This is because your location does not support Gemini API
@flowiseai
-
Installing Flowise: Open Source Version Management Guide
By
–
Always open source, try installing a specific version like npm install -g flowise@2.2.7
-
NVIDIA Partners to Optimize Local AI Models on RTX PCs
By
–
Super stoked to be an official partner of @nvidia
, enabling users with RTX AI PCs to use local models like Deepseek, Llama, Mistral via NIM microservices on Flowise. They are optimized for NVIDIA GPUs, boosting inference performance up to 2x Read more: -
Setting Up Queue Mode in Flowise AI for Background Jobs
By
–
To set up Queue mode, it's pretty straightforward. pnpm run start & pnpm run start-worker This runs the main server and workers separately, enabling background job processing. Step-by-step guide: https://
docs.flowiseai.com/configuration/
running-flowise-using-queue
… Try it out and let us know your thoughts! -
BullMQ Dashboard: Job Queue Monitoring and Observability
By
–
5) Better Observability BullMQ provides a built-in dashboard where you can: View queued, active, completed, and failed jobs Retry failed jobs manually Track job execution time & delays
-
Job Queue: Offloading Tasks to Background Workers
By
–
3) Why use Job Queue? Frees the main server by offloading long tasks to background workers. Scales easily by adding or removing workers based on load. Reliability – jobs stay in Redis, allowing recovery from crashes or restarts.
-
Scaling Workers for High Throughput Systems
By
–
4) Scaling Workers for High Throughput As demand increases, scaling is easy: – Each worker processes jobs independently, so you can add more workers without modifying the main server. – Workers can run on separate machines, containers, or pods for horizontal scaling.
-
Distributed Task Queue Architecture with Redis and Workers
By
–
1) The Core Architecture At a high level, we have: Main Server: Handles API requests and database operations. Redis (BullMQ): A task queue for processing background jobs. Workers: Dedicated instances listening to the queue and executing tasks.
-
Scaling AI Apps: Asynchronous Task Queues and Distributed Workers
By
–
Apps like ChatGPT, Claude, and Gemini handle millions of requests per second But how do they do it ? The secret lies in asynchronous task queues, distributed workers, and scalable infrastructure. In Flowise you can achieve that using Queue mode. Here's how it works:
-
MCP Package Custom Node Configuration for Users
By
–
No we don't need to host it anywhere, it's just an index.js file from the MCP package. We are also adding a custom MCP node which let users specify their own MCP configuration