File size: 5,489 Bytes
a31ddf7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
import json
import os
import re
import time

import yaml
from duckduckgo_search.exceptions import DuckDuckGoSearchException
from smolagents import FinalAnswerTool, Tool, OpenAIServerModel, CodeAgent


python_interpreter_max_print_outputs_length = 10**6


class CustomDuckDuckGoSearchTool(Tool):
    name = "web_search"
    description = """Performs a duckduckgo web search based on your query (think a Google search) then returns the top search results."""
    inputs = {"query": {"type": "string", "description": "The search query to perform."}}
    output_type = "string"

    def __init__(self, max_results=10, **kwargs):
        super().__init__()
        self.max_results = max_results
        try:
            from duckduckgo_search import DDGS
        except ImportError as e:
            raise ImportError(
                "You must install package `duckduckgo_search` to run this tool: for instance run `pip install duckduckgo-search`."
            ) from e
        self.ddgs = DDGS(**kwargs)

    def forward(self, query: str) -> str:
        num_tries = 5
        for cnt in range(num_tries):
            try:
                results = self.ddgs.text(query, max_results=self.max_results)
                break
            except DuckDuckGoSearchException as e:
                print(e)
                if cnt == num_tries - 1:
                    raise
            time.sleep(1.5)

        if len(results) == 0:
            raise Exception("No results found! Try a less restrictive/shorter query.")
        postprocessed_results = [f"[{result['title']}]({result['href']})\n{result['body']}" for result in results]
        return "## Search Results\n\n" + "\n\n".join(postprocessed_results)


class CustomVisitWebpageTool(Tool):
    name = "visit_webpage"
    description = (
        "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."
    )
    inputs = {
        "url": {
            "type": "string",
            "description": "The url of the webpage to visit.",
        }
    }
    output_type = "string"

    def forward(self, url: str) -> str:
        try:
            import requests
            from markdownify import markdownify
            from requests.exceptions import RequestException

            from smolagents.utils import truncate_content
        except ImportError as e:
            raise ImportError(
                "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
            ) from e
        try:
            # Send a GET request to the URL with a 20-second timeout
            response = requests.get(url, timeout=20)
            response.raise_for_status()  # Raise an exception for bad status codes

            # Convert the HTML content to Markdown
            markdown_content = markdownify(response.text).strip()

            # Remove multiple line breaks
            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

            return truncate_content(markdown_content, python_interpreter_max_print_outputs_length)

        except requests.exceptions.Timeout:
            return "The request timed out. Please try again later or check the URL."
        except RequestException as e:
            return f"Error fetching the webpage: {str(e)}"
        except Exception as e:
            return f"An unexpected error occurred: {str(e)}"


class SmolAgent:
    def __init__(self, openai_api_key=None):
        final_answer = FinalAnswerTool()
        search_tool = CustomDuckDuckGoSearchTool(max_results=3)
        visit_webpage_tool = CustomVisitWebpageTool()
        model = OpenAIServerModel(
            model_id="gpt-4.1-2025-04-14",
            # model_id="gpt-4.1-mini-2025-04-14",
            # model_id="gpt-4.1-nano-2025-04-14",
            max_completion_tokens=1024,
            temperature=0.01,
            api_key=openai_api_key,
        )
        with open('prompt_templates.yaml', 'r') as f:
            prompt_templates = yaml.safe_load(f)
        with open('system_prompt.txt', 'r') as f:
            prompt_templates['system_prompt'] = f.read()
        self.agent = CodeAgent(
            model=model,
            prompt_templates=prompt_templates,
            tools=[search_tool, visit_webpage_tool, final_answer],
            max_steps=10,
            verbosity_level=100,
            grammar=None,
            planning_interval=None,
            name='Advanced GAIA Agent',
            description=None,
            max_print_outputs_length=python_interpreter_max_print_outputs_length,
        )
        self.agent.visualize()

    def run(self, task: dict[str, str]) -> str:
        if len(task.get('file_name')) != 0:
            return ''  # skip questions where file processing is needed

        question = task.get('question')
        if question.find('www.youtube.com') != -1:
            return ''  # skip questions where file processing is needed

        return self.agent.run(question)


if __name__ == '__main__':
    openai_key = os.getenv('OPENAI_API_KEY')
    if not openai_key:
        with open("data/openai.key", "r") as f:
            openai_key = f.read().strip()

    agent = SmolAgent(openai_api_key=openai_key)

    with open('data/questions.json', 'r') as f:
        questions = json.load(f)

    for q in questions:
        print('\n===')
        print(q)
        print('\n---')
        a = agent.run(q)
        print('\n---')
        print(a)