About DataStax Langflow
|
This release contains access to DataStax Langflow as a Tech Preview. The Tech Preview is intended for you to view the capabilities of DataStax Langflow, and to provide your feedback to the product team. You are permitted to use the information only for evaluation purposes and not for use in a production environment. IBM provides the information without obligation of support and "as is" without warranty of any kind. |
DataStax Langflow is a fully managed, cloud-native platform that brings the power of Langflow’s visual flow builder to the cloud. Built on the same open-source foundation as Langflow OSS, it offers:
-
Visual Flow Builder: Create complex GenAI applications through an intuitive drag-and-drop interface.
-
Enterprise-Grade Infrastructure: Scalable, secure, and reliable cloud platform.
-
Flexible Integration: Connect to any vector database, embedding model, or LLM.
-
No Infrastructure Management: Focus on building applications, not managing servers.
Ready to build your first GenAI application? Create a DataStax Langflow account in the Astra Portal, open the quickstart guide, and be up and running in minutes.
After completing the quickstart, see the Langflow OSS documentation to continue learning about Langflow flows, components, and agents.
Differences between DataStax Langflow and Langflow OSS
This documentation covers features specific to DataStax Langflow. DataStax Langflow includes most of the core Langflow OSS functionality, but there are important differences:
- MCP isn’t available
-
MCP servers and clients aren’t available in DataStax Langflow. To use MCP servers or clients, you must use Langflow OSS.
- Some components aren’t available
-
Some Langflow OSS components aren’t available in DataStax Langflow, such as the following:
-
FAISS
-
Ollama
-
LM Studio
-
Git Loader
-
Qdrant
-
All local-storage database components, such as ChromaDB. DataStax Langflow only supports cloud-based databases, such as Astra DB.
-
- DataStax Dotenv values are ephemeral
-
The DataStax Dotenv component can load values from an
.envfile, but these files are stored on ephemeral disks that don’t persist between flow runs, and they cannot be shared across users or executions. Use global variables for persistent configuration. - Authentication methods
-
DataStax Langflow uses JWT (JSON Web Token) authentication, wheras Langflow OSS uses API key-based authentication.
This means that authentication workflows and API integration patterns differ between DataStax Langflow and Langflow OSS, such as when calling the
/runand/webhookendpoints. - Logs and monitoring
-
In DataStax Langflow, logs are managed by the platform and not directly accessible to users. For comprehensive logging capabilities, consider using Langflow OSS where you have full control over log storage and access.
- Shareable playground is not available
-
The shareable playground is not available in DataStax Langflow. Anyone in your Astra DB organization can access your playground. If you have the correct permissions, you can add a user to your organization. To use the shareable playground, use Langflow OSS.
- Embedded chat widget is not available
-
The embedded chat widget is not available in DataStax Langflow. To embed your flow in a chat widget, use Langflow OSS.
