Feed aggregator

Ask HN: How do you optimize Google search for good long-form technical content?

Hacker News - Sun, 04/21/2024 - 10:13pm

These days I don't quite like the search results(especially website that rhymes with Radium) ridden with basic to-do list tutorials or full of generic chatGPT text dump. All fluff, no insights.

Please share your tips/tricks/collection to optimize search results for good long-form technical articles.

Fwiw I follow company blogs(Eg: AWS well architected, Netflix, Stickfix, Shopify etc) and find that to be much better value for time spent.

Comments URL: https://news.ycombinator.com/item?id=40110932

Points: 1

# Comments: 2

Categories: Hacker News

Show HN: Open-source multi-modal LLM chat agent

Hacker News - Sun, 04/21/2024 - 9:48pm

Hi everyone,

I’m learning LLM and AI. And I’m building a multi-modal full stack LLM chat agent. [0]

Using semantic-router for dynamic conversation routing, and LiteLMM for model providers.

It was lots of fun to learn and build.

Here is the full list of large language models. I will update more models in the future. [1]

And, of course you can use Llama 3 via Ollama locally!

I will be adding function calling support (tools use) for the models to have it more capable, like an agent, in the future.

Hope this project helps everyone to try out using multi-modalities LLM providers agent!

[0] GitHub: https://github.com/vinhnx/VT.ai [1] List of LLM models currently supported: https://github.com/vinhnx/VT.ai/blob/main/src/vtai/llms_conf...

Comments URL: https://news.ycombinator.com/item?id=40110828

Points: 1

# Comments: 0

Categories: Hacker News

Pages