Langflow

Langflow is a powerful building and deployment tool for AI agents and workflows. Langflow offers with a visual no-code builder and a built-in API server. API access to agents simplifies their integration into applications on any framework or stack. Langflow comes with a comprehensive feature set for compatibility with major LLMs, vector databases, and other AI tools.

1. Create a cloud network and a subnet to host the virtual machine (VM).

2. Create a security group in the cloud network and configure the rules as follows:

   Traffic direction	Description	Port range	Protocol	Source / Destination	CIDR blocks
   Ingress	Langflow	7860	TCP	CIDR	0.0.0.0/0
   Ingress	SSH	22	TCP	CIDR	0.0.0.0/0
   Egress	Any Egress	0-65535	Any	CIDR	0.0.0.0/0

3. Get an SSH key pair for connection to the VM.

4. In the Marketplace, find Langflow and click Create VM.

   1. Under Network settings, specify the cloud network, subnet, and security group you created earlier.

   2. Under Access, specify the username and public SSH key for connection to the VM.

   3. Complete setting up your VM and click Create VM.

      Wait for the VM to be created and the application to be installed: this may take up to 10 minutes.

5. Get a username and password to log in to the app:

   1. Learn the VM’s public IP address.

   2. Connect to the VM over SSH. Use the username you set when creating the VM and the private SSH key you created earlier.

   3. Run this command on the VM:

      sudo cat /root/default_passwords.txt
      

      Result:

      admin
      AbcdfA2HzJt6********
      

6. To connect to Langflow’s web UI, open this URL in your browser:

   http://<VM_public_IP_address>:7860
   

   In the window that opens, enter the username and password you got earlier.

• Visual builder. Quick start into creating projects with a user-friendly interface.
• Customization. Developers can customize any component using Python.
• Playground. Instant testing and adaptation of configured processes with detailed step-by-step control.
• MAS (multi-agent system) orchestration. Manages and retrieves conversations between multiple agents.
• API deployment or JSON export for use in Python apps.
• Observability. Integration with LangSmith, LangFuse, and other tools for enhanced monitoring.
• Security and scalability. Designed to cater to the needs of large businesses.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the relevant response times depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms and conditions here.