diff --git a/pilot/server/llmserver.py b/pilot/server/llmserver.py index 763d0f81e..f92024385 100644 --- a/pilot/server/llmserver.py +++ b/pilot/server/llmserver.py @@ -101,7 +101,7 @@ def generate(prompt_request: PromptRequest): "stop": prompt_request.stop } - response = [] + response = [] output = generate_stream_gate(params) for rsp in output: # rsp = rsp.decode("utf-8") @@ -109,7 +109,7 @@ def generate(prompt_request: PromptRequest): print("[TEST: output]:", rsp_str) response.append(rsp_str) - return {"response": response} + return {"response": rsp_str} @app.post("/embedding")