Skip to content

server: maintain chat completion id for streaming responses #5988

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 3 commits into from
Mar 11, 2024
Merged

server: maintain chat completion id for streaming responses #5988

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7e72b99
server: maintain chat completion id for streaming responses
mscheong01 Mar 11, 2024
ade9b90
Update examples/server/utils.hpp
ggerganov Mar 11, 2024
fc7442a
Update examples/server/utils.hpp
ggerganov Mar 11, 2024
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
7 changes: 4 additions & 3 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3195,11 +3195,12 @@ int main(int argc, char ** argv) {
ctx_server.queue_results.add_waiting_task_id(id_task);
ctx_server.request_completion(id_task, -1, data, false, false);

const auto completion_id = gen_chatcmplid();
if (!json_value(data, "stream", false)) {
server_task_result result = ctx_server.queue_results.recv(id_task);

if (!result.error && result.stop) {
json result_oai = format_final_response_oaicompat(data, result.data);
json result_oai = format_final_response_oaicompat(data, result.data, completion_id);

res.set_content(result_oai.dump(-1, ' ', false, json::error_handler_t::replace), "application/json; charset=utf-8");
} else {
Expand All @@ -3208,11 +3209,11 @@ int main(int argc, char ** argv) {
}
ctx_server.queue_results.remove_waiting_task_id(id_task);
} else {
const auto chunked_content_provider = [id_task, &ctx_server](size_t, httplib::DataSink & sink) {
const auto chunked_content_provider = [id_task, &ctx_server, completion_id](size_t, httplib::DataSink & sink) {
while (true) {
server_task_result result = ctx_server.queue_results.recv(id_task);
if (!result.error) {
std::vector<json> result_array = format_partial_response_oaicompat(result.data);
std::vector<json> result_array = format_partial_response_oaicompat(result.data, completion_id);

for (auto it = result_array.begin(); it != result_array.end(); ++it) {
if (!it->empty()) {
Expand Down
12 changes: 6 additions & 6 deletions examples/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,7 +378,7 @@ static json oaicompat_completion_params_parse(
return llama_params;
}

static json format_final_response_oaicompat(const json & request, json result, bool streaming = false) {
static json format_final_response_oaicompat(const json & request, json result, const std::string & completion_id, bool streaming = false) {
bool stopped_word = result.count("stopped_word") != 0;
bool stopped_eos = json_value(result, "stopped_eos", false);
int num_tokens_predicted = json_value(result, "tokens_predicted", 0);
Expand Down Expand Up @@ -412,7 +412,7 @@ static json format_final_response_oaicompat(const json & request, json result, b
{"prompt_tokens", num_prompt_tokens},
{"total_tokens", num_tokens_predicted + num_prompt_tokens}
}},
{"id", gen_chatcmplid()}
{"id", completion_id}
};

if (server_verbose) {
Expand All @@ -427,7 +427,7 @@ static json format_final_response_oaicompat(const json & request, json result, b
}

// return value is vector as there is one case where we might need to generate two responses
static std::vector<json> format_partial_response_oaicompat(json result) {
static std::vector<json> format_partial_response_oaicompat(json result, const std::string & completion_id) {
if (!result.contains("model") || !result.contains("oaicompat_token_ctr")) {
return std::vector<json>({result});
}
Expand Down Expand Up @@ -471,7 +471,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
{"role", "assistant"}
}}}})},
{"created", t},
{"id", gen_chatcmplid()},
{"id", completion_id},
{"model", modelname},
{"object", "chat.completion.chunk"}};

Expand All @@ -482,7 +482,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
{"content", content}}}
}})},
{"created", t},
{"id", gen_chatcmplid()},
{"id", completion_id},
{"model", modelname},
{"object", "chat.completion.chunk"}};

Expand All @@ -509,7 +509,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
json ret = json {
{"choices", choices},
{"created", t},
{"id", gen_chatcmplid()},
{"id", completion_id},
{"model", modelname},
{"object", "chat.completion.chunk"}
};
Expand Down