Iulia Feroli
Senior Developer Advocate @Elastic
Amsterdam, The Netherlands
Actions
After working on many sides of tech I’ve finally found my perfect match as a developer advocate at Elastic - focusing on creating content for, and learning from the tech community. I love creating videos, blogs, demos and sessions to get people excited about the possibilities of tech. I specialize in anything NLP, search, data science, MLOPs, generative AI, and more.
Links
Area of Expertise
Topics
Harry Potter and the Elastic Python Clients
Ever wanted to revisit your favourite moments in a book or movie? To find that specific scene you don’t remember the exact dialogue from, but you know it was funny or emotional? Look no further! Call it overkill, but I’ve indexed the Harry Potter books and movie scripts to enable just that - complex, semantic search. By combining different third party LLMs (like sentiment analysis) and native vector search capabilities; with some extra special Elastic optimising magic sprinkled on top - we can go on a magical search journey. All of it powered by the (multiple!) Elastic Python clients.
Grounding RAG Applications with JavaScript, Langchain and Elasticsearch (part1)
Everywhere we look we see examples of leveraging AI technologies not just while building software, but in our web applications too. While developers want to embrace new shiny technologies, tech leaders raise concerns about the risk of exposing their data for training alongside other accuracy issues such as source hallucination.
Using vector search and other data sources alongside LLMs can ground applications to a known source, allowing domain-specific responses to be generated. In this workshop, you'll build 2 AI applications to learn about RAG, AI agents and technologies including AI SDK, Langchain, JS and Elasticsearch, while pointing out alternatives along the way.
Build a RAG application with LLMs, semantic search, and GenAI
Are LLMs the shiniest toys around that everyone wants added to their solution ASAP? Or are the potential hallucinations, data security concerns, and steep learning curve still putting you off from giving into the hype?
There’s no better fix than just trying it out yourself.
This is your chance to dedicate a few hours to understanding and experimenting with the necessary building blocks and running your own RAG solution. At the end of this workshop you’ll have your own running web-based retrieval-augmented assistant, grounded on your personal data. Not only that, since we’re designing a modular solution, you can easily swap models, data handling, prompts, or design choices to adapt and evolve your app whenever you want to experiment with the new kid on the block.
Cure your GenAI FOMO and check off that “figure out this LLM thing” off your to-do list today!
## Overview
* Quick breakdown of LLMs, vectors & embeddings, semantic search, GenAI, popular open source tools, models & frameworks
(i.e. Llama, Mistral, Gemma, HuggingFace, LangChain, etc)
* Model selection up to the user - customising your app according to desired use case w/ starter code blocks
* Experiment with chunking strategies & data input
(optional to integrate with data stored in a different source)
* Build RAG architecture with LangChain & ElasticSearch
(optional to explore other chain options)
* Build web interface with Python + Flask
(optional explore alternatives like JS and PHP for front end w/ additional repos)
* Test model & responses, prompt engineering, introduce testing pipeline & observability intro
## Requirements & Materials
* Class will follow a GitHub tutorial w/ worksheets & code samples
* Bring your laptop, have a code editor, Python installation, and Docker setup
* Pre-requisite work (options & instructions will be included in repo):
* Download the LLM(s) of choice (default will be ollama + llama3.1)
* Install ElasticSearch (locally or via cloud)
Building my own (accurate!) Spotify Wrapped
Wrapped has become one of the most widely anticipated data analytics dashboards of the year. But what happens when the results aren't as complex (or accurate) as people were expecting? Data scientists come in to save the day!
Using elasticsearch and kibana I will be creating my own musical trends and insights using the user generated data - that you can also download and follow along with!
From queries, filters, and aggregations to visualizations, time series analysis, and brat summer - we will explore how search analytics can be used for every day cases.
Open Source Day 2024 Sessionize Event
DevWorld
7,500 DEVELOPERS - FESTIVAL OF TECH
Session: Harry Potter and the Elastic Python Clients
WeAreDevelopers Live 2024 (Season 7) Sessionize Event
Iulia Feroli
Senior Developer Advocate @Elastic
Amsterdam, The Netherlands
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top