E134: Making Complex Data RAG-Ready with Unstructured

Open Source Startup Podcast

Player FM - Internet Radio Done Right

0-10 subscribers

اضافه شده در two سال پیش

محتوای ارائه شده توسط Robby (MTF); Tim (Essence VC). تمام محتوای پادکست شامل قسمت‌ها، گرافیک‌ها و توضیحات پادکست مستقیماً توسط Robby (MTF); Tim (Essence VC) یا شریک پلتفرم پادکست آن‌ها آپلود و ارائه می‌شوند. اگر فکر می‌کنید شخصی بدون اجازه شما از اثر دارای حق نسخه‌برداری شما استفاده می‌کند، می‌توانید روندی که در اینجا شرح داده شده است را دنبال کنید.https://fa.player.fm/legal

We Have The Receipts

1
Battle Camp S1: Reality Rivalries with Dana Moon & QT 1:00:36

22 روز پیش1:00:36

پخش در آینده

لیست ها

پسندیدن

دوست داشته شد

1:00:36

Do you have fond childhood memories of summer camp? For a chance at $250,000, campers must compete in a series of summer camp-themed challenges to prove that they are unbeatable, unhateable, and unbreakable. Host Chris Burns is joined by the multi-talented comedian Dana Moon to recap the first five episodes of season one of Battle Camp . Plus, Quori-Tyler (aka QT) joins the podcast to dish on the camp gossip, team dynamics, and the Watson to her Sherlock Holmes. Leave us a voice message at www.speakpipe.com/WeHaveTheReceipts Text us at (929) 487-3621 DM Chris @FatCarrieBradshaw on Instagram Follow We Have The Receipts wherever you listen, so you never miss an episode. Listen to more from Netflix Podcasts.…

حدود یک سال پیش 37:06

MP3•خانه قسمت

Brian Raymond is Founder & CEO of Unstructured, the platform to extract and transform complex data for use with every major vector database and LLM framework. Their open source project has 7K stars on GitHub and includes libraries and APIs that let users build custom preprocessing pipelines for labeling, training, and production machine learning pipelines. Today, they have over 6M downloads and 50K companies using their tools.

Unstructured has raised $65M from investors including Bain, Essence VC, and Menlo Ventures.

In this episode, we dig into Brian's process of talking to 100 data scientists before launching Unstructured, why the long tail of data matters for LLMs, competing with their own open source, why being a "boring company" is valuable for today's LLM stack, why they liked having government design partners, why world-class design & marketing are huge differentiators for open source companies & more!

175 قسمت

#Tech #Robby (Cowboy VC) & Tim (Essence VC #Robby (Cowboy VC #Tim (Essence VC

E134: Making Complex Data RAG-Ready with Unstructured

Open Source Startup Podcast

0-10 subscribers

published حدود یک سال پیش

اشتراک گذاری

MP3•خانه قسمت

Unstructured has raised $65M from investors including Bain, Essence VC, and Menlo Ventures.

175 قسمت

#Tech #Robby (Cowboy VC) & Tim (Essence VC #Robby (Cowboy VC #Tim (Essence VC

همه قسمت ها

1
E175: How Dragonfly Is Taking on Redis With a New Data Store 39:42

19 hours پیش39:42

39:42

Roman Gershman is Co-Founder & CTO of Dragonfly , the drop-in Redis replacement for heavy data workloads that has significant performance, cost, and scale benefits. Their open source dragonflydb has 28K stars on GitHub. Dragonfly has raised $21M from investors including Quiet Capital and Redpoint. In this episode, we dig into: The challenges with Redis The users that have really benefitted from Dragonfly (high scale + real-time needs - gaming, B2C) The benefits of being multi-threaded How they got some of their bigger users / customers like Twilio, SoFi, and Spotify…

