jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
485 Commits 43 Branches 9 Tags
d97882ec8e2840b9903c3e68a140484d5f2bc805
Commit Graph

251 Commits

Author SHA1 Message Date
David Kinder
d97882ec8e doc: fix incorrect path to png image files (#783) 
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
 2024-09-11 13:22:44 +08:00
feng-intel
63406dc050 Yaml: add comments to specify gaudi device ids. (#753) 
Signed-off-by: fengding <feng1.ding@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-11 12:02:18 +08:00
Lianhao Lu
ff6f841ec0 README: fix broken links (#781) 
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
 2024-09-11 09:41:01 +08:00
XinyaoWa
d73129cbf0 Refactor folder to support different vendors (#743) 
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
 2024-09-10 23:27:19 +08:00
Lianhao Lu
ba94e0130d Add ui/nginx support in K8S manifest for ChatQnA/CodeGen/CodeTrans/Docsum (#773) 
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
 2024-09-10 16:30:14 +08:00
Letong Han
aebc23f5ae [ChatQnA] Update README for ModelScope (#770) 
Signed-off-by: letonghan <letong.han@intel.com>
 2024-09-10 13:50:36 +08:00
Zhenzhong1
36fb9a987d [ChatQnA] Update benchmarking manifests (#766) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-10 11:07:48 +08:00
shaohef
a2745b22a7 Provide the method to get nke-10k-2023.pdf (#769) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-09 14:52:38 +08:00
Sihan Chen
ebe6b473e9 Add megaservice definition without microservice wrappers (#700) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-06 18:49:28 +08:00
Lianhao Lu
0629696333 K8S manifest: Update ChatQnA/CodeGen/CodeTrans/DocSum 
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug #752 introduced by PR #669

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
 2024-09-06 16:09:42 +08:00
David Kinder
67394b88fa doc: fix headings and indenting (#748) 
* doc: fix headings and indenting
* only one H1 header (for title) is allowed
* fix indenting under ordered lists

Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
 2024-09-06 12:59:33 +08:00
chen, suyue
947936ed7b Update v0.9 RAG release data (#747) 
* run both xeon and gaudi when both hardware detect

Signed-off-by: chensuyue <suyue.chen@intel.com>

* add v0.9 RAG release data

Signed-off-by: chensuyue <suyue.chen@intel.com>

* update system summary

Signed-off-by: chensuyue <suyue.chen@intel.com>

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

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

---------

Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-06 09:55:55 +08:00
WenjiaoYue
758d236463 Add chatQnA UI manifest (#669) 
* Add chatQnA UI manifest

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update port

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* add nginx config

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* update code

* update nginx config

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update nginx config

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update ui IP

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update yaml

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update api

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update env config

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update env

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* update specify node

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* update node-type

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update yaml

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* update yaml

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* delete nodeSelector

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* update dataprep api

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* add node-type

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

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

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

* delete specify nodeSelector

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

* delete useless space

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>

---------

Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-05 22:44:10 +08:00
Zhenzhong1
ac3486038c [ChatQnA] udate OOB & Tuned manifests (#738) 
* update OOB manifests

* update tgi parameters

* update OOB manifests for w/o rerank

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

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

* update tgi parameters

* update tgi parameters for v0.9 w/o rerank

* update OOB manifests 2.0.4->2.0.1 for w/o rerank

* update tuned manifests

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

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

* update tuned manifests

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-05 22:23:51 +08:00
chen, suyue
e0bc5f2a4d update logs from standard cd perf workflow (#733) 
Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-05 14:58:24 +08:00
Letong Han
6b617d6743 [ChatQnA] Update README for without Rerank Pipeline (#740) 
* update readme for chatqna w/o rerank

Signed-off-by: letonghan <letong.han@intel.com>

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

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

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-05 14:49:12 +08:00
huiyan2021
43b2ae59a1 Fix readme for nv gpu (#727) 2024-09-05 08:33:07 +08:00
Zhenzhong1
6730b242cc [ChatQnA] Update retrieval & dataprep manifests (#717) 
* modify tgi hyperparameters

