Image ingestion improvements#2
Merged
mhbuehler merged 8 commits intomelanie/mm-rag-enhancedfrom Oct 24, 2024
Merged
Conversation
Signed-off-by: Melanie Buehler <[email protected]>
Signed-off-by: Melanie Buehler <[email protected]>
4 tasks
Signed-off-by: Melanie Buehler <[email protected]>
Signed-off-by: Melanie Buehler <[email protected]>
dmsuehir
approved these changes
Oct 23, 2024
Collaborator
dmsuehir
left a comment
dmsuehir
left a comment
There was a problem hiding this comment.
LGTM, the only changes that I would be unsure of are the proxy changes in the test file, because it looks like the tests are run with GHA (for example here), and the docker builds and tests seem to be successful, so it's hard to know if the proxy changes would break anything from GHA runs.
dmsuehir
requested changes
Oct 23, 2024
| exit 1 | ||
| else | ||
| echo "[ $SERVICE_NAME ] Content is as expected." | ||
| fi |
Collaborator
There was a problem hiding this comment.
Sorry, one comment that I have after reviewing Omar's PR - in the test for get_videos (which he's renaming to get_files) it's currently checking RESPONSE_BODY for the video name, but can you add to make it also check for the image name?
Signed-off-by: Melanie Buehler <[email protected]>
Signed-off-by: Melanie Buehler <[email protected]>
…hbuehler/GenAIComps into melanie/combined_image_video_ingestion
dmsuehir
approved these changes
Oct 24, 2024
mhbuehler
pushed a commit
that referenced
this pull request
Apr 28, 2025
) * Fix image build issue (opea-project#1553) Signed-off-by: chensuyue <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Unified default port number for the same service in text2graph and text2sql (opea-project#1554) Signed-off-by: Yao, Qing <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * new: `OpeaArangoDataprep` (#2) * new: `third_parties/arangodb` * new: `OpeaArangoDataprep` * cleanup * fix: `vllm` instead of `tgi` * fix: dataprep compsoe * cleanup Signed-off-by: Anthony Mahanna <[email protected]> * new: `OpeaArangoRetriever` (#3) * new: `OpeaArangoRetriever` * cleanup Signed-off-by: Anthony Mahanna <[email protected]> * new: deps Signed-off-by: Anthony Mahanna <[email protected]> * fix typo: `test_retrievers_arango.sh` Signed-off-by: Anthony Mahanna <[email protected]> * updated retriever-arango compose file Signed-off-by: Anthony Mahanna <[email protected]> * correction Signed-off-by: Anthony Mahanna <[email protected]> * add json-repair to dataprep-arango requirements Signed-off-by: Anthony Mahanna <[email protected]> * Fix network error, change WORKPATH Signed-off-by: Anthony Mahanna <[email protected]> * extra time for health check retriever Signed-off-by: Anthony Mahanna <[email protected]> * extended retriever healthcheck 90secs Signed-off-by: Anthony Mahanna <[email protected]> * correction Signed-off-by: Anthony Mahanna <[email protected]> * Update arangodb.py Signed-off-by: Anthony Mahanna <[email protected]> * Removing hugging face token requirement from test file Signed-off-by: Anthony Mahanna <[email protected]> * Update test_dataprep_arango with network tests and additional logs Signed-off-by: Anthony Mahanna <[email protected]> * Running CI after docker rate limit Signed-off-by: Anthony Mahanna <[email protected]> * Base case remove HF_token, no additional tests Signed-off-by: Anthony Mahanna <[email protected]> * Adding VLLM check and logs, currently VLLM not working in CI/CD Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: compose.yaml Signed-off-by: Anthony Mahanna <[email protected]> * update: arangodb healthcheck Signed-off-by: Anthony Mahanna <[email protected]> * cleanup Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: retriever test Signed-off-by: Anthony Mahanna <[email protected]> * fix: typo Signed-off-by: Anthony Mahanna <[email protected]> * rem: unused vars Signed-off-by: Anthony Mahanna <[email protected]> * fix: indent Signed-off-by: Anthony Mahanna <[email protected]> * temp: swap vllm healthcheck with sleep Signed-off-by: Anthony Mahanna <[email protected]> * fix: typo Signed-off-by: Anthony Mahanna <[email protected]> * fix: component name typo Signed-off-by: Anthony Mahanna <[email protected]> * fix: support `EmbedDoc` for retriever Signed-off-by: Anthony Mahanna <[email protected]> * fix: `getattr` Signed-off-by: Anthony Mahanna <[email protected]> * fix: CURL command Signed-off-by: Anthony Mahanna <[email protected]> * revert 6061484 Signed-off-by: Anthony Mahanna <[email protected]> * Update xtune file and change DDP paramter (opea-project#1552) Signed-off-by: jilongwa <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * add N/A option (opea-project#1561) Signed-off-by: ZhangJianyu <[email protected]> Co-authored-by: