# Margdarshak

## Steps to Run

To run the project, use the following commands:

```sh
# Run the project
API_KEY=<openai api key> cargo run
```

## The project uses the following dependencies:

- `anyhow`: For error handling.
- `async-trait`: For async functions in traits.
- `bytes`: For working with byte buffers.
- `http-body-util`: For working with HTTP bodies.
- `hyper`: For HTTP server and client implementation.
- `tokio`: For asynchronous runtime.
- `tracing`: For application-level tracing and logging.

## Project Logic

The project is structured to handle HTTP requests and process them using a wizard model. Here is a brief overview of the logic:

1. **Initialization**: The `run` function initializes the `TargetRuntime` with HTTP, file system, and environment IO components. It then scrapes data from a specified URL and processes it into a query.

2. **Wizard Interaction**: A `Wizard` instance is created using the processed query and an API key from the environment. The wizard is used to ask questions and get responses.

3. **HTTP Server**: The `AppCtx` struct, which holds the `Wizard` instance and the scraped data, is passed to the HTTP server. The server listens for incoming requests.

4. **Request Handling**: When a request is received, the `handle_request` function processes the request body, creates a `Question` instance, and uses the wizard to get a response. The response is then sent back to the client.

This setup allows the project to dynamically process and respond to HTTP requests using the wizard model.