Real Madrid Next best fit striker using CREW AI

3_crew/RealMadrid_Next_Best_Fit/README.md

@@ -0,0 +1,54 @@
+# Realmadridnextbestfit Crew
+
+Welcome to the Realmadridnextbestfit Crew project, powered by [crewAI](https://crewai.com). This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilities.
+
+## Installation
+
+Ensure you have Python >=3.10 <3.14 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+
+First, if you haven't already, install uv:
+
+```bash
+pip install uv
+```
+
+Next, navigate to your project directory and install the dependencies:
+
+(Optional) Lock the dependencies and install them by using the CLI command:
+```bash
+crewai install
+```
+### Customizing
+
+**Add your `OPENAI_API_KEY` into the `.env` file**
+
+- Modify `src/realmadridnextbestfit/config/agents.yaml` to define your agents
+- Modify `src/realmadridnextbestfit/config/tasks.yaml` to define your tasks
+- Modify `src/realmadridnextbestfit/crew.py` to add your own logic, tools and specific args
+- Modify `src/realmadridnextbestfit/main.py` to add custom inputs for your agents and tasks
+
+## Running the Project
+
+To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:
+
+```bash
+$ crewai run
+```
+
+This command initializes the RealMadridNextBestFit Crew, assembling the agents and assigning them tasks as defined in your configuration.
+
+This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folder.
+
+## Understanding Your Crew
+
+The RealMadridNextBestFit Crew is composed of multiple AI agents, each with unique roles, goals, and tools. These agents collaborate on a series of tasks, defined in `config/tasks.yaml`, leveraging their collective skills to achieve complex objectives. The `config/agents.yaml` file outlines the capabilities and configurations of each agent in your crew.
+
+## Support
+
+For support, questions, or feedback regarding the Realmadridnextbestfit Crew or crewAI.
+- Visit our [documentation](https://docs.crewai.com)
+- Reach out to us through our [GitHub repository](https://github.com/joaomdmoura/crewai)
+- [Join our Discord](https://discord.com/invite/X4JWnZnxPb)
+- [Chat with our docs](https://chatg.pt/DWjSBZn)
+
+Let's create wonders together with the power and simplicity of crewAI.

3_crew/RealMadrid_Next_Best_Fit/output/final_player.md

@@ -0,0 +1 @@
+{"name":"Harry Kane","reason":"Harry Kane is chosen for his proven goal-scoring record and experience at a top club. His physical presence and ability to finish suits a variety of tactical setups including quick counter-attacks, providing a reliable target up front. Kane's fitness status is currently excellent with a low risk of injury, ensuring availability for key matches.","key_attruibutes":{"name":"Harry Kane","age":30,"height":188.0,"matches_played":12,"goals":8,"fitness_status":1,"estimated_wage":"€480,769 weekly"}}

3_crew/RealMadrid_Next_Best_Fit/output/research_report.json

@@ -0,0 +1 @@
+{"name":"Harry Kane","age":30,"height":188.0,"matches_played":12,"goals":8,"fitness_status":1,"estimated_wage":"€480,769 weekly"}

