Lance Martin @RLanceMartin
@LangChainAI, Prev: ML for self-driving (Nuro, Ike, Uber ATG) 🚘 🤖, PhD @stanford 🧪. San Francisco, CA Joined May 2009-
Tweets857
-
Followers9K
-
Following241
-
Likes3K
I tried LangSmith evaluation for financial RAG today. Pleased to report it does a bunch of heavy lifting. • loading dataset • creating RAG pipeline • running evaluator My favorite is that eval results are automatically displayed in real-time UI. Before, I was tracking…
Mistral Agent Cookbooks Great to work with @sophiamyang to contribute 3 cookbooks to @MistralAI! I’ve used LangGraph to build agents reliably with Mistral-7b on up to Mistral-Large. Short explainer w/ code linked: youtu.be/sgnrL7yo1TE?si…
Fully local RAG agent with Llama3-8b Threw a few things at Llama3-8b on my first test drive (routing, fallback to web search, retrieval / answer grading, RAG). Seems very strong! Short vid building this flow from scratch / initial impressions: youtu.be/-ROS6gfYIts?fe…
My RAG From Scratch tutorial is live on @freeCodeCamp -- covers over a dozen of my favorite papers on RAG w/ accompanying code notebooks (all open source). Thanks @beaucarnes! Video: youtube.com/watch?v=sVcwVQ…
LLM app development is rate-limited by quality evals. There's a paradox of LLM, prompt, etc choice. Recently put together a short guide on setting up custom evals. Playlist (5 min vids): youtube.com/playlist?list=… Code: github.com/langchain-ai/l… x.com/LangChainAI/st…
LLM app development is rate-limited by quality evals. There's a paradox of LLM, prompt, etc choice. Recently put together a short guide on setting up custom evals. Playlist (5 min vids): youtube.com/playlist?list=… Code: github.com/langchain-ai/l… x.com/LangChainAI/st… https://t.co/NdD1hS3ipr
Amazing work breaking down different RAG steps by the one and only @RLanceMartin
Amazing work breaking down different RAG steps by the one and only @RLanceMartin
RAG From Scratch Here's a set of short (5-10 min videos) and notebooks explaining > a dozen of my favorite RAG papers. Took a stab at implementing each idea myself (all code open source) and grouped according to the diagram. Repo: github.com/langchain-ai/r… Video playlist:…
Fun RAG flow I worked on w/ @cohere command-R. Ties together (1) routing, (2) structured output w/ online unit tests, (3) RAG. command-R is good for flows like this b/c it's fast + structured outputs (for online tests) and good at RAG / routing. x.com/LangChainAI/st…
Fun RAG flow I worked on w/ @cohere command-R. Ties together (1) routing, (2) structured output w/ online unit tests, (3) RAG. command-R is good for flows like this b/c it's fast + structured outputs (for online tests) and good at RAG / routing. x.com/LangChainAI/st… https://t.co/kcBoiLSKVB
I enjoyed @simonw's writeup on ColBERT, a nice method for high granularity document embedding from @lateinteraction & @matei_zaharia. Did a deep dive into ColBERT + RAGatouille. Short video, ntbk on usage, and useful links here: x.com/LangChainAI/st…
I enjoyed @simonw's writeup on ColBERT, a nice method for high granularity document embedding from @lateinteraction & @matei_zaharia. Did a deep dive into ColBERT + RAGatouille. Short video, ntbk on usage, and useful links here: x.com/LangChainAI/st… https://t.co/DpEIFvB5WI
I often hear that evals are the most confusing part of creating LLM AI products. It's a shame b/c IMO, domain-specific evals are the most important part of an AI product! I've written a detailed blog post with real examples on how to do this (1/3) hamel.dev/blog/posts/eva…
