Build docwrangler-lite no-code interface #439
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Implement the DocWrangler Lite feature, allowing users to generate DocETL pipelines from natural language descriptions. This includes a new API endpoint for pipeline generation and execution, and a frontend interface for user interaction. Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>
|
Cursor Agent can help with this pull request. Just |
Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implement DocWrangler Lite, a no-code interface for building and iterating on DocETL pipelines using natural language.
This PR introduces a new
/dwlitefrontend experience and a corresponding/api/dwliteroute. The frontend allows users to specify tasks and desired outputs in natural language, upload datasets, and control sampling. The backend leverages an AI planner to generate, validate, and execute DocETL pipelines, providing a simplified, iterative user experience without requiring manual YAML or Jinja editing.