Activity
Mon
Wed
Fri
Sun
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
What is this?
Less
More

Memberships

Zero to Pitch

2k members • Free

AI Business Trailblazers Hive

12.9k members • Free

AI Developer Accelerator

11k members • Free

Eon City

396 members • $27/m

Agent Zero

2.1k members • Free

4 contributions to Agent Zero
Experimenting with video content
is there a way how to get A0 to describe the content of a video clip? does it need special tools/APIs for that?
1 like • Nov '24
I would try: Ask it to write code that takes screenshots every 1second of the video and save them to a folder, then install an ollama vision model to analyse each image locally.
Tutorial: How to create a new Tool
This is a quick example of how to add a new tool to agent zero, there may be other ways to accomplish this, but since i couldn't find a good example i will share my code here. This uses a free joke api just for an example proof of concept , most llms already contain many jokes by default, so its not very practical, but a current weather api implementation would be coded similar. To add a new tool to Agent Zero we need to create two new files and modify a third file. The steps to add a basic tool that requests a joke from an api and returns it to agent zero are: (note that this tool does not take any arguments, look at the existing 'knowledge_tool.py' on how to add arguments, such as 'question') 1. Add the new tool code by adding file: query_joke_api_tool.py 2. Create a markdown file that agent zero will include in the prompt so that the LLM knows what the tools capabilities are: agent.system.tool.joke.md 3. Modify the agent.system.tools.md file so that our new tool is included in the LLM prompt, practically registering our new tool. Agent zero automatically knows where to look to find and execute this tool. Explicitly ask the LLM to use this tool and it should use it. Step 1 Create file: # /python/tools/query_joke_api_tool.py import requests from urllib.parse import urlparse from python.helpers.tool import Tool, Response from python.helpers.errors import handle_error class QueryJokeApiTool(Tool): async def execute(self, **kwargs): url = "https://icanhazdadjoke.com/" headers = { "Accept": "text/plain"} print("*** Agent Zero has called the QueryJokeApiTool") try: # Attempt to make the API request response = requests.get(url, headers=headers, timeout=5) # Check if the request was successful (status code 200) if response.status_code == 200: myjoke = response.text.strip() return Response(message=f"Joke content:\n\n{myjoke}", break_loop=False)
TAVILY API for search?
I think it may be a good idea to add the possibility of using TAVILY API (tavily.com) for search, as they have a free tier.
1 like • Nov '24
I have used tavily for search, but for better flexibility i asked chatgpt to write a selenium chromedriver agent tool thats able to bypass alot of restrictions encountered when scraping or searching the web, all for free.
Ubuntu Install Instructions
Is there a reason why there is not dedicated Linux Installation Instructions, or is it expected that Linux users will will use the OSX instructions?
2 likes • Oct '24
My Ubuntu installation is working well now, I discovered that I don't need docker-desktop running in the background, Just need docker installed and execte "docker login" before starting A0.
1-4 of 4
Matthew Kelly
2
7points to level up
@matthew-kelly-5720
Self taught programmer who works as an electrical engineer by day and hacks during the night.

Active 28d ago
Joined Oct 2, 2024
Powered by