1
E174: The SDF / DBT Acquisition (1 + 1 = 3) 39:43

18 روز پیش39:43

39:43

Lukas Schulte is Co-Founder & CEO of SDF Labs , the developer platform that scales SQL understanding across organizations, which was recently acquired by data transformation unicorn dbt Labs . In this episode, he's joined by Anders Swanson , Senior Developer Experience Advocate at dbt, to discuss the acquisition and future of data engineering. In this episode, we dig into: How the acquisition happened, as well as the M&A process How dbt thinks about building capabilities internally vs. making acquisitions How the SDF platform will improve the lives of dbt users The most challenging parts about the integration What the future developer experience for data teams will be like A glimpse into the future of data engineering…

1
E173: Feature Flagging with OpenFeature 35:03

۵ weeks پیش35:03

35:03

Andrew Norris is Co-Founder & CEO of DevCycle , the leading feature flagging platform based on the OpenFeature project. OpenFeature provides a standard for feature flagging unifying tools behind a common interface and avoiding vendor lock-in at the code level. DevCycle is a product created by Taplytics , the platform for marketing and product teams to A/B test. In 2023, they raised $5M to scale DevCycle. In this episode, we dig into: The creation of DevCycle through insights at Taplytics Learning to sell to engineers (DevCycle) vs. marketing teams (Taplytics) The decision to keep Talytics going vs. focus solely on DevCycle Why engineers prefer open standards like OpenFeature How their GTM works alongside OpenFeature…

1
E172: How MetalBear Makes Cloud Development 100x Faster 35:22

۶ weeks پیش35:22

35:22

Aviram Hassan is Co-Founder & CEO of MetalBear , the cloud development platform that lets developers run local code as if it were part of their remote environment. Their project, mirrord , has 4K stars on GitHub and is loved by users at companies like SentinelOne, Flexport, and Run.ai . In this episode, we dig into: How traditional staging environments create friction for cloud developers Their unique approach that allows for concurrency - and educating the market on it How open source helped build trust with big, enterprise customers early The story behind their first big customer win Focusing on a killer, fast time to value implementation Introducing monetization early, and how their products align with open source mirrord…

1
E171: How Companies Like Block Build Viral Open Source Projects 40:08

۷ weeks پیش40:08

40:08

Manik Surtani is Head of Open Source and Bradley Axen is Principal Engineer at Block. Manik was key to launching Block's Open Source Programs Office and Bradley is a major open source contributor - including the project Goose which is Block's extensible AI agent project. It currently has over 11K stars on GitHub and has been used for a number of internal use cases at Block as well as by the general AI builder ecosystem. In this episode, we dig into: Block's history releasing and supporting open source projects, and how that led to the creation of the programs office How big companies like Block approach open source and come up with ideas for projects like Goose The Goose project and how it's different from other agent frameworks…

1
E170: From Idea to Working Web App Using Only Python with Reflex 39:19

۸ weeks پیش39:19

39:19

Nikhil Rao is Co-Founder of Reflex , the open source framework to build and deploy web apps in python. Their project, also called reflex, has over 22K stars on GitHub and is a library to build full-stack web apps. Reflex has raised $5M from investors including Lux Capital. In this episode, we dig into: The power of deploying apps using only Python Balancing abstraction and code level access for users The challenges low code frameworks have had becoming production-grade The apps users are building with Reflex How he thought about Reflex Cloud Their vision to be as big as React…

1
E169: Building New Standards for Observability - Lightstep & OpenTelemetry 38:31

۹ weeks پیش38:31

38:31

Ben Sigelman is the Co-Founder & CEO of observability platform Lightstep as well as Co-Creator of open source observability frameworks OpenTracing and OpenTelemetry . Lightstep was acquired by ServiceNow in 2021 and OpenTelemetry was released in 2019 and has since become the standard observability framework. In this episode, we dig into: The founding story for Lightstep - including the initial pivot into the idea The benefits Lightstep got from open sourcing OpenTracing The OpenTracing and OpenCensus merger into OpenTelemetry Why OpenTelemetry has been so widely adopted Ben's perspective on the many companies building with OpenTelemetry today How their team made the decision to take the ServiceNow acquisition Company building learnings around team building (& more!)…

