- Unstructured Data in LLMs88 Colin P Kelly Jr St, San Francisco, CA
This is an in-person event! Registration is required to get in. Github will email you a form the day before the event, which you will need to complete for your access pass. Registration will close 2 days before the event.
Topic: Connecting your unstructured data with Generative LLMs
What we’ll do:
Have some food and refreshments. Hear three exciting talks about unstructured data and generative AI.
5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Jiang Chen, Head of Ecosystem & AI Platform, Zilliz
6:35 - 7:00 - Mike Del Balso, CEO and Co-Founder, Tecton
7:05 - 7:30 - Chaoyu Yang, CEO & Founder, BentoML
7:35 - 7:45 - Yi Zhang, CEO & Co-founder, Relari.ai
7:45 - 8:30 - NetworkingWho Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.Tech Talk 1: Building RAG with self-deployed Milvus vector database and Snowpark Container Services
Speaker: Jiang Chen
Abstract: This talk will give hands-on advice on building RAG applications with an open-source Milvus database deployed as a docker container. We will also introduce the integration of Milvus with Snowpark Container Services.Tech Talk 2: Full RAG: A Modern Architecture for Hyperpersonalization
Speaker: Mike Del Balso
Abstract: Mike Del Balso, CEO & Co-Founder at Tecton, presents "Full RAG," a novel approach to AI recommendation systems, aiming to push beyond the limitations of traditional models through a deep integration of contextual insights and real-time data, leveraging the Retrieval-Augmented Generation architecture. This talk will outline Full RAG's potential to significantly enhance personalization, address engineering challenges such as data management and model training, and introduce data enrichment with reranking as a key solution. Attendees will gain crucial insights into the importance of hyperpersonalization in AI, the capabilities of Full RAG for advanced personalization, and strategies for managing complex data integrations for deploying cutting-edge AI solutions.Tech Talk 3: RAG as a service with BentoML
Speaker: Chaoyu Yang, BentoML
Abstract: Building Retrieval-Augmented Generation (RAG) systems with open-source and custom AI models is a complex task. This talk explores the challenges in productionizing RAG systems, including retrieval performance, response synthesis, and evaluation. We’ll discuss how to leverage open-source models like text embeddings, language models, and custom fine-tuned models to enhance RAG performance. Additionally, we’ll cover how BentoML can help orchestrate and scale these AI components efficiently, ensuring seamless deployment and management of RAG systems in the cloud.Lightning demo: Using Synthetic Data to Test and Fine-Tune LLM applications
Speaker: Yi Zhang, Relari ai
Abstract: In this talk, Yi will walk through a data-driven approach to test and improve LLM / RAG applications. In particular, he will cover how to use Relari's synthetic data platform and open-source evaluation framework "continuous-eval" to systematically harden and fine-tune LLM systems. Relari is backed by top investors including Y Combinator, Soma Capital and General Catalyst.When:
June 3, 2024
5:30PMWhere:
This is an in-person event! Registration is required to get in. Registration will close 2 days before the event. Co-sponsored by Zilliz (maintainers of Milvus) and Tecton.Can't make it in person? We will also be streaming live: https://www.twitch.tv/vectordatabase
- Unstructured Data in LLMs88 Colin P Kelly Jr St, San Francisco, CA
This is an in-person event! Registration is required in order to get in. Github will email you a form the day before the event, which you will need to complete for your access pass.
