Edward

809 posts

Edward banner
Edward

Edward

@aestheticedwar1

Machine Learning Engineer at @weaviate_io passionate about open source, machine learning and indie games! ✨

Berlin Katılım Eylül 2019
405 Takip Edilen2.3K Takipçiler
Sabitlenmiş Tweet
Edward
Edward@aestheticedwar1·
Open Source RAG with Ollama! 🥳 YouTube: youtube.com/watch?v=swKKRd… The newest Verba v1.0.0 update is out, and it’s... ✨ B-E-A-U-T-I-F-U-L ✨  We added many exciting things to Verba, including open-source models powered by Ollama, Frontend Customization, and many Quality of Life features. It’s so much; we made a whole video about it. Watch the deep-dive video by @victorialslocum , @philipvollet , and me to learn how to set up a local-running open-source RAG app in just a few minutes. You can also try out the new Verba version directly in our free live demo: Live Demo: verba.weaviate.io If you want to start immediately, this GitHub Repo covers you! (We also just hit the 2.6k stars 🎉). It contains all the information about features and installation. GitHub: github.com/weaviate/Verba
YouTube video
YouTube
Edward tweet media
English
7
82
398
40.1K
Edward
Edward@aestheticedwar1·
I've been testing something that makes me forget I ever needed to code. The next version of Elysia is about to change how you build AI workflows. We're excited to share that the Weaviate team has started building the next version of Elysia – and it's bringing some pretty promising capabilities to the table. The headline feature: Pipeline Builder. ⚒️ 🤓 Here's what it does: With the Pipeline Builder, you can now create your own custom tools and orchestrate custom decision trees directly in the frontend. This means you get complete flexibility to design workflows for any use case you need – whether that's specialized data retrieval, multi-step reasoning processes, or entirely custom agentic behaviors – all while harnessing the complete Elysia infrastructure. For context, Elysia's existing architecture already supports custom tools and conditional branching in Python; however, bringing this capability to the frontend opens up the framework to a much wider range of users and use cases. You can iterate faster, experiment with different configurations, and build sophisticated agentic workflows without context-switching between code and interface. You can read more about Elysia in our recent blog post, GitHub and Documentation Blog Post: weaviate.io/blog/elysia-ag… GitHub: github.com/weaviate/elysia Documentation: weaviate.github.io/elysia/
Edward tweet media
English
0
3
9
702
Edward retweetledi
Bela Wiertz
Bela Wiertz@blwiertz·
300 people queuing for Big Berlin Hack We are soo back! 🚀
Bela Wiertz tweet media
English
25
8
141
7.8K
Edward retweetledi
Bela Wiertz
Bela Wiertz@blwiertz·
1 day of building the future of AI in London 👇 See the full episode on YT: @Tech-Europe" target="_blank" rel="nofollow noopener">youtube.com/@Tech-Europe
English
1
3
11
750
Edward retweetledi
Victoria Slocum
Victoria Slocum@victorialslocum·
The London AI Hack was absolutely epic. Hosted by @techeurope_ @weaviate_io @elevenlabs @OpenAI and so many others in @meetgranola's London office, it was such a sick venue for an amazing event. Seeing the amount of builders building the coolest projects - from AI apps to wild experiments - made the energy absolutely unreal. We’re hosting our next biggest hack ever next month in Berlin, see you there? luma.com/big-berlin-hack Shoutout round: @blwiertz @NimaSadeghifard the best hosts, @aestheticedwar1 the epic videographer, @drdannywilliams @philipvollet and all you others who made the day even better 😄
English
1
6
30
2.2K
Edward retweetledi
Adam / AJ Chan
Adam / AJ Chan@itsajchan·
