PROJECT 2025

Meeting 6/30

Housekeeping

Introduction

Attendees

Mentorship

Contributors Workflow

Web Site / Blog

Have updates to share this month?

We're preparing the June edition of the decentralized digest, reaching over 300k subscribers.

If you'd like your project, blog, or news announcement featured, simply upload your URL(s) here

Thank you for your continued contributions!

Dev Issues

Project #1
RAG Multi Agent

LF Event CFP Dashboard

Open Source AI Week | LF Events

Find alternative to LANCHAIN create our own or find other libraries.

Project #2
Snowflake Connection

Meeting Tuesday with Timm 12pm edt Join our Cloud HD Video Meeting 819 5510 3058Passcode: tB32hH

https://us05web.zoom.us/j/81955103058?pwd=BJHtTHFfXbbptZCpipYlTm1XwkTvRh.1 ID: 819 5510 3058 Passcode: tB32hHNew Ideas

Open Source AI Week 2025

Summary:

NEW IDEAS

KBAI -

Transcript:
Overview

Action Items

More options

Outline

✨ AIFAQ 2025 Goals

1. Overall Project Goals for AIFAQ (Organizational Level)

(To move from Sandbox to Incubation at LFDT and get early paying customers)

a. Technical and Community Goals (to qualify for Incubation at LFDT):

• Expand Active Contributors: Grow to at least 5+ consistent contributors outside the founding team, documented in GitHub activity.

• Establish Governance: Implement a clear Technical Steering Committee (TSC) charter and lightweight governance model aligned with LFDT best practices.

• Production-Ready MVP: Deliver a production-quality MVP for the AIFAQ platform, showing enterprise-grade performance, security, and usability.

• Document Use Cases: Publish 2–3 real-world case studies demonstrating AIFAQ solving enterprise FAQs or documentation automation.

• Community Engagement: Host at least 2 public webinars, 1 workshop, and quarterly updates to the LFDT and open-source community.

• Security and Compliance: Complete basic security audits and compliance documentation (e.g., data handling policies).

b. Business Goals (to build customer traction):

• Land 2–3 Pilot Customers: Sign early-stage pilot programs with at least 2–3 enterprise customers (offering free or discounted pilots initially).

• Launch Paid Offering: Define pricing tiers and launch a beta paid service (SaaS or managed service model) by Q4 2025.

• Marketing & Sales Enablement:

  • Publish one white paper describing AIFAQ’s unique value proposition.

  • Create sales deck, website landing page, and downloadable 1-pager for outreach.

• Investor and Grant Readiness: Prepare a pitch deck and start conversations with potential grants or impact investors aligned with AI/OSS innovation.

Mentorship Project Goals

A. Multi-Agent RAG (Retrieval-Augmented Generation) System

Technical Goals:

• Multi-Agent Architecture: Build a working prototype of modular agents (retriever, router, summarizer, responder) communicating through an orchestrator.

• Plugin Support: Enable pluggable data sources (e.g., Confluence, GitHub Wikis, custom PDFs).

• Scalable RAG Pipeline: Implement efficient document chunking, embedding caching, and vector search optimizations.

• Agent Collaboration Logic: Develop logic for agents to delegate subtasks among themselves dynamically (example: a retriever agent passes relevant docs to a summarizer agent).

• Baseline Evaluation Metrics: Create benchmark tests to measure precision, latency, and accuracy improvements vs. a simple single-agent model.

Community Deliverables:

• Public Demo Repository with a clean README and deployment instructions (Docker optional).

• Technical Blog Post: Write a blog post showcasing how multi-agent RAG outperforms single-agent baseline.

B. Snowflake Connector for AIFAQ

Technical Goals:

• Data Pipeline Integration: Build a robust connector to extract structured FAQ or knowledge base data from Snowflake tables.

• Authentication & Security: Implement secure authentication (OAuth, token-based) for enterprise Snowflake accounts.

