Update main.py

main.py

@@ -1,61 +1,10 @@
-from fastapi import FastAPI
+from flask import Flask
+from langchain_community.llms import Ollama
 
-from langchain_community.llms import LlamaCpp
-from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
-from langchain_core.prompts import PromptTemplate
+app = Flask(__name__)
 
-from langserve import add_routes
-from fastapi.middleware.cors import CORSMiddleware
+llm = Ollama(model="phi3")
 
-app = FastAPI(
-    title="LangChain Server",
-    version="1.0",
-    description="A simple api server using Langchain's Runnable interfaces",
-)
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=['*'],
-    allow_methods=['*'],
-    allow_headers=['*'],
-    allow_credentials=True
-)
-
-
-template = """Give a very concise one word answer to question.
-Question: {question}
-Answer:
-"""
-
-prompt = PromptTemplate.from_template(template)
-
-# Callbacks support token-wise streaming
-callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
-
-n_gpu_layers = -1  # The number of layers to put on the GPU. The rest will be on the CPU. If you don't know how many layers there are, you can use -1 to move all to GPU.
-n_batch = 512  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
-
-# Make sure the model path is correct for your system!
-llm = LlamaCpp(
-    model_path="Phi-3-mini-4k-instruct-q4.gguf",
-    n_gpu_layers=n_gpu_layers,
-    n_batch=n_batch,
-    callback_manager=callback_manager,
-    verbose=True,  # Verbose is required to pass to the callback manager
-)
-
-add_routes(
-    app,
-    prompt | llm,
-    path='/test'
-)
-
-# if __name__ == "__main__":
-#     import uvicorn
-
-#     uvicorn.run(app)
-
-# llm_chain = prompt | llm
-
-# question = "Hi"
-# x = llm_chain.invoke({"question": question})
+@app.route("/<lol>")
+def test(lol):
+    return llm.invoke(lol)