Files
moloapp/src/openai/core/chat_model.h
T

48 lines
1.4 KiB
C++

#pragma once
// OpenaiChatModel: llm::ChatModel over the OpenAI API in either dialect,
// the Responses API (default) or Chat Completions.
#include <functional>
#include <memory>
#include <string>
#include "llm/chat_types.h"
#include "openai/core/chat_completions.h"
#include "openai/core/responses.h"
#include "openai/core/wire/chat_wire.h"
namespace molo::openai::core {
enum class Dialect { kResponses, kChatCompletions };
struct ChatModelConfig {
Dialect dialect = Dialect::kResponses;
WireOptions wire;
};
class OpenaiChatModel : public llm::ChatModel {
public:
explicit OpenaiChatModel(std::shared_ptr<llm::ApiClient> client, ChatModelConfig config = {});
// OPENAI_API_KEY from llm::Config; not configured without it.
static std::shared_ptr<OpenaiChatModel> from_env(ChatModelConfig config = {});
std::string vendor() const override { return "openai"; }
llm::ChatResponse generate(const llm::ChatRequest& request) override;
void stream(const llm::ChatRequest& request,
const std::function<bool(const llm::ChatChunk&)>& on_chunk) override;
Dialect dialect() const { return config_.dialect; }
bool configured() const { return client_->configured(); }
private:
void check(const llm::ChatRequest& request) const;
std::shared_ptr<llm::ApiClient> client_;
ChatModelConfig config_;
ResponsesService responses_;
ChatCompletionsService chat_;
};
} // namespace molo::openai::core