LangChain, every mention
63 scenes · ← back to LangChain
tap a year for its mentions
every year anyone Shawn Wang 29Alessio Fanelli 12Harrison Chase 10James Reggio 4Umar Jamil 3Vasek Mlejnsky 2Sunil Pai 2Shunyu Yao 2Samuel Colvin 2Matthias Wagner 2
Verbatim, from the transcripts: the passages where LangChain comes up
⚡️ Competing with ChatGPT and Sierra, building a $10M ARR company — Yasser Elsaid, Founder, Chatbase
- ▶ 4:16 unnamed speaker The OG, built-on Langchain, Pinecone, OpenAI, deployed to Vercel. 2 times in the scene
⚡️ OpenClaw's Memory Sucks and the fix is simple — Dhravya Shah, Supermemory
- ▶ 26:38 unnamed speaker You know, I think Langchain has their own take. 2 times in the scene
⚡️Context Graphs: according to the authors — Jaya Gupta, Ashu Garg, Foundation Capital
- ▶ 0:15 unnamed speaker Uh, Jaya, we apparently met three years ago at the Langchain hackathon where, uh, Factory was born. 3 times in the scene
Brex’s AI Hail Mary — With CTO James Reggio (acquired for $5B by Capital One!)
- ▶ 14:37 James Reggio Uh, whereas, like, Langchain was available at the time, two and a half, three years ago, uh, it didn't quite feel, uh, right to us when we were trying to 4 times in the scene
[State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute
- ▶ 8:50 Andy Konwinski The way I think of it is DSP is something closer, more akin to a leg chain.
⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
- ▶ 12:07 Matthias Wagner You know, we use Langchain, Langgraph here under the hood. 2 times in the scene
- ▶ 31:17 unnamed speaker Um, you use, you said you use LandGraph, uh, LandChain.
⚡️ Ship AI recap: Agents, Workflows, and Python — w/ Vercel CTO Malte Ubl
- ▶ 9:43 unnamed speaker But I think it was not a given that AISDK would be a winner because of Langchain, because of Mastra, because of, you know, everyone else trying to, to get that spot, except that you guys have the perfect package name.
Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
- ▶ 3:01 Barak Lenz And actually when lag chain came out, they, they like said, you know, miracle systems was our inspiration.
Context Engineering for Agents - Lance Martin, LangChain
- ▶ 0:12 Shawn Wang Uh, we are so happy to be in the remote studio with Lance Martin from Langchain, LangGraph, and everything else he does. 2 times in the scene
Long Live Context Engineering - with Jeff Huber of Chroma
- ▶ 8:43 Jeff Huber For many years running, Chrome has been the number one used project broadly, but also within communities like LinkChain and Llama Index.
- ▶ 23:21 Shawn Wang Lance Martin from Langchain did a really nice blog post of like all the different separations.
The AI Coding Factory
- ▶ 0:18 Shawn Wang Matan and Eno, my favorite story about the founding of Factory is that you met at the Langchain hackathon, and I'm very annoyed because I was at that hackathon, and I didn't start a company. 2 times in the scene
- ▶ 1:29 Shawn Wang If I recall that Langchain Hackathon wasn't about code generation, how do you sort of get, find the idea maze to factory?
- ▶ 50:16 Shawn Wang Are you guys at a Langchain shop? 2 times in the scene
Why Every Agent needs Open Source Cloud Sandboxes
- ▶ 40:11 Vasek Mlejnsky Well, I have a, I have, I don't know if this is an unpopular opinion, but, like, people keep telling me, ah, Langchain isn't popular, but if you look at its stats, like, it has twenty million downloads per month. 2 times in the scene
Tiny Teams: $6m ARR, 5m users with 4 employees — Sid Bendre, Oleve (Quizard AI/Unstuck AI)
- ▶ 21:31 unnamed speaker Any of the vector databases that you like, any of the API, AI gateways that you like, just literally anything, any framework, Langchain, no?