Balaji @balajis
1.0M Followers 4K Following Immutable money, infinite frontier, eternal life. #BitcoinAssaf Elovic @assaf_elovic
3K Followers 99 Following Tweeting about AI in human language. Building https://t.co/CvLkwlFfYL and https://t.co/iOfJFCdyjFVictor Chigne @VictorChig52156
1 Followers 134 Following精神病狗婊子杂.. @frkglp
0 Followers 3K Following 神病狗婊子杂种邓小平,刘少奇就是整个世界的敌人,它那套歪把戏不除,世界战乱不断。Cgkl精神病狗婊子杂种习近平被凌迟处死。Cgk凌迟处死精神病狗婊子杂种中共狗屁家族邓小平,习近平,陈云,刘少奇,陈一新,张又侠,何卫东,刘振立,苗华,董军。锸s你跟踪本人的精神病狗婊子杂种全部中共空军、警察、台湾间谍CTO @ Stealth @ctoatstealth
139 Followers 521 Following Building an unhinged AGI God Bot to disrupt enterprise. Angel investor. {e/acc}^{e/acc}. Ex @openai, Ex @tesla, Ex @nvidia, YC S20. Reality is a parody.bpiz.eth @bpiz_eth
136 Followers 876 FollowingSam Julien @samjulien
9K Followers 2K Following Director of #DevRel @get_writer, instructor @eggheadio. Professional gate-opener. Improve as a dev & dev advocate at https://t.co/HQ5Rzsoa92 ✉️.Vij.ai @appikumar29437
11 Followers 79 Following Gen AI enthusiast | Continuous Learner| Part of the #0to100xEngineer community.Adam Schmidt @404AdamNotFound
43 Followers 14 Following Navy veteran turned full stack coding bootcamp student: From missile and radar systems to software systems. Sharing my daily learnings and code snippets.Richard @fbabelle
0 Followers 16 FollowingRaul Mata @raulmatasp
59 Followers 322 Following Brasileiro de São Paulo, Advogado formado pela Faculdade de Direito do Mackenzie/SP, entusiasta por criptomoedas e economia, apaixonado pelo Brasil.redefinedbyai @redefinedbyai
25 Followers 246 Following Guess what, my predictions on AI are happening one projects at a time 😉s.lee @slee_shark
14 Followers 59 FollowingChirag Patel @chiragpatel1499
276 Followers 484 Following DevOps Engineer | Cloud Enthusiasm | 1x GCP | AWS | 2x Azure | Kubernetes | Docker | Jenkins | TerraformAlper Bahcekapili @AlperBahcekapi3
0 Followers 14 FollowingStephanie Rowland @Mikl830262Mikl
16 Followers 329 FollowingStefan Juang @StefanJuang
147 Followers 1K Following The final goal of AI is not just to create intelligent machines, but to understand intelligence itself.Linda1566 @Linda15661997
31 Followers 320 FollowingGiri @giridharant_
467 Followers 2K FollowingMostly Apt @maahuja
19 Followers 405 Followingabdelrahman lila @ALila2003
16 Followers 114 FollowingCitta Manas @cittamanasayu
0 Followers 9 Followingnova ツ @bussinpotato
2 Followers 48 Following ai and nlp researcher, also specialises in red-team cybersecurity. skill hoarder. also trying to learn languages and be more social (and failing at it)Ehsan @EhsanToday
90 Followers 2K FollowingKishor Nanda @kishorrocks5
27 Followers 370 Following Chasing the Dreams. Making Real world Apps | ❤ Prob Solver | Exploring Stuff | ML & InfoSec Enthusiast 💀James Richman @jamesrichmanx
16K Followers 223 FollowingBernard🤖 @BernardLiu18
43 Followers 500 Following Web3 Buidler | PM in @Knn3Network @TypoX_AI https://t.co/AMWZvfK22Fcore @_0xcore
280 Followers 5K Following eacc engineer. statistical physics @LeCnam, @stanfordsymsys, @hexagonedao, @lagigacity, @_0xcore, @buildcitiesCamille @CamilleData
1 Followers 26 Following Data & AI in a Data Tech 🚀 | Fusing Retail with Data & AI | MSc in Structural Biochemistry 🧬 | #TransinTech Advocate | #AiForCommonGoodIkram @tanjibpa