• Connector API: Develop a simple API interface to trigger data pulls, syncs, and refreshes on-demand.

• Auto-Sync and Scheduling: Allow scheduled pull jobs and delta updates (new or modified rows only).

Business/Strategic Deliverables:

• Enterprise Use Case Demo: Showcase pulling an enterprise customer’s knowledge base into AIFAQ using Snowflake in a demo environment.

• Documentation & SDK: Release an open-source SDK or connector package on GitHub with easy-to-follow examples.

• Outbound Messaging: Write 1 LinkedIn article or case study targeting Snowflake’s huge enterprise customer base (joint marketing potential if successful).

MEETING NOTES

Meeting 6/23

Meeting 6/23
https://docs.google.com/presentation/d/1cmt_UeWI2mg6zt-O0aWvC3gnD4p_L9T-bKUO9hHkgys/edit?slide=id.g3680bd627b5_0_0#slide=id.g3680bd627b5_0_0

Housekeeping

Introduction

Attendees
Bobbi Muscara (Me)te

Suryansh Shakya

Anuj SaxenaLP

LOCHAN PAUDELRM

Ryan MadhuwalaGC

Gianluca Capuzzi

Jayaram

Mercy Boma

Sumana Sree

Peter Chmiel

Mentorship

Contributors Workflow

Web Site / Blog

Have updates to share this month?

We're preparing the June edition of the decentralized digest, reaching over 300k subscribers.

If you'd like your project, blog, or news announcement featured, simply upload your URL(s) here

Thank you for your continued contributions!

Dev Issues

Project #1
RAG Multi Agent

LF Event CFP Dashboard

Open Source AI Week | LF Events

Find alternative to LANCHAIN create our own or find other libraries.

Project #2
Snowflake Connection

Meeting Tuesday with Timm 12pm edt Join our Cloud HD Video Meeting riunione: 819 5510 3058Passcode: tB32hH

https://us05web.zoom.us/j/81955103058?pwd=BJHtTHFfXbbptZCpipYlTm1XwkTvRh.1 ID: 819 5510 3058 Passcode: tB32hHNew Ideas

Open Source AI Week 2025

Summary:

NEW IDEAS

KBAI - example of how/where to deploy our solution

Peter

Transcript:
Overview

The meeting focused on improving the developer's guide, suggesting a clean repository with three branches: main, agents, and snowflake. A workflow for contributors was outlined, including forking the repo, creating local branches, coding, committing, and opening pull requests. A user guide for onboarding people was also discussed. The team is working on a proof of concept with Snowflake, using FIDO documents and achieving a 1-hour implementation. They plan to create new issues for response pages and vector database content display. Additionally, the idea of using graph databases for improved similarity search was proposed, and a new website for project contributions was introduced.

Action Items

More options

This list can be reordered. To drag an action item, press space or enter on the drag handle. Use the up and down arrow keys to move the action item. To drop the item, press space or enter again. To cancel drag and drop, press escape.

Create a new page to display a list of responses, showing the question, answer, and relevant documents.

 Implement a feature to display the content of the vector database in the Streamlit app.

 Investigate moving prompts to text files instead of keeping them in the config file.

 Implement the code to handle downloading and ingesting YouTube video transcripts.

 Investigate using graph databases for improved similarity search, in addition to the current vector database approach.

Outline

Using new technologies for client problems, with a focus on cleaning the repository and creating a developer's guide.

Developers should clean the repository and create three branches for different projects.

Creating a user guide for onboarding people in a project, with a focus on GitHub activities and flow.

Developer creates list of commands with screenshots to avoid common errors in GitHub activities.

Creating Wiki pages for developer workflow and contribution guidelines.

Unknown Speaker considers creating Wiki pages for developer workflow and contributions.

Implementing a new project management tool, with mentions of Snowflake and multi-agent systems.

Unknown Speaker seeks input on designing a wiki page for tracking workflow and issues related to snowflake and multi-agent projects.

