Wenqi Glantz @wenqi_glantz
Mom, wife, architect with a passion for technology and crafting quality products medium.com/@wenqiglantz Greater Philadelphia Area Joined June 2022-
Tweets146
-
Followers1K
-
Following871
-
Likes2K
Let’s walk through RAG pain points and solutions! 🧑🏫🎬 We’re excited to feature @wenqi_glantz for a video walkthrough video of her popular “12 RAG Pain Points and Solutions” blog post, which is the most comprehensive cheatsheet we’ve seen of pain points that occur at every stage…
It was a pleasure presenting at the livestream event today, organized by Neil Kanungo and Ryan Siegler from KDB.AI! I enjoyed the lively discussions with both of them and unpacking some of the RAG pain points and proposed solutions. Check out the recording for…
On a quest for enterprise RAG, we explore how we craft RAG microservices from an RAG pipeline POC developed in a Colab notebook. Specifically, we draft our microservices with the following approach: ✅ We use create-llama command line tool offered by @llama_index, which…
We explore NeMo Guardrails, an open-source toolkit developed by @nvidia for easily adding programmable guardrails to LLM-based conversational systems. We dive into the implementation details on how to add NeMo Guardrails to an RAG pipeline built with…
🚀 Learn how to Build Secure RAG apps in Production *in 60 mins* with @llama_index + @lighthouzai + @AIatMeta Llama Guard 🌟 RAG apps are all the rage in #AI #GenerativeAI, but how do you build *secure* apps that can be reliably put in production? Join @wenqi_glantz to learn:…
12 RAG Pain Points and Proposed Solutions 💡 Building production RAG is hard. @wenqi_glantz compiled a list of 12 (!!) RAG pain points + added a full solution list to each one with @llama_index abstractions 🔥 We’ve put out cheatsheets before, but this one is much more…
I enjoyed sharing Llama Guard with "Generative AI In Enterprise" Meetup group (meetup.com/generative-ai-…) last night! Thanks to Ujjal Bhattacharjee for organizing the virtual meetup, and the opportunity to share Llama Guard with the group! youtube.com/watch?v=d5iBCK… Colab notebook:…
Finally! Codellama-70b as Copilot in VSCode! 😱 You can now harness the power of the most advanced code generation model, Code Llama 70B, right in Visual Studio Code with @perplexity_ai This model has outperformed even GPT-4 in code writing, and it's now seamlessly integrated…
Adding Noise Increases Performance In RAG! 🤯 RAG has become one of the hottest research topics, and a new research paper is released almost daily. This latest one is especially interesting as it has a counter-intuitive finding. The paper titled "The Power of Noise: Redefining…
Based on a recent paper “Seven Failure Points When Engineering a Retrieval Augmented Generation System” (arxiv.org/pdf/2401.05856…), we explore the seven failure points and propose solutions for each one of them in my latest blog. In addition, we add five more pain points, commonly…
Since the launch in late November 2023, @llama_index has curated over 50 LlamaPacks to help jump-start your RAG pipeline development. Among these, many advanced retrieval packs emerged. In my latest article, we dive into seven advanced retrieval packs: 🌟 Hybrid Fusion 🌟 Query…
Continuing our learning journey of @maximelabonne’s llm-course (lnkd.in/eNZHticu), we experiment with model merge, model evaluation, and model fine-tuning. The possibility of open-source models surpassing proprietary models is growing exponentially! towardsdatascience.com/exploring-merg…
Inspired by @maximelabonne's great work in his llm-courses GitHub repo (github.com/mlabonne/llm-c…), we take a deep dive into model quantization with GGUF and llama.cpp, and we evaluate the models with @llama_index. Check out my blog for detailed findings. medium.com/towards-data-s…
