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.

Sign up for GitHub

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

Jump to bottom

RAG is slow in ChatQnA demo on Xeon #584

Closed
NeoZhangJianyu opened this issue Aug 13, 2024 · 5 comments
Closed

RAG is slow in ChatQnA demo on Xeon #584

NeoZhangJianyu opened this issue Aug 13, 2024 · 5 comments
Assignees
@kevinintel @Zhenzhong1
Labels
aitce

Comments

@NeoZhangJianyu
Copy link
Collaborator

I setup the demo based on ChatQnA (TGI) on Xeon (GNR).
Try RAG by the UI.
After upload the PDF file (2-5M), I search a question.
It will take 10-15s.

When update a text file with 3 lines, it's 2-3s.

Customer find the slow issue on embedding stage.
@Zhenzhong1
Copy link
Collaborator

@NeoZhangJianyu Hi

Which version of the TEI did you use for embedding? Did you implement reranking? If so, was it done on CPU or HPU?

Additionally, could you provide details about all images you used and how you built your ChatQnA pipeline?

@NeoZhangJianyu
Copy link
Collaborator Author

I use the docker image built from the dockerfiles in this project.
comment id: 3913c7b

I don't implement reranking.
The docker build follow the script/cmd in guide in ChatQnA: https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker/xeon/README.md

@Zhenzhong1
Copy link
Collaborator

Zhenzhong1 commented Aug 21, 2024 •
edited
Loading

@NeoZhangJianyu

Embedding should work well on GNR. Later we will apply Neural Speed ​​(internal) to speed up embedding serving.

Also, we will investigate this issue.

@Zhenzhong1
Copy link
Collaborator

Zhenzhong1 commented Sep 4, 2024 •
edited
Loading

@NeoZhangJianyu @lvliang-intel

Hello, we’ve evaluated the embedding performance.

Our testing data shows a significant performance gap between TEI 1.2 and TEI 1.5. Please verify which TEI version you are currently using.

In OPEA v0.9, TEI performance should not be an issue.

@NeoZhangJianyu
Copy link
Collaborator Author

It's great!

wangkl2 pushed a commit to wangkl2/GenAIExamples that referenced this issue Dec 11, 2024
@letonghan
remove revision for tei (opea-project#584)
d609071 
Signed-off-by: letonghan <[email protected]>
wangkl2 pushed a commit to wangkl2/GenAIExamples that referenced this issue Dec 11, 2024
@a32543254 @pre-commit-ci
@Spycsh @BaoHuiling @ZePan110 @lkk12014402 @sharanshirodkar7 @lvliang-intel @letonghan @chensuyue @tileintel @berkecanrizai @Liangyx2 @kevinintel
optimize rerank with backend ref (opea-project#579)
d76751a 
* add rerank with neural speed

Signed-off-by: Dong, Bo1 <[email protected]>

* add the code

Signed-off-by: Dong, Bo1 <[email protected]>

* add the code

Signed-off-by: Dong, Bo1 <[email protected]>

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

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

Signed-off-by: Dong, Bo1 <[email protected]>

* fix mismatched response format w/wo streaming guardrails (opea-project#568)

* fix mismatched response format w/wo streaming  guardrails

* fix & debug

* fix & rm debug

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

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

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* Fix guardrails out handle logics for space linebreak and quote (opea-project#571)

* fix mismatched response format w/wo streaming  guardrails

* fix & debug

* fix & rm debug

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

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

* debug

* debug

* debug

* fix pre-space and linebreak

* fix pre-space and linebreak

* fix single/double quote

* fix single/double quote

* remove debug

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

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

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* BUG FIX: LVM security fix (opea-project#572)

* add url validator

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

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

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

* add validation for video_url

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

---------

Signed-off-by: BaoHuiling <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* Modify output messages. (opea-project#569)

* Reduced output.

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

* Output the location where the modified Dockerfile file is referenced.