Using Snowflake for data storage and analysis.

Unknown Speaker discusses snowflake activities with Tim and Jairam, sharing a short guide for implementation.

Uploading data into Snowflake database for semantic search.

Unknown Speaker discusses joining Founder Casetone program and uploading files to Snowflake.

Using Snowflake cloud and Streamlit for data analysis.

Unknown Speaker discusses using Snowflake cloud and Streamlit to create a fast and easy page.

Improving language model responses with new features.

Unknown Speaker discusses improving response quality in Snowflake, including creating a new page for storing and displaying responses.

Using Python script to extract dictionary content from files and search for substrings in text.

Unknown Speaker discusses Python script for extracting dictionary content from files and searching for substrings in text.

Implementing a Python script to handle YouTube video transcripts.

Unknown Speaker discusses implementing a Python script to handle YouTube video transcripts.

Improving similarity search algorithm using metadata and graph databases.

Unknown Speaker discusses improving similarity search algorithm using metadata and graph DB.

Using agents tools for training and finding niche in the market.

Unknown Speaker discusses using agents tools for training, competing with larger companies, and scheduling a meeting on the wiki page.

Improving data extraction for crypto and fi projects.

Unknown Speaker discusses updating data for Fi and crypto Mondays, manually extracting text and creating Python script to automate process.

Speaker plans to clean and align local and online versions, remove unnecessary data, and test for bad answers before deploying to production or local environment.

Using land graph and lane chain for data storage, and potential use of semantic network for chat bot development.

Unknown Speaker discusses land graph and land chain solutions for chat memory (12 words)

Speaker mentions semantic network used by crypto Mondays for chat bot (13 words)

Graph databases and vector databases for improved similarity search.

Unknown Speaker discusses graph database and vector DB for similarity search, mentioning potential partnership or integration.

Unknown Speaker shares link to graph database company's website for further investigation.

Using AI to answer supply chain questions through chatbots.

Unknown speaker discusses using AI to answer supply chain questions within messaging platforms.

Using chatbots for community onboarding and differentiating from competition.

Unknown Speaker discusses using Chatbot in Discord for onboarding contributors in a community.

Speaker shares a real-use case for Chatbot, highlighting its potential for differentiation and improvement of skills.

Creating a website for AI Fauci project with GitHub integration.

Unknown Speaker: Created website for AI Fauci project, showcasing contributions and issues.

Unknown Speaker: Developers can use website to easily contribute to AI Fauci project.

Hello Community,

Have updates to share this month?

We're preparing the June edition of the decentralized digest, reaching over 300k subscribers.

If you'd like your project, blog, or news announcement featured, simply upload your URL(s) here

Thank you for your continued contributions!

_._,_._,_

Dev Meeting 6/16
https://docs.google.com/presentation/d/1XHg3eHJkDbyjBVOBjqU6M67GtFdm6jByFH3oSFvoqQA/edit?slide=id.g2ee9afa5c40_0_0#slide=id.g2ee9afa5c40_0_0

• Mentorship Orientation Session

• Contribution workflow

• Multi-agents activities

• Snowflake activities

Housekeeping

Introduction

Attendees

Bobbi Muscara (Ledger Academy) (Me)

Anuj saxena

Suryansh Shakya 

Ryan Madhuwala

Gianluca Capuzzi

LOCHAN PAUDEL

Jayaram

More 

Mercy Boma

Mentorship

Mentorship Orientation session this coming Tuesday, June 17th at 8am Pacific.

