dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat(api): add correlationID to Track Chat requests (#3668)

Browse source 
* Add CorrelationID to chat request

Signed-off-by: Siddharth More <siddimore@gmail.com>

* remove get_token_metrics

Signed-off-by: Siddharth More <siddimore@gmail.com>

* Add CorrelationID to proto

Signed-off-by: Siddharth More <siddimore@gmail.com>

* fix correlation method name

Signed-off-by: Siddharth More <siddimore@gmail.com>

* Update core/http/endpoints/openai/chat.go

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Siddharth More <siddimore@gmail.com>

* Update core/http/endpoints/openai/chat.go

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Siddharth More <siddimore@gmail.com>

---------

Signed-off-by: Siddharth More <siddimore@gmail.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
siddimore 2024-09-28 08:23:56 -07:00 • committed by GitHub
parent e94a50e9db
commit 50a3b54e34
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 36 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
backend/backend.proto
View file

@ -136,6 +136,7 @@ message PredictOptions {
repeated Message Messages = 44;
repeated string Videos = 45;
repeated string Audios = 46;
string CorrelationId = 47;
}
// The response message containing the result

14
backend/cpp/llama/grpc-server.cpp
View file

@ -2106,6 +2106,9 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, llama
data["ignore_eos"] = predict->ignoreeos();
data["embeddings"] = predict->embeddings();
// Add the correlationid to json data
data["correlation_id"] = predict->correlationid();
// for each image in the request, add the image data
//
for (int i = 0; i < predict->images_size(); i++) {
@ -2344,6 +2347,11 @@ public:
int32_t tokens_evaluated = result.result_json.value("tokens_evaluated", 0);
reply.set_prompt_tokens(tokens_evaluated);
// Log Request Correlation Id
LOG_VERBOSE("correlation:", {
{ "id", data["correlation_id"] }
});
// Send the reply
writer->Write(reply);
@ -2367,6 +2375,12 @@ public:
std::string completion_text;
task_result result = llama.queue_results.recv(task_id);
if (!result.error && result.stop) {
// Log Request Correlation Id
LOG_VERBOSE("correlation:", {
{ "id", data["correlation_id"] }
});
completion_text = result.result_json.value("content", "");
int32_t tokens_predicted = result.result_json.value("tokens_predicted", 0);
int32_t tokens_evaluated = result.result_json.value("tokens_evaluated", 0);