Treatment chat

ml/remote/llm::chat

Configuration

⬡ llm: ml/remote/llm::RemoteLlm

Inputs

⇥ prompt: Stream<string>

Outputs

↦ error: Stream<string>
↦ failed: Stream<void>
↦ response: Stream<string>

Send prompts to a remote LLM and receive complete responses.

For each string received on prompt, sends a single-turn chat request to the configured provider and emits the full response text on response. If the request fails, failed and error are emitted instead.

ℹ️ load is not required — the provider is initialised when the program starts. Use stream instead if you want token-by-token output.

graph LR
     T("chat()")
     P["🟩 🟩 …"] -->|prompt|   T
     T -->|response| R["🟩 🟩 …"]
     T -->|failed|   F["🟩 🟩 …"]
     T -->|error|    E["🟩 🟩 …"]

     style P fill:#ffff,stroke:#ffff
     style R fill:#ffff,stroke:#ffff
     style F fill:#ffff,stroke:#ffff
     style E fill:#ffff,stroke:#ffff

use ml/remote/llm::RemoteLlm
use ml/remote/llm::chat

treatment example()
  model llm: RemoteLlm(backend = "mistral", api_key = "...", model = "mistral-small-latest")
  input  prompt:   Stream<string>
  output response: Stream<string>
{
    chat[llm=llm]()
    Self.prompt -> chat.prompt,response -> Self.response
}