I have never forgotten that long intense drive home, in the summer, with no air conditioning, and playing Pink Floyd on full volume the whole way.

Because of this, "The Wall" has always been Floyd's second best album.

Dabarqus was created to address these issues with a stand-alone, all-in-one solution with no runtime dependencies. It's written in C++ and has built-in vector search, an industry-standard embedding model, and a REST API for easy development integration.

I made an example python chatbot that uses Dabarqus with Ollama, and put it in the Github repo.

I'd love your feedback – is anything missing? What would make Dabarqus more useful?

Thanks for checking this out. Looking forward to your thoughts.

Comments URL: https://news.ycombinator.com/item?id=41985890

Points: 3

# Comments: 1

I’m really excited to show off a project I’ve been tweaking and tuning for more than seven months.

One thing that drove me nuts about running LLMs locally was having to use terminals, install Python, and write code for the most basic things. I write software, but I don’t want to have to write it just to use a chatbot. So, I made Wingman with a friendly interface that lets you get started with zero coding or terminals required. It runs on MacOS and Windows, and even evaluates AI models up front to determine if they will run on your machine.

There’s other stuff it does, too, like let you save prompts, set system prompts per conversation, and change AI models mid-conversation. I added a way to sort models by popular or trending. It’s been pretty helpful to me for staying on top of all of the new models dropping.

But it still has a little way to go to be ready for really special things like planning and reasoning. So, I need to get some more feedback from people on different configurations. I’d love it if you checked it out, saw if it was useful, and maybe broke it so I could find fixes.

Thank!

I’m really excited to show off a project I’ve been tweaking and tuning for more than seven months.

One thing that drove me nuts about running LLMs locally was having to use terminals, install Python, and write code for the most basic things. I write software, but I don’t want to have to write it just to use a chatbot. So, I made Wingman with a friendly interface that lets you get started with zero coding or terminals required. It runs on MacOS and Windows, and even evaluates AI models up front to determine if they will run on your machine.

There’s other stuff it does, too, like let you save prompts, set system prompts per conversation, and change AI models mid-conversation. I added a way to sort models by popular or trending. It’s been pretty helpful to me for staying on top of all of the new models dropping.

But it still has a little way to go to be ready for really special things like planning and reasoning. So, I need to get some more feedback from people on different configurations. I’d love it if you checked it out, saw if it was useful, and maybe broke it so I could find fixes.

Thank!

Comments URL: https://news.ycombinator.com/item?id=39953318

Points: 13

# Comments: 2

Before the current weed era, weed was always compared favorably, by smokers, to alcohol with the adage: Weed is illegal, yet I've never seen a bar fight after everyone gets high.

Now we can do a real comparison of the effects of weed smoking on the general public, the same way we've done with drinking.

It’s a ridiculous headline, I know. But, that is the gist of this article. It just doesn’t say so. Pharmaceutical drugs, and the pharmaceutical industry is highly regulated. It is very expensive to comply with drug manufacturing and distribution regulations. Those regulatory expenses are so high that it is simply not profitable enough for any company to produce these cheap generic drugs at a sustainable profit. It doesn’t make sense for a pharmaceutical company to comply with all regulations and make a profit on inexpensive, generic drugs.

The real headline is “Generic Drugs are Over Regulated, Making Them too Expensive to Produce”

---

Sure, let's break down the problem:

1. Identify the topmost window: We can use the `winapi` crate in Rust to interact with the Windows API. The function `GetForegroundWindow` can be used to get a handle to the topmost window.

2. Check if the window is a Windows Explorer window: We can use the `GetClassNameW` function to get the class name of the window. If the window is a Windows Explorer window, the class name should be `CabinetWClass`.

3. Get the path of the active folder in the Windows Explorer window: This is a bit more complex. We can use the `SHGetPathFromIDListW` function from the Shell API to get the path from an item ID list. However, getting the item ID list for the active folder in a Windows Explorer window is not straightforward. We might need to use COM interfaces like `IShellWindows` to get the `IWebBrowserApp` for the window, and then use `IWebBrowserApp::LocationURL` to get the URL of the active folder.

4. Return the path as a string or a blank string: This is straightforward. We just need to convert the path to a string and return it, or return a blank string if the window is not a Windows Explorer window.

Here is a skeleton of the function in Rust:

  ```rust
  extern crate winapi;

  use std::ptr;
  use std::ffi::OsString;
  use std::os::windows::ffi::OsStringExt;
  use winapi::um::winuser::{GetForegroundWindow, 
  GetClassNameW};
  use winapi::um::shellapi::SHGetPathFromIDListW;
  use winapi::shared::minwindef::MAX_PATH;

  fn get_active_folder_path() -> String {
      // Get the topmost window
      let hwnd = unsafe { GetForegroundWindow() };

      // Get the class name of the window
      let mut class_name = vec![0u16; MAX_PATH + 1];
      unsafe {
          GetClassNameW(hwnd, class_name.as_mut_ptr(), class_name.len() as i32);
      }

    // Convert the class name to a string
    let class_name = OsString::from_wide(&class_name)
          .to_string_lossy()
          .into_owned();

      // Check if the window is a Windows Explorer window
      if class_name.starts_with("CabinetWClass") {
          // TODO: Get the item ID list for the active folder in the Windows Explorer window
          // TODO: Use SHGetPathFromIDListW to get the path from the item ID list
          // TODO: Convert the path to a string and return it
      }

      // If the window is not a Windows Explorer window, return a blank string
      "".to_string()
  }
  ```

---

ChatGPT is not really equipped to do this level of code design because there are too many steps for it to handle at once. It can handle your instructions if it could first write a detailed design spec, then write code and unit tests, then run them, read the compiler output, and iteratively make changes.

IOW, this would require a purpose-built solution which uses ChatGPT's underlying engine to take your list of requirements and turn them into built and tested code.