3 Followers 46 FollowingMustafa Işıldak @mustafaisildak
18K Followers 3K Following Entrepreneur • Just open your •.• ||| AI, Automation, Robotics, Blockchain • RPA, ML, DL, Fine-tuning, RAG, Pretraining, Quantization, Python, Langchain, GPTs.Charlie Cheng-Jie Ji @charlie_jcj02
78 Followers 515 Following Gorilla LLM, CS & DS @ UC Berkeley, Data 100 Lead TA, Working towards LLM Tool Use, AI safety李虎 @liugddx
48 Followers 545 FollowingNikita @nikitavoloboev
4K Followers 7K Following Make @LearnAnything_ Learn in public: https://t.co/GbFvuErkYn macOS course: https://t.co/JdbJWru6zG https://t.co/94R8ER7K2h https://t.co/ROkqhyhpEKzekzen @zekzen
118 Followers 616 Following Dalgacı Mahmut ile Hüznün kuşları arasında sinusoidal bir hayat.Ahmed Ali @AhmedAl23358705
3 Followers 132 FollowingDana Mahmood @deordered
25 Followers 731 Following Fine-tuning AI models oftentimes & practicing philosopher at other times.Andrej Karpathy @karpathy
980K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxYann LeCun @ylecun
712K Followers 719 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Balaji @balajis
1.0M Followers 4K Following Immutable money, infinite frontier, eternal life. #Bitcoinclem 🤗 @ClementDelangue
91K Followers 5K Following Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI buildersFrançois Chollet @fchollet
470K Followers 769 Following Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.sunny madra @sundeep
20K Followers 4K Following Head of Groq Cloud, prev co-f (@definitiveio acq. by @groqInc, autonomic acq. by @ford, and xtreme labs acq. by pivotal/@vmware), angel investor.Nathan Benaich @nathanbenaich
51K Followers 32K Following solo member of investment staff @airstreet, brewing ambition @airstreetcafe, next token predictor @airstreetpressSam Whitmore @sjwhitmore
12K Followers 2K Following building @newcomputer. not a cat (or a man) in real life. I like to run a lot! @kensho @harvard @StuyNYAstasia Myers @AstasiaMyers
4K Followers 1K Following General Partner at @Felicis. Prev. @Redpoint @QuietCapital & @cisco_invests. Blog: https://t.co/fZRzRA4Yi2Noam Brown @polynoamial
34K Followers 612 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus, the first superhuman no-limit poker AIs | Co-created CICERO | PhD from @SCSatCMUCraig Dennis @craigsdennis
6K Followers 5K Following Developer Educator, AI @cloudflare | Previously on this channel @twilio, @treehouse, @idealist, and Returned @PeaceCorps VolunteerEric Topol @EricTopol
694K Followers 589 Following physician-scientist, author, editor. Ground Truths: https://t.co/YhatcBT0hALukasz Kaiser @lukaszkaiser
7K Followers 47 FollowingAnthropic @AnthropicAI
262K Followers 26 Following We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant Claude at https://t.co/aRbQ97uk4d.Siqi Chen @blader
66K Followers 3K Following 🏗️ Love to build stuff (@runwayco, @sandboxvr, @postmates, @zynga) people love. 💸 Investor @amplitude_hq, @mercury, @owner, @elevenlabsio, @slope_finance ++Logan Kilpatrick @OfficialLoganK
92K Followers 2K Following Lead product for @Google AI Studio and working on the Gemini API, helping developers build with AI, my views!Bagatur Askaryan @baga_tur
126 Followers 245 FollowingMaxime Labonne @maximelabonne
12K Followers 437 Following Author of Hands-On Graph Neural Networks https://t.co/Q8victWUmR • Machine Learning ScientistHamel Husain @HamelHusain
