Langflow

Langflow is a robust platform designed for creating and deploying AI-driven agents and workflows. It offers developers an intuitive visual authoring interface along with an integrated API server that transforms each agent into an API endpoint, enabling seamless integration into applications across various frameworks and stacks. Langflow is equipped with essential features and supports all major large language models (LLMs), vector databases, and an expanding range of AI tools.

I’ll translate the provided text from Russian to English:

1. Obtain an SSH key pair to connect to the virtual machine (VM).

2. Create a VM from a public image. In the Image/boot disk selection section, go to the Cloud Marketplace tab and select Langflow. In the Access section:

   • in the Login field, enter the username;

   • in the SSH key field, paste the contents of the file with the public SSH key.

3. Make sure that the selected Security Group allows incoming ports TCP/22 and TCP/7860.

4. Click Create VM and wait for the deployment process to complete.

5. To connect to the web interface, open the following URL in a web browser:

   http://<virtual machine address>:7860
   

6. To get the password for login, connect to the VM via SSH and execute the following command:

   sudo cat /root/default_passwords.txt
   

• Visual Builder. Quickly start and iterate on projects with an easy-to-use interface.

• Code Access. Developers can modify any component using Python for greater customization.

• Playground. Test and refine flows instantly with detailed step-by-step control.

• Multi-agent Orchestration. Manage and retrieve conversations across multiple agents.

• Deployment Options. Deploy as an API or export as JSON for use in Python applications.

• Observability. Integrate with LangSmith, LangFuse, and other tools for enhanced monitoring.

• Enterprise-Level Security and Scalability. Designed to meet the needs of large organizations.

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.