This is the biggest update we've had in a while. Flowise v2.0 and Flowise Cloud With v2.0, we've introduced Sequential Agentic Workflow. The new agentic workflow allows you to: ⛓️Chain agents together 🔁Loopback mechanisms 🙋Human-in-the-Loop 🔶Conditional branches Different from existing chatflow which relies LLM to act on its own,... now you have greater control over the flow. Huge shoutout to team for the exceptional LangGraph framework, which made all of this possible! We're also excited to announce the closed beta release of Flowise Cloud! In addition to all existing features, cloud version also includes Evals and Logging. Join the waitlist here: Here's 7 examples to help you get started with agentic workflow:show more

1/7 Agentic RAG A self-improving RAG that checks the relevance of retrieved documents to the user's question. If the documents are found to be irrelevant, the agent will rephrase the question and loop back to retrieve a new set of documents until they pass the relevance score.

2/7 Human in the Loop Enable the agent to pause at specific stages and request human approval before continuing, which is useful for preventing the agent from autonomously executing sensitive operations.

3/7 Plan & Execute Similar to BabyAGI and AutoGPT, agent will first come up with a multi-step plan, and then go through that plan one item at a time. After accomplishing a particular task, plan is then revisited and modified as appropriate.

4/7 Support Routing Assistant A customer support assistant that can route to specific agent teams to resolve user queries. For this example: frontline support can engage in conversations with users or direct them to the billing or technical team for further assistance.

5/7 Reflection Agent Reflection agent is able to review its past actions and use the information for downstream tasks. In this scenario, a writer creates an essay, which is then graded by a teacher. This loop continues for several iterations.

6/7 Fan out, Fan in One of the cool things we can do is create branches for parallel execution, and be able to merge it back into one node

7/7 Hierarchical Teams Develop multiple agents from the ground up. You can also create sub-teams with top-level supervisor, complemented by mid-level supervisors, forming a hierarchical multi agents!

All the examples above are available as templates. These are just a few examples of what can be accomplished using this new agentic workflow approach. We're eager to see what you create with it! Release note: Docs:

For Flowise Cloud, there are built-in Evaluations and Logging functionalities. Tokens, costs, and performance of LLMs can be traced, and also comes with versioning! Hop on to our waitlist We're granting access to to users in batches starting today

This is a massive update! Sequential agents are going to be a game changer. I look forward to creating detailed tutorials on this.