LLM API Task Execution for Natural Language Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users lack the skills to perform sophisticated data analyses using complex data analysis tools and struggle to interact with data sources through Application Programming Interfaces (APIs) due to overwhelming complexity and the need for multiple function calls.
Innovation Solution
Utilizing Large Language Models (LLMs) to determine and execute API calls based on natural language queries, simplifying the interaction with data sources by generating and executing API calls to provide answers to user queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If data analysis tools provide sophisticated analysis capabilities, then analysis power is improved, but user interface complexity increases making tools unusable for average users
Solution Approach 1:
The patent introduces a natural language processing intermediary layer between the user and the complex data analysis tools. Users can interact with the system using simple natural language queries instead of dealing with complex interfaces, while the intermediary translates these queries into appropriate API calls and analysis operations. This mediator handles the complexity internally while presenting a simple interface to users.
2Adaptability or versatility
If API specifications provide detailed function calls and parameters, then data access capability is improved, but task execution difficulty increases for end users
Solution Approach 1:
The system implements self-service by automatically generating and executing the appropriate API calls based on user intent. Instead of requiring users to manually construct complex API calls with multiple parameters and function calls, the system autonomously analyzes the user's natural language query, determines the necessary API operations, and executes them without user intervention. This allows the system to leverage detailed API specifications while maintaining ease of use.
Data Source
AI summary
Systems and methods include reception of a natural language query of a data source, generation of a first prompt to prompt determination of a plan to respond to the query, receiving the plan from a text generation model in response to the first prompt, generation of a second prompt to prompt determination of an API call and a parsing instruction, the second prompt including the plan, reception of the API call and the parsing instruction from the model in response to the second prompt, reception of a response to the API call from the data source, generation of a third prompt to prompt determination of a parsed response, the third prompt including the response and the parsing instruction, reception of the parsed response from the model in response to the third prompt, and determination of an answer to the query based on the parsed response.