Added support for research articles suggestion

crew/research_article_suggester.py

@@ -0,0 +1,150 @@
+from crewai import Agent, Task, Crew
+from langchain_openai import ChatOpenAI
+from tavily import TavilyClient
+import os
+import json
+from pydantic import BaseModel, Field
+from crewai.tasks.task_output import TaskOutput
+from datetime import datetime, timedelta
+
+from tools.scrape_website import scrape_tool
+
+MAX_RESULTS = 5
+AGE_OF_RESEARCH_PAPER = 60
+
+class RecentArticleSuggester:
+    """
+    Suggests recent research articles based on a given topic.
+    """
+
+    def __init__(self):
+        self.tavily_client = TavilyClient(api_key=os.getenv("TAVILY_API_KEY"))
+
+    def kickoff(self, inputs={}):
+        self.topic = inputs["topic"]
+        suggested_research_papers = self._suggest_research_papers()
+        return suggested_research_papers
+
+    def _suggest_research_papers(self):
+        query = f"research papers on {self.topic} published in the last week"
+        results = self.tavily_client.search(query, max_results=MAX_RESULTS)['results']
+        print("Search Results: ", results)
+        pitch_crew = self._create_pitch_crew()
+        research_paper_suggestions = []
+        for result in results:
+            try:
+                info = pitch_crew.kickoff(inputs={
+                    "title": result["title"],
+                    "url": result["url"],
+                    "content": result["content"]
+                })
+                research_paper_suggestions = research_paper_suggestions + \
+                    [info]
+            except BaseException as e:
+                print(f"Error processing article '{result['title']}': {e}")
+
+        return research_paper_suggestions
+
+    def _create_pitch_crew(self):
+        information_gatherer = Agent(
+            role="Research Paper Information Retriever",
+            goal="Gather required information for the given research papers.",
+            verbose=True,
+            backstory=(
+                "You are an expert in gathering required details "
+                "about the given research paper."
+            ),
+            llm=ChatOpenAI(model="gpt-3.5-turbo", temperature=0.2),
+            tools=[scrape_tool],
+        )
+
+        def evaluator(output: TaskOutput):
+            article_info = json.loads(output.exported_output)
+            try:
+                date_obj = datetime.strptime(
+                    article_info['published_on'], "%d/%m/%Y")
+
+                # Calculate the date that was 14 days ago from today
+                start_date = datetime.now() - timedelta(days=AGE_OF_RESEARCH_PAPER)
+
+                # Compare if the input date is older
+                if date_obj < start_date:
+                    raise BaseException(f"{date_obj} Older than given timeframe {start_date}")
+
+            except ValueError:
+                print("Invalid date format. Please use dd/mm/yyyy.")
+                return False
+
+        information_gathering_task = Task(
+            description=(
+                "Here is the information of a research paper: title {title}, "
+                "url: {url} and content: {content}.\n"
+                "Gather following information about the research paper: "
+                "1. When was the research paper published and present it in dd/mm/yyyy format. "
+                "2. Who is the author of the research paper. "
+            ),
+            expected_output=(
+                "Following details of the research paper: title, url, "
+                "content/summary, date it was published and author."
+            ),
+            agent=information_gatherer,
+            async_exection=False,
+            output_json=ResearchPaper,
+            callback=evaluator,
+        )
+
+        pitcher = Agent(
+            role="Curiosity Catalyst",
+            goal="To pique the user's curiosity to read the research paper.",
+            verbose=True,
+            backstory=(
+                "As a Curiosity Catalyst, you know exactly how to pique the user's curiosity "
+                "to read the research paper."
+            ),
+            llm=ChatOpenAI(model="gpt-3.5-turbo", temperature=0.2),
+            tools=[scrape_tool],
+        )
+
+        create_pitch = Task(
+            description=(
+                "Craft the pitch so to that it teases the research paper's most intriguing aspects, "
+                "by posing questions that the research paper might answer or "
+                "highlighting surprising facts to pique the user's curiosity "
+                " to read the research paper so that he is up-to-date with latest research."
+            ),
+            expected_output=(
+                "All the details of the research paper along with the pitch."
+            ),
+            tools=[scrape_tool],
+            agent=pitcher,
+            context=[information_gathering_task],
+            output_json=ResearchPaperWithPitch,
+        )
+
+        crew = Crew(
+            agents=[information_gatherer, pitcher],
+            tasks=[information_gathering_task, create_pitch],
+            verbose=True,
+            max_rpm=4,
+        )
+
+        return crew
+
+
+class ResearchPaper(BaseModel):
+    title: str
+    url: str
+    summary: str
+    author: str = Field(description="author of the article")
+    published_on: str = Field(
+        description="Date the article was publised on in foramt dd/mm/yyyy")
+
+
+class ResearchPaperWithPitch(BaseModel):
+    title: str
+    url: str
+    summary: str
+    author: str = Field(description="author of the article")
+    published_on: str = Field(
+        description="Date the article was publised on in foramt dd/mm/yyyy")
+    pitch: str

requirements.txt

@@ -5,3 +5,4 @@ langchain_community
 langchain_google_genai
 langchain_openai
 streamlit
+tavily-python

test.py

@@ -0,0 +1,5 @@
+from crew.research_article_suggester import RecentArticleSuggester
+
+suggester = RecentArticleSuggester()
+results = suggester.kickoff(inputs={"topic": "GenAI"})
+print(results)