File size: 9,689 Bytes
9505e38 6c9d559 9505e38 3b013ba 9505e38 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | import imageio
import os
import re
import tempfile
import yt_dlp
from datetime import timedelta
from google import genai
from google.genai import types
from smolagents import tool
from typing import List, Optional
from youtube_transcript_api import YouTubeTranscriptApi
# YouTube Video Review Tool
@tool
def review_youtube_video(url: str, question: str) -> str:
"""Reviews a YouTube video and answers a specific question about that video.
Args:
url (str): the URL to the YouTube video.
question (str): The question you are asking about the video
Returns:
str: The answer to the question
"""
try:
client = genai.Client(api_key=os.getenv("GEMINI_KEY"))
model = "models/gemini-1.5-flash-8b"
response = client.models.generate_content(
model=model,
contents=types.Content(
parts=[
types.Part(file_data=types.FileData(file_uri=url)),
types.Part(text=question),
]
),
)
return response.text
except Exception as e:
return f"Error asking {model} about video: {str(e)}"
@tool
def use_vision_model(
question: str, image_paths: List[str], mime_type: str
) -> str:
"""Use a Vision Model to answer a question about a set of images.
Args:
question (str): The question you are asking about the images.
image_paths (List[str]): The paths to the images to use for the question.
mime_type (str): The mime type of the image.
Returns:
str: The answer to the question
"""
try:
client = genai.Client(api_key=os.getenv("GEMINI_KEY"))
model = "models/gemini-2.0-flash-001"
# Prepare the content parts
parts = []
for image_path in image_paths:
with open(image_path, "rb") as f:
image_bytes = f.read()
response = []
for chunk in client.models.generate_content_stream(
model=model,
contents=[
question,
types.Part.from_bytes(data=image_bytes, mime_type=mime_type),
],
):
response.append(chunk.text)
return " ".join(response)
except Exception as e:
return f"Error using vision model: {str(e)}"
# YouTube Frames to Images Tool
@tool
def video_frames_to_images(
url: str,
folder_name: str,
sample_interval_seconds: int = 5,
) -> List[str]:
"""Extracts frames from a video at specified intervals and saves them as images.
Args:
url (str): the URL to the video.
folder_name (str): the name of the folder to save the images to.
sample_interval_seconds (int): the interval between frames to sample.
Returns:
List[str]: A list of paths to the saved image files.
"""
# Create a subdirectory for the frames
frames_dir = os.path.join(folder_name, "frames")
os.makedirs(frames_dir, exist_ok=True)
ydl_opts = {
"format": "bestvideo[height<=1080]+bestaudio/best[height<=1080]/best",
"outtmpl": os.path.join(folder_name, "video.%(ext)s"),
"quiet": True,
"noplaylist": True,
"merge_output_format": "mp4",
"force_ipv4": True,
}
try:
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(url, download=True)
video_path = next(
(
os.path.join(folder_name, f)
for f in os.listdir(folder_name)
if f.endswith(".mp4")
),
None,
)
if not video_path:
raise RuntimeError("Failed to download video as mp4")
reader = imageio.get_reader(video_path)
metadata = reader.get_meta_data()
fps = metadata.get("fps")
if fps is None:
reader.close()
raise RuntimeError(
"Unable to determine FPS from video metadata"
)
frame_interval = int(fps * sample_interval_seconds)
image_paths: List[str] = []
for idx, frame in enumerate(reader):
if idx % frame_interval == 0:
# Save frame as image
image_path = os.path.join(
frames_dir, f"frame_{idx:06d}.jpg"
)
imageio.imwrite(image_path, frame)
image_paths.append(image_path)
reader.close()
return image_paths
except Exception as e:
raise RuntimeError(f"Error processing video frames: {str(e)}") from e
@tool
def transcribe_youtube(url: str) -> str:
"""Transcribes a YouTube video using YouTube Transcript API or Gemini as fallback.
Args:
url (str): the URL to the YouTube video.
Returns:
str: The transcript of the YouTube video.
"""
try:
# First try using YouTube Transcript API
video_id = _extract_video_id(url)
if not video_id:
raise ValueError(f"Invalid YouTube URL: {url}")
try:
# Try to get transcript in English
transcript_chunks = YouTubeTranscriptApi.get_transcript(
video_id, languages=["en"]
)
# Combine all chunks into a single transcript with timestamps
transcript = ""
for chunk in transcript_chunks:
timestamp = str(timedelta(seconds=int(chunk["start"])))
transcript += f"[{timestamp}] {chunk['text']}\n"
return transcript
except Exception as transcript_error:
print(
f"Failed to get transcript using YouTube API: {str(transcript_error)}"
)
print("Falling back to Gemini-based transcription...")
# Fallback to Gemini-based transcription
with tempfile.TemporaryDirectory() as tmpdir:
# Download audio from YouTube
ydl_opts = {
"format": "bestaudio/best",
"outtmpl": os.path.join(tmpdir, "audio.%(ext)s"),
"quiet": True,
"noplaylist": True,
"postprocessors": [
{
"key": "FFmpegExtractAudio",
"preferredcodec": "wav",
"preferredquality": "192",
}
],
}
try:
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(url, download=True)
audio_path = next(
(
os.path.join(tmpdir, f)
for f in os.listdir(tmpdir)
if f.endswith(".wav")
),
None,
)
if not audio_path:
raise RuntimeError(
"Failed to download audio"
) from transcript_error
# Use Gemini to transcribe the audio
client = genai.Client(api_key=os.getenv("GEMINI_KEY"))
model = "models/gemini-1.5-flash-8b"
# Read the audio file
with open(audio_path, "rb") as audio_file:
audio_data = audio_file.read()
# Create the content with audio data
contents = types.Content(
parts=[
types.Part(
file_data=types.FileData(
mime_type="audio/wav",
data=audio_data,
)
),
types.Part(
text="Please transcribe this audio file. Include timestamps if possible."
),
]
)
# Generate transcription
response = client.models.generate_content(
model=model, contents=contents
)
return response.text
except yt_dlp.utils.DownloadError as e:
raise RuntimeError(
f"Error downloading YouTube video: {str(e)}"
) from transcript_error
except Exception as e:
raise RuntimeError(
f"Error processing YouTube video: {str(e)}"
) from transcript_error
except Exception as e:
raise RuntimeError(f"Error in YouTube transcription: {str(e)}") from e
def _extract_video_id(url: str) -> Optional[str]:
"""Extract video ID from YouTube URL.
Args:
url (str): the URL to the YouTube video.
Returns:
str: The video ID of the YouTube video.
"""
patterns = [
r"(?:youtube\.com\/watch\?v=|youtube\.com\/embed\/|youtu\.be\/)([^&\n?#]+)",
r"(?:youtube\.com\/v\/|youtube\.com\/e\/|youtube\.com\/user\/[^\/]+\/|youtube\.com\/[^\/]+\/|youtube\.com\/embed\/|youtu\.be\/)([^&\n?#]+)",
]
for pattern in patterns:
match = re.search(pattern, url)
if match:
return match.group(1)
return None
|