mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-14 16:35:55 +02:00
Xuan-Son Nguyen
c92e806d1c
* init stream * add stream for shell tool * add test * nits * update docs
42 lines
977 B
C++
42 lines
977 B
C++
#pragma once
|
|
|
|
#include "server-common.h"
|
|
#include "server-http.h"
|
|
#include "server-queue.h"
|
|
|
|
#include <atomic>
|
|
#include <functional>
|
|
|
|
struct server_tool {
|
|
std::string name;
|
|
std::string display_name;
|
|
bool permission_write = false;
|
|
bool support_stream = false; // if true, output can be streamed
|
|
|
|
virtual ~server_tool() = default;
|
|
virtual json get_definition() const = 0;
|
|
|
|
struct stream {
|
|
server_response & qr;
|
|
int id;
|
|
std::function<bool()> alive;
|
|
void push(const std::string & chunk);
|
|
};
|
|
virtual json invoke(json params, stream * st = nullptr) const = 0;
|
|
|
|
json to_json() const;
|
|
};
|
|
|
|
struct server_tools {
|
|
std::vector<std::unique_ptr<server_tool>> tools;
|
|
|
|
// for streaming
|
|
server_response queue_res;
|
|
std::atomic<int> res_id{0};
|
|
|
|
void setup(const std::vector<std::string> & enabled_tools);
|
|
|
|
server_http_context::handler_t handle_get;
|
|
server_http_context::handler_t handle_post;
|
|
};
|