Min Yu is inviting you to a scheduled Zoom meeting.
Join Zoom Meeting
https://zoom.us/j/98669319646?pwd=RZGxaVms3Y12lYQHdktPSA5djsjvaq.1

Meeting ID: 986 6931 9646
Passcode: 252379

Contributors Workflow

https://docs.google.com/document/d/1TFjbMEqZbZlB8wklabpY3Tc9qA0VxThW/edit

https://docs.google.com/document/d/1TFjbMEqZbZlB8wklabpY3Tc9qA0VxThW/edit?usp=sharing&ouid=105225806016454599738&rtpof=true&sd=true

Web Site / Blog

Dev Issues

Open

Project #1
RAG Multi Agent

LF Event CFP Dashboard

Open Source AI Week | LF Events

Find alternative to LANCHAIN create our own or find other libraries.

Project #2
Snowflake Connection

New Ideas

Open Source AI Week 2025

Summary:

Dev Meeting 6/9

Housekeeping

https://docs.google.com/presentation/d/1QsI-XwWaSRSkxP3hLOJF-72oDzD-xKnJIiflNuj4AH8/edit?slide=id.g2a7ffc9cce9_0_5#slide=id.g2a7ffc9cce9_0_5

https://docs.google.com/presentation/d/1QVmZOgZvDcMU151N7HoIh1Nuiq1HUt8_6tmdV4VfAFY/edit?usp=sharing

Introduction

Attendees

Dev Issues
https://lf-hyperledger.atlassian.net/wiki/spaces/labs/pages/20290949/AI+FAQ+2025#Dev-Issues

Web Site / Blog

• Test System:
  3 ways 1) login in and asak questions, 2) Request admin access to add documents, NEED YOUTUBE VIDEO TESTERS. 3) Copy the code to your local device and update sections for Gianluca review.

Project #1
RAG Multi Agent

https://events.linuxfoundation.org/open-source-summit-korea/

https://events.linuxfoundation.org/open-source-summit-japan/

Introduce Team Leaders
Lonhan Paudel and Ryan M
Create information to present to the group to teach us about the project
Future:
Apply project to Open Source AI Week 2025

Project #2
Snowflake Connection

Introduce Team Leaders
Sumana S and Jayaram
Future:
Prepare presentation for the Princeton blockchain and AI meetup late June early July and research global events in the fall.

New Ideas

Open Source AI Week 2025

Summary:

Outline

Besu activity and onboarding sessions with a focus on Linux Foundation and decentralized trust.

Unknown Speaker discusses Besu activity and onboarding sessions with Bobbi.

Testing and installing a system for generating responses to questions.

Ryan proposes testing the system by installing a local version and assigning tasks to agents and mentees.

Linux Foundation development meeting, attendees introduce themselves.

Ranit introduces himself as a new attendee and mentions working on ethics projects for CNCF.

Testing a system with Ryan and J RAM.

Ryan shares his document on testing issues for the main system.

AI model's accuracy in providing detailed answers.

Unknown Speaker tested Chatbot's accuracy on 50 questions, finding it impressively accurate in providing step-by-step guidance.

Chatbot struggled with precise value answers, repeating questions and failing to provide direct answers in some cases.

Speaker suggests improving the model's decision-making process to provide more detailed answers while maintaining accuracy.

Comparing chat GBT and Basu for privacy issues and installation.

Unknown Speaker compares ChatGBT and Basu's privacy approaches, finds interesting options.

AI chatbot's accuracy and limitations.

Unknown Speaker: ChatGPT provided correct answers, but sometimes gave "cop-out" responses.

Unknown Speaker: ChatGPT didn't analyze information correctly, and sometimes gave false positives.

Unknown Speaker: ChatGPT doesn't hallucinate, but it doesn't follow the same project as the system being developed.

Testing a knowledge base system with admin access.

Unknown Speaker grants admin access to test system, add documents, and ask questions.

Speaker discovers issues with YouTube video downloads, unsure of exact cause.

Downloading YouTube video transcripts using Langchain library, with issues related to updated AWS and community forum messages.

Unknown Speaker discusses issues with downloading YouTube video transcripts and potential solutions.

Testing and improving a system, with emphasis on local installations and GitHub collaboration.

Unknown Speaker encourages listeners to test and learn the system, then propose solutions and code changes.

