生成式人工智能潜力的释放：软件工程师的MLOps和LLM部署策略

Python 
 # Install the required library
 # pip install ai_vllm_library
 from ai_vllm import Model, Params, BatchService

 # Load the model
 model = Model.load("ai_model/llm-15b")

 # Define parameters
 params = Params(temp=0.9, max_tokens=150)

 # Create a batch of prompts
 prompts = ["AI future", "Generative models", "MLOps trends", "Future of robotics"]

 # Use the BatchService for offline batch predictions
 batch_service = BatchService(model, params)

 results = batch_service.predict_batch(prompts)

 # Print the results
 for prompt, result in zip(prompts, results):
 print(f"Prompt: {prompt}\nResult: {result}\n")

Python 
 # Install the required libraries
 # pip install ai_vllm_library flask

 from ai_vllm import Model, Params
 from flask import Flask, request, jsonify
 app = Flask(__name__)

 # Load the model
 model = Model.load("ai_model/llm-15b")

 # Define parameters
 params = Params(temp=0.9, max_tokens=150)
 @app.route('/predict', methods=['POST'])

 def predict():
 data = request.json
 prompt = data.get('prompt', '')
 result = model.predict([prompt], params)
 return jsonify({"result": result[0]})

 if __name__ == '__main__':
 app.run(port=5000)

Python 
 # Install the required library
 # pip install genai_inference flask

 from flask import Flask, request, jsonify
 from genai_infer import TextGenerator
 app = Flask(__name__)
 
 # Initialize the TextGenerator
 generator = TextGenerator("genai/llm-15b")
 @app.route('/generate_text', methods=['POST'])
 
 def generate_text():
  data = request.json
  prompt = data.get('prompt', '')
  response = generator.generate(prompt)
  return jsonify({"generated_text": response})
 
 if __name__ == '__main__':
 app.run(host='0.0.0.0', port=5000)

Dockerfile 
 # Use an official Python runtime as the base image
 FROM python:3.8-slim

 # Set the working directory in the container
 WORKDIR /app

 # Copy the current directory contents into the container
 COPY . /app

 # Install the required libraries
 RUN pip install genai_inference flask

 # Make port 5000 available to the world outside this container
 EXPOSE 5000

 # Define environment variable for added security
 ENV NAME World

 # Run app.py when the container launches
 CMD ["python", "app.py"]

Shell 
 docker build -t genai_web_server .
 docker run -p 5000:5000 genai_web_server

Shell 
 curl -X POST -H "Content-Type: application/json" -d '{"prompt":"The future of AI"}' http://localhost:5000/g

Python 
 # Install the required library
 # pip install openllm flask
 
 from flask import Flask, request, jsonify
 from openllm import TextGenerator
 app = Flask(__name__)
 
 # Initialize the TextGenerator from OpenLLM
 generator = TextGenerator("openllm/llm-15b")

 @app.route('/generate', methods=['POST'])
 def generate():
  data = request.json
  prompt = data.get('prompt', '')
  response = generator.generate_text(prompt)
  return jsonify({"generated_text": response})
 
 if __name__ == '__main__':
 app.run(host='0.0.0.0', port=8080)

Shell 
 curl -X POST -H "Content-Type: application/json" -d '{"prompt":"The evolution of MLOps"}' http://localhost:8080/gene

Python 
 # Install the required library
 # pip install ray[serve]
 import ray
 from ray import serve
 from openllm import TextGenerator
 
 ray.init()
 client = serve.start()
 
 def serve_model(request):
  generator = TextGenerator("ray/llm-15b")
  prompt = request.json.get("prompt", "")
  return generator.generate_text(prompt)
 
 client.create_backend("llm_backend", serve_model)
 client.create_endpoint("llm_endpoint", backend="llm_backend", route="/generate")

 if __name__ == "__main__":
  ray.util.connect("localhost:50051")

Shell 
 curl -X POST -H "Content-Type: application/json" -d '{"prompt":"The intricacies of RayServe"}' http://localhost:8000/generate