abort gradio

app_gradio.py

@@ -1,45 +0,0 @@
-import gradio as gr
-from llama_cpp import Llama
-
-llm = Llama(model_path="./model.bin")
-
-with open('system.prompt', 'r', encoding='utf-8') as f:
-    prompt = f.read()
-
-title = "Openbuddy LLama Api"
-desc = '''<h1>Hello, world!</h1>
-This is showcase how to make own server with OpenBuddy's model.<br>
-I'm using here 3b model just for example. Also here's only CPU power.<br>
-But you can use GPU power as well!<br><br>
-<h1>How to GPU?</h1>
-Change <code>`CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS`</code> in Dockerfile on <code>`CMAKE_ARGS="-DLLAMA_CUBLAS=on"`</code>. Also you can try <code>`DLLAMA_CLBLAST`</code>, <code>`DLLAMA_METAL`</code> or <code>`DLLAMA_METAL`</code>.<br>
-Powered by <a href="https://github.com/abetlen/llama-cpp-python">llama-cpp-python</a> and <a href="https://www.gradio.app/">Gradio</a>.<br><br>
-<h1>How to test it on own machine?</h1>
-You can install Docker, build image and run it. I made <code>`run-docker.sh`</code> for ya. To stop container run <code>`docker ps`</code>, find name of container and run <code>`docker stop _dockerContainerName_`</code><br>
-Or you can once follow steps in Dockerfile and try it on your machine, not in Docker.<br><br>
-Also it can run with quart+uvicorn! Check the repo!'''
-
-def greet(request: str, max_tokens: int = 64, override_system_prompt: str = ""):
-    try:
-        system_prompt = override_system_prompt if override_system_prompt != "" else prompt
-        max_tokens = max_tokens if max_tokens > 0 and max_tokens < 256 else 64
-        userPrompt = system_prompt + "\n\nUser: " + request + "\nAssistant: "
-    except: return "ERROR 400: Not enough data"
-    try:
-        output = llm(userPrompt, max_tokens=max_tokens, stop=["User:", "\n"], echo=False)
-        print(output)
-        return output["choices"][0]["text"]
-    except Exception as e:
-        print(e)
-        return "ERROR 500: Server error. Check logs!!"
-
-demo = gr.Interface(
-    fn=greet,
-    inputs=[gr.Text("Hello, how are you?"), gr.Number(64), gr.Textbox()],
-    outputs=["text"],
-    description=desc,
-    title=title,
-    allow_flagging="never"
-).queue()
-if __name__ == "__main__":
-    demo.launch()

requirements.txt

@@ -1,3 +1,2 @@
 quart
-uvicorn
-gradio
+uvicorn