Topic: Connecting your unstructured data with Generative AI
What we’ll do:
Have some food and refreshments. Hear three exciting talks and a demo about unstructured data and generative AI.5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Sourabh Agrawal, Co-founder and maintainer, UpTrain
6:35 - 7:00 - Jiang Chen, Head of Ecosystem & AI Platform, Zilliz
7:05 - 7:30 - Shangyin Tan, key contributor, DSPy
7:35 - 7:45 - Community demo - Ben Cerchio & Ming He, Co-founders, Secludy
7:45 - 8:30 - NetworkingTech Talk 1: Challenges associated with using LLM-as-a-judge
Speaker: Sourabh Agrawal
Abstract: Using LLMs to determine quality of LLM applications has gained a lot of interest recently, rightly so because it is highly scalable and solves the subjective nature of human evaluations. However, building production-grade evaluations is much more complicated than prompting the LLM to act as a judge and grade the given response. In this talk, we will cover the key techniques employed in industry + academia on how to effectively define LLM-based evaluations, understand associated challenges and look at what lies beyond evaluation. We will learn real-world instances of how these evaluations can be leveraged to improve your LLM applications.Tech Talk 2: Building production ready data pipelines with Milvus and Spark
Speaker: Jiang Chen
Abstract: Spark is the widely used ETL tool for processing, indexing and ingesting data to serving stack for search. Milvus is the production-ready open-source vector database. In this talk we will show how to use Spark to process unstructured data to extract vector representations, and push the vectors to Milvus vector database for search serving.Tech Talk 3: Programming Foundation Models with DSPy
Speaker: Shangyin Tan
Abstract: Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.Community Demo: Generating privacy-protected synthetic data using Secludy and Milvus
Speakers: Ben Cerchio and Ming He
Abstract: During this demo, the founders of Secludy will demonstrate how their system utilizes Milvus to store and manipulate embeddings for generating privacy-protected synthetic data. Their approach not only maintains the confidentiality of the original data but also enhances the utility and scalability of LLMs under privacy constraints. Attendees, including machine learning engineers, data scientists, and data managers, will witness first-hand how Secludy's integration with Milvus empowers organizations to harness the power of LLMs securely and efficiently.Who Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.When:
June 10, 2023
5:30PMWhere:
This is an in-person event. Registration using this form is required to get into the event. Registration in advance will close 2 days before the event. Sponsored by Zilliz maintainers of Milvus.Can't make it in person? We will also be streaming live: https://www.twitch.tv/vectordatabase
- Unstructured Data in LLMs88 Colin P Kelly Jr St, San Francisco, CA
This is an in-person event! Registration is required in order to get in. Github will email you a form the day before the event, which you will need to complete for your access pass.
Topic: Connecting your unstructured data with Generative AI
What we’ll do:
Have some food and refreshments. Hear three exciting talks about unstructured data and generative AI.5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Charles Xie, CEO, Zilliz
6:35 - 7:00 - Joe Maionchi, VP R&D, Aparavi
7:05 - 7:30 - Tech Talk 3
7:35 - 7:45 - Community demo
7:45 - 8:30 - NetworkingWho Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.Talk 1: Milvus and Zilliz
Speaker: Charles XieTech Talk 2: Unstructured Data Preparation for AI
Speaker: Joe Maionchi
Abstract: Aparavi is a privacy-centric data fabric platform that provides deep intelligence for corporate unstructured data without moving, copying, or sharing the data. It automates data preparation for AI projects, adding classifications, anonymizing PII, and ensuring full traceability of embeddings back to the source.We'll demonstrate how Aparavi's Platform can find, clean, and embed data from a large variety of distributed unstructured data sources (e.g. Outlook, Google Drive, Azure) into an AI project using the Milvus vector DB. We'll then retrieve semantically relevant corporate information based on a user query, anonymize PII, and feed it into an on-prem retrieval-augmented LLM, showcasing a conversation with your enterprise data.
When:
July 16, 2023
5:30PMWhere:
This is an in-person event. Registration using this form is required to get into the event. Registration in advance will close 2 days before the event. Co-sponsored by Aparavi and Zilliz maintainers of Milvus.Can't make it in person? We will also be streaming live: https://www.twitch.tv/vectordatabase
- Unstructured Data in LLMs88 Colin P Kelly Jr St, San Francisco, CA
This is an in-person event! Registration is required in order to get in. Github will email you a form the day before the event, which you will need to complete for your access pass.
Topic: Connecting your unstructured data with Generative AI
What we’ll do:
Have some food and refreshments. Hear three exciting talks about unstructured data and generative AI.5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Tech Talk 1
6:35 - 7:00 - Tech Talk 2
7:05 - 7:30 - Tech Talk 3
7:35 - 7:45 - Community demos
7:45 - 8:30 - NetworkingWho Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.When:
August 5, 2023
5:30PMWhere:
This is an in-person event. Registration using this form is required to get into the event. Registration in advance will close 2 days before the event. Sponsored by Zilliz maintainers of Milvus.Can't make it in person? We will also be streaming live: https://www.twitch.tv/vectordatabase
- Unstructured Data in LLMs88 Colin P Kelly Jr St, San Francisco, CA
This is an in-person event! Registration is required in order to get in. Github will email you a form the day before the event, which you will need to complete for your access pass.
Topic: Connecting your unstructured data with Generative AI
What we’ll do:
Have some food and refreshments. Hear three exciting talks about unstructured data and generative AI.5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Tech Talk 1
6:35 - 7:00 - Tech Talk 2
7:05 - 7:30 - Amit Sangani, Senior Director, Meta
7:35 - 7:45 - Community demos
7:45 - 8:30 - NetworkingTech Talk 3: Llama 3 !!
Speaker: Amit SanganiWho Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.When:
September 9, 2023
5:30PMWhere:
This is an in-person event. Registration using this form is required to get into the event. Registration in advance will close 2 days before the event. Sponsored by Zilliz maintainers of Milvus.Can't make it in person? We will also be streaming live: https://www.twitch.tv/vectordatabase