CSV Agent

The CSV Agent is a specialized node designed to answer queries about data stored in CSV files. It combines the power of language models with the ability to analyze CSV data, allowing users to ask questions and receive insights about their CSV content using natural language.

Node Details

• Name: csvAgent
• Type: AgentExecutor
• Category: [[Agents]]
• Version: 3.0

Description

This agent is used to answer queries on CSV data. It leverages a language model to interpret user questions, generates Python code to analyze the CSV data, and then provides human-readable answers based on the analysis results.

Parameters

1. CSV File (Required)

   • Type: file
   • File Type: .csv
   • Description: The CSV file to be analyzed.

2. Language Model (Required)

   • Type: BaseLanguageModel
   • Description: The language model used for interpreting queries and generating responses.

3. System Message (Optional)

   • Type: string
   • Description: A custom system message to set the behavior of the agent.
   • Default: A predefined message instructing the agent to act as an AI assistant.

4. Input Moderation (Optional)

   • Type: Moderation[]
   • Description: Applies moderation to detect potentially harmful input before processing.

5. Custom Pandas Read_CSV Code (Optional)

   • Type: code
   • Description: Custom Pandas read_csv function to load the CSV data.
   • Default: read_csv(csv_data)

Input

• A natural language query about the data in the specified CSV file.

Output

• A detailed answer to the query, based on analysis of the CSV data.

How It Works

1. The agent first loads the CSV file using either the default or custom Pandas read_csv function.
2. It converts the CSV data into a Pandas DataFrame using Pyodide (a Python runtime for the browser).
3. A language model interprets the user’s query and generates Python code to analyze the data.
4. The generated Python code is executed using Pyodide to perform the analysis.
5. The results of the analysis are then passed back to the language model to generate a human-readable response.
6. The final answer is returned to the user.

Use Cases

• Querying CSV data without writing complex formulas or scripts.
• Generating insights and summaries from CSV files.
• Performing data analysis on CSV content using natural language queries.
• Educational tools for teaching data analysis concepts.
• Quick data exploration for business intelligence.

Special Features

• File Storage Integration: Can load CSV files from file storage systems.
• Custom CSV Loading: Supports custom Pandas read_csv code for specialized CSV loading requirements.
• Input Moderation: Optional moderation to prevent processing of potentially harmful queries.
• Streaming Responses: Supports both streaming and non-streaming response modes.

Notes

• The node uses Pyodide to run Python code in a JavaScript environment, allowing for powerful data analysis capabilities.
• It supports loading multiple CSV files if needed.
• The system message can be customized to tailor the agent’s behavior and response style.
• Error handling is implemented to provide meaningful feedback if the analysis fails.

The CSV Agent node provides a powerful interface for interacting with CSV data using natural language, making it easier for users to gain insights from their CSV files without needing to write complex queries or scripts. It’s particularly useful for data analysts, business users, or anyone who needs to quickly extract information from CSV data without diving into the technicalities of data manipulation.