Skip to content
Nappai Documentation

Runnable Data Batch

Runnable Data Batch is a component in the Nappai automation system that processes lists of data by executing specific operations known as “runnables.” This component is essential for managing data batches and applying predefined operations to each data item, making it a powerful tool for automating data processing tasks.

Relationship with BaseRunnableDataBatchComponent

Runnable Data Batch is built on top of the BaseRunnableDataBatchComponent, inheriting its functionalities. This relationship allows it to leverage the robust data handling and processing capabilities provided by the base component, ensuring efficient execution of runnables on data batches.

Inputs

  • Data List: A list of data items that need to be processed. This input determines which data will be subjected to the runnable operations.

Outputs

Runnable Data Batch produces results related to the execution of runnables on the data batch. These outputs may include execution results or processing states, which can be used to inform subsequent steps in your workflow.

Usage Example

Imagine you have a list of customer data that needs to be processed to extract specific insights. By using the Runnable Data Batch component, you can automate the execution of predefined operations on each customer data entry, streamlining your data analysis process.

Templates

Currently, there are no specific templates where this component is pre-configured. However, it can be integrated into custom workflows within the Nappai system.

  • libSQLRetrieverTool: Tool for interacting with libSQL Retriever.
  • Embedding Similarity: Computes similarity between two embedding vectors.
  • SQLite: Interacts with SQLite databases.
  • Tool Calling Agent: Uses tools to perform tasks.
  • OpenAI Tools Agent: Utilizes OpenAI tools for various operations.
  • Cassandra: Vector store with search capabilities.
  • Supabase: Vector store with search capabilities.
  • Milvus: Vector store with search capabilities.
  • MongoDB Atlas: Vector store with search capabilities.
  • Pinecone: Vector store with search capabilities.
  • Qdrant: Vector store with search capabilities.
  • Astra DB: Vector store with search capabilities.
  • PGVector: Vector store with search capabilities.
  • Redis: Vector store with search capabilities.
  • Vectara: Vector store with search capabilities.
  • Weaviate: Vector store with search capabilities.
  • Upstash: Vector store with search capabilities.
  • Couchbase: Vector store with search capabilities.
  • FAISS: Vector store with search capabilities.
  • Deeplake Database: Vector store with search capabilities.
  • Chroma DB: Vector store with search capabilities.

Tips and Best Practices

  • Ensure your data list is well-structured to maximize the efficiency of runnable operations.
  • Familiarize yourself with the operations defined as runnables to better understand the processing outcomes.

Security Considerations

When processing sensitive data, ensure that appropriate data protection measures are in place to prevent unauthorized access or data breaches. Always comply with relevant data privacy regulations.