GeezerVison is showing github.com — feat: Adding Docling RAG demo by franciscojavierarceo · Pull Request #5109 · feast-dev/feast
Conversation
What this PR does / why we need it:
This PR introduces enhancements to the RAG (Retrieval-Augmented Generation) demo, adds support for PDF transformation with Docling, and updates various components for better feature handling and testing.
-
examples/rag-docling/*
- Updated the quickstart guide to include Docling and Milvus usage for transforming PDFs and storing/retrieving embeddings.
- Added a new notebook (
docling-demo.ipynb) demonstrating the use of Docling for text extraction from PDFs.
- Added a new notebook (
docling-quickstart.ipynb) showing how to use Feast to ingest and retrieve text data from the online store.
- Introduced new functions for embedding text and generating chunk IDs.
- Added support for Docling and Milvus in feature definitions and transformations.
- Enhanced feature view configurations for PDF handling.
- Updated the configuration to use Milvus as the online store with vector search capabilities.
-
sdk/python/feast/feature_store.py
- Enhanced
_get_feature_view_and_df_for_online_write to handle feature view transformations differently for singleton and non-singleton cases.
-
sdk/python/tests/unit/online_store/test_online_retrieval.py
- Uncommented a previously skipped test for local Milvus to ensure it runs in CI.
-
sdk/python/tests/unit/online_store/test_online_writes.py
- Added a new test class
TestOnlineWritesWithTransform to validate PDF handling and feature transformations during online writes.
-
sdk/python/tests/unit/test_on_demand_python_transformation.py
- Updated the test for
docling_transform_docs to handle multiple inputs and validate the transformation logic.
Which issue(s) this PR fixes:
N/A
Misc:
N/A
Sorry, something went wrong.
Uh oh!
There was an error while loading. Please reload this page.
jfw-ppi
pushed a commit
to jfw-ppi/feast
that referenced
this pull request
Jun 7, 2025
* feat: Adding Docling RAG demo
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updated demo
Signed-off-by: Francisco Javier Arceo <[email protected]>
* cleaned up notebook
Signed-off-by: Francisco Javier Arceo <[email protected]>
* adding chunk id
Signed-off-by: Francisco Javier Arceo <[email protected]>
* adding quickstart demo that is WIP and updating docling-demo to export unique chunk-id
Signed-off-by: Francisco Javier Arceo <[email protected]>
* adding current tentative exmaple repo
Signed-off-by: Francisco Javier Arceo <[email protected]>
* adding current temporary work
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updating demo script to rename things
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updated quickstart
Signed-off-by: Francisco Javier Arceo <[email protected]>
* added comment
Signed-off-by: Francisco Javier Arceo <[email protected]>
* checking in progress
Signed-off-by: Francisco Javier Arceo <[email protected]>
* checking in progress for now, still have some issues with vector retrieval
Signed-off-by: Francisco Javier Arceo <[email protected]>
* okay think i have most things working
Signed-off-by: Francisco Javier Arceo <[email protected]>
* removing commenting and unnecessary code
Signed-off-by: Francisco Javier Arceo <[email protected]>
* uploading demo
Signed-off-by: Francisco Javier Arceo <[email protected]>
* uploading other files
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updated repo exaxmple
Signed-off-by: Francisco Javier Arceo <[email protected]>
* checking in current notebook, almost there
Signed-off-by: Francisco Javier Arceo <[email protected]>
* fixed linter
Signed-off-by: Francisco Javier Arceo <[email protected]>
* fixed transformation logic:
Signed-off-by: Francisco Javier Arceo <[email protected]>
* removed print
Signed-off-by: Francisco Javier Arceo <[email protected]>
* added README with description
Signed-off-by: Francisco Javier Arceo <[email protected]>
* removing print
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updating
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updating metadata file
Signed-off-by: Francisco Javier Arceo <[email protected]>
* updated readme and adding dataset
Signed-off-by: Francisco Javier Arceo <[email protected]>
---------
Signed-off-by: Francisco Javier Arceo <[email protected]>
Signed-off-by: Jacob Weinhold <[email protected]>
Reviewers
shuchu
shuchu approved these changes
Uh oh!
There was an error while loading. Please reload this page.
Assignees
No one assigned
Milestone
No milestone
Development
Successfully merging this pull request may close these issues.
Uh oh!
There was an error while loading. Please reload this page.
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.
|