root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

server : allow to get default generation settings for completion (#5307)

Browse Source
This commit is contained in:
Alexey Parfenov 2024-02-05 08:10:22 +00:00 committed by GitHub
parent e6f8177532
commit a2d60c9158
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 21 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
examples/server/README.md
View File

@ -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.

7
examples/server/server.cpp
View File

@ -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");
});