Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 5, 2024
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion examples/server/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.

Expand Down
7 changes: 6 additions & 1 deletion examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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");
});
Expand Down