𝐁𝐮𝐢𝐥𝐝𝐢𝐧𝐠 𝐀𝐈 𝐚𝐠𝐞𝐧𝐭𝐬 𝐢𝐬 𝐡𝐚𝐫𝐝. Prompt engineering is a nightmare, and connecting them to your data and tools is a complex mess. What if you could solve all three at once? That's exactly what I explored in my latest AI Engineer Spotlight episode with @vinit_agr and @jindalish , the creators of the conversational agent platform, hellotars.com. They’ve built a system that lets any developer create a sophisticated AI agent that can: 1️⃣ 𝐀𝐜𝐜𝐞𝐬𝐬 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞: We plugged in our entire Weaviate documentation, which Tars indexed into a vector database (powered by @weaviate_io! 🚀) for smart, accurate retrieval. 2️⃣ 𝐔𝐬𝐞 𝐓𝐨𝐨𝐥𝐬: The agent seamlessly captured my details and sent them to a Google Sheet—but it could just as easily be Salesforce or HubSpot. 3️⃣ 𝐓𝐡𝐢𝐧𝐤 & 𝐑𝐞𝐚𝐬𝐨𝐧: Tars’s prompt generator created the agent’s "brain" from a simple, high-level goal. The result? A production-ready agent built in minutes, not weeks. Check out the full episode to see how they're abstracting away the complexity of building conversational AI. Link in the comments! Congrats to the Tars team on their incredible work! Want to try out Weaviate? Create a free cluster today --> https://console[dot]weaviate[dot]cloud console.weaviate.cloud
English
1
4
13
1.4K
Edward retweetledi
Bela Wiertz
Bela Wiertz@blwiertz·
🚀 I’m creating Europe’s most ambitious builder space: The Sandbox. I believe the ceiling of what you can achieve is defined by the 6–8 people you work with every day. Beyond that, the marginal value of ambition around you quickly decreases. In San Francisco, you find those people on every corner. In Europe, not so much. That’s why we need to actively create spaces where the most ambitious builders can meet, collide, and create. If we don’t, the next generation of founders and innovators will book a one-way ticket, and Europe will lose them. That’s what The Sandbox is here to change. 🎥 The first video from Week 1 is now live on the @techeurope_ YouTube channel (@Tech-Europe" target="_blank" rel="nofollow noopener">youtube.com/@Tech-Europe). 👉 Follow the journey, and/or apply to join us (forms.techeurope.io/sandbox/applic…).
English
4
14
62
3.6K
Edward retweetledi
Bela Wiertz
Bela Wiertz@blwiertz·
🚀 A weekend made for all European builders! 📅 October 11–12 | 📍 Berlin | 👩‍💻 300+ builders | 🌙 2 days + overnight hacking Join Now: luma.com/big-berlin-hack
English
0
5
29
2.2K
Edward retweetledi
Build Fast with AI
Build Fast with AI@BuildFastWithAI·
🚀 Meet Elysia : The Agent Framework That Runs & Chooses Tools For You. - Build custom tools in minutes - Query your own DB via @weaviate_io - Agents handle regression, correlations & predictions - From simple math → advanced analysis Code Below 👇
Build Fast with AI tweet media
English
3
10
62
2.9K
Unicorn Studio
Unicorn Studio@hiunicornstudio·
New shader effect cooking. Should I release it?
English
29
12
370
14.5K
Edward
Edward@aestheticedwar1·
@tristanbob @weaviate_io it's a framework AND web app that you can both use for different use cases - so yes, you can build production app with it we built glowe.app with it
English
0
0
4
246
Edward
Edward@aestheticedwar1·
We just released our open source agentic RAG framework, Elysia! Big bonus? It comes with a full web app - also open source 🤯 🤯 🤯 Even bigger bonus? For each query, you see the actual @weaviate_io source code that was used to traverse through your dataset - and it works with all of your Weaviate data out of the box 🎁 We have a live demo that you can check out: elysia.weaviate.io Aaaaand if you want to get it yourself, open your Terminal and type: pip install elysia-ai & elysia start GitHub: github.com/weaviate/elysia BlogPost: weaviate.io/blog/elysia-ag…
English
2
30
181
15.5K
Basit A. Khan
Basit A. Khan@basit_designs·
Dark mode always hits different, agreed?
English
42
9
358
17.4K
Edward
Edward@aestheticedwar1·
In Pedion Elysion - pip install elysia-ai Welcome to Elysia, your open-source agentic RAG framework with a fully end-to-end frontend application on top of it and built on top of @weaviate_io - easily installable through one single pip install and one single command: start elysia Most AI applications are chatbots stuck in a text-only world. We show you how our framework dynamically decides not just what to say, but also 𝗵𝗼𝘄 to show it. It’s a complete rethink of RAG applications that brings transparency, intelligence, and visual flexibility to your data interactions. + we have an epic trailer ❤️‍🔥 NOW AVAILABLE!!!!111 Read more about Elysia in our newest blog post: weaviate.io/blog/elysia-ag… Try out free live demo: elysia.weaviate.io Install it now: github.com/weaviate/elysia