How to Deploy your LLM App 101 ⚙️ Here’s a fantastic primer by @wenqi_glantz on how to deploy a @llama_index app to a full-fledged service on AWS Fargate, with Terraform (@HashiCorp) and an automated CI/CD pipeline with @github Actions. This is a must read for literally any AI…
We explore how to deploy @llama_index's RAGs chatbot to AWS ECS fargate, fully automated with infrastructure and application pipelines, end-to-end. #DevOps medium.com/towards-data-s…
Safeguard your RAG pipelines with Llama Guard 🦙🛡️ A big part of making LLMs “production-ready” is securing their inputs (prompt injection) and outputs (code execution, sensitive information disclosure) 🔐 In a special blog post on TDS, @wenqi_glantz shows you how to use Llama…
Llama Guard was released by @AIatMeta nearly 3 weeks ago. How exactly do we use Llama Guard in our RAG pipelines to moderate LLM inputs and outputs and combat prompt injection? Check out my latest article for details. towardsdatascience.com/safeguarding-y…
ft.eth @tractusF
109 Followers 1K FollowingUnaArnold @1znIR176wjvX5k
0 Followers 37 FollowingElsaWatt @6VS5dOd098g9ADO
0 Followers 56 Followingchristopher smith @LynnChristopher
17 Followers 38 FollowingAgatha @hinagae94555298
2 Followers 683 FollowingEllen @hitotsu36363579
2 Followers 677 FollowingKX @kxsystems
4K Followers 938 Following Build data-driven applications and turbo-charge your favorite analytic, AI, and ML tools in any cloud or at the edge.Riis Maltese @errejesseme
144 Followers 518 Following Software Architect & Project Manager Here, There, EverywhereDJ @python_deck
6K Followers 5K Following Python | C++ | Java | HFT | Open source code with concepts | Experienced developer, Written and more importantly read tons of production codeMikayel @MikayelHarut
269 Followers 300 Following Tech, human behavior, & AI. Sentiments expressed = eigenvectors of my personal opinion matrix, not a shared vector space. head of growth @activeloopaiyang liu @liu_yang82284
2 Followers 27 FollowingLarryChen @LarryChen8276
24 Followers 481 FollowingLu @asoelu001
12 Followers 697 FollowingTa Dang Khoa @TaDangKhoa
0 Followers 34 FollowingAshirbad Dash @ASHIRBAD__DASH
222 Followers 2K FollowingJ Zh @JZh692669342157
7 Followers 3 FollowingShravan Sunder @ShravanSunder
145 Followers 1K Following 👷🏽♂️ Software Team Lead at @Xero 🦾 Totally into AI agents atm 🌱 Find me at https://t.co/N652zG82dB 🎠 Prior @buidlguidl knight web3Corneliu @corneliu_au
119 Followers 1K Followingyanan @yanan1147289
0 Followers 4 FollowingTarandeep Singh @Singh316Singh
140 Followers 2K Followingmonki e/acc @monki_ye
120 Followers 446 Following cogsci, nomadic SWE, WW III refugee | Pope at the cult of simulation x vivarium | time=compute / monk1@airchatShojaei @realshojaei
1K Followers 2K Following AI Researcher | building AI Agents & LLM applicationsSudarshan Koirala @mesudarshan
741 Followers 216 Following ML Engineer, CS Graduate @AaltoUniversity | 🎥Youtube: https://t.co/Vv1FKhaQuP, Opinions are my own.DataGrail @DataGrail
5K Followers 2K Following DataGrail is the Privacy Control Center for modern brands to reduce risk and build trust. Backed by @Okta @DocuSign @HubSpot @AmericanExpress @ThomsonReutersAndrew Sage @sage34178
82 Followers 736 FollowingA P @AltCounterBug
1 Followers 7 FollowingPrateek Yadav @prateeky2806
2K Followers 2K Following Ph.D. at @unccs Continual Model Adaptation and Composition Previously @MSFTResearch, @AmazonScience, @iitmadras. UG @iiscbangalore. Opinions are my own.Thiwanka Jayasiri (TJ.. @ThiwankaCJayasi
223 Followers 2K Following Re-design the way we compute @AntiumSVikas Kawadia @vkawadia
104 Followers 208 Following Applied ML Eng Leadership @Meta, currently working on Reels and Video recommendations . Previously ranking and relevance @Nextdoor.Burn The Servers @burntheservers
170 Followers 1K Following Burn The Servers: The First Human/AI Composed Love Story/Tell All in History. ❤️◀️📱 {love is subversive} ✍️ - 404 Author Not Found (human)Arcee.ai @arcee_ai
