> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server. # Struct Relay Host Runtime Client > API documentation for the Rust `RelayHostRuntimeClient` struct in crate `nemo_relay_worker_proto`. Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker`. ```rust pub struct RelayHostRuntimeClient { /* private fields */ } ``` ## Implementations ### `impl RelayHostRuntimeClient`


#### `connect`


Attempt to create a new client by connecting to a given endpoint.

### `impl RelayHostRuntimeClientwhere T: GrpcService, T::Error: Into, T::ResponseBody: Body + Send + 'static, ::Error: Into + Send,`


#### `new`


#### `with_origin`


#### `with_interceptor`


#### `send_compressed`


Compress requests with the given encoding.

This requires the server to support it otherwise it might respond with an error.

#### `accept_compressed`


Enable decompressing responses.

#### `max_decoding_message_size`


Limits the maximum size of a decoded message.

Default: `4MB`

#### `max_encoding_message_size`


Limits the maximum size of an encoded message.

Default: `usize::MAX`

#### `emit_mark`


#### `push_scope`


#### `pop_scope`


#### `create_scope_stack`


#### `drop_scope_stack`


#### `tool_next`


#### `llm_next`


#### `llm_stream_next`


## Trait Implementations

### `impl Clone for RelayHostRuntimeClient`


#### `clone`


#### `clone_from`


### `impl Debug for RelayHostRuntimeClient`


#### `fmt`