23K Followers 2K Following Researcher focusing on LLMs: https://t.co/iVZDFdIQiE Previously, dev tools and infra for ML. Ex @Github, @Airbnb, @DataRobot. @fastdotai core contributor.Jason McGhee @_jason_today
752 Followers 143 Following CTO & co-founder @ https://t.co/FL896XvDUU | prev co-founder Cursor (acq by @DataRobot) | UX, ML, Productivity, Personalized EducationRyan @dexter_brandt
738 Followers 1K Following hosting events for cracked founders ~ Lead @ https://t.co/4xdeNkPr2k. ~ Bootstrapped https://t.co/OaCk8jUORa to 40k MRRFabricated Knowledge @_fabknowledge_
16K Followers 464 Following Simplifying the world of semiconductor investing in the age of AI. Join over 39,000 free readers. It's secular (but cyclical) stupid Read more VAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Itamar Friedman @itamar_mar
4K Followers 421 Following Excited about the future of intelligent software development. CEO & co-founder @CodiumAIChristian Szegedy @ChrSzegedy
32K Followers 2K Following #deeplearning, #ai research scientist. Opinions are mine.Bindu Reddy @bindureddy
124K Followers 339 Following CEO of @abacusai, using Gen AI to build Applied AI and LLM agents and systems at scale, ex-AWS / Google, passionate about human behavior and open-source AGIJoão Gante @joao_gante
2K Followers 549 Following ML @huggingface 🤗, making text generation users happy. PhD from @istecnico 🇵🇹Devendra Chaplot @dchaplot
8K Followers 365 Following Building next-gen AI at @MistralAI. Past: Research Scientist at Facebook AI Research. Ph.D. @SCSatCMU, BTech @iitbombay CS.Together AI @togethercompute
27K Followers 304 Following The future of AI is open-source. Let's build together.surya @sdand
10K Followers 668 FollowingArthur Mensch @arthurmensch
40K Followers 874 Following Co-founder and CEO @MistralAI. Apply https://t.co/yHGRZAtjcxGuillaume Lample @GuillaumeLample
37K Followers 648 Following Cofounder & Chief Scientist https://t.co/hLfvKLkFHd (@MistralAI). Working on LLMs. Ex @MetaAI | PhD @Sorbonne_Univ_ | MSc @CarnegieMellon | X11 @PolytechniqueCharles 🎉 Frye @charles_irl
9K Followers 2K Following ai engineer at @modal_labs. he/him. ex @full_stack_dl, @weights_biases, phd Berkeley @Redwood_Neuro.Chip Huyen @chipro
92K Followers 442 Following Data processing on GPUs @VoltronData Designing ML Systems: https://t.co/G81hL2dWmr @designmlsys #AI x #GPUBeff Jezos — e/acc .. @BasedBeffJezos
102K Followers 2K Following chief accelerator & founder @ e/acc // thermodynamic priest // Kardashev gradient climber // memetic warlord // building @extropic_aiMistral AI @MistralAI
91K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCPIsaac B. Kardon @IBKardon
3K Followers 507 Following Senior fellow for China studies @CarnegieEndow & adjunct professor @SAISHopkins. Book: https://t.co/CQal9tOZrJ…Dave Font @davefontenot
13K Followers 5K Following 🏯 building the program for repeat founders @HF0Residency 🚀 early backer ramp, optimism, pave, crossmint, https://t.co/mHQInNULWw, https://t.co/UrZdMVRDO2 and more...molly cantillon @mollycantillon
3K Followers 310 Following building @heynoxcom @stanford __ prev @langchainai @replicate @calderaxyzjason liu @jxnlco
19K Followers 1K Following sabbatical @southpkcommons, angel investor?? prev @stitchfix @metaOne of the main ways that RAG applications can generate incorrect outputs is if the retrieval step messes up @RLanceMartin walks through how to test for exactly that Important to test each step in a RAG pipeline in addition to the end-to-end result!