Sleep-Time Compute — Letta AI (Charles Packer, Charlie Snell, Kevin Lin)
- ▶ 32:58 Shawn Wang I think, then the other thing was, I also wanted to shout out like Langmem is, is relaunched from Langchain as well. 2 times in the scene
The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
- ▶ 1:17:17 Shawn Wang Um, yeah, I'd say Langchain has, has an interesting one.
npm install Agents — with Sunil Pai and Rita Kozlov (VP AI) of Cloudflare
- ▶ 2:22 Sunil Pai So that's kind of the take that we're doing here, which is not letting you bring your own code, whether it's written in the AISDK, Lang chain, et cetera, et cetera.
- ▶ 27:37 Sunil Pai I think the Langchain people just put out a paper today which talks about the six patterns, and I badly want to implement all of them, like, in the next few days on Cloudflare agents.
smol agents are all you need
- ▶ 0:35 Aymeric (Emmerich) So this essay, what is an AI agent written by Harrison Chase from Langchain.
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 7:47 Alessio Fanelli And early on, I would say everybody like, you know, Langchain and like a Pedente kind of like a first class support. 2 times in the scene
- ▶ 16:38 Shawn Wang It does make me think that not only are you competing with Langchain now, and obviously Instructor, and now you're going into sort of the more, like, orchestrated things like Airflow, Prefect, Daxter, those guys. 2 times in the scene
- ▶ 29:02 Shawn Wang My rant here is that, you know, versions of this appear in Langchain and all, every single framework has to have its own little thing, a version of that.
- ▶ 35:25 Samuel Colvin I suspect Pedantic AI will be the first agent framework that implements those semantic attributes properly, because again, we control Pedantic AI, and we can say this is important for observability, whereas most of the other agent…
- ▶ 41:05 Samuel Colvin Uh, I don't think we know the answer yet, but I mean, I was on the, I guess this is kind of semi-public because it was on, I was on the call with the OpenTelemetry call last week talking about Gen.ai and there was someone from Arise…
Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
- ▶ 4:22 unnamed speaker Not to pick on them, like, you know, Langchain, Pydantic, which we also just talked to is like, all this doesn't belong in your app code. 2 times in the scene
- ▶ 25:18 unnamed speaker Uh, chatbot with single person, chatbot multiple people, but then also, like, passive agents are coming up, you know, like, working in the backgrounds, you know, if they're, like, reading my emails for me and notifying me, LangChain is…
2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- ▶ 11:09 Shawn Wang And I think if you correlate that with software that we asked Harrison Chase on, on the LangChain episode, it was true.
- ▶ 53:01 Shawn Wang You say Langchain, Lama index still growing. 2 times in the scene
Agents @ Work: Lindy.ai (with live demo!)
- ▶ 0:40 Florent Crivello So you can think of, we are to Langchain as Airtable to MySQL.
- ▶ 4:37 unnamed speaker And what was the choosing between kind of like this drag and drop, low code, whatever, super code driven, maybe like the LangChains, AutoGPT of the world.
Agents @ Work: Dust.tt — with Stanislas Polu
- ▶ 17:56 Alessio Fanelli And I would say in Silicon Valley, the two hottest companies at the time were you and Langchain. 2 times in the scene
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- ▶ 0:34 Harrison Chase Langchain, Langsmith, Langgraf, pushing on all of them, lots of cool stuff related to a lot of the stuff that we're going to talk about today, probably.
- ▶ 2:57 Alessio Fanelli Which was a big part of your defense, but also Harrison, when you came on the podcast last year, you said that was one of the first papers that you saw when you were getting inspired for Langchain.
- ▶ 9:23 Harrison Chase And so this is one of the things that we've seen in LinkedIn is people who build their own applications generally write their own tools.
