topdog/supersonic
1
0
Fork 0
mirror of https://github.com/tencentmusic/supersonic.git synced 2026-04-28 20:04:27 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

[improvement][docs]Update README to improve motivation part

Browse Source
This commit is contained in:
jerryjzhang
2023-10-08 14:08:48 +08:00
parent 69242f9f2d
commit e3b3e8861d
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -8,12 +8,12 @@
## Motivation
The emergence of Large Language Model (LLM) like ChatGPT is reshaping the way information is retrieved. In the field of data analytics, both academia and industry are primarily focused on leveraging LLM to convert natural language into SQL (so called text2sql or nl2sql). While some works show promising results, they are still not applicable to real-world scenarios. The biggest obstacle stems from the
The emergence of Large Language Model (LLM) like ChatGPT is reshaping the way information is retrieved. In the field of data analytics, both academia and industry are primarily focused on leveraging LLM to convert natural language into SQL (so called text2sql or nl2sql). While some works exhibit promising results, their **reliability** is inadequate for real-world applications.
From our perspective, the key to filling the real-world gap lies in three aspects:
1. Introduce a semantic layer encapsulating underlying data context(joins, formulas, etc) to reduce **complexity**.
2. Augment the LLM with schema mappers(as a kind of preprocessor) and semantic correctors(as a kind of postprocessor) to mitigate **hallucination**.
3. Utilize heuristic rules to improve **efficiency**(in terms of latency and cost).
3. Utilize heuristic rules when necessary to improve **efficiency**(in terms of latency and cost).
With these ideas in mind, we develop SuperSonic as a practical reference implementation and use it to power our real-world products. Additionally, to facilitate further development of ChatBI, we decide to open source SuperSonic as an extensible framework.