Загрузка видео...

Не удалось загрузить видео

На главную

Until now, adding web search to open-source models meant hand-wiring orchestration, managing separate keys, and paying latency taxes on every round trip. Today, we're solving that. We're excited to introduce Baseten Hosted Tools and Baseten Grounded Inference to bring real-time web search server-side to open models running on Baseten...

baseten's profile picture

Baseten

23,133 subscribers

31,280 просмотров • 1 месяц назад •via X (Twitter)

Новости и политикаОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Andrey Styskin
Andrey Styskin1 месяц назад

Baseten x Keenable ❤️

Фото профиля Baseten
Baseten1 месяц назад

🙌

Фото профиля Ishan Goswami
Ishan Goswami1 месяц назад

Exa 🤝 Baseten

Фото профиля kes
kes1 месяц назад

Great working with you guys on this!

Фото профиля Baseten
Baseten1 месяц назад

💚

Фото профиля Exa Developers
Exa Developers1 месяц назад

💚

Фото профиля Teo Gonzalez
Teo Gonzalez1 месяц назад

Love to see @baseten 🤝 @ExaAILabs

Фото профиля Baseten
Baseten1 месяц назад

@ExaAILabs 💚

Фото профиля Manish Tyagi
Manish Tyagi1 месяц назад

Excited to see this unfold!

Фото профиля Turk 🇺🇸
Turk 🇺🇸1 месяц назад

@saranormous Seems biased. Mentions Dreamforce happening in SF and says nothing about Grok galaxy which has more overall attendees than any baseball game happening this week in SF

Фото профиля RemoteBrowser
RemoteBrowser1 месяц назад

The latency tax framing is the real pain point. The round trips add up fast when the model decides to search mid-generation. Does Hosted Tools keep the search call inside the same inference loop, or is it still a separate hop?

Похожие видео

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:
17:43

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:

Baseten

27,032 просмотров • 1 месяц назад

figuring out how to upgrade go version using gpt-oss:120b, ollama's web search MCP server, and OpenAI codex open source models for coding are here
0:39

figuring out how to upgrade go version using gpt-oss:120b, ollama's web search MCP server, and OpenAI codex open source models for coding are here

parth

37,958 просмотров • 1 год назад

Introducing Web Search Agents: expert level web search that self-learns your domain to deliver perfect web context, while burning less tokens. Generic web search tools start from scratch every time they run. Web Search Agents compound their expertise to adapt web search and crawling to your use case — finding the exact data you need, more efficiently. Learn more below in our blog:
1:28

Introducing Web Search Agents: expert level web search that self-learns your domain to deliver perfect web context, while burning less tokens. Generic web search tools start from scratch every time they run. Web Search Agents compound their expertise to adapt web search and crawling to your use case — finding the exact data you need, more efficiently. Learn more below in our blog:

Nimble

363,920 просмотров • 3 месяцев назад

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.
0:49

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

Baseten

35,382 просмотров • 1 год назад

Give your AI agents access to the entire live web. Web Search, Fetch, Browser, and Agent. Four web primitives. One API key. Every layer built in-house. And we're just getting started! Sign up at and get 500 steps. No credit card.
1:06

Give your AI agents access to the entire live web. Web Search, Fetch, Browser, and Agent. Four web primitives. One API key. Every layer built in-house. And we're just getting started! Sign up at and get 500 steps. No credit card.

TinyFish

437,883 просмотров • 6 месяцев назад

we're releasing an experimental typescript sdk! npm install xAI-official/sdk get text, voice, image and video in one sdk, with the latest grok models and tools that run on our servers, like real-time X search, web search, code execution and remote mcp
0:35

we're releasing an experimental typescript sdk! npm install xAI-official/sdk get text, voice, image and video in one sdk, with the latest grok models and tools that run on our servers, like real-time X search, web search, code execution and remote mcp

eric zakariasson

125,689 просмотров • 1 месяц назад

we're bringing the context of the world wide web to your data. ask anything, get answers in Hex web search for the hex agent is live powered by Parallel Web Systems was so fun to work with Travers & the parallel team on this!
2:09

we're bringing the context of the world wide web to your data. ask anything, get answers in Hex web search for the hex agent is live powered by Parallel Web Systems was so fun to work with Travers & the parallel team on this!

Olivia Koshy

14,952 просмотров • 5 месяцев назад

We're having a blast at Databricks Data + AI Summit! We're talking with builders about three easy ways to bring Nimble's live web search into Databricks: 1. Ask Genie to search the web and bring any data into any table 2. Call Nimble via SQL to enrich your tables 3. Build an end-to-end app on Databricks to monitor and visualize anything on the web
0:40

We're having a blast at Databricks Data + AI Summit! We're talking with builders about three easy ways to bring Nimble's live web search into Databricks: 1. Ask Genie to search the web and bring any data into any table 2. Call Nimble via SQL to enrich your tables 3. Build an end-to-end app on Databricks to monitor and visualize anything on the web

Nimble

62,226 просмотров • 4 месяцев назад

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.
1:20

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.

