With this new API, we can translate a large book within 24 hours, 50% less cost. Hopefully. Possible another feature in MindMac 🤔

Let's see how to use OpenAI Batch API in 5 steps. 1⃣ Prepare batch file in JSONL format 2⃣ Upload the batch file 3⃣ Call batch API 4⃣ Get batch information 5⃣ Get output content 🧵for detailed commands. Kudos to the API clarifications from Jeff Harris Peter Welinder OpenAI Developers

Peter Yang ollama Mindmac works quite well and has some advance features

Ryan Shrout A cool app to try it out is MindMac. You can run ollama inference locally with RAG and import data for search from Google search API It basically runs everything locally and pings Google for the external data

Used ollama serving llama3 70b and Google's search index to ask an LLM a question and get a response with real time web results. Fully offline local LLM inference with web search on top. Wild times.

🥳 MindMac 1.9.13 is here! With Llama 3 on Groq, you won't believe how FAST it is. Get ready to turbocharge your productivity!

I highly recommend MindMac if you’re looking for an llm client. You can run local models, add your own api endpoint if the model isn’t hosted and us OpenAI embedding models to run files through other models. These guys killed it!

Love these words 💘. We truly appreciate all of our customers who consistently trust and bring us motivated moments like this. Just serve, and all will come.

GPT-4o - works with text, image (vision), and audio, and even has memory skill. It looks like it has a lot of potential. Can't wait to try!

Wow wow wow. GPT-4o, 2x faster is real 🙀. The new MindMac version is on the way 🥳.

🎉🔥 GPT-4o with vision and text capabilities is here – now 2x faster and 50% cheaper! Plus, it comes with advanced audio features (STT, TTS) and DeepSeek models. Discover all the new updates in MindMac v1.9.16 🚀

Looks like we won't have to switch models anymore! All in one 🙀. Let's make it happen in MindMac🤘🏼