Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Function call for Groq 😎 Hey Groq Inc I've developed a proxy server enabling function calls for Groq cloud, couldn't wait for you guys :D, and it has OpenAI interface compatibility. It works seamlessly with libraries like LlamaIndex, LangChain, and my favorite, PhiData. Check out this demo video to...

unclecode's profile picture

Unclecode (Hossein)

2,426 subscribers

40,917 görüntüleme • 2 yıl önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

Woke up and was like "what!!!" seeing the community reactions and interest for the first time 😂 Super glad people are into it. So, I'm gonna jump to release the first version by this week! But after that, I need the community to step in and contribute cuz I can't do it alone 😅 Maybe we'll turn it into a function call proxy for all open source models running locally (ollama) and on GroqCloud. Thx @GroqInc for your active engagement. I will try to create a post and explain my approach for this proxy server.

Gavin profil fotoğrafı
Gavin2 yıl önce

@GroqInc Awesome 👏. We’re working on function calling but greatly appreciate community contributions in the area!

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

@GroqInc You're welcome! What Groq does is like bringing electricity everywhere, and in 2024, AI is the electricity. Can't wait for native support, especially for fine-tuning and uploading user's custom models.

Jawa profil fotoğrafı
Jawa2 yıl önce

@GroqInc This is so cool. We’re really excited about bringing y’all more features. Love seeing the community as excited as we are!

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

@GroqInc How could it not be, when you're processing 500+ tokens per second in such a deterministic way!! It's like being on steroids! Anyway feel good to contribute here and love being part of speeding up AI.

Jonathan profil fotoğrafı
Jonathan2 yıl önce

@GroqInc This is a huge unlock for agents. You could execute multiple function call trajectories and pick the best one, all without waiting a lifetime.

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

@GroqInc Exactly! Imagine running multiple pipelines all in parallel. You could have a simulated world with tons of agents collaborating at speeds of 500-1000 tokens per second 🤩

Alex Volkov (Thursd/AI) profil fotoğrafı
Alex Volkov (Thursd/AI)2 yıl önce

@GroqInc Dope will cover this in this weeks #ThursdAI

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

@GroqInc Appreciate that! Planning to release the first baby version by this week. I'll make a short video to explain the code and ask the community to join and help improve it.

Unclecode (Hossein) profil fotoğrafı
Unclecode (Hossein)2 yıl önce

Function Call Proxy Update, Stardate 47457.1! (Guess when is this reference 😉) Hey community & @GroqInc, making progress on the function call. Might release the server early for everyone to test while I polish the code & prep the repo. Oh, and yeah, showing off my monitor 😁

Benzer Videolar

So how good is gpt-oss at function calling for real use cases and how to implement it correctly on Groq? Meet Autosheet: a GroqLabs project to showcase gpt-oss models running on Groq Inc! It's a browser spreadsheet driven by AI with built-in MCP server support. A video & 🧵
5:58

So how good is gpt-oss at function calling for real use cases and how to implement it correctly on Groq? Meet Autosheet: a GroqLabs project to showcase gpt-oss models running on Groq Inc! It's a browser spreadsheet driven by AI with built-in MCP server support. A video & 🧵

Rick Lamers

26,321 görüntüleme • 9 ay önce

Llama 4 voice agent starter kit with Groq Inc and Pipecat AI ➡️ Groq STT (distil-whisper-large-v3) ➡️ Groq Llama 4 (llama-4-scout-17b-16e-instruct) ➡️ Groq TTS (playai-tts) ➡️ Function calling ➡️ Deploy to Pipecat Cloud for production ➡️ Optionally add a twilio phone number for telephone voice AI
1:48

Llama 4 voice agent starter kit with Groq Inc and Pipecat AI ➡️ Groq STT (distil-whisper-large-v3) ➡️ Groq Llama 4 (llama-4-scout-17b-16e-instruct) ➡️ Groq TTS (playai-tts) ➡️ Function calling ➡️ Deploy to Pipecat Cloud for production ➡️ Optionally add a twilio phone number for telephone voice AI

kwindla

58,649 görüntüleme • 1 yıl önce

I finally got my hands to Fixkey and added Groq Inc support there and damn its fast it translated 5k characters (600 words) to german from english in < 2 seconds thats crazy comment if you want beta | free for everyone while groq API is free :)
1:35

