Multimodal inputs in the `DraftValidation` class
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
Research direction
Start by reading the DraftValidation and Validate.prompt() entry points, then review DataScan and the linked How DraftValidation Works guide to understand the existing flow. Done means defining and implementing support for image or PDF inputs so the LLM can use them with the data summary to produce executable validation code.
Written by the indexing model from the issue text.
Description
Prework
- Read and abide by the Pointblank code of conduct and contributing guidelines.
- Search for duplicates among the existing issues (both open and closed).
Proposal
Continuing on the theme of multimodal inputs, I thought it'd be really cool if the DraftValidation class could support multimodal inputs (images and PDF), just as Validate.prompt() now does. A rough sketch of how that would work, drawing inspiration from the How DraftValidation Works steps:
- A statistical summary of your data is generated using the DataScan class.
- This summary is converted to JSON format and sent to your selected LLM provider.
- NEW: You provide the
DraftValidationclass with an image or PDF file describing what the data should look like. For example, the image could be a schema diagram, while the PDF could outline the project configuration elements that the data should conform to. - The LLM uses the summary and multimodal input along with knowledge about Pointblank’s validation capabilities to generate a validation plan.
- The result is returned as executable Python code that you can use directly or modify as needed
Happy to get feedback from you @rich-iannone, and iterate. I'd love to implement this.
- Dominant language
- Python
- Stars
- 494
- Forks
- 38
- Avg merge
- 13h 39m
- Merged PRs (30d)
- 16
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from posit-dev/pointblank
-
Type: ★ Enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
posit-dev/pointblank#379 ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 48/100
posit-dev/pointblank#395 ·
Maintainers usually reply within 1 day
-
ibis.pyspark col_vals_in_set produces invalid SQLMay be free again @rich-iannone claimed this 296 days ago, and no pull request is open. OpenDifficulty: [2] Intermediate Effort: [3] High Priority: [3] High Type: ☹︎ Bug
posit-dev/pointblank#335 · 1 comment · 1 assignee ·
Maintainers usually reply within 1 day
-
YAML value column selectorMay be free again @rich-iannone claimed this 315 days ago, and no pull request is open. OpenDifficulty: [2] Intermediate Effort: [3] High Priority: [3] High Type: ☹︎ Bug
posit-dev/pointblank#333 · 1 comment · 1 assignee ·
Maintainers usually reply within 1 day
-
Type: ⁇ Question
Difficulty 5/5 Over a week Newbie friendliness 25/100
posit-dev/pointblank#323 ·
Maintainers usually reply within 1 day
All issues in posit-dev/pointblank
Similar issues
-
fix formatting of the sample database page of the docsPossibly taken @Aaqibhafeezkhan claimed this today. Opendocumentation good first issue help wanted
Difficulty 1/5 Under an hour Newbie friendliness 72/100
chaoss/CollectOSS#544 · 1 comment ·
Maintainers usually reply within 1 day
-
area/plugin good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
kestra-io/plugin-soda#137 ·
-
Difficulty 2/5 Half a day Newbie friendliness 62/100
ibm-granite/granite.build#504 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day