1
E168: One (Multi-Model) Database to Rule Them All - SurrealDB 39:36

11 weeks پیش39:36

39:36

Tobie Morgan Hitchcock is the Co-Founder & CEO of SurrealDB , the next generation serverless cloud database for modern applications. Their open source database, also called surrealdb , has 30K stars on GitHub. SurrealDB has raised $26M from investors including FirstMark and Georgian. In this episode, we dig into: Taking a broad vs. niche approach to building a new database How coming from a non-traditional DB background helped Tobie take a new, first principles approach How graph databases best reflect how humans think The importance of design for infra products How enterprises vs. SMBs / individual users view their value How open source helped them develop trust with large companies Planning out their cloud offering…

1
E167: Taking on Network Security with a Zero Trust Approach with NetBird 34:50

12 weeks پیش34:50

34:50

Misha Bragin is the Founder & CEO of NetBird , the open source zero trust networking platform that allows companies and individuals to create secure private networks without the hassle of corporate networks. Their open source, also called netbird , has over 12K stars on GitHub and connects devices into a secure WireGuard-based overlay network. NetBird has raised $4M from investors including InReach Ventures. In this episode, we discuss: Pivoting away from their initial hardware-based approach How the growth in remote employees has driven demand Why VPNs needed to be reinvented Why they use the WireGuard protocol What's different about their approach vs. Tailscale Managing big and small users at the same time Why most technical founders should hire a technical marketer early…

1
E166: Making Open Source Reliable & Secure with Fossa 40:06

13 weeks پیش40:06

40:06

Kevin Wang is Founder & CEO of Fossa , the product security platform that automates compliance & security across open source third party code, suppliers, and tools. In this episode, we discuss: Where Kevin's interest in open source started Learning to work with big enterprises The shift from scanning to fixing Repositioning from an engineering to security platform Resisting the market pressure to push hard into AI…

1
E165: Can DevTools Get to $1B ARR? 42:52

14 weeks پیش42:52

42:52

Max Stoiber is Co-Founder & CEO of Stellate , the GraphQL edge platform recently acquired by Shopify. In this episode, we discuss: The Stellate journey from idea to initial traction to acquisition The market size (and limitations) for GraphQL, APIs, and DevTools How he ran a top-notch acquisition process for Stellate Why startups fail…

1
E164: Taking on Auth0 with Open Source Zitadel 34:02

15 weeks پیش34:02

34:02

Florian Forster is Co-Founder & CEO of Zitadel , the cloud security platform aiming to build the future of identity and access management. Their open source project, also called zitadel , provides identity infrastructure and has 10K stars on GitHub. In this episode, we dig into: The benefits of having an open source auth vendor Authentication vs. authorization Building the "GitLab for identity" Why customization matters for an auth product Demand for self-hosting options for auth Appealing to developers and security teams…

1
E163: Using Feedback Loops to Optimize LLM-Based Applications 38:12

16 weeks پیش38:12

38:12

Viraj Mehta is the Co-Founder & CTO of TensorZero which is an open-source infrastructure platform that creates a feedback loop for optimizing LLM applications. Their open source project helps users turn production data into smarter, faster, and cheaper models. In this episode, we dig into: The benefits of feedback loops for LLMs Helping their users choose the best underlying models for their applications "Recipes" as a potential monetization path The most common optimizations for LLM-based apps Educating users on what's possible with LLMs…

1
E162: The AI Code Editor War with Zed 30:04

19 weeks پیش30:04

30:04

Nathan Sobo is the Founder of Zed , the next-gen code editor that enables high-performance collaboration - powered by AI. Open source zed has 53K Stars on GitHub and is used by engineers at Vercel, Apple, Anthropic, and GitLab. Prior to founding Zed, Nathan created the editor Atom at GitHub which reached 1M+ active users. Zed has raised from investors including Redpoint and Root Ventures. In this episode, we dive into Nathan's deep history with code editors including the widely adopted GitHub editor Atom, the decision to make Zed open source (and the massive 10x growth that came from it), how AI changed their trajectory, why collaboration is core to becoming the defacto editor, anchoring on performance and responsiveness, how they're thinking about the commercial side of Zed & more!…