Parallel Web Systems

670,433 просмотров • 1 год назад

Added web search to Papers with Code's upcoming chat interface This runs on Hugging Face Inference Providers via Baseten (new DeepSeek-V4 Flash), using Exa's MCP server, running inside a Modal container Drop your HF username, and I'll add you, eager for feedback :)
0:24

Added web search to Papers with Code's upcoming chat interface This runs on Hugging Face Inference Providers via Baseten (new DeepSeek-V4 Flash), using Exa's MCP server, running inside a Modal container Drop your HF username, and I'll add you, eager for feedback :)

Niels Rogge

20,030 просмотров • 3 месяцев назад

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵
0:59

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵

Baseten

59,352 просмотров • 1 год назад

Nimble is now an OpenAI plugin for ChatGPT and Codex, giving OpenAI models deeper context from the web. With Nimble, ChatGPT and Codex can: - Discover more complete web context by combining web search with computer use to navigate and paginate websites, capturing data that doesn’t show up in search results - Improve web search efficiency with self-learning agents that optimize web retrieval methodology after every run - Govern web retrieval with source controls, confidence scores, and evidence for every data point Available now in the Plugins tab. Learn more here:
0:39

Nimble is now an OpenAI plugin for ChatGPT and Codex, giving OpenAI models deeper context from the web. With Nimble, ChatGPT and Codex can: - Discover more complete web context by combining web search with computer use to navigate and paginate websites, capturing data that doesn’t show up in search results - Improve web search efficiency with self-learning agents that optimize web retrieval methodology after every run - Govern web retrieval with source controls, confidence scores, and evidence for every data point Available now in the Plugins tab. Learn more here:

Nimble

99,796 просмотров • 1 месяц назад

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!
0:37

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!

Akshay 🚀

90,404 просмотров • 1 год назад

Introducing Parallel Search Turbo: the fastest and most affordable way to bring the web to your AI.
1:36

Introducing Parallel Search Turbo: the fastest and most affordable way to bring the web to your AI.

Parallel Web Systems

403,027 просмотров • 3 месяцев назад

Introducing Together Chat! Use DeepSeek R1 (hosted in North America) & other top open source models to do web search, coding, image generation, & image analysis. Available today for free!
1:19

Introducing Together Chat! Use DeepSeek R1 (hosted in North America) & other top open source models to do web search, coding, image generation, & image analysis. Available today for free!

Together AI

101,646 просмотров • 1 год назад

You can now officially use Exa web search inside Grok Build! Exa is the fastest and most accurate web search, built for agents.
0:25

You can now officially use Exa web search inside Grok Build! Exa is the fastest and most accurate web search, built for agents.

Exa

474,477 просмотров • 3 месяцев назад

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.
0:25

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,983 просмотров • 6 месяцев назад

We’re excited to share the beta release of our tool use API! Now developers can easily equip any LLM with hosted open-source tools for web search, web crawling, and maps data (+ more coming soon). Under the hood, it's powered by MCP — but that's just an implementation detail ↓
3:19

We’re excited to share the beta release of our tool use API! Now developers can easily equip any LLM with hosted open-source tools for web search, web crawling, and maps data (+ more coming soon). Under the hood, it's powered by MCP — but that's just an implementation detail ↓

OpenTools

126,620 просмотров • 1 год назад

- AI agent that lives on your web page - Animated React components - Deploy apps without managing infrastructure - Free animated/3D icons designer - Open-source context API to search, scrape
0:42

- AI agent that lives on your web page - Animated React components - Deploy apps without managing infrastructure - Free animated/3D icons designer - Open-source context API to search, scrape

Csaba Kissi

37,517 просмотров • 2 месяцев назад

🚀 Introducing Dynamic Intelligence for Replit Agent We're unlocking next-level problem solving with: 🧠 Extended Thinking ⚡️ High Power Model 🌐 Web Search Now the Agent thinks deeper, reasons better, and surfs the web to get you complete solutions. This allows Agent to solve challenging and open ended problems like—app performance optimizations, complex debugging, UI overhauls etc. Rolling out to all users starting today!
0:45

🚀 Introducing Dynamic Intelligence for Replit Agent We're unlocking next-level problem solving with: 🧠 Extended Thinking ⚡️ High Power Model 🌐 Web Search Now the Agent thinks deeper, reasons better, and surfs the web to get you complete solutions. This allows Agent to solve challenging and open ended problems like—app performance optimizations, complex debugging, UI overhauls etc. Rolling out to all users starting today!

Replit ⠕

111,754 просмотров • 1 год назад