English
2
15
81
5.5K
Julian Garnier
Julian Garnier@JulianGarnier·
It's decided, I'm making a course! I'll explain how the new Anime.js website was created by recreating the entire landing page from scratch, while sharing all the animation tricks and techniques I've learned throughout the years. Join the waitlist in the link below 👇
English
101
168
3K
135.1K
Edward retweetledi
Victoria Slocum
Victoria Slocum@victorialslocum·
How do you build an end-to-end agentic RAG app? Lucky for you, you can just run two commands: ‘pip install elysia-ai’ and ’elysia start’ I wrote a massive blog post detailing all the things we built into this 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲 𝗲𝗻𝗱-𝘁𝗼-𝗲𝗻𝗱 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸: weaviate.io/blog/elysia-ag… But if you don't have time to read though that, here’s the TLDR version 🔽 Instead of the typical "text in, text out" approach, Elysia uses a decision tree architecture where intelligent agents determine the best tools to use, evaluate results, and decide whether to continue or complete their tasks. It's an AI that actually thinks through problems step-by-step in a controllable, user-understandable format. The three main things that set Elysia apart: 1️⃣ 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗧𝗿𝗲𝗲𝘀 𝘄𝗶𝘁𝗵 𝗦𝗺𝗮𝗿𝘁 𝗔𝗴𝗲𝗻𝘁𝘀: Each node has a decision agent with global context awareness. They evaluate past actions, current state, and future possibilities to choose the optimal tool. Plus, they can handle errors intelligently – if something fails, they'll try a different approach rather than just giving up. 2️⃣ 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗶𝘀𝗽𝗹𝗮𝘆𝘀: Elysia chooses from seven display formats – tables, e-commerce cards, tickets, conversations, documents, charts, and more. It analyzes your data structure and automatically picks the most appropriate way to present information. 3️⃣ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗗𝗮𝘁𝗮 𝗘𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲: Unlike traditional RAG systems that perform blind searches, Elysia analyzes your collections first. It understands your data structure, creates summaries, generates metadata, and uses this knowledge to handle complex queries intelligently. The frontend displays the entire decision tree as it's traversed, showing you exactly why it made each choice. No more black-box AI systems – you get complete transparency into the reasoning process. We built Elysia to be the successor to Verba, taking everything we learned about RAG applications and pushing it to the next level. It's not just about retrieving and generating anymore – 𝗶𝘁'𝘀 𝗮𝗯𝗼𝘂𝘁 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗔𝗜 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁𝘀 𝘁𝗵𝗮𝘁 𝘁𝗿𝘂𝗹𝘆 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗮𝗻𝗱 𝗽𝗿𝗲𝘀𝗲𝗻𝘁 𝗶𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗲𝗳𝗳𝗲𝗰𝘁𝗶𝘃𝗲𝗹𝘆. GitHub: github.com/weaviate/elysia Demo: elysia.weaviate.io Get started: #getting-started?utm_source=channels&utm_medium=vs_social&utm_campaign=elysia&utm_content=680444793" target="_blank" rel="nofollow noopener">weaviate.io/blog/elysia-ag…
English
5
33
229
12.1K
Edward
Edward@aestheticedwar1·
Hacking away at midnight—working on some epic frontend for Elysia’s secret sauce… Decision Trees! 🌳 Believe me when I say that Elysia is an extremely powerful framework for navigating different data sources, queries, and returning results—all thanks to a decision tree-based approach. You’ll be able to see exactly what’s happening behind the scenes in the frontend, from your query all the way to the final leaf node, with each selected node showing the reasoning behind why it was chosen. Super excited to release this soon—there’s so much to show. Can’t wait! 🫡
English
0
1
5
265