import requests import json import sys from PIL import Image import base64 text = sys.argv[1] image_path = sys.argv[2] #image = Image.open(image_path) with open(image_path, "rb") as file: image = str(base64.b64encode(file.read())) print("image:", type(image)) sample = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: What are the key differences between renewable and non-renewable energy sources?###Assistant: Renewable energy sources are those that can be replenished naturally in a relatively short amount of time, such as solar, wind, hydro, geothermal, and biomass. Non-renewable energy sources, on the other hand, are finite and will eventually be depleted, such as coal, oil, and natural gas. Here are some key differences between renewable and non-renewable energy sources:\n1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable energy sources are finite and will eventually run out.\n2. Environmental impact: Renewable energy sources have a much lower environmental impact than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, and other negative effects.\n3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically have lower operational costs than non-renewable sources.\n4. Reliability: Renewable energy sources are often more reliable and can be used in more remote locations than non-renewable sources.\n5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different situations and needs, while non-renewable sources are more rigid and inflexible.\n6. Sustainability: Renewable energy sources are more sustainable over the long term, while non-renewable sources are not, and their depletion can lead to economic and social instability.\n###Human: " prompt = sample + text + "\n###Assistant:" url = "http://task345865.training:6801/worker_generate_stream" headers = {'User-Agent': 'LLaVA Client'} pload = { 'model': 'output_test_checkpoint-6500', 'prompt': prompt, "images": [image], 'temperature': 0.5, 'max_new_tokens': 512, 'stop': '###'} response = requests.post(url, headers=headers, json=pload, stream=True, timeout=10) for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"): if chunk: data = json.loads(chunk.decode()) text = data["text"].split("###")[-1].split(":")[1] if text.count("<") == 2 and text.count(">") == 2: res = text elif text.count("<") == 1 and text.count(">") == 1: res = text + text else: res = "<127><127>" print(res)