- ▶ 16:52 Harrison Chase And so for context, I think at Langchain and at other places as well, we found it like we and others found it pretty easy to implement kind of like react in a standard way. 2 times in the scene
- ▶ 46:29 Harrison Chase We haven't thought about that from the perspective, like we're not trying to design LangChain or LangGraph to be friendly, but I mean, I think to be friendly for agents to write. 3 times in the scene
- ▶ 1:23:10 Shunyu Yao Did you write it with Nantian? 2 times in the scene
The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
- ▶ 1:00:02 Shawn Wang In here is sort of the Instructure, Langchain,
[Paper Club] Writing in the Margins: Chunked Prefill KV Caching for Long Context Retrieval
- ▶ 21:46 Umar Jamil Chunking techniques, like you can do with the lung chain, for example.
- ▶ 26:20 Umar Jamil Uh, yes, this is not any, we are not doing any change to the model architecture, so you don't have to fine-tune anything, you don't have to change anything, like the, um, uh, can you use this stuff with, like, a Lank pane?
- ▶ 45:56 Umar Jamil And it helps much more than, uh, chunking separately like we do with the APIs, right, with the Lung chain, because you are paying double, twice the cost of prefilling.
Building AGI with OpenAI's Structured Outputs API
- ▶ 52:55 Shawn Wang And like, if I'm an existing Langchain, Lama index, whatever, how do you compare?
- ▶ 1:04:17 Alessio Fanelli It's like, you know, Llama with like one L, or like all, all these different things, or like LangChain, and like transcribes LangChain in like...
The Winds of AI Winter (Q2 Four Wars of the AI Stack Recap)
- ▶ 1:02:47 unnamed speaker And then the framework companies have to become ops companies, which is what Langchain is.
How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)
- ▶ 27:27 Adam Wiggins I feel like there's some of that discussion around Langchain right now.
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI
- ▶ 42:29 Harrison Chase Um, but my name is Harrison, uh, uh, a co-founder of Langchain. 3 times in the scene
The State of AI in production — with David Hsu of Retool
- ▶ 28:19 Shawn Wang The, sort of, uh, lag chain, VectorDB reg layer is understood.
The Four Wars of the AI Stack - Dec 2023 Recap
- ▶ 2:55 unnamed speaker And people forgot about our friends at Langchain, Lama index, and some of the things that were maybe top of mind vector DBs, you know, it seemed like everybody was releasing a vector DB early in the year.
- ▶ 54:54 unnamed speaker What does, what's the first product of LangChain, LangSmith, which is an ops thing, right? 2 times in the scene
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 1:07:00 Shawn Wang Which is something that LangChain and Llama Index do. 2 times in the scene
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
- ▶ 1:15:10 Shawn Wang Um, Harrison from Langchain has been talking about this sort of two by two matrix with the Ragas. 2 times in the scene
Powering your Copilot for Data - with Artem Keydunov from Cube.dev
- ▶ 9:54 Alessio Fanelli And so initially a lot of your use cases were more, you know, BI related, but you recently released a Langtrain integration.
- ▶ 34:21 Alessio Fanelli We, we heard the same from Harrison and Langtrim, uh, that most people just use OpenAI. 2 times in the scene
RAG is a hack - with Jerry Liu of LlamaIndex
- ▶ 5:29 Alessio Fanelli And before we dive into, um, Lama Index, what do they feed you a robust intelligence that both Hugh and Harrison from Langchain came out of it at the same time? 3 times in the scene
- ▶ 1:12:38 Jerry Liu Um, uh, like, I would check out the guide if you guys haven't already, and I think it's in our docs, but instead of just using, um, you know, either the kind of, like, uh, the retriever query engine in Lomindex or, like, the conversational…
Generating your AI Media Empire - with Youssef Rizk of Wondercraft.ai
- ▶ 36:26 Shawn Wang Yeah, you mentioned that you were listening to the Langchain episode, and Langchain is also similarly, like, in my mind, very high tension, but also, obviously, important for them to stay relevant on top of all the trends. 2 times in the scene
- ▶ 45:35 Youssef Rizk Um, I was listening to the Langchain episode that you guys did, and
- ▶ 56:19 Shawn Wang Um, do you use Langchain? 3 times in the scene