🚀You can now build AI Web Agents that outperform Gemini and ChatGPT in information retrieval and share them with your community in less than 10 lines of code!
🌊LaVague (
github.com/lavague-ai/LaVagu…), our Large Action Model (
#LAM) framework, now makes it easy to share your agents by building a Gradio demo with a simple ‘agent.demo()’!
📖You can find a Colab to run an AI Agent specialized in retrieving the latest papers on Hugging Face.
Colab:
colab.research.google.com/gi…
Docs:
docs.lavague.ai/en/latest/do…
What are the results? Well, we put it to the test by asking different proprietary Conversational AI the question:
“What is the most trendy recent paper on text to video on
@huggingface papers? Provide the date and a summary of the paper”, our Agent beats them all!
❌Gemini: found a paper from 2023
❌OpenAI: found a paper from 2023
✅LaVague: found the latest paper !
Amazing to see how leveraging LAMs enable to solve decades-old problems that not even Google has cracked: information retrieval on public data!
But this is only the beginning: LaVague also makes it possible to create Agents that have access to your private data, for instance in your SaaS tools like Notion, Salesforce, and so on.
We hope this new demo feature will help builders share their work and democratize
#Agents further!
If you want to learn more about Large Action Models, don’t hesitate to check our webinar on how to design and improve Large Action Models using LLMs on the 13th of June at 9 am PST!
Webinar:
lu.ma/v2mr2ynn
You can also join our Discord (
discord.gg/SDxn9KpqX9 to chat with us, to ask questions or contribute to our open-source project (
docs.lavague.ai/en/latest/do…)