File size: 2,997 Bytes
3079197 484e5ab 3079197 d0db329 3079197 d0db329 3079197 d0db329 3079197 d0db329 3079197 d0db329 3079197 d0db329 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from abc import ABC
from openai import OpenAI
import os
import base64
from io import BytesIO
class Base(ABC):
def __init__(self, key, model_name):
pass
def describe(self, image, max_tokens=300):
raise NotImplementedError("Please implement encode method!")
def image2base64(self, image):
if isinstance(image, BytesIO):
return base64.b64encode(image.getvalue()).decode("utf-8")
buffered = BytesIO()
try:
image.save(buffered, format="JPEG")
except Exception as e:
image.save(buffered, format="PNG")
return base64.b64encode(buffered.getvalue()).decode("utf-8")
def prompt(self, b64):
return [
{
"role": "user",
"content": [
{
"type": "text",
"text": "请用中文详细描述一下图中的内容，比如时间，地点，人物，事情，人物心情等。",
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{b64}"
},
},
],
}
]
class GptV4(Base):
def __init__(self, key, model_name="gpt-4-vision-preview"):
self.client = OpenAI(key)
self.model_name = model_name
def describe(self, image, max_tokens=300):
b64 = self.image2base64(image)
res = self.client.chat.completions.create(
model=self.model_name,
messages=self.prompt(b64),
max_tokens=max_tokens,
)
return res.choices[0].message.content.strip()
class QWenCV(Base):
def __init__(self, key, model_name="qwen-vl-chat-v1"):
import dashscope
dashscope.api_key = key
self.model_name = model_name
def describe(self, image, max_tokens=300):
from http import HTTPStatus
from dashscope import MultiModalConversation
response = MultiModalConversation.call(model=self.model_name,
messages=self.prompt(self.image2base64(image)))
if response.status_code == HTTPStatus.OK:
return response.output.choices[0]['message']['content']
return response.message
|