Overview
We propose to create a private Discord bot or Docs widget (permitting users to “engage with your documents”) for Nervos, utilizing the functionalities of advanced Large Language Models (LLMs). This bot or widget will link Nervos’ Github repositories, documentation, related articles, and Discord Q&A history, granting users a platform to ask questions in a natural language. This solution is geared towards enhancing Developer Relations, Customer Support, and Community Support experiences within the Nervos network.
Our primary objective is to enhance Nervos’ DevRel and Community Support teams, decrease the support hours on Discord, and accelerate responses to frequently asked questions. This guarantees that both the teams and users get answers more effectively and efficiently.
Background
The success of Web3 technical projects is deeply connected to a robust ecosystem of developers utilizing the protocols. Developers become acquainted with different projects through examining developer documentation and Github repositories. However, documentation alone cannot cover all aspects, requiring a team of individuals to provide primary support to those developing or using the protocol.
Developer Relations and Community Support teams serve as the first human interface with protocols. Their roles are crucial in the project: building developer communities and ensuring the alignment of product-market fit.
A common hurdle is the scarcity of human resources to address the many requests and inquiries teams receive daily. Our solution aims to equip Nervos’ support teams to focus on their core strengths: resolving unique customer issues, instilling trust in the protocol, and nurturing an active and engaged community. By introducing a bot or widget capable of answering previously asked questions, support teams can become more efficient and provide superior service to end-users.
Team
Ali Agha is a technologist and entrepreneur focused on decentralized solutions. In his previous venture, Olypsis Technologies, Ali provided Web3 consulting services to countless startups and major corporations like IBM and Thomson Reuters. Ali began his journey in the blockchain space in 2015 when he discovered bitcoin. Since then, he has dedicated his career to creating a fairer and more equitable world through the power of decentralization.
Github: OlypsisAli · GitHub
Twitter: https://twitter.com/iamAliAgha
Tenzin Rose is an entrepreneur and full-stack developer with a background in enterprise sales. He’s collaborated with global startups and enterprises, aiding them in successfully deploying projects and generating revenue. His current interests include web development and deciphering the complex equations in ZKP and ML.
Github: niznet89 (Tenzin Rose) · GitHub
Twitter: https://twitter.com/tenzin_rose
Project Plan
Pre-Implementation: Collaborate with the DevRel, Customer Support, and Community Support teams to understand their needs, identify problems, and determine where the bot or widget can be most helpful. These insights will guide the selection of data sources for implementation.
Milestone 1 - Implementation of Data Sources [3 weeks]: Following the discovery phase, we will integrate 3-4 high-value data sources into the bot or widget. We will use the Llama Index to set up indices and a vector database to enable embeddings-based search on queries. This milestone will involve refining file loading, index creation, and data source integration.
End state: Have 3-4 data sources that can be queried.
Expected bugs: hallucinations, mismatches on query/documents.
Milestone 2 - Testing and Optimization + Deploy to Production [3 weeks]: This crucial phase will focus on eradicating hallucinations and refining prompt engineering to ensure only relevant answers are given, with source material and links for users to follow up on. The goal is to make the bot or widget production-ready.
End state: A production-ready bot or widget approved by the Customer / Community Support teams, ready for deployment on Nervos’ Discord channel or Docs page.
Technical Details:
Note: All repositories are currently private. The Tali team is pleased to invite a Nervos team member into the repository to view the currently built code.
The proposed Discord bot or Docs widget will be developed using the latest Large Language Models (LLMs) and other cutting-edge technologies. Here’s an outline of the technical components involved in the project:
Data Collection and Indexing: This phase involves collecting data from Nervos’ GitHub repositories, official documentation, relevant articles, and past Q&A from Discord. We will use the Llama Index to set up indices and a vector database to enable embeddings-based search on queries.
Bot Development: We plan to use Python for the bot’s back-end development. This involves the integration of LLMs like OpenAI for understanding and generating responses to user queries. In the front-end, we will ensure seamless integration with Discord or as a widget for the documentation page.
Optimization: This phase includes refining prompt engineering and eradicating any hallucinations or mismatches. We’ll be using tools like Deeplake and Cohere for enhancing performance and achieving optimized results.
Deployment and Maintenance: The bot will be hosted on Digital Ocean, ensuring high availability and performance. Regular maintenance, updates, and improvements will be part of our ongoing commitment.
Proposed Technology Stack:
- OpenAI
- Llama Index
- Digital Ocean (hosting)
- Deeplake
- Cohere
- NextJS + Vercel for Web App deployment
Funding Requirements:
We request a $7,500 USD grant to build and maintain the bot. The budget allocation includes:
- Infrastructure costs: 12 month provision (depending on usage)
- OpenAI token usage
- Digital Ocean hosting
Development costs:
- Contract work from Data Science/ML experts if needed.
- Time & materials for developing integrations.