1
E161: Reimagining Python Notebooks with Marimo 34:14

22 weeks پیش34:14

34:14

Akshay Agrawal is the Founder & CEO of Marimo , the next generation Python notebook. Their open source reactive notebook for Python, also called marimo , has almost 9K stars on GitHub. Marimo has raised $5M from investors including AIX Ventures. In this episode, we dig into Akshay's love of building developer tools for data teams, his journey from PhD to founder, what a great developer experience means for data teams, why reproducibility was a key problem for them to solve, how he thinks about monetization when other notebooks like Jupyter don't focus on making money & more!…

Open Source Startup Podcast

1
E160: Open Source Secrets Management with Infisical 39:33

23 weeks پیش39:33

39:33

Vlad Matsiiako is CEO & Co-Founder of Infisical , the open source secrets management platform. Their open source project, also called infisical , has 16K stars on GitHub and helps users sync secrets across their teams and infrastructure. Infisical has raised $3M from investors including Gradient and YC. In this episode, we dig into their path from closed to open source, their big user wins (including government users), the importance of reliability for products in and around this category, the organic growth that came from their community, their AI strategy & more!…

Open Source Startup Podcast

1
E159: Innovating on Distributed SQL Databases with Yugabyte 41:41

23 weeks پیش41:41

41:41

Karthik Ranganathan is Founder & CTO of Yugabyte , the PostgreSQL-compatible distributed database for cloud native applications. Their open source database, also called yugabyte , has almost 10K stars on GitHub. Yugabyte has raised almost $300M and sits at a $1.3B valuation. They've raised from investors including Sapphire Ventures, Lightspeed, and 8VC. In this episode, we dig into the enormous interest Yugabyte had at the onset as transactional databases were due for innovation, the key architecture choices they made, the initial launch, key early customer wins, the importance of positioning as a distributed SQL company, their evolving open source strategy, building alongside the Postgres community, the decision to bring on an outside CEO & much more!…

Open Source Startup Podcast

1
E158: Open Source Diagramming and Charting with Mermaid Chart 40:47

24 weeks پیش40:47

40:47

Andrew Firestone is CEO and Knut Sveidqvist is CTO of Mermaid Chart , the open source text-based diagraming software platform. The mermaid project has over 70K stars on GitHub and is an open source diagramming and charting tool. Mermaid Chart has raised $7.5M from investors including Open Core Ventures. In this episode, we dig into the mermaid project's 8 year journey, going from side project to company, working with GitLab founder Sid Sijbrandij to bring Andrew in as CEO & more!…

Open Source Startup Podcast

1
E157: Build Your Own Production-Grade AI CoPilots With Copilotkit 36:08

25 weeks پیش36:08

36:08

Atai Barkai is Co-Founder & CEO of Copilotkit , the platform to build production-grade AI Copilots 10x faster. Their open source project, also called copilotkit , has almost 13K stars on GitHub and provides React UI + elegant infrastructure for AI Copilots, in-app AI agents, AI chatbots, and AI-powered Textareas. In this episode, we dig into Copilotkit's incredible open source growth trajectory, the importance of tutorials and templates to grow community in a new product area, understanding all of the user types and use cases people were using their open source for, competing with vertical copilots, the future of copilots and when AI becomes more autonomous & more!…

Open Source Startup Podcast

1
E156: Code-First Product Integrations with Ampersand 25:53

26 weeks پیش25:53

25:53

Lauren Long is Co-Founder & CTO of Ampersand , the developer platform for native product integrations. Ampersand has raised $5M from investors including Matrix, Base Case Capital, Flex Capital, and 2.12 Angels. In this episode, we dig into their differentiation as a "code-first" product, why they focused on the GTM vertical to start (Salesforce was the first integration), why their CLI is open source but their orchestration layer is closed source, how being transparent on pricing has been a differentiator for them & much more!…

Open Source Startup Podcast

1
E155: Taking on Elasticsearch - the ParadeDB Story 33:17

27 weeks پیش33:17

33:17

Philippe Noël is Co-Founder & CEO of ParadeDB , the modern Elasticsearch alternative built on Postgres. They're purpose-built for heavy, real-time workloads and their open source project, also called paradedb , has over 6K stars on GitHub. ParadeDB has raised $2M from investors including General Catalyst & YC. In this episode, we dig into the benefits of connecting search directly to the database (ie. no ETL), the types of users / use cases that really benefit from ParadeDB (e-commerce, FinTech, etc.), the decision to focus on Postgres, making adoption super easy, Philippe's learnings as a second-time founder & more!…