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

* for test

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

* Restore test file.

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

---------

Signed-off-by: zepan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* refine logging code. (opea-project#559)

* add ut and refine logging code.

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

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

* update microservice port.

---------

Co-authored-by: root <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* adding lancedb to langchain vectorstores (opea-project#291)

* adding lancedb to langchain vectorstores

Signed-off-by: sharanshirodkar7 <[email protected]>

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

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

---------

Signed-off-by: sharanshirodkar7 <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: lvliang-intel <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* Refine Dataprep Milvus MS (opea-project#570)

Signed-off-by: letonghan <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* final version

Signed-off-by: Dong, Bo1 <[email protected]>

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

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

Signed-off-by: Dong, Bo1 <[email protected]>

* update the readme

Signed-off-by: Dong, Bo1 <[email protected]>

* add the sign

Signed-off-by: Dong, Bo1 <[email protected]>

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

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

Signed-off-by: Dong, Bo1 <[email protected]>

* fix error for pre ci

Signed-off-by: Dong, Bo1 <[email protected]>

* add the ut

Signed-off-by: Dong, Bo1 <[email protected]>

* update docker file

Signed-off-by: Dong, Bo1 <[email protected]>

* update CI test log achieve (opea-project#577)

Signed-off-by: chensuyue <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* Multimodal dataprep (opea-project#575)

* multimodal embedding for MM RAG for videos

Signed-off-by: Tiep Le <[email protected]>

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

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

* develop data prep first commit

Signed-off-by: Tiep Le <[email protected]>

* develop dataprep microservice for multimodal data

Signed-off-by: Tiep Le <[email protected]>

* multimodal langchain for dataprep

Signed-off-by: Tiep Le <[email protected]>

* update README

Signed-off-by: Tiep Le <[email protected]>

* update README

Signed-off-by: Tiep Le <[email protected]>

* update README

Signed-off-by: Tiep Le <[email protected]>

* update README

Signed-off-by: Tiep Le <[email protected]>

* cosmetic

Signed-off-by: Tiep Le <[email protected]>

* test for multimodal dataprep

Signed-off-by: Tiep Le <[email protected]>

* update test

Signed-off-by: Tiep Le <[email protected]>

* update test

Signed-off-by: Tiep Le <[email protected]>

* update test

Signed-off-by: Tiep Le <[email protected]>

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

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

* cosmetic update

Signed-off-by: Tiep Le <[email protected]>

* remove langsmith

Signed-off-by: Tiep Le <[email protected]>

* update API to remove /dataprep from API names and remove langsmith

Signed-off-by: Tiep Le <[email protected]>

* update test

Signed-off-by: Tiep Le <[email protected]>

* update the error message per PR reviewer

Signed-off-by: Tiep Le <[email protected]>

---------

Signed-off-by: Tiep Le <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* add: Pathway vector store and retriever as LangChain component (opea-project#342)

* nb

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

* init changes

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

* docker

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

* example data

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

* docs(readme): update, add commands

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

* fix: formatting, data sources

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

* docs(readme): update instructions, add comments

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

* fix: rm unused parts

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

* fix: image name, compose env vars

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

* fix: rm unused part

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

* fix: logging name

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

* fix: env var

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

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

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

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

* fix: rename pw docker

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

* docs(readme): update input sources

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

* nb

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

* init changes

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

* fix: formatting, data sources

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

* docs(readme): update instructions, add comments

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

* fix: rm unused part

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

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

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

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

* fix: rename pw docker

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

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

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

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

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

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

* feat: mv vector store, naming, clarify instructions, improve ingestion components

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

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

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

* tests: add pw retriever test
fix: update docker to include libmagic

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

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

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

* implement suggestions from review, entrypoint, reqs, comments, https_proxy.

