You can read more details about the <a href="https://www.starlette.dev/requests/" class="external-link" target="_blank">`Request` object in the official Starlette documentation site</a>.

/// note | Technical Details

You could also use `from starlette.requests import Request`.

**FastAPI** provides it directly just as a convenience for you, the developer. But it comes directly from Starlette.

  private fun assertConnectionReused(vararg requests: Request?) {
    for (i in requests.indices) {
      val response = client.newCall(requests[i]!!).execute()
      response.body.string() // Discard the response body.
      assertThat(server.takeRequest().exchangeIndex).isEqualTo(i)
    }
  }

  private fun assertConnectionNotReused(vararg requests: Request?) {
    for (request in requests) {

[well-formed commit message]: https://google.github.io/eng-practices/review/developer/cl-descriptions.html

#### Merging pull requests ####

Due to Guava's nature as a subset of Google's internal codebase which is
automatically synced to the public GitHub repository, we are unable to merge
pull requests directly into the master branch. Instead, once a pull request is
ready for merging, we'll make the appropriate changes in the internal codebase

		"Total number of invalid requests", "type")

	apiRequestsWaitingTotalMD = NewGaugeMD(apiRequestsWaitingTotal,
		"Total number of requests in the waiting queue", "type")
	apiRequestsIncomingTotalMD = NewGaugeMD(apiRequestsIncomingTotal,
		"Total number of incoming requests", "type")

	apiRequestsInFlightTotalMD = NewGaugeMD(apiRequestsInFlightTotal,
		"Total number of requests currently in flight", "name", "type")

You can import it from `fastapi.requests`:

```python
from fastapi.requests import HTTPConnection
```

assignees: ''

---

## IMPORTANT NOTES

**Community Edition**: MinIO community edition is now source-only. Install via `go install github.com/minio/minio@latest`

**Feature Requests**: We are no longer accepting feature requests for the community edition. For feature requests and enterprise support, please subscribe to [MinIO Enterprise Support](https://min.io/pricing).

Die gleichen Modelle werden von den Requests gemeinsam genutzt, es handelt sich also nicht um ein Modell pro Request, pro Benutzer, oder ähnliches.

Stellen wir uns vor, dass das Laden des Modells **eine ganze Weile dauern** kann, da viele **Daten von der Festplatte** gelesen werden müssen. Sie möchten das also nicht für jeden Request tun.

	responses <-chan Response
	cancel    context.CancelCauseFunc

	// Requests sent to the server.
	// If the handler is defined with 0 incoming capacity this will be nil.
	// Channel *must* be closed to signal the end of the stream.
	// If the request context is canceled, the stream will no longer process requests.
	// Requests sent cannot be used any further by the called.
	Requests chan<- []byte

	muxID uint64
	ctx   context.Context
}

# Set to true to add reviewers to pull requests
addReviewers: false

# Set to true to add assignees to pull requests
addAssignees: author

# A number of assignees to add to the pull request
# Set to 0 to add all of the assignees.
# Uses numberOfReviewers if unset.

MinIO server allows to throttle incoming requests:

- limit the number of active requests allowed across the cluster
- limit the wait duration for each request in the queue

These values are enabled using server's configuration or environment variables.

## Examples

### Configuring connection limit