Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
What is this?
Less
More

Memberships

AI Developer Accelerator

10.8k members โ€ข Free

5 contributions to AI Developer Accelerator
Chain VS State Machines
Hello everyone, I am reading about agentic RAG and have been learning more about LangGraph. So far I saw that LangGraph works with state machines that allows loops to get better retrieval than chains (Apparently). I want some insights on what is the difference between this and allow delegating tasks in CrewAI. I could create an agent in crewAI that is in charge of reflection and re assigning a task (looping over). Thank you in advance for participating! Here is an article that explains more Agentic RAG with LangGraph https://blog.langchain.dev/agentic-rag-with-langgraph/
GPT 4.5? GPT 5?
Any thoughts on this guys? They say it might be a vnew version of GPT that is more powerful and accurate.
Using output of an agent as an input for a task in CrewAI
Hey guys, Do you know how can we provide an input variable for a task that has to be figured out first by the previous agent? For example, let's say the first agent will have to search for the URL of the Twitter profile of the CEO of a company given by the user. Then the second agent must use the URL found by the first agent as an input to use a scraper tool, analyze the last 20 tweets and summarize its findings. I am confused on how you can explicitly add the url parameter to the task to use it as an input.
0 likes โ€ข Apr '24
I will try this approach! Thank you!
0 likes โ€ข Apr '24
@Tom Welsh I am having trouble calling the output. It shows an error that I think is because according to crewAI documentation: "In crewAI, the output of one task is automatically relayed into the next one, but you can specifically define what tasks' output, including multiple should be used as context for another task. This is useful when you have a task that depends on the output of another task that is not performed immediately after it. This is done through the context attribute of the task." https://docs.crewai.com/core-concepts/Tasks/#referring-to-other-tasks Therefore, I think the context section should be context={search_task} instead of context={'twitter_url': search_task.output}
what do you think of this agent framework?
I've stumble upon this https://github.com/VRSEN/agency-swarm the creator claims that it give you more control than other frameworks like crewai would like to know your thought and if some of you have tried it
0 likes โ€ข Apr '24
@Vinod Tharian Why is this highlighted as a drawback? What does Agency swarm rely on to do the work?
Recommend scraper tool and instagram profile image analysis tool
I am setting up a crew that is able to search the web for news (I use Serper) about a company and information about their important executives. Then I want to fetch for the social media profiles of these executives and then gather their latest tweets, Instagram feed, public appearances, podcasts episodes etc. Based on the context I want to know: 1 - What tools or APIs do you recommend to scrape tweets besides the Twitter API (Any examples I can check? Any scraper I can test with a free version will also be helpful) 2 - If I want to get insights about the Instagram feed of a given user, which approach would you suggest? Should I use GPT Vision? (Any examples are appreciated)
1
0
1-5 of 5
Daniel Avila
1
3points to level up
@daniel-avila-9011
Prompt engineer. Some coding experience. Excited about process automation with AI

Active 488d ago
Joined Apr 26, 2024
Powered by