dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-28 06:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

feat: move llama to a grpc

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-07-15 01:19:43 +02:00
parent b816009db0
commit 58f6aab637
13 changed files with 454 additions and 340 deletions
Download patch file Download diff file Expand all files Collapse all files

8
pkg/grpc/proto/llmserver.proto
View file

@ -12,6 +12,7 @@ service LLM {
rpc Predict(PredictOptions) returns (Reply) {}
rpc LoadModel(ModelOptions) returns (Result) {}
rpc PredictStream(PredictOptions) returns (stream Reply) {}
rpc Embedding(PredictOptions) returns (EmbeddingResult) {}
}
message HealthMessage {}
@ -41,7 +42,6 @@ message PredictOptions {
float MirostatTAU = 21;
bool PenalizeNL = 22;
string LogitBias = 23;
string PathPromptCache = 24;
bool MLock = 25;
bool MMap = 26;
bool PromptCacheAll = 27;
@ -52,6 +52,8 @@ message PredictOptions {
float TopP = 32;
string PromptCachePath = 33;
bool Debug = 34;
repeated int32 EmbeddingTokens = 35;
string Embeddings = 36;
}
// The response message containing the result
@ -79,4 +81,8 @@ message ModelOptions {
message Result {
string message = 1;
bool success = 2;
}
message EmbeddingResult {
repeated float embeddings = 1;
}