I finally got my hands to Fixkey and added Groq Inc support there and damn its fast it translated 5k characters (600 words) to german from english in < 2 seconds thats crazy comment if you want beta | free for everyone while groq API is free :)

Robert Lukoszko

14,178 görüntüleme • 2 yıl önce

Stagehand is getting really fast ... See how Llama 3 70b on Groq Inc outperforms OpenAI 4o in speed on this form fill 54.48 seconds for groq VS 62.75 for 4o🤯
0:57

Stagehand is getting really fast ... See how Llama 3 70b on Groq Inc outperforms OpenAI 4o in speed on this form fill 54.48 seconds for groq VS 62.75 for 4o🤯

Kyle Jeong

26,095 görüntüleme • 1 yıl önce

Groq is the world's fastest LLM (Large Language Model). Faster than ChatGPT, Claude, and Google Gemini. And you can use it for free! Here's Groq answering a megaprompt of 300+ words instantly. In less than a second, it created a preliminary outline for a journal article and a writing schedule. It's unbelievable!
0:34

Groq is the world's fastest LLM (Large Language Model). Faster than ChatGPT, Claude, and Google Gemini. And you can use it for free! Here's Groq answering a megaprompt of 300+ words instantly. In less than a second, it created a preliminary outline for a journal article and a writing schedule. It's unbelievable!

Mushtaq Bilal, PhD

162,550 görüntüleme • 2 yıl önce

PSA: OpenAI is putting the Open back in OpenAI and Groq Inc has Day 0 support. 🤗 GPT-OSS 20B and 120B, hybrid-reasoning models with built-in browser search and code execution are now live for instant inference. P.S. We've also launched OpenAI Responses API compatibility.
0:29

PSA: OpenAI is putting the Open back in OpenAI and Groq Inc has Day 0 support. 🤗 GPT-OSS 20B and 120B, hybrid-reasoning models with built-in browser search and code execution are now live for instant inference. P.S. We've also launched OpenAI Responses API compatibility.

Hatice Ozen

80,584 görüntüleme • 10 ay önce

Apple Intelligence looks amazing, but we can’t try it until later this year. So I created an iPhone shortcut that uses Llama 3 with Groq completely for free, and check out how fast it is 🤯 Full video tutorial in the comments.
0:22

Apple Intelligence looks amazing, but we can’t try it until later this year. So I created an iPhone shortcut that uses Llama 3 with Groq completely for free, and check out how fast it is 🤯 Full video tutorial in the comments.

Alvaro Cintas

29,902 görüntüleme • 2 yıl önce

Very few people have built successful chips for AI, and Jonathan Ross has done it twice, first with the Google TPU and then again with the Groq Inc LPU.
2:56

Very few people have built successful chips for AI, and Jonathan Ross has done it twice, first with the Google TPU and then again with the Groq Inc LPU.

sunny madra

504,798 görüntüleme • 7 ay önce

PSA: Qwen's Qwen-2.5-Coder-32B-Instruct is now live on Groq Inc for insanely fast (and smart) code generation. See below for instructions to add to Cursor.
1:27

PSA: Qwen's Qwen-2.5-Coder-32B-Instruct is now live on Groq Inc for insanely fast (and smart) code generation. See below for instructions to add to Cursor.

Hatice Ozen

36,643 görüntüleme • 1 yıl önce

introducing gen an experimental llm as a server that serves freshly generated html for any endpoint its fun to explore and stumbling upon something that never existed before you clicked is kinda amazing uses gpt-oss with groq (thanks groq and sama &lt;3)
0:22

introducing gen an experimental llm as a server that serves freshly generated html for any endpoint its fun to explore and stumbling upon something that never existed before you clicked is kinda amazing uses gpt-oss with groq (thanks groq and sama &lt;3)

soham

29,281 görüntüleme • 9 ay önce

Introducing `gut` - an AI agent for git 🤖🧑‍💻 This is a really neat CLI-based tool from Clelia Bertelli that lets you ask about and execute git commands through natural language! Describe what you want to do in English (e.g. a complex rebase), and it’ll let you review and auto-execute each command while explaining what it does. It’s a neat, minimal helper tool for anyone ramping up on version control tools like git + GitHub. Powered by LlamaIndex 🦙 workflows and Groq Inc To use it: `pip install gut-ai` Repo:
5:33

