Community Hangout, July 2024: Local AI
Вставка
- Опубліковано 20 жов 2024
- This month we focused on our new support for locally run LLMs and how to set them up in three different ways. Community member Jim Le shows the power of the new HTTP Request Tool for agents, and how it can unlock external data for your AI workflows.
We're currently finishing the Local AI package and will add the link here soon.
As always, we started off with community and product updates, and we’ll wrap up with a round of questions and answers.
Chapters:
00:34 Agenda
01:48 Community Updates
08:47 Product Updates
18:43 Job Updates
19:34 Installing and using Local AI
50:02 Creating HTTP Tools
Links:
Sign up for future n8n Community Hangouts: n8n.io/communi...
Sign up for the n8n Community Newsletter: n8n.io/newslet...
Thank you, this is great!
Thanks Matt! Hope to see you at the next one :)
Excellent! Following the video, I deployed a Qwen2 1.5b on my VPS using Ollama and it is working like a champ but only using the sub-Ollama node. However, it is giving error when I use it with the OpenAI Chat sub-node by changing the base URL. Is there a reason while Ollama-based LLMs are not compatible with the OpenAI Chat sub-Node? Also, currently the more advanced AI nodes such as the AI Tool Agents nodes do not connect with Ollama chat sub-node. Can we have this in the next update please? @n8n
This is great! One thing we really need however, is streaming server side events, I can't build AI apps without it, so currently have to code my own cloud functions and trigger them with n8n, or use web sockets etc, would be great to do it all within n8n! Are you working on this? Buildship have it, we need it too!
That's an interesting question and our engineers have some questions about it. Could you please open a topic on our forum so we can discuss this more?
@@n8n-io I have raised in the forum.
Very interesting
Thanks! Glad to hear you enjoyed it.