ZhangJianyu <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Test latest gaudi docker container (opea-project#1477) Update base gaudi container into the latest version, docker pull vault.habana.ai/gaudi-docker/1.20.1/ubuntu22.04/habanalabs/pytorch-installer-2.6.0:latest, https://docs.habana.ai/en/latest/Installation_Guide/Additional_Installation/Docker_Installation.html#use-intel-gaudi-containers Signed-off-by: chensuyue <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * fix audioqna male voice setting (opea-project#1559) Co-authored-by: Letong Han <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * added error handling for lvm (opea-project#1556) Signed-off-by: okhleif-IL <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * enable mysql db for sql agent (opea-project#1431) Signed-off-by: cheehook <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Enlarge DocSum prompt buffer (opea-project#1567) * Enlarge DocSum prompt buffer Follow PR opea-project#1471 Signed-off-by: XinyaoWa <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Update vLLM parameter max-seq-len-to-capture (opea-project#1565) Signed-off-by: lvliang-intel <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * fix: lint Signed-off-by: Anthony Mahanna <[email protected]> * fix: missing import Signed-off-by: Anthony Mahanna <[email protected]> * new: healtcheck for dataprep-arangodb Signed-off-by: Anthony Mahanna <[email protected]> * update: arangodb readmes Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: test_dataprep_arango.sh Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: test_dataprep_arango.sh (PT2) Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: test_dataprep_arango.sh (PT3) Signed-off-by: Anthony Mahanna <[email protected]> * update: test_dataprep_arango.sh Signed-off-by: Anthony Mahanna <[email protected]> * fix: whitespace Signed-off-by: Anthony Mahanna <[email protected]> * Remove Transformers versions from requirements.txt file (opea-project#1547) * Remove Transformers versions from requirements.txt file Signed-off-by: Abolfazl Shahbazi <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Remove index_names from files for dataprep-get request (opea-project#1569) * remove index_names from files fot get request Signed-off-by: Mustafa <[email protected]> * update the tests Signed-off-by: Mustafa <[email protected]> * update the tests Signed-off-by: Mustafa <[email protected]> * update the tests Signed-off-by: Mustafa <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add validation check for 'all' as an index_name Signed-off-by: Mustafa <[email protected]> * fix for readme file Signed-off-by: Mustafa <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Mustafa <[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]> Signed-off-by: Anthony Mahanna <[email protected]> * Upgrade Optimum Habana version to fix security check issue (opea-project#1571) Signed-off-by: lvliang-intel <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Make llamaguard compatible with both TGI and vLLM (opea-project#1581) Signed-off-by: lvliang-intel <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Fix Dockerfile error and add CI test for IPEX (opea-project#1585) * Fix Dockerfile error and add CI teat Signed-off-by: lvliang-intel <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Reduce multilang tts docker image size (opea-project#1587) * fix audioqna male voice setting * reduce multilang tts docker image size Signed-off-by: Anthony Mahanna <[email protected]> * unset OPENAI_KEY in CI test (opea-project#1586) Signed-off-by: Rita Brugarolas <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * Add AWS Credentials for CD test (opea-project#1588) * Fix CD test issue Signed-off-by: ZePan110 <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * update: shorten ingest_dataprep.txt Signed-off-by: Anthony Mahanna <[email protected]> * revert: a4d943e Signed-off-by: Anthony Mahanna <[email protected]> * new: `DataprepRequest` model (opea-project#1525) * new: `DataprepRequest` * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: docstrings * rem: `ingest_from_graphDB` * new: dep injection * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: verbose `input` processing * attempt: replace `kwargs` with params * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rem: `db_type` ref: opea-project#1525 (comment) * attempt: require `base` * Revert "attempt: require `base`" This reverts commit 620ca6b. * new: `DataprepRequest` * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: docstrings * rem: `ingest_from_graphDB` * new: dep injection * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: verbose `input` processing * attempt: replace `kwargs` with params * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rem: `db_type` ref: opea-project#1525 (comment) * attempt: require `base` * Revert "attempt: require `base`" This reverts commit 620ca6b. * Fix dataprep request class issue of Redis (#1) * new: `DataprepRequest` * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: docstrings * rem: `ingest_from_graphDB` * new: dep injection * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: verbose `input` processing * attempt: replace `kwargs` with params * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rem: `db_type` ref: opea-project#1525 (comment) * attempt: require `base` * Revert "attempt: require `base`" This reverts commit 620ca6b. * fix dataprep request class of redis Signed-off-by: letonghan <[email protected]> * revert change in redis.py Signed-off-by: letonghan <[email protected]> --------- Signed-off-by: letonghan <[email protected]> Co-authored-by: Anthony Mahanna <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Anthony Mahanna <[email protected]> Co-authored-by: Liang Lv <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * revert: `DataprepRequest` for multimodal * revert: `DataprepRequest` for multimodal (PT2) * fix: conditionally fetch unique `DataprepRequest` attributes * fix bugs in dataprep util script Signed-off-by: letonghan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * revert change of pgvector Signed-off-by: letonghan <[email protected]> * fix indices bug for redis Signed-off-by: letonghan <[email protected]> * minor fix for redis Signed-off-by: letonghan <[email protected]> * ingest file into rag_redis_test Signed-off-by: letonghan <[email protected]> * update indice name Signed-off-by: letonghan <[email protected]> --------- Signed-off-by: letonghan <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Liang Lv <[email protected]> Co-authored-by: Letong Han <[email protected]> Co-authored-by: letonghan <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> * revert: bc4445c Signed-off-by: Anthony Mahanna <[email protected]> * revert: d17f6aa Signed-off-by: Anthony Mahanna <[email protected]> * Revert "new: `DataprepRequest` model (opea-project#1525)" (opea-project#1592) This reverts commit 88947ab. Signed-off-by: Anthony Mahanna <[email protected]> * add hyperlinks Signed-off-by: Anthony Mahanna <[email protected]> * revert: 4eb9ec4f Signed-off-by: Anthony Mahanna <[email protected]> * new: ArangoDBDataprepRequest Signed-off-by: Anthony Mahanna <[email protected]> * fix: lint Signed-off-by: Anthony Mahanna <[email protected]> * cleanup: delete_files Signed-off-by: Anthony Mahanna <[email protected]> * remove: env mutation Signed-off-by: Anthony Mahanna <[email protected]> * fix: move openai key env var to top of file Signed-off-by: Anthony Mahanna <[email protected]> --------- Signed-off-by: chensuyue <[email protected]> Signed-off-by: Anthony Mahanna <[email protected]> Signed-off-by: Yao, Qing <[email protected]> Signed-off-by: jilongwa <[email protected]> Signed-off-by: ZhangJianyu <[email protected]> Signed-off-by: okhleif-IL <[email protected]> Signed-off-by: cheehook <[email protected]> Signed-off-by: XinyaoWa <[email protected]> Signed-off-by: lvliang-intel <[email protected]> Signed-off-by: Abolfazl Shahbazi <[email protected]> Signed-off-by: Mustafa <[email protected]> Signed-off-by: Rita Brugarolas <[email protected]> Signed-off-by: ZePan110 <[email protected]> Signed-off-by: letonghan <[email protected]> Co-authored-by: chen, suyue <[email protected]> Co-authored-by: Yao Qing <[email protected]> Co-authored-by: lasyasn <[email protected]> Co-authored-by: Ajay Kallepalli <[email protected]> Co-authored-by: jilongW <[email protected]> Co-authored-by: Neo Zhang Jianyu <[email protected]> Co-authored-by: ZhangJianyu <[email protected]> Co-authored-by: Spycsh <[email protected]> Co-authored-by: Letong Han <[email protected]> Co-authored-by: Omar Khleif <[email protected]> Co-authored-by: cheehook <[email protected]> Co-authored-by: XinyaoWa <[email protected]> Co-authored-by: Liang Lv <[email protected]> Co-authored-by: Abolfazl Shahbazi <[email protected]> Co-authored-by: Mustafa <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: rbrugaro <[email protected]> Co-authored-by: ZePan110 <[email protected]> Co-authored-by: letonghan <[email protected]>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Description
Improves previous image ingestion implementation by reusing the existing
/generate_captionsendpoint instead of creating a new one, reducing code. I also updated READMEs and tests in both repos. Goes with this PR in GenAIExamples.Issues
RFC
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
No new dependencies
Tests