Langflow

About

Langflow is a new visual framework for building multi-agent and RAG applications. It is open-source, Python-powered, fully customizable, and LLM and vector store agnostic.

Its intuitive interface allows for easy manipulation of AI building blocks, enabling developers to quickly prototype and turn their ideas into powerful, real-world solutions.

How to Use LAPLAS API via Langflow

A user of the Langflow framework can create a working AI pipeline (a flow) by simply adding visual components, connecting their inputs and outputs in the required order, and setting various available parameters in each component.

At the center of such a flow is one or more sequential model components that generate text using LLMs. Choose Models > LAPLAS in the sidebar, then click the "+" button or simply drag and drop the model element onto the work area. After that, connect it to your input and output elements:

The component at the center creates a chat model instance powered by LAPLAS API.

Inputs

Only 1-2 key parameters are usually displayed directly on the model component body. To configure most parameters, you need to click on the model element and then click the Controls button that appears above the model component.

Name	Type	Description
max_tokens	Integer	The maximum number of tokens to generate. Set to 0 for unlimited tokens. Range: 0-128000.
model_kwargs	Dictionary	Additional keyword arguments for the model.
model_name	String	The name of the LAPLAS model to use. Options are predefined in LAPLAS_CHAT_MODELS.
laplas_api_base	String	The base URL of the LAPLAS API. Defaults to https://api.apilaplas.com.
api_key	SecretString	The LAPLAS API Key to use for the model.
temperature	Float	Controls randomness in the output. Default: 0.1.
seed	Integer	Controls reproducibility of the job.

Outputs

Name	Type	Description
text	String	Chat model response.
model	LanguageModel	An instance of ChatOpenAI configured with the specified parameters.

For further information about the framework, please check the official Langflow documentation.