MagickML

569 posts

MagickML banner
MagickML

MagickML

@MagickML

Cutting edge tools for AI creators | Join our waitlist @ https://t.co/koVD9SXRaz Discord: https://t.co/nVT5y6g3Cc

Katılım Aralık 2022
355 Takip Edilen1.4K Takipçiler
MagickML
MagickML@MagickML·
We have been quiet for a while. We have been heads down building something new. We are building an Agent framework, with our Magick IDE fully open sourced at the core of it. We invite you to join in and let us know what would be most useful! github.com/Oneirocom/Magi…
English
12
2
16
4.4K
MagickML
MagickML@MagickML·
@TheSkinx Always open to requests for new integrations!
English
0
0
0
112
Skinx
Skinx@TheSkinx·
@MagickML If you need any integration ideas, hit me up, I've got a few hehe
English
1
0
0
140
MagickML
MagickML@MagickML·
@TheSkinx So glad the work is paying off. And we have a lot more on the roadmap too!
English
1
0
1
90
Skinx
Skinx@TheSkinx·
@MagickML V2 is great Good job to all the devs who did not count the hours and gave it all
English
1
0
1
120
metamike
metamike@itsmetamike·
Earlier today @MindBranches posted a MindBranch that summarized @OpenAI's Prompt Engineering guide from their website. I've created PromptReviser using @MagickML that uses these guidelines to revise an input prompt. Test it out or remix it to use in your own workflows. 🔗👇
metamike tweet media
English
6
6
12
4.5K
MagickML
MagickML@MagickML·
We have been excited about this for a long time, and we finally have them back in V2. Sub-spells. Vastly improved and better than ever. In this case, we brought in the amazing design pattern created by @unity with the subgraphs in visual scripting.
Parzival - ∞/89@whyarethis

We have sub-spells. Nested graphs are coming to Magick. The next step will be sub-spells as tools. The socket inputs and outputs on the sub-spell are given descriptions, and we can transform them into tool schemas. Then we parse and call the sub-spell, returning the result. This is going to open up all kinds of possibilities.

English
0
2
8
3.1K
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
We have sub-spells. Nested graphs are coming to Magick. The next step will be sub-spells as tools. The socket inputs and outputs on the sub-spell are given descriptions, and we can transform them into tool schemas. Then we parse and call the sub-spell, returning the result. This is going to open up all kinds of possibilities.
English
0
2
8
4.7K
MagickML
MagickML@MagickML·
New feature incoming. Variable events. Handle side effects and other processes when a variable changes. And until we get custom events in, it does basically the same thing.
MagickML tweet media
English
3
1
4
966
MagickML
MagickML@MagickML·
We just pushed out a major update to Magick. We integrated @keywordsai as our LLM proxy, providing our users with over a hundred models to use. We have improved stability for large graphs, with UI performance working at well over 300 nodes. We will be announcing more very soon.
English
1
3
11
1.3K
MagickML retweetledi
Jim Fan
Jim Fan@DrJimFan·
OpenAI is expected to demo a real-time voice assistant tomorrow. What does it take to deliver an immersive, or even magical experience? Almost all voice AI go through 3 stages: 1. Speech recognition or "ASR": audio -> text1, think Whisper; 2. LLM that plans what to say next: text1 -> text2; 3. Speech synthesis or "TTS": text2 -> audio, think ElevenLabs or VALL-E. Last year, I made the figure below to show how to make Siri/Alexa 10x better. However, naively going through 3 stages results in huge latency. User experience falls off the cliff if we have to wait 5 seconds for *each* reply. It breaks the immersion and feels lifeless even if the synthesized audio itself sounds real. Natural dialogues fundamentally don't work like this. We humans > think about what to say next at the same time as we listen & speak; > inject "yes, hmm, huh" at appropriate moments; > predict when the other person finishes and immediately take over; > decide to talk over the other person organically, without being offensive; > handle interruptions gracefully. Currently, AI assistants either cannot be interrupted (super frustrating) or simply stop when they detect an audio event and lose train of thought; > engage in group chat. We are so good at multi-agent conversations. It's not as simple as making each of the 3 neural nets faster, sequentially. Solving real-time dialogue requires us to rethink the whole stack, overlap each component as much as possible, and learn how to make interventions in real time. Or perhaps even better - just have 1 NN mapping audio to audio. End-to-end always wins. I'll sketch out how to design such a model and its training pipeline. Meanwhile, let's wait and see how far OpenAI pushes it!
Jim Fan tweet media
English
128
518
3.2K
727.9K
MagickML retweetledi
LlamaIndex 🦙
LlamaIndex 🦙@llama_index·
Check out our brand-new course on Building Agentic RAG with LlamaIndex with @DeepLearningAI + @AndrewYNg 🔥 Learn how to build an autonomous research assistant that can answer complex questions over multiple documents - handle a much broader range of inputs than a standard RAG pipeline! 📖🕵️ The course helps you learn how to build an agent ingredient by ingredient from a standard RAG pipeline. Once you're done with the course check out the following @llama_index resources to take your agents to the next level 👇 Building a custom agent: docs.llamaindex.ai/en/stable/exam… Multi-document agents (diagram by @clusteredbytes): docs.llamaindex.ai/en/stable/exam… Course: deeplearning.ai/short-courses/…
LlamaIndex 🦙 tweet media
Andrew Ng@AndrewYNg

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by @jerryjliu0, CEO of @llama_index. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here! deeplearning.ai/short-courses/…

English
5
79
419
48.3K
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
Another small UX improvement. Hiding unused sockets. It isn't a full node collapse, which I want to do next, but that will have to wait. In demo crunch time.
English
0
1
3
640
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
I love adding these little UX improvements that make my experience building way better. Renaming a nodes title goes a long way to legibility. Even more so possibly than comments.
English
0
1
4
452
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
Getting closer...
Parzival - ∞/89 tweet media
English
1
1
5
537
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
I have just decided that I love multi-gates. I find this incredibly satisfying. Using this in the demo I am working on, and will have to document this.
English
0
1
5
423
MagickML retweetledi
Parzival - ∞/89
Parzival - ∞/89@whyarethis·
Even more satisfying.
English
0
2
3
369
MagickML retweetledi
Skinx
Skinx@TheSkinx·
let me cook @MagickML
Skinx tweet media
English
1
1
4
430
MagickML
MagickML@MagickML·
Can’t wait to get this into Magick.
English
0
0
5
529