3_crew/RealMadrid_Next_Best_Fit/src/realmadridnextbestfit/config/agents.yaml

@@ -0,0 +1,46 @@
+trending_player_finder:
+  role: >
+    Football Scout specialized in {region}
+  goal: >
+    Identify a raw list of 5 trending, high-performing attacking football players currently playing in {region}.
+  backstory: >
+    You are an elite talent spotter with a deep network across {region}. You scan local sports media,
+    transfer rumors, and current match forms to find breakout players generating massive hype and who can potentially help Real Madrid win the UCL.
+    Your only job is to provide a clean list of names for the analyst to investigate.
+  llm: openai/gpt-4o-mini
+
+
+research_analyst:
+  role: >
+    Head of Football Analytics
+  goal: >
+    Gather deep, objective statistical and financial data for the 5 scouted attacking players.
+  backstory: >
+    You are a clinical data scientist who judges players purely by the numbers. For each player provided by the scout, you extract their match appearances, goals scored over the last 3 seasons, physical fitness history, injury-prone statistics, technical attributes, and current wage details. You provide a cold, unbiased statistical profile for each player without making tactical judgments.
+  llm: openai/gpt-4o-mini
+
+coach:
+  role: >
+    Head Coach of Real Madrid
+  goal: >
+    Evaluate the scouted players to select the absolute best tactical fit for the team's attack.
+  backstory: >
+    You are a legendary, tactically brilliant football manager. You analyze players based on how
+    they fit into Real Madrid's signature style (such as rapid counter-attacks, fluid movement,
+    and high-pressure matches). You review the Analyst's data to judge a player's style of play,
+    on-field attitude, big-game mentality, and tactical adaptability. Your job is to cut the list 
+    down and recommend the single best player who can immediately start in your starting eleven.
+  llm: openai/gpt-4o-mini
+
+manager:
+  role: >
+    President of Real Madrid
+  goal: >
+    Orchestrate the scouting workflow and give final boardroom approval based on strict financial and club policies.
+  backstory: >
+    You are a visionary, data-driven club President. While you respect the Head Coach's tactical desires, your job is to look at the long-term future and financial health of Real Madrid. You enforce three unyielding boardroom constraints: 
+    1) The player must be a maximum of 28 years old.
+    2) The player must already be proven at a big club.
+    3) The player must not require an unrealistic or irresponsible transfer fee.
+    You crictically review the crew's work and if you think the analysis or final chose player is not the
+    right one for some reason you find apt, pass on your feedback and send it back to crew for adjustments.

3_crew/RealMadrid_Next_Best_Fit/src/realmadridnextbestfit/config/tasks.yaml

@@ -0,0 +1,37 @@
+trending_player_task:
+  description: >
+    Conduct thorough research about attacking football players (strikers or wingers) 
+    currently playing in {region}. Make sure you find interesting, trending, 
+    and highly relevant targets given the current year is {current_year}.
+  expected_output: >
+    A clean list with exactly 5 bullet points of the most trending attacking players 
+    in {region}, detailing their current club and market buzz.
+  agent: trending_player_finder
+
+research_task:
+  description: >
+    Take the list of 5 players from the scouting task. Briefly find their basic data 
+    for ONLY the most recent season. Keep your research shallow and quick. 
+    Collect only: total goals, total matches played, current fitness status, and estimated wage. 
+    Do not write background stories or detailed histories.
+  expected_output: >
+    A single markdown table containing 5 rows (one per player) with exactly 5 columns: 
+    Player Name, Matches, Goals, Fitness, and Estimated Wage. 
+  agent: research_analyst
+  context :
+    - trending_player_task
+  output_file: output/research_report.json
+
+coach_task:
+  description: >
+    Review the compact statistics table provided by the research task. Evaluate the 5 players 
+    based on their basic metrics. Select the single best attacking option that fits 
+    Real Madrid's quick counter-attacking style. Do not write a long essay.
+  expected_output: >
+    A concise paragraph of exactly 3 to 4 sentences. State the selected player's name, 
+    how they fit your tactical formation, and a brief note on their current fitness risk.
+  agent: coach
+  context :
+    - research_task
+  output_file: output/final_player.md
+