249 Followers 189 Following Arcee is the leader in domain-adapted LLMs w/ our Small Language Models (SLMs) & our Model Merging innovations https://t.co/ZjIQuOcoknFERAL Performance @FERALPerforman1
12K Followers 13K Following Patriotic American brand FERAL Performance - Attitude-Drive-Determination that Americans made Legendary Not PC Not Sorry Deal with it IFB Patriots 🇺🇸♥️🇺🇸Aisha @Aisha6109541471
46 Followers 142 FollowingAshish Patel @imashish2604
109 Followers 292 Following AI Researcher Scientist & Chief Data Scientist at IBM | Author of Hands-on Time Series Analytics with Python | Keras Contributor | IBM QuantumMarcelo Guerra Hahn @marceguerra
10K Followers 10K Following Educator | Engineering Leader | Speaker | ex-SoundCommerce | ex-Tableau | ex-MSFTDr Stephen Harwood #S.. @drsharwood
40K Followers 35K Following Researching, writing & innovating #TrustInTech #TechForGood #equality #sustainability #emergingtech #SDGs #futures #AI #digital #MSSL #UCL @TechnoForeSightakdjhfkla @akdjhfkla
0 Followers 348 FollowingAdam Voulstaker @adamvoulstaker
50 Followers 268 Following From UK live in New Zealand Day job is self employed IT Consultant (AI & SEC GRC) https://t.co/bu1cI4VHnQ https://t.co/lmZqeFocKrRuben Garzon @rgarjc
50 Followers 688 FollowingKelvin Onwordi @kelvadoprivate
69 Followers 73 Followingraytronix.ai @raytronixAI
2K Followers 5K Following The official account of https://t.co/6gp7wuHTTE. We specialize in innovative AI solutions for the 21st century. #AI #ML #AIagent #AItools #FutureOfComputingDevi Parikh @deviparikh
23K Followers 151 Following Former Sr. Director, GenAI @Meta. Prof @GeorgiaTech. Generative artist https://t.co/z4n9IRQ3s5. Co-founded Caliper. @CarnegieMellon @RowanUniversity alum.Tarandeep Singh @Singh316Singh
140 Followers 2K FollowingShravan Sunder @ShravanSunder
145 Followers 1K Following 👷🏽♂️ Software Team Lead at @Xero 🦾 Totally into AI agents atm 🌱 Find me at https://t.co/N652zG82dB 🎠 Prior @buidlguidl knight web3Andrej Baranovskij @andrejusb
6K Followers 151 Following 👨💻 ML/Python/JavaScript/Oracle Developer @katana_ml 👨💼 Founder @katana_ml 📺 Video https://t.co/70YyWj6LGc 📖 GitHub https://t.co/hdIT2dFTr7DataGrail @DataGrail
5K Followers 2K Following DataGrail is the Privacy Control Center for modern brands to reduce risk and build trust. Backed by @Okta @DocuSign @HubSpot @AmericanExpress @ThomsonReutersEduardo Laureano @eduardolaureano
1K Followers 545 Following Here to learn, connect and laugh. Building an Application Platform for Data Apps @SnowflakeDB. Previously @Meta @AzureFunctionsSudarshan Koirala @mesudarshan
741 Followers 216 Following ML Engineer, CS Graduate @AaltoUniversity | 🎥Youtube: https://t.co/Vv1FKhaQuP, Opinions are my own.Prateek Yadav @prateeky2806
2K Followers 2K Following Ph.D. at @unccs Continual Model Adaptation and Composition Previously @MSFTResearch, @AmazonScience, @iitmadras. UG @iiscbangalore. Opinions are my own.Arcee.ai @arcee_ai
249 Followers 189 Following Arcee is the leader in domain-adapted LLMs w/ our Small Language Models (SLMs) & our Model Merging innovations https://t.co/ZjIQuOcoknLewis Tunstall @_lewtun
9K Followers 425 Following 🤗 LLM engineering & research @huggingface 📖 Co-author of "NLP with Transformers" book 💥 Ex-particle physicist 🤘 Occasional guitarist 🇦🇺 in 🇨🇭Nous Research @NousResearch
18K Followers 29 Following The AI Accelerator Company. https://t.co/vrD0aDJetoEden Marco @EdenEmarco177
1K Followers 264 Following LLMs @google cloud | Best-seller @udemy InstructorEduardo Castillo @EmpireCastillo
1K Followers 86 Following 🎯8 Figures+ prior sales in service industries. Now helping frustrated owners to learn, implement, & leverage AI into their business productivity. 🤖 👨🦯Ashish Patel @imashish2604
109 Followers 292 Following AI Researcher Scientist & Chief Data Scientist at IBM | Author of Hands-on Time Series Analytics with Python | Keras Contributor | IBM QuantumMarcelo Guerra Hahn @marceguerra
