add support for curiosity_catalyst

agents/curiosity_catalyst.py

@@ -1,10 +1,12 @@
 from crewai import Agent
 from llms.gemini import gemini
+from tools.scrape_website import scrape_tool
 
 curiosity_catalyst = Agent(
   role="Curiosity Catalyst",
   goal="To pique the user's curiosity to read the article.",
   verbose=True,
+  tools=[scrape_tool],
   backstory=(
     "As a Curiosity Catalyst, you know exactly how to pique the user's curiosity "
     "for reading the articles."

agents/learning_curator.py

@@ -5,7 +5,7 @@ from llms.gemini import gemini
 
 learning_curator = Agent(
     role="Personal Learning Curator",
-    goal="Make sure you present an article on the topics that the user is interested in, "
+    goal="Make sure you present 5 articles on the topics that the user is interested in, "
     "the article should provide the user with an incremental learning.",
     verbose=True,
     backstory=(

agents/learning_profiler.py

@@ -4,7 +4,7 @@ from llms.gemini import gemini
 
 learning_profiler = Agent(
     role="Personal Learning Profiler",
-    goal="Make sure to create an excellent learning profile of the user.",
+    goal="Make sure to create an excellent learning profile of the user based on his interests and previous reading history.",
     verbose=True,
     tools=[scrape_tool],
     backstory=(

app.py

@@ -5,11 +5,18 @@ from crew.article_suggestion import article_recommendation_crew
 
 result = article_recommendation_crew.kickoff(inputs={
   "interests": "GenAI, Architecture, Agentic Programming",
-  "previous_article_insights": "Agentic Design Patterns (https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/)\n"
+  "previous_article_insights":
+  "Agentic Design Patterns (https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/)\n"
   "Reflection: The LLM examines its own work to come up with ways to improve it. "
   "Tool Use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data. "
   "Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal "
-  "Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would."
+  "Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would.\n\n"
+  "GenAI Multi-Agent Systems (https://thenewstack.io/genai-multi-agent-systems-a-secret-weapon-for-tech-teams/)\n"
+  "Multi-agent systems go beyond the task-oriented roles to truly super-charge development and strategy teams. "
+  "Successful multi-agent systems act as a “digital twin” for your development team. "
+  "Different Approaches: 1. Centralized, with one agent in the center that collects and assimilates all the other outputs. "
+  "2. Distributed, where there is no central controller and the agents coordinate directly with one another in an “agent swarm. "
+  "3. Hierarchical, where agents are organized in teams or hierarchical layers.\n"
 })
 
 print(result)

crew/article_suggestion.py

@@ -2,14 +2,17 @@ from crewai import Crew
 from agents.learning_profiler import learning_profiler
 from agents.learning_curator import learning_curator
 from agents.article_evaluator import article_evaluator
+from agents.curiosity_catalyst import curiosity_catalyst
 from tasks.create_learning_profile import learning_profile_task
 from tasks.new_article_suggestion import article_suggestion_task
 from tasks.evaluate_articles import evaluation_task
+from tasks.create_article_pitch import article_pitch_task
 from llms.gemini import gemini
 
 article_recommendation_crew = Crew(
-    agents=[learning_profiler, learning_curator, article_evaluator],
-    tasks=[learning_profile_task, article_suggestion_task, evaluation_task],
+    agents=[learning_profiler, learning_curator, article_evaluator, curiosity_catalyst],
+    tasks=[learning_profile_task, article_suggestion_task, evaluation_task, article_pitch_task],
     verbose=True,
+    memory=True,
     # manager_llm=gemini
 )

tasks/create_article_pitch.py

@@ -0,0 +1,20 @@
+from crewai import Task
+from agents.curiosity_catalyst import curiosity_catalyst
+from tools.scrape_website import scrape_tool
+from utils.recommended_article import RecommendedArticle
+
+article_pitch_task = Task(
+  description=(
+    "Create a pitch for each of the articles that have passed evaluation. "
+    "Craft the pitch so to that it teases the article's most intriguing aspects, "
+    "by posing questions that the article might answer or "
+    "highlighting surprising facts to pique the user's curiosity "
+    " to read the article for incremental learning."
+  ),
+  expected_output=(
+    "Json array of all the artilces that have passed evaluation phase. Each article should have the following keys title, article_url, pitch and reason behind the recommedation"
+  ),
+  # output_json=RecommendedArticle,
+  tools=[scrape_tool],
+  agent=curiosity_catalyst
+)

tasks/new_article_suggestion.py

@@ -3,7 +3,7 @@ from agents.learning_curator import learning_curator
 
 article_suggestion_task = Task(
   description=(
-    "Suggest 4 articles to the user based on his learning profile. "
+    "Suggest 5 recent articles (i.e published in last 10 days ) to the user based on his learning profile. "
     "The articles should provide incremental learning to the user."
   ),
   expected_output=(

utils/recommended_article.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel
+
+class RecommendedArticle(BaseModel):
+  title: str
+  url: str
+  pitch: str
+  reason_for_recommendation: str