Mentorship program orientation and onboarding.

Unknown Speaker encourages mentees to attend Linux Foundation orientation meeting on June 17.

Speaker discusses using Slack channel for dev issues and testing Linux Foundation wiki page.

AI project assignments and snowflake program.

Unknown Speaker suggests team members work on separate projects related to AI and snowflake.

Jen Luca agrees, proposes short presentation on project expectations next week.

Mentorship projects for AI FAQ lab, goal is to move from labs to incubation.

Unknown Speaker suggests sharing information through Slack or informal meetings to help mentorship projects.

Unknown Speaker encourages individuals to get involved in maintaining the code base for AI FAQ project at Hyperledger or Linux Foundation.

Website design and development.

Jen, Luca, and Peter discuss design for crypto Mondays website, including color scheme and layout.

They agree to schedule a meeting to finalize content and upload to WordPress.

Promoting blogs and social media, testing Linux Foundation projects, and improving website and mentorship.

Unknown Speaker encourages team to share blog posts and LinkedIn posts to build a fan base for the project.

Unknown Speaker plans to send action items to test the system and summarize results, with a goal of getting a website meeting for the team.

AI and Linux projects, with mention of paid version and GPU.

Ryan discusses their spider project, including coding and AI elements.

Open source AI event and project registration.

Unknown Speaker suggests following social media accounts for project exposure (0:48:18)

Unknown Speaker mentions open source AI week event with registration open till June (0:49:40)

Open source AI event planning and snowflake project presentation.

Unknown Speaker discusses open source AI week in October, looking for project alignment and potential travel support.

Snowflake team presentation opportunity in September or October, possibly at Linux Foundation event or open source conference.

Dev Meeting 6/2

Housekeeping

https://docs.google.com/presentation/d/1QsI-XwWaSRSkxP3hLOJF-72oDzD-xKnJIiflNuj4AH8/edit?slide=id.g2a7ffc9cce9_0_5#slide=id.g2a7ffc9cce9_0_5

Introduction

Attendees

Dev Issues
https://lf-hyperledger.atlassian.net/wiki/spaces/labs/pages/20290949/AI+FAQ+2025#Dev-Issues

Web Site / Blog

Project #1
RAG Multi Agent

Introduce Team Leaders

Project #2
Snowflake Connection

Introduce Team Leaders

New Ideas

Meeting Notes

https://lf-hyperledger.atlassian.net/wiki/spaces/labs/pages/20290949/AI+FAQ+2025#Meeting-Notes

Dev Meeting 5/13

Gianluca Capuzzi M

Himanshu MahajanAW

Akshay WaghmareAJ

Ayush JhaAW

Amarta Waghani

MADUGULA JAYARAM

Shafayet Ahmed

Siddharth Lalwani

Mercy Boma

Peter Chmiel

Sumana Sree

Dev Meeting 5/6

Bobbi Muscara, Gianluca, Peter, Anju Maurya, Siddharth Lalwani, Rajas Samse (Student), Amrita Waghani, MADUGULA JAYARAM, Altafur Rahman

2024Learning Objectives

• Learn LLM background technology

• Learn Javascript language and framework

• Learn basics of Front-end development

• Learn Cloud architecture and deployment

• Learn how to create high quality documentation

Expected Outcome and Deliverables

• An LLM prototype with acceptable time response and implementation costs

• A Front-end component prototype

• A simple container architecture

• A good quality documentation

A huge thank you to everyone who applied — we had an impressive pool of
candidates, and we're happy to share that 4 mentees have been accepted
into the program. 🙌

Note: Starting this cycle, accepted mentees will no longer receive
stipends, but will be eligible for travel expense allotments to present
their work at approved conferences and events.

We're also opening up additional spots through our Collaborative
Learning Program — more details coming Monday. Don't miss the kickoff
meeting — it's going to be packed with exciting learning opportunities,
project deep dives, and ways to get involved!