Open Source Startup Podcast

1
E154: Bringing OpenTelemetry to Mobile Observability 41:40

28 weeks پیش41:40

41:40

Eric Futoran is Co-Founder & CEO of Embrace , the mobile observability platform built on OpenTelemetry. Embrace has raised almost $80M from investors including NEA, Greycroft & Eniac. In this episode, we dig into the creation of mobile observability as a category and how Embrace helped evangelize it, what makes mobile observability unique, why they open sourced their SDKs, how aligning with OpenTelemetry changed their trajectory, the difference between having product-market-fit and GTM-market-fit, shifting from just focusing on mobile teams to mobile + DevOps teams & more!…

Open Source Startup Podcast

1
E153: Dead Simple Dev Environments with Daytona 39:28

30 weeks پیش39:28

39:28

Ivan Burazin is Co-Founder & CEO of Daytona , the open source developer environment management platform. Their open source manager, also called daytona , has 9K stars on GitHub. Daytona has raised $5M from investors including Upfront Ventures. In this episode, we dig into Daytona's plan to be the fastest growing cloud development environment, how consistent and frequent content has become a huge driver of their growth, how bringing successful DevTool founders as angels helped with initial credibility and growth, thinking about the user and buyer's motivations, open source license decisions and the future of open source licenses (MIT + Apache are the only true open source licenses in their perspective) & more!…

Open Source Startup Podcast

1
E152: Taking on Bitly with Dub.co - an Open Source Alternative for Link Management 31:59

33 weeks پیش31:59

31:59

Steven Tey is Founder & CEO of Dub.co , the open source link management infrastructure platform for modern marketing teams. Their open source project, also called dub , has almost 18K stars on GitHub and is used by teams at companies like Vercel, Raycast, and Perplexity. In this episode, we dig into starting Dub.co as a side project and how it ultimately turned into a company, their initial positioning as a Bitly alternative, their focus on great design and how that shows up in all parts of their product and marketing, how analytics unlocked much higher ACVs and value for customers, how getting a top Hackernews post helped drive early momentum, their vision to become an end-to-end attribution platform & more!…

Open Source Startup Podcast

1
E151: Taking on DBT by Combining Data Transformation with a Query Engine 31:14

33 weeks پیش31:14

31:14

Lukas Schulte is Co-Founder and CEO of SDF Labs (Semantic Data Fabric), the data transformation layer and query engine platform. They're an open core company powered by the Apache Data Fusion query engine. SDF Labs has raised $9M from investors including RTP Global and Two Sigma Ventures. In this episode, we dig into the complications and pain points with the Modern Data Stack, shifting left with data (ie. moving more over to the client), competing with DBT by adding a query engine, why building in Rust was important, why their CLI is closed source, the importance of a strong partner strategy as a data company & more!…

Open Source Startup Podcast

1
E150: Fast Analytics with Metabase 39:35

34 weeks پیش39:35

39:35

Sameer Al-Sakran is CEO of Metabase , the open-source analytics and business intelligence platform. Their open source project, also called metabase , has over 38K stars on GitHub. Metabase has raised $51M from investors including NEA, Insight and Expa. In this episode, we dig into the company's 10 year journey, what it means to have a "developer friendly analytics platform", eliminating the friction with BI by making Metabase super fast to get started with, keeping the product simple, juggling short-term execution with their long-term vision & more!…

Open Source Startup Podcast

1
E149: One AI Agent to Rule Them All? 36:16

35 weeks پیش36:16

36:16

Stanislas Polu is Co-Founder of Dust , the platform for companies to create and operate custom AI assistants for a range of use cases. Dust has raised $20M from investors including Sequoia. In this episode, we dig into the diverse set of users and use cases for Dust, how Dust spreads within an organization, their unique approach to open source, competing with vertical AI agents, augmenting humans instead of replacing them, predictions on the future of the agent space & more!…

