Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Expand prompts.py to work with SQL schema input #75

Open
emmaver opened this issue Dec 15, 2023 · 1 comment · May be fixed by #76
Open

Expand prompts.py to work with SQL schema input #75

emmaver opened this issue Dec 15, 2023 · 1 comment · May be fixed by #76
Assignees
@emmaver
Milestone
BioHackathon2

Comments

@emmaver
Copy link
Contributor

emmaver commented Dec 15, 2023

Allow to create a prompt engine from a relational database schema definition file, so that SQL queries can be generated with accurate information about the database that one wants to query
@emmaver emmaver added this to the BioHackathon2 milestone Dec 15, 2023
@emmaver emmaver self-assigned this Dec 15, 2023
@emmaver emmaver linked a pull request Dec 15, 2023 that will close this issue
first commit for prompt engine using SQL schema definition #76
Draft
@emmaver
Copy link
Contributor Author

emmaver commented Dec 15, 2023

What needs to be worked on before this can be merged:

  • fine tune system messages informing the LLM about the database
    • improve relationship extraction from the schema definition: make use of foreign keys (?)
    • implement trying to match the column names of tables that need to be joined to hint that to the LLM
    • ...
  • create some tests

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@emmaver emmaver

Labels
None yet
Projects
None yet
Milestone
BioHackathon2
Development

Successfully merging a pull request may close this issue.

first commit for prompt engine using SQL schema definition biocypher/biochatter
1 participant
@emmaver