Hey guys, can someone tell me what is going on in these lines of code? "book_outline": [ chapter_outline.model_dump_json() for chapter_outline in self.state.book_outline ] Here is the original section from the BookFlow (crewai crash course) async def write_chapters(self): print("Writing Book Chapters") tasks = [] async def write_single_chapter(chapter_outline): output = ( WriteBookChapterCrew() .crew() .kickoff( inputs={ "goal": self.state.goal, "topic": self.state.topic, "chapter_title": chapter_outline.title, "chapter_description": chapter_outline.description, "book_outline": [ chapter_outline.model_dump_json() for chapter_outline in self.state.book_outline ], } ) ) title = output["title"] content = output["content"] chapter = Chapter(title=title, content=content) return chapter for chapter_outline in self.state.book_outline: print(f"Writing Chapter: {chapter_outline.title}") print(f"Description: {chapter_outline.description}") # Schedule each chapter writing task task = asyncio.create_task(write_single_chapter(chapter_outline)) tasks.append(task)

What is the cheapest LLM you have found to do research (not creative) tasks? This agent would need to use tools like web searching and web scraping and be able to follow directions well. I have tried gpt-4o-mini and it does not seem to follow directions very well and does not seem to want to scrape websites although it will do an ok job of searching the web with serper. Gpt-4o does a better job, but is more expensive. What is your experience?

Hey everyone! Now there’s a link that contains the complete CrewAI documentation in a .txt file, so you can feed it into any LLM or agent, or even add it using ‘@‘ in cursor. https://docs.crewai.com/llms-full.txt This should make things way easier. Same goes for Anthropic/Claude: http://docs.anthropic.com/llms-full.txt

Hi guys. I'm a medium developer, but I can mostly get things to work the way I need in the end. However, the bane of my existence is the "production" side of things. Installing dependencies and all the stuff that makes my mind numb with dullness. Which begs the question: Does any one have a good guide or suggestion for deploying a crew to some place where it can be reached as an API (and no, CrewAI's on setup did nothing for me). 🙏

I've got something working fairly well. It takes in the email address of the interviewer, a file path to the interviewee's resume, and a URL to the job description. The results are a MD file with talking points that try to align information from interviewee's resume with the job description, taking into account information found via the interviewer's email address. I think I'll need to update the code to use a custom tool for using LinkedIn's API as the results of using ScrapeWebsiteTool() when fetching LinkedIn data is not what I was expecting. In any case, an example of the talking points result is attached. I'll probably clean it up a bit more and post it to my github in case others find it useful.