Open Source Startup Podcast

1
E148: Software Refactoring in the Age of AI 30:00

37 weeks پیش30:00

30:00

Jonathan Schneider is Co-Founder & CEO of Moderne , the platform for code migrations. Moderne has raised up to a Series A from investors including Intel Capital and True Ventures. In this episode, we dig into the importance of software refactoring and the security and engineering challenges that come up when code isn't maintained, why they started with Java refactoring, their rewrite open source project, how the amount of code created with GenAI has made refactoring an even bigger challenge & more!…

Open Source Startup Podcast

1
E147: The Over-complication of API Management - What Went Wrong? 39:54

38 weeks پیش39:54

39:54

James Perkins is Co-Founder & CEO of Unkey , the open source API management platform that helps developers secure, manage, and scale their APIs. Their project, also called unkey , has almost 3K stars on GitHub. Unkey has raised from investors including Essence VC, Sunflower, and The New Normal Fund. In this episode, we dig into the complicated API tooling landscape, getting their early start with crypto and AI companies, what great DevEx means to them (simplicity is key), their scalable pricing model, splitting work between Co-Founders, their expansion plan and how they plan on grow capabilities without over-complicating the product & more!…

Open Source Startup Podcast

1
E146: Inventing Virtual Kubernetes Clusters 37:10

39 weeks پیش37:10

37:10

Lukas Gentele is Co-Founder & CEO of Loft , the platform engineering company behind "kubernetes virtualization" to reduce costs and create efficiencies for teams with high (and growing) kubernetes usage. They allow any organization to scale self-service access to Kubernetes from 10 to 10,000 engineers. Loft recently raised $24M led by Khosla Ventures and previously raised from investors including Fusion Fund. In this episode, we dig into the company's journey through a shift from being a PaaS ( devpod ) to virtualization of kubernetes ( vcluster ), the rapid feedback loop you get from having an open source-based company, why Lukas thinks open source founders should be more commercial from the start & more!…

به Player FM خوش آمدید!

Player FM در سراسر وب را برای یافتن پادکست های با کیفیت اسکن می کند تا همین الان لذت ببرید. این بهترین برنامه ی پادکست است که در اندروید، آیفون و وب کار می کند. ثبت نام کنید تا اشتراک های شما در بین دستگاه های مختلف همگام سازی شود.

به بیش از 500 موضوع گوش کنید

0-10 subscribers

مشابه Open Source Startup Podcast

2025 - American Silver Eagle .999 Fine Silver with our Smyrnacoin Certificate of Authenticity Dollar Uncirculated US Mint

Amazon eGift Card - Bright Balloons (Animated)

Amazon Basics Multipurpose Copy Printer Paper, 8.5 x 11 inches, 20 lb, 1 Ream, 500 Sheets, 92 Bright, White

پادکست هایی که ارزش شنیدن دارند

Open Source Startup Podcast « » E134: Making Complex Data RAG-Ready with Unstructured

E134: Making Complex Data RAG-Ready with Unstructured

پادکست هایی که ارزش شنیدن دارند

به Player FM خوش آمدید!

Amazon Fire HD 10 tablet (newest model) built for relaxation, 10.1" vibrant Full HD screen, octa-core processor, 3 GB RAM, 32 GB, Black

The Let Them Theory: A Life-Changing Tool That Millions of People Can't Stop Talking About

USANOOKS Microfiber Cleaning Cloth Grey - 12 Pcs (12.5"x12.5") - High Performance - 1200 Washes, Ultra Absorbent Microfiber Towel Weave Grime & Liquid for Streak-Free Mirror Shine - Car Washing Cloth

Amazon Basics Dog and Puppy Pee Pads with Leak-Proof Quick-Dry Design for Potty Training, Standard Absorbency, Regular Size, 22 x 22 Inches, Pack of 100, Blue & White

The Let Them Theory: A Life-Changing Tool That Millions of People Can't Stop Talking About

مشابه Open Source Startup Podcast

راهنمای مرجع سریع

Open Source Startup Podcast « »
E134: Making Complex Data RAG-Ready with Unstructured