mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 10:24:35 +00:00
server : allow to get default generation settings for completion (#5307)
This commit is contained in:
parent
e6f8177532
commit
a2d60c9158
@ -264,7 +264,21 @@ Notice that each `probs` is an array of length `n_probs`.
|
||||
|
||||
It also accepts all the options of `/completion` except `stream` and `prompt`.
|
||||
|
||||
- **GET** `/props`: Return the required assistant name and anti-prompt to generate the prompt in case you have specified a system prompt for all slots.
|
||||
- **GET** `/props`: Return current server settings.
|
||||
|
||||
### Result JSON
|
||||
|
||||
```json
|
||||
{
|
||||
"assistant_name": "",
|
||||
"user_name": "",
|
||||
"default_generation_settings": { ... }
|
||||
}
|
||||
```
|
||||
|
||||
- `assistant_name` - the required assistant name to generate the prompt in case you have specified a system prompt for all slots.
|
||||
- `user_name` - the required anti-prompt to generate the prompt in case you have specified a system prompt for all slots.
|
||||
- `default_generation_settings` - the default generation settings for the `/completion` endpoint, has the same fields as the `generation_settings` response object from the `/completion` endpoint.
|
||||
|
||||
- **POST** `/v1/chat/completions`: OpenAI-compatible Chat Completions API. Given a ChatML-formatted json description in `messages`, it returns the predicted completion. Both synchronous and streaming mode are supported, so scripted and interactive applications work fine. While no strong claims of compatibility with OpenAI API spec is being made, in our experience it suffices to support many apps. Only ChatML-tuned models, such as Dolphin, OpenOrca, OpenHermes, OpenChat-3.5, etc can be used with this endpoint. Compared to `api_like_OAI.py` this API implementation does not require a wrapper to be served.
|
||||
|
||||
|
@ -334,6 +334,7 @@ struct llama_server_context
|
||||
|
||||
// slots / clients
|
||||
std::vector<llama_client_slot> slots;
|
||||
json default_generation_settings_for_props;
|
||||
|
||||
llama_server_queue queue_tasks;
|
||||
llama_server_response queue_results;
|
||||
@ -430,6 +431,9 @@ struct llama_server_context
|
||||
slots.push_back(slot);
|
||||
}
|
||||
|
||||
default_generation_settings_for_props = get_formated_generation(slots.front());
|
||||
default_generation_settings_for_props["seed"] = -1;
|
||||
|
||||
batch = llama_batch_init(n_ctx, 0, params.n_parallel);
|
||||
|
||||
// empty system prompt
|
||||
@ -2614,7 +2618,8 @@ int main(int argc, char **argv)
|
||||
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
|
||||
json data = {
|
||||
{ "user_name", llama.name_user.c_str() },
|
||||
{ "assistant_name", llama.name_assistant.c_str() }
|
||||
{ "assistant_name", llama.name_assistant.c_str() },
|
||||
{ "default_generation_settings", llama.default_generation_settings_for_props }
|
||||
};
|
||||
res.set_content(data.dump(), "application/json; charset=utf-8");
|
||||
});
|
||||
|
Loading…
Reference in New Issue
Block a user