FlowiseAI (YC S23)

Today, we're supporting MCP in Flowise! There has been a lot of discussion about MCP lately. From our perspective, MCP is nothing fancy - just tools with third-party APIs or functions, wrapped under a unified protocol that can be consumed by client LLM applications. In fact, we've had something similar for a long time with Langchain Tools. However, MCP offers two key benefits: - Its open protocol isn’t limited to specific frameworks - Client applications (like us, Cursor, Windsurf, etc) can offload the burden of maintaining and updating these tools to the official MCP creators These MCP servers (a.k.a. tools) are provided to the LLM, allowing it to decide when and how to use them. This is sometimes referred to as an "agentic" approach, as opposed to a "deterministic" approach like Zapier, where each step must be explicitly mapped out. In real-world scenarios, you might find yourself needing both approaches depending on the use case. It's still early days, and it will take time for the community to establish standards. We're excited to see where this goes! More about MCP: https://lnkd.in/grPMihv7

With all these new models dropping, that means... We are having a new release too! v2.2.6: ? New models added: - OpenAI: gpt 4.5 preview - Anthropic: claude sonnet 3.7, also supporting Vertex and Bedrock - Google: gemini 2.0 flash ?? Post Processing Add custom function like redaction, moderation, replacement, and etc, before sending the final output response. ?? New Analytic Arize AI is a leading company in AI Observability and Evaluation. Excited to collaborate with their team and integrate Arize AX and Phoenix, into Flowise! ?? Tavily Tool Tavily Search API is a search engine built specifically for AI agents, delivering real-time, accurate, and factual results at speed. You can now use it as a tool for agent as the search capability! ?? There's lots of small improvements and bugfixes as well, thank you to all contributors! Release note: https://lnkd.in/enpbv97e

A história do Dr. Zequinha. O cardiologista Dr. José Luiz Ferreira dos Santos, mais conhecido como Dr. Zequinha, foi aluno da nossa última Imers?o de IA. Ele tem 72 anos e é médico na cidade de Leme, no interior de S?o Paulo. Na foto abaixo, Dr. Zequinha está criando seus próprios "Agentes de IA", que s?o algoritmos treinados para executar tarefas específicas, gerando mais eficiência e produtividade nas tarefas diárias, repetitivas. Dr. Zequinha chamou a aten??o n?o pela profiss?o ou idade. Mas pela sua consciência a respeito da requalifica??o profissional. Ele sabe que, por maior que tenha sido o sucesso que teve até aqui, agora vai ser diferente. A inteligência artificial é uma ferramenta muito poderosa, que potencializa a inteligência humana. Enxergar dessa maneira faz com que as barreiras da idade, da localiza??o e do conhecimento caiam por terra. Todos nós deveríamos seguir o exemplo do Dr. Zequinha. Aprender sobre IA, n?o se acomodar com o sucesso, viver o aprendizado contínuo e ter coragem para enfrentar os desafios - e oportunidades - que vir?o pela frente. N?o há limites para quem quer aprender sobre o uso da IA. Aliás, quanto mais experiência você tem, melhor o contexto que você entrega para o algoritmo. Ent?o, vá em frente, comece agora. ? VENHA PARA minha nova newsletter e acesse a conteúdos inéditos e análises exclusivas: juniorborneli.substack.com. é gratuito. #startse #nowledge #agora #novaeconomia

OpenAI released O3 Mini few hours ago, now available to be used in Flowise! What we love about O3 Mini is its ability to use function calling. With WolframAlpha and the Code Interpreter, O3 Mini can solve math problems that GPT-4 failed to solve. Technical paper: https://lnkd.in/e9E9vV_v

2 days ago DeepSeek AI released R1 open source models with performance on par with OpenAI o1 reasoning models. Now supported on Flowise v2.2.4! ?? DeepSeek R1 (hosted and ollama) ?? Rerank-2 by VoyageAI ??? Logs streaming to S3 ?? AWS Secret Manager for encrypt/decrypt It's mind-blowing to have the 7B model (DeepSeek-R1) perform on par with O1-Mini

At CES 2025, NVIDIA announced foundation models (offered as NIM microservices) running locally on RTX AI PCs. We’re proud to partner with NVIDIA AI to integrate NIM into Flowise, enabling developers to build AI applications using local LLMs. Press release: https://lnkd.in/ep8DpXfp Quick guide on how to use NVIDIA NIM on Flowise: https://lnkd.in/eumU2G7Y

They say you shouldn't push a new release right before the holidays... So, here we go - v2.2.3 of Flowise ?? ?? Graph RAG using Neo4j GraphRAG is a technique that enhances RAG with knowledge graphs. Using Neo4J, we can easily create these graphs, and enabling structured and semi-structured information into the retrieval process. ??? Groq Whisper, Azure Cognitive Speech to Text More Speech to Text models added! ? Composio Tools With Composio, users can connect Agents built in Flowise with over 250+ tools such as Jira, Github, Hubspot, Salesforce and many more! ?? Deepseek Chat New chat model to be used within Flowise! ?? Epub document source Epub is an e-book file format that uses the ".epub" file extension. Now available as part of document sources There are also many small improvements and bug fixes. Check them out here: https://lnkd.in/eVh8YN2e Hopefully, this makes for a good enough Christmas present ??

Excited to partner up with IBM to have Watsonx integration in Flowise ?? You can use IBM's foundational models, such as Granite, alongside other open-source models like Llama and Mistral. This marks a major step toward bringing AI Agent orchestration to enterprise settings. Step by step guide: https://lnkd.in/em8YA7U3

Single Sign On (SSO) is now available on Flowise Enterprise! This feature allows using a single identity provider (IdP), starting with Microsoft Entra ID https://lnkd.in/eUmKmt4t

Stripe recently released new SDK built for AI agents: https://lnkd.in/euy3dXFb The new era of financial agentic workflows is here. Here's an example workflow by one of our users in manufacturing industry: 1.) Upload invoice images 2.) LLM calculates total bill 3.) Payment link created with the calculated amount Excited to see what can we build with this!