orarbel

Hi LinkedIn friend!

Here is how I managed to have the agent I'm building reduce token usage.

1. My agent has 62 tools (and growing quickly in terms of number of tools..)
2. Each tool has a description. All in all I was sending the entire 62 tools+description in every agent turn. 

It came out to 10k tokens before even the system prompt+user prompt - ON EVERY TURN.

The solution I found was to do a preflight LLM request to select only the relevant tools for the user request.

orarbel

import time
import pytest
from langchain.agents import initialize_agent, AgentType
from langchain.agents.agent import AgentExecutor
from langchain.tools import Tool
from langchain_community.llms import OpenAI
from langchain.prompts import PromptTemplate
from langgraph.prebuilt import create_react_agent
# Agno imports
from agno.agent.agent import Agent

orarbel

import java.io.*;
import java.net.*;
import java.util.*;
import java.util.Map.Entry;



public class CourseRegister implements Runnable {

	boolean debug = false;

orarbel

Yo all the users that Yo'ed your Yo service ("subscribers"):

curl --data "api_token=<token>" http://api.justyo.co/yoall/

---------------------------------------------------------------------

Specific user Yo:

curl --data "api_token=<token>&username=<username>" http://api.justyo.co/yo/