File size: 3,041 Bytes
b43a1bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
91
92
93
94
95
96
import anthropic
import os
import base64
import httpx

os.environ["ANTHROPIC_API_KEY"] = os.getenv("ANTHROPIC_API_KEY")
client = anthropic.Anthropic()


def create_claude_request_for_text_completion(message_schema):
    message = client.messages.create(
        model="claude-3-5-sonnet-20240620",
        max_tokens=1000,
        temperature=0,
        messages=message_schema)
    return message.content[0].text


def create_claude_image_request_for_image_captioning(system_prompt, caption_prompt, image_data):
    try:
        message = client.messages.create(
            model="claude-3-5-sonnet-20240620",
            max_tokens=1024,
            messages=[
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": system_prompt
                        },
                        {
                            "type": "image",
                            "source": {
                                "type": "base64",
                                "media_type": f"image/jpeg",
                                "data": image_data
                            }
                        },
                        {
                            "type": "text",
                            "text": caption_prompt
                        }
                    ]
                }
            ]
        )
    except:
        message = client.messages.create(
            model="claude-3-5-sonnet-20240620",
            max_tokens=1024,
            messages=[
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": system_prompt
                        },
                        {
                            "type": "image",
                            "source": {
                                "type": "base64",
                                "media_type": f"image/png",
                                "data": image_data
                            }
                        },
                        {
                            "type": "text",
                            "text": caption_prompt
                        }
                    ]
                }
            ]
        )
    return message.content[0].text


def embed_base64_for_claude(image_path):
    # Open the image file in binary mode
    with open(image_path, "rb") as image_file:
        # Read the image and encode it to base64
        image_data = base64.b64encode(image_file.read()).decode("utf-8")
    return image_data


def extract_data_from_text_xml(text_xml, tag):
    import re
    re_command = f"<{tag}>(.*?)</{tag}>"
    data = re.findall(re_command, text_xml, re.DOTALL)
    final_string = ""
    for idx, item in enumerate(data, start=1):
        output_extraction = f"{idx}:\n{item.strip()}\n"
        final_string = final_string + output_extraction
    return final_string