10K Followers 10K Following Educator | Engineering Leader | Speaker | ex-SoundCommerce | ex-Tableau | ex-MSFTLeonie @helloiamleonie
7K Followers 407 Following 🖋️ Technical writer https://t.co/mXXEyoAUJZ 🥑 Developer Advocate @weaviate_io 🦆 Kaggle Notebooks Grandmaster https://t.co/3wrvdColIaOmar Khattab @lateinteraction
11K Followers 2K Following CS PhD candidate @StanfordNLP. 2022 Apple Scholar in AI/ML. Author of ColBERT (https://t.co/2ZtgXoa1np), DSPy (https://t.co/BH7WmMKDXR), & various retrieval & LM systems.Dr Stephen Harwood #S.. @drsharwood
40K Followers 35K Following Researching, writing & innovating #TrustInTech #TechForGood #equality #sustainability #emergingtech #SDGs #futures #AI #digital #MSSL #UCL @TechnoForeSightOneSubmitAI @OpenAIGPT5
473 Followers 2K Following Get First 1,000 Paying users for Your AI @OpenAI & SaaS Organically Submit Once, get featured on 100+ directories to boost your traffic 💯Follow backPino Patera @pinopatera
116 Followers 2K FollowingDerrick Abincha @gesaka_mutuma
214 Followers 1K Following Building @japa_universe, immigration software for Africans. 3x founder | DS and MLTomek Gancarczyk @tomekgancarczyk
259 Followers 619 Following Computational designer @tylko_furnitureAadesh Gupta @AadeshGupta
79 Followers 958 Following Research & Development Engineer at Amelia Labs (AI/ML | Deep Learning | NLP | Backend Developer)Catalin Acatrinei @CatalinAtWork
783 Followers 4K Following Views expressed here are my own. Retweets are not endorsements.Alim Karim | alimk.et.. @alim__k
190 Followers 401 Following Product. Trust & security software @intel. Interested in #business #technology #product and visits to the gym. Assembled in ⟦ 🇹🇿 🇨🇦 🇺🇸 ⟧. Views = my own.Prof. Sally Eaves @sallyeaves
140K Followers 115K Following Innovating #tech #education #business CEO CTO Advisor Prof #AI #5G #SDGs #CyberSecurity #Cloud #IoT #ESG #TechForGood #FinTech #STEM #BHUSA #MWC23Todd Kueny — e/acc @techgazetteco
3K Followers 6K Following Empowering worlds where AI enriches lives, solves complex problems, and inspires continuous learning.Qasim Ali @QasimAliSidhu
168 Followers 1K Following AI First Tech Savvy Technical Customer Support Engineer #AI #GenerativeAI #GenAI #FutureAILeaders #AIFirstDr. Shailesh Jain @DrShaileshJain2
179 Followers 930 Following Doctorate | Sr. Learning Solutions Manager at Anaconda 🐍LangChain4j @langchain4j
2K Followers 679 Following Build LLM-powered applications in Java, Quarkus and Spring Boot. Chatbots, agents, RAG and much more! https://t.co/5nBDPenP6lElon Musk @elonmusk
181.4M Followers 585 FollowingMatija Grcic @matijagrcic
997 Followers 5K Following Father of two. AWS Architect, PSM I, MCSD, MCTS. Speaker. Lover of espresso, whisky, hiking, photography and beer. Owned by https://t.co/6aM7z52zbVJimmy Yeh @ChihYuNewRich
21 Followers 506 Following I am working on a problem that humans have been attempting to solve for 50 years.Sankar Nagarajan @nsankar
79 Followers 757 Following Passionate about harnessing the power of Data Science, Machine Learning & AI to solve complex challenges. Principal Data Scientist - Virtana Corp.Nick Omeyer @NickOmeyer
199 Followers 1K Following Co-founder @StepsizeHQ • Tweets about building with LLMs 🛠️Erik Cohen @ecohen_dev
172 Followers 2K Following Web Developer @BenchSci. @GeorgiaTech OMSCS Student 𝗛𝗮𝘀𝗮�.. @hasan_zmzm
498 Followers 3K Following 𝐈𝐧𝐟𝐨𝐒𝐞𝐜 || 𝐖𝐞𝐛𝟑 || 𝐁𝐮𝐠𝐁𝐨𝐮𝐧𝐭𝐲 || 𝐉𝐚𝐢𝐥𝐛𝐫𝐞𝐚𝐤 || 𝐇𝐮𝐦𝐚𝐧 𝐑𝐢𝐠𝐡𝐭𝐬John Cena @JohnCena
14.3M Followers 775K Following A forum of thoughts and perspectives designed to ignite conversations and actions leading to growth, and occasional self promotion. #NeverGiveUp #RiseAboveHateCaroline de Brito Got.. @dbg_caroline
95 Followers 602 Following linguist & sculptor | cognitive science | chronic pain & patient language | data strategy at NVIDIA | she/herJacek (Jomsborg.eth) @timelessdev
