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.

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

Initial text and document embedders implementation #1

Merged
merged 6 commits into from
Jan 16, 2025

Conversation

gadmarkovits
Copy link
Owner

Description

Implemented a text embedder and a document embedder to integrate OPEA with Haystack.

Issues

RFC

Type of change

List the type of change like below. Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds new functionality)
  • Breaking change (fix or feature that would break existing design and interface)
  • Others (enhancement, documentation, validation, etc.)

Dependencies

Haystack

Tests

Ran e2e test on a local machine against a Xeon instance running the ChatQnA example.

Sorry, something went wrong.

gadmarkovits pushed a commit that referenced this pull request Jan 14, 2025
* Adds an endpoint for image ingestion

Signed-off-by: Melanie Buehler <[email protected]>

* Combined image and video endpoint

Signed-off-by: Melanie Buehler <[email protected]>

* Add test and update README

Signed-off-by: Melanie Buehler <[email protected]>

* fixed variable name for embedding model (#1)

Signed-off-by: okhleif-IL <[email protected]>

* Fixed test script

Signed-off-by: Melanie Buehler <[email protected]>

* Remove redundant function

Signed-off-by: Melanie Buehler <[email protected]>

* get_videos, delete_videos --> get_files, delete_files (opea-project#3)

Signed-off-by: okhleif-IL <[email protected]>

* Updates test per review feedback

Signed-off-by: Melanie Buehler <[email protected]>

* Fixed test

Signed-off-by: Melanie Buehler <[email protected]>

* Add support for audio files multimodal data ingestion (opea-project#4)

* Add support for audio files multimodal data ingestion

Signed-off-by: dmsuehir <[email protected]>

* Update function name

Signed-off-by: dmsuehir <[email protected]>

---------

Signed-off-by: dmsuehir <[email protected]>

* Change videos_with_transcripts to ingest_with_text

Signed-off-by: Melanie Buehler <[email protected]>

* Add image support to video ingestion with transcript functionality

Signed-off-by: Melanie Buehler <[email protected]>

* Update test and README

Signed-off-by: Melanie Buehler <[email protected]>

* Updated for review suggestions

Signed-off-by: Melanie Buehler <[email protected]>

* Add two tests for ingest_with_text

Signed-off-by: Melanie Buehler <[email protected]>

* LVM TGI Gaudi update for prompts without images (opea-project#7)

* LVM Gaudi TGI update for prompts without images

Signed-off-by: dmsuehir <[email protected]>

* Wording

Signed-off-by: dmsuehir <[email protected]>

* Add a test

Signed-off-by: dmsuehir <[email protected]>

---------

Signed-off-by: dmsuehir <[email protected]>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Change dummy image to be b64 encoded instead of the url (opea-project#9)

Signed-off-by: dmsuehir <[email protected]>

* Updates based on review feedback (opea-project#10)

Signed-off-by: dmsuehir <[email protected]>

* Test fix (opea-project#11)

Signed-off-by: dmsuehir <[email protected]>

---------

Signed-off-by: Melanie Buehler <[email protected]>
Signed-off-by: okhleif-IL <[email protected]>
Signed-off-by: dmsuehir <[email protected]>
Co-authored-by: dmsuehir <[email protected]>
Co-authored-by: Omar Khleif <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Abolfazl Shahbazi <[email protected]>
Copy link

@julian-risch julian-risch left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks quite good to me already! 👍 Just left some minor comments about to_dict and from_dict.

Copy link

@julian-risch julian-risch left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Found one last typo in the output of OPEATextEmbedder. Everything else looks good to me. Happy to approve right after the typo is fixed!

Signed-off-by: Gad Markovits <[email protected]>
Copy link

@julian-risch julian-risch left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks very good to me! 👍

@gadmarkovits gadmarkovits merged commit fdbfd6f into main Jan 16, 2025
8 of 10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants