diff --git a/README.md b/README.md index 25ce24621..637ba3a3d 100644 --- a/README.md +++ b/README.md @@ -100,6 +100,17 @@ curl 127.0.0.1:8080/generate \ -H 'Content-Type: application/json' ``` +Embed: + +```shell +curl 127.0.0.1:8080/embed \ +-X POST \ +-d '{ +"inputs": "[INST] Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? [/INST]" +}' \ +-H 'Content-Type: application/json' +``` + Prompt a LoRA adapter: ```shell diff --git a/server/lorax_server/server.py b/server/lorax_server/server.py index aafab68a5..f98d7a9f8 100644 --- a/server/lorax_server/server.py +++ b/server/lorax_server/server.py @@ -96,6 +96,7 @@ async def Prefill(self, request: generate_pb2.PrefillRequest, context): ) async def Embed(self, request: generate_pb2.EmbedRequest, context): + print("!!! EMBED") if not self.model.supports_embeddings: raise ValueError("Model does not support embeddings")