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

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

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

* fix: update docker tags in test and readme

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

* tests: add separate pathway vectorstore test

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

---------

Signed-off-by: Berke <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Sihan Chen <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* Add local Rerank microservice for VideoRAGQnA (opea-project#496)

* initial commit

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

* save

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

* add readme, test script, fix bug

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

* update video URL

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

* use default

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

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

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

* update core dependency

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

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

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

* use p 5000

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

* use 5037

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

* update ctnr name

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

* remove langsmith

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

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

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

* add rerank algo desc in readme

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

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

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

---------

Signed-off-by: BaoHuiling <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* Add Scan Container. (opea-project#560)

Signed-off-by: zepan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* fix SearchedMultimodalDoc in docarray (opea-project#583)

Signed-off-by: BaoHuiling <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* update image build yaml (opea-project#529)

Signed-off-by: chensuyue <[email protected]>
Signed-off-by: zepan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* add microservice for intent detection (opea-project#131)

* add microservice for intent detection

Signed-off-by: Liangyx2 <[email protected]>

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

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

* update license copyright

Signed-off-by: Liangyx2 <[email protected]>

* add ut

Signed-off-by: Liangyx2 <[email protected]>

* refine

Signed-off-by: Liangyx2 <[email protected]>

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

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

* update folder

Signed-off-by: Liangyx2 <[email protected]>

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

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

* fix test

Signed-off-by: Liangyx2 <[email protected]>

---------

Signed-off-by: Liangyx2 <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Dong, Bo1 <[email protected]>

* Make the scanning method optional. (opea-project#580)

Signed-off-by: zepan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* add code owners (opea-project#586)

Signed-off-by: Dong, Bo1 <[email protected]>

* remove revision for tei (opea-project#584)

Signed-off-by: letonghan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* Bug fix (opea-project#591)

* Check if the document exists.

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

* Add flag output.

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

* Modify nginx readme.

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

* Modify document detection logic

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

---------

Signed-off-by: zepan <[email protected]>
Signed-off-by: Dong, Bo1 <[email protected]>

* fix ut issue

Signed-off-by: Dong, Bo1 <[email protected]>

* merge the main

Signed-off-by: Dong, Bo1 <[email protected]>

* align with new pipeline

Signed-off-by: Dong, Bo1 <[email protected]>

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

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

* align with newest pipeline

Signed-off-by: Dong, Bo1 <[email protected]>

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

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

* upload code

Signed-off-by: Dong, Bo1 <[email protected]>

* update the ut

Signed-off-by: Dong, Bo1 <[email protected]>

* add docker path

Signed-off-by: Dong, Bo1 <[email protected]>

* add the docker path

Signed-off-by: Dong, Bo1 <[email protected]>

---------

Signed-off-by: Dong, Bo1 <[email protected]>
Signed-off-by: BaoHuiling <[email protected]>
Signed-off-by: zepan <[email protected]>
Signed-off-by: sharanshirodkar7 <[email protected]>
Signed-off-by: letonghan <[email protected]>
Signed-off-by: chensuyue <[email protected]>
Signed-off-by: Tiep Le <[email protected]>
Signed-off-by: Berke <[email protected]>
Signed-off-by: Liangyx2 <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Sihan Chen <[email protected]>
Co-authored-by: Huiling Bao <[email protected]>
Co-authored-by: ZePan110 <[email protected]>
Co-authored-by: lkk <[email protected]>
Co-authored-by: root <[email protected]>
Co-authored-by: Sharan Shirodkar <[email protected]>
Co-authored-by: lvliang-intel <[email protected]>
Co-authored-by: Letong Han <[email protected]>
Co-authored-by: chen, suyue <[email protected]>
Co-authored-by: Tiep Le <[email protected]>
Co-authored-by: berkecanrizai <[email protected]>
Co-authored-by: Liangyx2 <[email protected]>
Co-authored-by: kevinintel <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@kevinintel kevinintel

@Zhenzhong1 Zhenzhong1

Labels
aitce
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@preethivenkatesh @NeoZhangJianyu @kevinintel @Zhenzhong1