LangSmith Evaluations: RAG Evaluation (Document Retrieval) Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith. This is the 14th video in our series focusing…
ollama run llama3-gradient
We've been in the kitchen cooking 🔥 Excited to release the first @AIatMeta LLama-3 8B with a context length of over 1M on @huggingface - coming off of the 160K context length model we released on Friday! A huge thank you to @CrusoeEnergy for sponsoring the compute. Let us know…
Finetuning Embeddings: Most people don't know that if you had any production-ready data, you should be able to fine-tune and outperform OpenAI. 1. With even 2,000 examples, you can fine-tune an embedding. 2. By using the Hugging Face Inference Server and Modal Labs, we showed…
We just released the first LLama-3 8B with a context length of over 160K onto Hugging Face! SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens, powered by @CrusoeEnergy's compute) by appropriately adjusting RoPE theta. 🔗 huggingface.co/gradientai/Lla…
Is there a way to backprop feedback across all components of a RAG system: Embedding model, prompt, re-ranker, context selection/creation? cc @hwchase17 @RLanceMartin is this something I can do with LangGraph?
Summarized this thread (+100 responses) into a 1-pager My take, companies, insights, and type of work docs.google.com/document/d/14x…
Is anyone getting traction selling AI consulting & implementation services to SMBs? to enterprise?
@lateinteraction @hwchase17 @RLanceMartin I'd love to try this out, if there is a beta — I've the same handle on Github
@NirantK @hwchase17 @RLanceMartin This is a very hard problem! That’s one abstract way to describe 90% of what DSPy is trying to do for you. And we’re collaborating with Harrison and team to make it work for arbitrary LangGraph runnables by June.
@RLanceMartin Hey @RLanceMartin ... really loved this one! QQ: It looks like you running this locally on a Mac. Was it still an x86 one, or how did you get GPT4All embeddings (which require AVX support) to run on Apple silicon?
Come join us in Toronto on Thursday, May 2nd! lu.ma/devs5 Space is limited, so please register soon.
Toronto AI devs come out next Thursday May 2nd to Cohere offices for the Toronto Local & Open Source AI Meetup! We have some great speakers lined up including @jxnlco (instructor) @madhavsinghal_ (replit) and @MikeBirdTech (openinterpreter) Thank you @aidangomez for hosting us!
Flow Engineering is all you need: Multiturn flows > few shot prompting! The excellent webinar recently hosted by @hwchase17 (@LangChainAI ) with @itamar_mar on Flow Engineering is the reminder we needed, inspiring this post! div.beehiiv.com/p/flow-enginee…
Great paper by Princeton NLP showing how LLMs can work on olympiad programming problems 3 main components: 1️⃣ Implement a coding agent with reflection (12.38% pass rate) 2⃣Add few-shot retrieval of expert reasoning examples (20.2% pass rate) 3⃣Add human-in-the-loop
🤖🏆LangGraph: Can Language Models Solve Olympiad Programming? 🤖🏆 Last week, Princeton researchers released the USACO benchmark dataset and showed that a zero-shot GPT-4 agent only passes 8.7% of the questions. We've implemented this paper in LangGraph and created a tutorial…
🤖🏆LangGraph: Can Language Models Solve Olympiad Programming? 🤖🏆 Last week, Princeton researchers released the USACO benchmark dataset and showed that a zero-shot GPT-4 agent only passes 8.7% of the questions. We've implemented this paper in LangGraph and created a tutorial…
⚡ LangSmith Evaluations: RAG Evaluation (Answer Hallucinations) ⚡ Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith. This is the 13th video in our series, focusing…
I’ve done a complete 180 on Langchain It’s really improved a ton especially with langsmith I can easily swap 4-5 different LLMs with 2 lines of code. All providers supported My agents mix and match various models (mostly using my own agent architecture under the hood)
I tried LangSmith evaluation for financial RAG today. Pleased to report it does a bunch of heavy lifting. • loading dataset • creating RAG pipeline • running evaluator My favorite is that eval results are automatically displayed in real-time UI. Before, I was tracking…
Hallucinations are a big pain point for RAG apps, @RLanceMartin walks through how to best test for them
⚡ LangSmith Evaluations: RAG Evaluation (Answer Hallucinations) ⚡ Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith. This is the 13th video in our series, focusing…
Does anyone have a reference implementation of function calling on llama 3 + vllm + outlines Surely someone has an open example - its helpful to see how other people are doing it b/c there are lots of ways of accomplishing this