Dynamic columns let you run prompts, code execution, retrievals, and more on your datasets
Most LLM applications are a lot more complex than just prompts.
For example, a RAG-based chatbot might have the following setup.
With Athina, you can build and prototype chains like this dynamically in a spreadsheet-like UI.
You can also build these pipelines in Flows.
You can add dynamic column to run prompts on an LLM, call an API endpoint, extract structured data, classify values, retrieve documents, etc
You can add as many dynamic columns as you would like to build up a complex data pipeline
Here’s a 30 second demo showing you how a dynamic column works.
For example: classify user query -> classify response -> check if classification matches
Currently, we support the following dynamic columns:
Useful to call external APIs (ex: transcription, get info from DB, etc)
Generate an LLM response by running a prompt on any model!
Classify values from other columns into user-defined labels
Extract an array of entities from any column
Retrieve documents from a vector database
Conditional execute any dynamic column based on the value of other columns
You can also Run Evaluations in the Datasets UI similar to dynamic columns.