1K Followers 5K Following The DAO investor. Early @Aleph__zero inv. Decentralization. Born on Vikings island called Jomsborg. Applied math. My posts are not financial advise.Andreas Kapp @andreaskapp
1K Followers 1K Following Software Engineer, Writer. Software Architect, Rust Developer. 🇨🇭 Favors transparency over secrecy, and accountability over blindly trusting authority.Check out our first-party guide to building advanced RAG with @llama_index + the AWS ecosystem ⭐️ ✅ integration with Bedrock LLMs/Knowledge Base/Agents ✅ Use S3 and Step Functions with LlamaParse and LlamaCloud ✅ Build Agentic RAG with Bedrock Agents + Lambda functions +…
We’re excited to feature @llama_index + AWS workshop materials featuring 3+ patterns for building LLM apps on AWS 💫 These include: 1️⃣ Using S3 as a data source for ingestion (with LlamaParse and LlamaCloud) 2️⃣ Use @llama_index with AWS Bedrock LLMs and embeddings 3️⃣ Using…
Before you build complex agent systems, I’d recommend building with the individual “agent ingredients” first to gain a better first principles understanding of how they work. Here are the main ingredients for building an agent (mini 🧵) Query Planning: Given the task +…
A 9-part series on RAG from Prototype to Production ⭐️ RAG in a notebook is easy, RAG serving live production users is hard. This tutorial series by Marco Bertelli is the perfect step-by-step resource to outline all the architectural components you need to productionize a full…
create-llama 0.1: the easiest way to build a full-stack LLM application - Specify any popular LLM (incl. llama3, phi3, claude, openai) - Specify any vector store - use either @llama_index python or typescript as the backend - get full-stack streaming + sources built in
create-llama is the easiest way to get started with a full-stack RAG application and take it all the way to production, and it just hit version 0.1! There's a ton of updates recently, including: ✅ @ollama support, so you can run llama3 and phi3 ✅ New vector database support…
Want to run Phi-3 on your laptop? @ollama has got you with day 0 support as usual! Check out this quick notebook showing completely local RAG using LlamaIndex and Ollama: colab.research.google.com/drive/1RoZzbL8… And Ollama's announcement tweet: x.com/ollama/status/…
Phi-3 Mini (3.8B) from @Microsoft was released today, claiming to match Llama 3 8B's performance! But how does it handle RAG, Routing, Query Planning, Text2SQL, Pydantic Program, and Agentic tasks? Thanks to @ravithejads, our benchmark cookbook offers an initial analysis: ✅ RAG…
🅿️ Phi-3 is now available on Hugging Face 3.8B parameter model in two versions: 4K and 128K context length. Excellent performance + MIT license, enjoy! 🥳 🤗 4k: huggingface.co/microsoft/Phi-… 🤗 128k: huggingface.co/microsoft/Phi-…
Phi-3 is the most capable ~4B model out there today - we're fast approaching a world where small models can reliably perform agentic reasoning ⚡️ This has the potential to make complex agent applications much more feasible in terms of cost and latency. There's still a slight…
Phi-3 Mini (3.8B) from @Microsoft was released today, claiming to match Llama 3 8B's performance! But how does it handle RAG, Routing, Query Planning, Text2SQL, Pydantic Program, and Agentic tasks? Thanks to @ravithejads, our benchmark cookbook offers an initial analysis: ✅ RAG…
Inspired by @AndrewYNg’s threads on agents in the past few weeks, I’m excited to share my talk from the @weights_biases conference that outlines how to build a general context-augmented research assistant 🧑🔬 Naive RAG is mostly good for simple questions in a single-shot setting.…
One of my favorite insights from this paper: knowledge graphs not only help with retrieval, but also with scientific discovery of new ideas/connections that were previously unexplored. You can do this by feeding an LLM an existing knowledge graph, and it will overlay the KG…
