File size: 6,589 Bytes
b7e35bf a8bf136 b7e35bf a8bf136 b7e35bf a8bf136 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
from smolagents import Tool
import wikipedia
from bs4 import BeautifulSoup
import io
import pandas as pd
import requests
from tabulate import tabulate
import os
import tempfile
from pathlib import Path
from PIL import Image
from io import BytesIO
from dotenv import find_dotenv, load_dotenv
from openai import OpenAI
from llama_index.readers.youtube_transcript import YoutubeTranscriptReader
from google import genai
from google.genai import types
import chess
class WikipediaSearch(Tool):
name = "wikipedia_search"
description = "Fetches wikipedia pages."
inputs = {
"query": {
"type": "string",
"description": "Query to be searched on wikipedia"
}
}
output_type = "string"
def forward(self, query:str)->str:
res = wikipedia.page(query)
bs = BeautifulSoup(res.html(), 'html.parser')
text_only = bs.get_text()
return text_only
class ExcelReader(Tool):
name = 'excel_processor'
description = "excel reading tool, processed files of .xlsx and .xls format."
inputs = {
"file_path": {
"type": "string",
"description": "path to the excel file"
}
}
output_type = "string"
def forward(self, file_path:str)->str:
df = pd.read_excel(file_path)
txt_excel = tabulate(df, headers="keys", tablefmt="github", showindex=False)
return txt_excel
class FileReader(Tool):
name = 'file_reader'
description = "reads saved files"
inputs = {
"file_path": {
"type": "string",
"description": "path to the file"
}
}
output_type = "string"
def forward(self, file_path:str)->str:
with open(file_path, "r") as file:
content = file.read()
return content
def download_files(task_id, file_name):
url = f'https://agents-course-unit4-scoring.hf.space/files/{task_id}'
response = requests.get(url, timeout=15)
tmp_dir = Path(tempfile.gettempdir()) / "project_files"
tmp_dir.mkdir(exist_ok=True)
filepath = os.path.join(tmp_dir, file_name)
with open(filepath, "wb") as f:
f.write(response.content)
return filepath
def get_images(file_format, file_path):
if file_format in ['png', 'jpeg', 'jpg']:
images = [Image.open(file_path).convert("RGB")]
else:
images = []
return images
class AudioTransciber(Tool):
name = 'audio_transcriber'
description = "transcribes audio files"
inputs = {
"file_path": {
"type": "string",
"description": "path to the file"
}
}
output_type = "string"
def forward(self, file_path:str)->str:
audio = open(file_path, 'rb')
client = OpenAI(api_key=os.getenv("OPEN_AI_KEY"))
transcript = client.audio.transcriptions.create(model='whisper-1',
file=audio)
return transcript
class YouTubeTranscipt(Tool):
name = 'youtube_transcript'
description = "a tool that returns a transcript for a youtube video. Youtube videos come from urls containing www.youtube.com"
inputs = {
"url": {
"type": "string",
"description": "url to the youtube video, has 'www.youtube.com' in it."
}
}
output_type = "string"
def forward(self, url:str)->str:
loader = YoutubeTranscriptReader()
documents = loader.load_data(ytlinks=[url])
transcript = documents[0].text
return transcript
class YouTubeVideoUnderstanding(Tool):
name = 'youtube_video_understanding'
description = "a tool that processes summarizes what is happenening in a youtube video. Youtube videos come from urls containing www.youtube.com"
inputs = {
"url": {
"type": "string",
"description": "url to the youtube video, has 'www.youtube.com' in it."
},
"prompt": {
"type": "string",
"description": "user prompt about the video content"
}
}
output_type = "string"
def forward(self, url:str, prompt:str)->str:
load_dotenv(find_dotenv())
client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
response = client.models.generate_content(
model='models/gemini-2.0-flash',
contents=types.Content(
parts=[
types.Part(
file_data=types.FileData(file_uri=url)
),
types.Part(text=prompt)
]
)
)
return response.text
class VegetableFruitClassification(Tool):
name = 'vegetable_fruit_classificaiton'
description = "a tool that can help classify fruits and vegetables"
inputs = {
"prompt": {
"type": "string",
"description": "user prompt about fruits or vegetables"
}
}
output_type = "string"
def forward(self, prompt:str)->str:
load_dotenv(find_dotenv())
client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
additional_context = """
The botanical distinction between fruits and vegetables is anatomical of the plant in question.
For example, a tomato has seeds, which would result in reproduction. Rhubarb is the stalk of a plant, and has no means of proliferation after consumption.
A tomato is a botanical fruit and rhubarb is botanically a vegetable. """
extended_prompt = prompt + additional_context
response = client.models.generate_content(
model='models/gemini-2.5-flash-preview-05-20',
contents=types.Content(
parts=[
types.Part(text=extended_prompt)
]
)
)
return response.text
class ChessSolver(Tool):
name = "chess_analysis_tool"
description = "analyzes the chess board to determine the best next move."
inputs = {
"image_path": {
"type": "string",
"description": "path to the image showing a chess board."
},
"current_player":{
"type": "string",
"description": "player whose turn it is. Acceptable inputs are 'black' or 'white'"
},
}
output_type = "string"
def forward(self, image_path:str, current_player:str)->str:
fen = chess.fen_notation(image_path, current_player)
best_move = chess.chess_analysis(fen)
return best_move |