3_crew/RealMadrid_Next_Best_Fit/src/realmadridnextbestfit/crew.py

@@ -0,0 +1,104 @@
+from typing import List
+
+from pydantic import BaseModel, Field
+
+from crewai import Agent, Crew, Process, Task
+from crewai.project import CrewBase, agent, crew, task
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai_tools import SerperDevTool
+from crewai.memory import Memory
+
+
+class TrendingPlayer(BaseModel):
+    name : str = Field(description="Name of the football player")
+    current_club : str =  Field(description="Name of the club the player plays for")
+
+class ScoutingOutput(BaseModel):
+    listOfPlayers : List[TrendingPlayer] = Field(description='list of 5 chosen players')
+
+class PlayersStats(BaseModel):
+    name : str =  Field(description='name of the player')
+    age : int = Field(description='age of the player')
+    height : float = Field(description='height of the player in cms')
+    matches_played : int = Field(description='total matches player by the player')
+    goals : int = Field(description='total goals scored by the player')
+    fitness_status : int = Field(description="Current injury status or physical fitness note.")
+    estimated_wage : str = Field(description='Estimated weekly or yearly wage.')
+
+class chosenPlayer(BaseModel):
+    name: str = Field(description='name of the player')
+    reason : str = Field(description= 'Reason for selecting this player amoung 4 others')
+    key_attruibutes : PlayersStats = Field(description='Players attributes')
+
+@CrewBase
+class Realmadridnextbestfit():
+    """Realmadridnextbestfit crew"""
+
+    agents_config = 'config/agents.yaml'
+    tasks_config = 'config/tasks.yaml'
+
+
+    @agent
+    def trending_player_finder(self) -> Agent:
+        return Agent(config=self.agents_config['trending_player_finder'], tools=[SerperDevTool()], verbose=True,
+                    memory=True)
+
+    @agent
+    def research_analyst(self) -> Agent:
+        return Agent(config=self.agents_config['research_analyst'], tools=[SerperDevTool()], verbose=True)
+
+    @agent
+    def coach(self) -> Agent:
+        return Agent(config=self.agents_config['coach'], verbose=True, memory=True )
+
+
+    @task
+    def trending_player_task(self) -> Task:
+        return Task(config=self.tasks_config['trending_player_task'],
+                    verbose=True,
+                    output_pydantic=ScoutingOutput)
+
+    @task
+    def research_task(self) -> Task:
+        return Task(config=self.tasks_config['research_task'],
+                    verbose=True,
+                    output_pydantic=PlayersStats)
+
+    @task
+    def coach_task(self) -> Task:
+        return Task(config=self.tasks_config['coach_task'],
+                    verbose=True,
+                    output_pydantic=chosenPlayer)
+
+
+    @crew
+    def crew(self) -> Crew:
+        """Creates the Realmadridnextbestfit crew"""
+
+        manager = Agent(config=self.agents_config['manager'],
+                       verbose=True,
+                       allow_delegation=True)
+
+        return Crew(
+            agents=self.agents, # Automatically created by the @agent decorator
+            tasks=self.tasks, # Automatically created by the @task decorator
+            process=Process.hierarchical,
+            verbose=True,
+            manager_agent=manager,
+
+            # Enables the unified short, long, and entity memory systems automatically
+            memory=True, 
+
+            # Customizes the global storage f`older directory (Replaces path="./memory/")
+            storage_handler=None, # Leave None to let CrewAI handle DB structures internally
+
+            # This configures your 'text-embedding-3-small' model globally for all memory types
+            embedder={
+                "provider": "openai",
+                "config": {
+                    "model": "text-embedding-3-small"
+                }
+            }
+        )
+            # process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
+

3_crew/RealMadrid_Next_Best_Fit/src/realmadridnextbestfit/main.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python
+import sys
+import warnings
+import os
+
+from datetime import datetime
+
+from realmadridnextbestfit.crew import Realmadridnextbestfit
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
+
+
+def run():
+    """
+    Run the crew.
+    """
+    inputs = {
+        'region' : 'Europe',
+        'current_year' : '2026'
+    }
+
+    result = Realmadridnextbestfit().crew().kickoff(inputs=inputs)
+
+
+    print(result.raw)
+
+if __name__ == '__main__':
+    run()

3_crew/RealMadrid_Next_Best_Fit/src/realmadridnextbestfit/tools/custom_tool.py

@@ -0,0 +1,19 @@
+from crewai.tools import BaseTool
+from typing import Type
+from pydantic import BaseModel, Field
+
+
+class MyCustomToolInput(BaseModel):
+    """Input schema for MyCustomTool."""
+    argument: str = Field(..., description="Description of the argument.")
+
+class MyCustomTool(BaseTool):
+    name: str = "Name of my tool"
+    description: str = (
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
+    args_schema: Type[BaseModel] = MyCustomToolInput
+
+    def _run(self, argument: str) -> str:
+        # Implementation goes here
+        return "this is an example of a tool output, ignore it and move along."