Using LLM-generated Knowledge Graphs to Accelerate Biomaterials Discovery 🧬🧠 This paper by @ProfBuehlerMIT constructed a massive knowledge graph over 1000 scientific papers on biological materials, in a “local-to-global” approach. By creating this massive ontology, the paper…
Here’s a great reference guide for building a full-stack RAG application with AWS Bedrock 👇 1. Setup access to Bedrock embeddings/LLMs 2. Use @llama_index to index and retrieve over PDFs 3. Build a full-stack @streamlit interface that you can interact with Big shoutout to…
A key challenge in productionizing LLM apps is data management - how do you deal with live, constantly changing data while minimizing cost and latency? Both @llama_index open-source and LlamaCloud have key features for efficiently managing documents, their associated chunks, and…
A good way to add query planning capabilities for agents is to prompt LLMs to do symbolic reasoning over tools. Instead of calling tools step-by-step (and using a separate LLM call for each step), you can plan out an entire plan sequence using placeholder variables where you'll…
Chain of Abstraction ⛓️💭 Lots of LLMs (@OpenAI, @MistralAI, @AnthropicAI) now support function calling for single-shot tool use, but existing frameworks struggle with multi-step query planning with tool use. Chain of Abstraction by (@silin_gao et al.) is a new technique where…
Introducing create-tsi - a toolkit to generate a full-stack, enterprise-grade (GDPR compliant) AI Application through a CLI interface! 🇪🇺🛠️🤖 This was done in collaboration with @tsystemscom, @MarcusSchiesser, and inspired by the @llama_index create-llama toolkit. Build a…
E2E RAG Stack powered by @cohere This is an excellent thread by @akshay_pachaar showing you how to use ALL the latest and greatest @cohere models to build a state-of-the-art RAG pipeline This includes the following: 1. @cohere ⌘R+ LLM 2. @cohere Embed V3 3. @cohere's latest…
Cohere has just launched Rerank-3, now available in our "RAG using ⌘R+" Studio. Experience @cohere's Full-stack RAG capabilities in this document chat app using: - Cohere's ⌘R+ as LLM - Cohere's Embed V3 - And Cohere's Rerank-3 Powered by @llama_index 🦙 Take it for a…
A key way to make your agent more controllable is through tools that can stop execution 🛠️ ✈️ In a travel agent, you want to stop execution after a booking is confirmed 🔎 In an agentic RAG pipeline, you want to stop after finding the answer and sending a reply We’re excited to…
🍃 Big day for @springboot developers! @sergialmar launched springbuilders.dev - the online community where we can share our content, opinions and learn from each other. If you're not there yet, come and say hi! springbuilders.dev
Build a lightweight ColBERT retrieval agent with memory 🔥 If you want to build a simple agent that can perform advanced retrieval over documents (HyDE + vector search + ColBERT by @lateinteraction) and also maintain conversation memory, here’s a super simple but effective…
Building Multi-Document Agents with @llama_index RAG with simple questions over a small set of data is easy, but a key goal for @llama_index is to solve complex QA over many docs. @andysingal presents an excellent overview of our multi-document agents. Instead of treating each…
An agentic extension for RAG is to treat documents as tools and agents instead of just text chunks - this allows you to dynamically interact with these documents beyond getting back a fixed list of chunks. This is a great blog post by @andysingal and diagram by @clusteredbytes…
Building Multi-Document Agents with @llama_index RAG with simple questions over a small set of data is easy, but a key goal for @llama_index is to solve complex QA over many docs. @andysingal presents an excellent overview of our multi-document agents. Instead of treating each…