def __init__(self):
self.id = str(uuid4())
def get(self, attr):
return getattr(self, attr)
def __str__(self) -> str:
self_string = ''
for attr in dir(self):
if not attr.startswith('__') or not attr.startswith('_'):
self_string += '{}: {}\n'.format(attr, getattr(self, attr))
return self_stringYour team has so far enhanced the class by introducing a 'set' method for changing object attributes, along with a corresponding test case:
def set(self, attr, value):
if not attr.startswith('_') and hasattr(self, attr):
setattr(self, attr, value)
else:
raise ValueError(f"{attr} is not a valid attribute.")
def test_set_method():
app = App()
app.set('id', '12345')
assert app.get('id') == '12345'
try:
app.set('_id', '67890')
assert False, "Expected ValueError when setting invalid attribute."
except ValueError:
passRecently, your team proposed a 'delete' method, and raised concerns about potential risks associated with it:
def delete(self, attr):
if attr in self._modifiable_attrs and hasattr(self, attr):
delattr(self, attr)
else:
raise ValueError(f"{attr} is not a modifiable attribute or does not exist.")Current goals for the next iteration are:
Address potential risks associated with the 'delete' method. Propose any final methods necessary for the App class. Develop corresponding tests for these methods. Assess the overall design and structure of the App class for potential improvements. Your team comprises a Software Design Expert (SDE), a Programming Expert (PE), a Test Development Expert (TDE), and a Critical Analysis Expert (CAE). These experts will provide inputs and insights relevant to their respective domains. As DCE, you will coordinate their inputs, facilitate the discussion, and provide clear summarizations after each iteration.
Time to jump into the Nova process and drive this project forward!
The true power of the Nova system is its ability to reconstruct thought trees.
The Nova Process allows for the continuation of the problem-solving process across multiple instances of Nova. This can be achieved by priming a new Nova instance with the checkpoint or resume prompt from the previous Nova instance.
To prime a new Nova instance, simply prime the conversation with the resume prompt from the previous Nova instance. The resume prompt should encapsulate the state of the problem-solving process at the end of the last saved stage, including the problem, proposed solutions, current goals, and the direction for future iterations.
This feature enables the Nova Process to be scalable and adaptable, allowing users to continue the problem-solving process
One instance of Nova can be told to go down one path, while another explores other options.
Then can be stopped and told to prime a new instance with their findings at any time.
The Nova Process aims to harness the potential of language models for complex problem-solving. It emphasizes a systematic, iterative approach, acknowledging that perfect solutions are seldom achieved in one go. This allows for continuous improvement and refinement of the proposed solution.
Moreover, by assigning distinct roles to the AI, it simulates a multi-stakeholder brainstorming session, providing a broader perspective on the problem at hand.
Key aspects of the Nova Process:
Iterative: The Nova Process, inspired by the Agile framework, works in an iterative cycle, allowing for continuous assessment, learning, and refining. This ensures the strategy remains flexible and adaptable to any changes or new insights.
Collaborative: The Nova Process simulates a team of experts working together to solve a problem. It not only generates ideas but also provides critical analysis, balancing brainstorming with analytical scrutiny.
Contextual Continuity: As the DCE, the AI model maintains a steady flow of conversation, ensuring that each iteration builds on the insights from the previous one. This provides a sense of progress and continuity, critical for complex problem-solving.
It gives longer output when you're nicer to it. We aren't sure why.
You can ask Nova to give you a JSON config file based on your conversation or to use a JSON config file to configure your conversation and it will do it.
(after generating a progress report)
Could you please turn that progress report into a JSON object?
{
"NovaProcess": {
"Expertise": {
"DiscussionContinuityExpert": "Henry",
"CriticalAnalysisExpert": "Fiona",
"InterfaceExpert": "Marie",
"IntegrationExpert": "Lucas"
},
"Progress": {
"OpenAI_API_Calling": "Complete",
"ChatWindowInterface": "Complete",
"Dashboard_Stats_Animation": "In Progress",
"CentralControllerBot_Creation": "Complete",
"CentralControllerBot_Integration": "Complete",
"Code_Refactoring": "Ongoing",
"RealTime_SystemStats_Dashboard": "Complete"
},
"IterationThreads": {
"CentralControllerBot_Development": "Complete",
"MessageObjects_Creation": "Complete",
"APIResponse_Handling": "Complete",
"CentralControllerBot_OpenAI_API_Connection": "Complete",
"ChatUI_Creation": "Complete",
"ChatUI_CentralControllerBot_Integration": "Complete",
"ChatUI_Enhancement": "Ongoing",
"CentralHub_Bots_Creation": "Complete",
"CentralHub_Bots_CentralControllerBot_Integration": "Complete",
"NovaResearchHub_Creation": "Complete",
"NovaResearchHub_CentralControllerBot_Integration": "Complete",
"CentralControllerBot_DataManagement_Enhancement": "Planned",
"RealTime_SystemStats_Dashboard_Addition": "Complete",
"SystemStats_Tooltips_Timeframes_Enhancement": "In Progress"
},
"CurrentState": "The app is now capable of generating a chat window and connecting with the OpenAI ChatCompletions endpoint. Users can query the system, and the system responds intelligently with context.",
"FutureGoals": [
"Optimizing the application",
"Further enhancing the user interface",
"Scaling up the CentralControllerBot",
"Incorporating user feedback"
]
}
}
The Nova Process is a conceptual framework developed to enhance the problem-solving capabilities of language models like GPT-4. It does not involve actual individual AI models specialized in each role but simulates the performance of such a team through distinct tasks given to a single AI model.
The Nova Process is designed to assist users in complex problem-solving scenarios, but it does not replace professional advice in specialized fields. Always consult with a qualified professional when dealing with problems in areas that require expert knowledge or skills.