This installs Crew Optimizer together with optional OR-Tools support for MILP solving. Add pytest, ruff, or other dev tools as needed (pip install pytest).
from crew_optimizer import OptimizerCrew
crew = OptimizerCrew(verbose=False)
lp_model = {
"name": "diet-toy",
"sense": "min",
"objective": {
"terms": [
{"var": "x", "coef": 3},
{"var": "y", "coef": 2},
],
"constant": 0,
},
"variables": [
{"name": "x", "lb": 0},
{"name": "y", "lb": 0},
],
"constraints": [
{
"name": "c1",
"lhs": {
"terms": [
{"var": "x", "coef": 1},
{"var": "y", "coef": 2},
],
"constant": 0,
},
"cmp": ">=",
"rhs": 8,
},
{
"name": "c2",
"lhs": {
"terms": [
{"var": "x", "coef": 3},
{"var": "y", "coef": 1},
],
"constant": 0,
},
"cmp": ">=",
"rhs": 6,
},
],
}
solution = crew.solve_lp(lp_model)
print(solution)
To integrate with a wider multi-agent workflow, call crew.build_crew() to obtain a Crew populated with the LP, MILP, and parser agents. Provide model inputs through CrewAI’s shared context as usual.
The MCP server includes a solve_word_problem_with_data tool that can parse data files (CSV, JSON, Excel) and use them to solve optimization word problems. This is particularly useful when you have data in files and want to formulate and solve optimization problems based on that data.
# Example: Solve a production planning problem with data from a CSV file
csv_data = """product,cost,capacity,demand
Widget,10,100,50
Gadget,15,80,60
Thing,12,120,40"""
problem = """
Minimize total cost subject to:
- Production of each product cannot exceed capacity
- Production must meet demand
- All production quantities are non-negative
"""
# The tool will parse the CSV, extract the cost, capacity, and demand values,
# and formulate the optimization problem automatically.