You can also check this cookbook in colab here

⭐ Star us on GitHub, join our Discord, or follow us on X

This notebook demonstrates how to set up and leverage CAMEL’s ability to do video analysis.

In this notebook, you’ll explore:

  • CAMEL: A powerful multi-agent framework that enables Retrieval-Augmented Generation and multi-agent role-playing scenarios, allowing for sophisticated AI-driven tasks.
  • Video Analysis: How to use CAMEL to read and generate descriptions of uploaded videos.

​
📦 Installation

%pip install "camel-ai[all]==0.2.16"

​
🔑 Setting Up API Keys

import os
from getpass import getpass

# Prompt for the API key securely
openai_api_key = getpass('Enter your API key: ')
os.environ["OPENAI_API_KEY"] = openai_api_key

Alternatively, if running on Colab, you could save your API keys and tokens as Colab Secrets, and use them across notebooks.

To do so, comment out the above manual API key prompt code block(s), and uncomment the following codeblock.

⚠️ Don’t forget granting access to the API key you would be using to the current notebook.

# import os
# from google.colab import userdata

# os.environ["OPENAI_API_KEY"] = userdata.get("OPENAI_API_KEY")

​
Set up an agent for video analysis task

from camel.agents import ChatAgent
from camel.configs.openai_config import ChatGPTConfig
from camel.messages import BaseMessage
from camel.prompts.prompt_templates import PromptTemplateGenerator
from camel.types import ModelType, ModelPlatformType
from camel.types.enums import RoleType, TaskType
from camel.models import ModelFactory

# Define system message
sys_msg_prompt = PromptTemplateGenerator().get_prompt_from_key(
    TaskType.VIDEO_DESCRIPTION, RoleType.ASSISTANT
)
sys_msg = BaseMessage.make_assistant_message(
    role_name="Assistant",
    content=sys_msg_prompt,
)

# Set model
model=ModelFactory.create(
    model_platform=ModelPlatformType.OPENAI,
    model_type=ModelType.GPT_4O,
    model_config_dict=ChatGPTConfig().as_dict(),
)

# Set agent
camel_agent = ChatAgent(
    sys_msg,
    model=model
)

​
Providing video and set user message

# Provide your video path
video_cctv = "/content/CCTV.mov"
with open(video_cctv, "rb") as video_cctv:
    video_bytes_cctv = video_cctv.read()

# Set user message
user_msg_cctv = BaseMessage.make_user_message(
    role_name="User",
    content="These are frames from a video that I want to upload. Generate a"
    "compelling description that I can upload along with the video.",
    video_bytes=video_bytes_cctv,
)

# Get response information
response_cctv = camel_agent.step(user_msg_cctv)
print(response_cctv.msgs[0].content)
# Provide your video path
video_help = "/content/help.mov"
with open(video_help, "rb") as video_help:
    video_bytes_help = video_help.read()

# Set user message
user_msg_help = BaseMessage.make_user_message(
    role_name="User",
    content="These are frames from a video that I want to upload. Generate a"
    "compelling description that I can upload along with the video.",
    video_bytes=video_bytes_help,
)

# Get response information
response_help = camel_agent.step(user_msg_help)
print(response_help.msgs[0].content)
# Provide your video path
video_content_mode = "/content/content mod.mov"
with open(video_content_mode, "rb") as video_content_mode:
    video_bytes_content_mode = video_content_mode.read()

# Set user message
user_msg_content_mode = BaseMessage.make_user_message(
    role_name="User",
    content="These are frames from a video that I want to upload. Generate a"
    "compelling description that I can upload along with the video.",
    video_bytes=video_bytes_content_mode,
)

# Get response information
response_content_mode = camel_agent.step(user_msg_content_mode)
print(response_content_mode.msgs[0].content)

​
🌟 Highlights

This notebook has guided you through setting up an agent and analyzing videos using CAMEL.

Now, you know how to generate description for uploaded videos.

That’s everything: Got questions about 🐫 CAMEL-AI? Join us on Discord! Whether you want to share feedback, explore the latest in multi-agent systems, get support, or connect with others on exciting projects, we’d love to have you in the community! 🤝

Check out some of our other work:

  1. 🐫 Creating Your First CAMEL Agent free Colab

  2. Graph RAG Cookbook free Colab

  3. 🧑‍⚖️ Create A Hackathon Judge Committee with Workforce free Colab

  4. 🔥 3 ways to ingest data from websites with Firecrawl & CAMEL free Colab

  5. 🦥 Agentic SFT Data Generation with CAMEL and Mistral Models, Fine-Tuned with Unsloth free Colab

Thanks from everyone at 🐫 CAMEL-AI

⭐ Star us on GitHub, join our Discord, or follow us on X