Introducing `gut` - an AI agent for git 🤖🧑‍💻 This is a really neat CLI-based tool from Clelia Bertelli that lets you ask about and execute git commands through natural language! Describe what you want to do in English (e.g. a complex rebase), and it’ll let you review and auto-execute each command while explaining what it does. It’s a neat, minimal helper tool for anyone ramping up on version control tools like git + GitHub. Powered by LlamaIndex 🦙 workflows and Groq Inc To use it: `pip install gut-ai` Repo:

Jerry Liu

17,065 görüntüleme • 11 ay önce

Llama 4 supports 12 different languages out of the box, making it a powerful brain for your voice agents! Running on Groq Inc Cloud and integrated with ElevenLabs Developers Conversational AI, it creates a fantastic multilingual agent setup. Give it a try below! 👇
1:21

Llama 4 supports 12 different languages out of the box, making it a powerful brain for your voice agents! Running on Groq Inc Cloud and integrated with ElevenLabs Developers Conversational AI, it creates a fantastic multilingual agent setup. Give it a try below! 👇

Thor 雷神 ⚡️

18,160 görüntüleme • 1 yıl önce

Kimi K2 + Groq Inc is performing browser operation for me twice as fast as OpenAI GPT 4.1 This isn't available right now, just internal R&amp;D for iterate
1:43

Kimi K2 + Groq Inc is performing browser operation for me twice as fast as OpenAI GPT 4.1 This isn't available right now, just internal R&amp;D for iterate

Andrew Jefferson

30,898 görüntüleme • 11 ay önce

What if ChatGPT had access to your GitHub repo? 🤔 I've been working on this for a while now, and today I hooked it up with a ChatGPT plugin:
0:43

What if ChatGPT had access to your GitHub repo? 🤔 I've been working on this for a while now, and today I hooked it up with a ChatGPT plugin:

YK aka CS Dojo 📺🐦

181,421 görüntüleme • 3 yıl önce

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!
2:15

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 görüntüleme • 4 ay önce

This is why Nvidia bought Groq. If Groq deploys a ton of low-cost inference chips, demand for training will increase massively. The more inference you have, the more training you need, and vice versa. Nvidia can keep its high margins selling chips for training forever.
0:35

This is why Nvidia bought Groq. If Groq deploys a ton of low-cost inference chips, demand for training will increase massively. The more inference you have, the more training you need, and vice versa. Nvidia can keep its high margins selling chips for training forever.

Lin

92,571 görüntüleme • 5 ay önce

Helpful information for you #smokers out there. I know this works, I've used it myself.
1:16

Helpful information for you #smokers out there. I know this works, I've used it myself.

Linda

142,102 görüntüleme • 4 ay önce

More than a year ago, I created this expense tracker app for myself, and recently I decided to launch this app for public release. I've therefore been working on this app for the past month to improve and add minor animation touches, for more 👇 The app is totally free, so go ahead and try it. Please let me know if you run into any issues.
0:44

More than a year ago, I created this expense tracker app for myself, and recently I decided to launch this app for public release. I've therefore been working on this app for the past month to improve and add minor animation touches, for more 👇 The app is totally free, so go ahead and try it. Please let me know if you run into any issues.

Kavsoft

49,717 görüntüleme • 1 yıl önce

HUGE PSA: Meta's Llama 4 Scout (17Bx16E MoE) is now live on Groq Inc for all users via console playground and Groq API. This conversational beast with native multimodality just dropped today and we're excited to offer Day 0 support so you can build fast.
0:54

HUGE PSA: Meta's Llama 4 Scout (17Bx16E MoE) is now live on Groq Inc for all users via console playground and Groq API. This conversational beast with native multimodality just dropped today and we're excited to offer Day 0 support so you can build fast.

Hatice Ozen

15,221 görüntüleme • 1 yıl önce