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

56 lines
1.9 KiB
C++

#include "openai/core/chat_model.h"
#include "openai/core/check.h"
#include "openai/core/client.h"
namespace molo::openai::core {
OpenaiChatModel::OpenaiChatModel(std::shared_ptr<llm::ApiClient> client, ChatModelConfig config)
: client_(client), config_(std::move(config)), responses_(client), chat_(client) {}
std::shared_ptr<OpenaiChatModel> OpenaiChatModel::from_env(ChatModelConfig config) {
return std::make_shared<OpenaiChatModel>(OpenaiClient::from_env(), std::move(config));
}
void OpenaiChatModel::check(const llm::ChatRequest& request) const {
Check::non_empty("model", request.model);
Check::require(!request.messages.empty(), "messages is required");
}
llm::ChatResponse OpenaiChatModel::generate(const llm::ChatRequest& request) {
check(request);
if (config_.dialect == Dialect::kResponses) {
ResponseRequest r = ResponsesWire::request(request, config_.wire);
return ResponsesWire::response(responses_.create(r));
}
ChatCompletionRequest r = ChatWire::request(request, config_.wire);
return ChatWire::response(chat_.create(r));
}
void OpenaiChatModel::stream(const llm::ChatRequest& request,
const std::function<bool(const llm::ChatChunk&)>& on_chunk) {
check(request);
if (config_.dialect == Dialect::kResponses) {
ResponseRequest r = ResponsesWire::request(request, config_.wire);
ResponsesChunkDecoder decoder;
responses_.stream(r, [&](const ResponseEvent& e) {
llm::ChatChunk chunk;
if (!decoder.decode(e, chunk)) return true;
return on_chunk(chunk);
});
return;
}
ChatCompletionRequest r = ChatWire::request(request, config_.wire);
r.include_usage = true;
ChatChunkDecoder decoder;
chat_.stream(r, [&](const clients::body::Json& doc) {
std::vector<llm::ChatChunk> chunks;
decoder.decode(doc, chunks);
for (const llm::ChatChunk& c : chunks)
if (!on_chunk(c)) return false;
return true;
});
}
} // namespace molo::openai::core