|
pulsatrix 1.1.0
|
Settings for an OpenAI-compatible chat-completions server (llama-server, vLLM, Ollama). More...
#include <provider.hpp>

Public Attributes | |
| std::string | base_url = "http://127.0.0.1:8080/v1" |
The URL before /chat/completions, for example llama-server's http://127.0.0.1:8080/v1 or Ollama's http://127.0.0.1:11434/v1. | |
| std::optional< Secret > | api_key |
Sent as Authorization: Bearer, if the server needs one. | |
| RetryPolicy | retry |
| std::chrono::milliseconds | read_timeout {600'000} |
Settings for an OpenAI-compatible chat-completions server (llama-server, vLLM, Ollama).
| std::optional<Secret> pulsatrix::orch::OpenAiCompatibleOptions::api_key |
Sent as Authorization: Bearer, if the server needs one.
| std::string pulsatrix::orch::OpenAiCompatibleOptions::base_url = "http://127.0.0.1:8080/v1" |
The URL before /chat/completions, for example llama-server's http://127.0.0.1:8080/v1 or Ollama's http://127.0.0.1:11434/v1.
| std::chrono::milliseconds pulsatrix::orch::OpenAiCompatibleOptions::read_timeout {600'000} |
| RetryPolicy pulsatrix::orch::OpenAiCompatibleOptions::retry |