* upgrade tgi 2.0.1 to 2.0.4

* Update dataprep-microservice_run.yaml

* Update retrieval-microservice_run.yaml

* Update retrieval-microservice_run.yaml

* Update dataprep-microservice_run.yaml

* Update dataprep-microservice_run.yaml

* Update dataprep-microservice_run.yaml

* Update retrieval-microservice_run.yaml

* Update retrieval-microservice_run.yaml
 2024-09-04 19:50:46 +08:00
Letong Han
4a51874e4d update readme for w/o rerank (#731) 
Signed-off-by: letonghan <letong.han@intel.com>
 2024-09-04 15:01:30 +08:00
Letong Han
55d287dfcf update readme to fix input length (#720) 
Signed-off-by: letonghan <letong.han@intel.com>
 2024-09-03 19:01:28 +08:00
Zhenzhong1
3563f5db6b [ChatQnA]Update manifests (#716) 
* update manifests for v0.9
 2024-09-03 15:24:54 +08:00
bjzhjing
8c40204eda react-ui: Add support to display Chinese (#713) 
* react-ui: Add support to display Chinese

llm-tgi microservice from GenAIComps has encoded each text, so Chinese
response will be shown as hexadecimal in react UI. Add support to decode
and display the response in Chinese. Also return raw response if no
pattern found.

Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: Ruoyu Ying <ruoyu.ying@intel.com>

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

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

---------

Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: Ruoyu Ying <ruoyu.ying@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-09-03 15:07:14 +08:00
Letong Han
afc3341156 Refine ChatQnA README for TGI (#715) 
* update chatqna readme for tgi

Signed-off-by: letonghan <letong.han@intel.com>

* update log block

Signed-off-by: letonghan <letong.han@intel.com>

---------

Signed-off-by: letonghan <letong.han@intel.com>
 2024-09-03 15:06:50 +08:00
sri-intel
e5ec38c796 Update port in set_env.sh for TGI endpoint (#649) 2024-09-03 15:05:44 +08:00
David Kinder
c6d811ab11 doc: remove invalid code block language (#705) 
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
 2024-09-03 10:10:56 +08:00
Louie Tsai
2ef83fc67b Update README.md and remove some open-source details (#682) 
According to TCEs' feedback, don't need to have those open-source project details in the flowchart.

Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
 2024-08-31 22:44:39 +08:00
Ying Chun Guo
2a6af6491a update mount path in xeon k8s (#696) 
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
 2024-08-30 15:09:00 +08:00
Letong Han
2a2ff45e2b Explain Default Model in ChatQnA and CodeTrans READMEs (#694) 
* explain default model in CodeTrans READMEs

Signed-off-by: letonghan <letong.han@intel.com>

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

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

* explain default model in ChatQnA READMEs

Signed-off-by: letonghan <letong.han@intel.com>

* add required models

Signed-off-by: letonghan <letong.han@intel.com>

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

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

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-08-29 21:22:59 +08:00
WenjiaoYue
32afb6501c update env (#678) 
Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>
 2024-08-29 10:29:35 +08:00
Abolfazl Shahbazi
1874dfd148 Remove 'vim' from all Dockerfiles (#663) 
Signed-off-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com>
Co-authored-by: lvliang-intel <liang1.lv@intel.com>
 2024-08-28 08:30:49 -07:00
Steve Zhang
4133757642 Change docs of kubernetes for curl commands in README (#661) 
* change docs for curl commands in README.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

* The Namespace 'CT' is invalid.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
 2024-08-27 19:36:37 +08:00
lvliang-intel
10c81f1c57 Update ollama run command (#668) 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
 2024-08-27 14:54:53 +08:00
xiguiw
dad8eb4b82 [Doc] Update ChatQnA flow chart (#542) 
* Update flow chart

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>

* Updated Flowchart

Signed-off-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com>

---------

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
Signed-off-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com>
Co-authored-by: Louie Tsai <louie.tsai@intel.com>
 2024-08-26 12:20:21 -07:00
lvliang-intel
af21e94a29 Add benchmark README for ChatQnA (#662) 
* Add benchmark README for ChatQnA

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

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

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

* add benchmark.yaml

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

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

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

* update yaml path

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* fix preci issue

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

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

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

* update title

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

---------

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-08-26 22:39:57 +08:00
chen, suyue
f78aa9ee2f add env for chatqna vllm (#655) 
Signed-off-by: chensuyue <suyue.chen@intel.com>
 2024-08-23 22:10:10 +08:00
Ying Hu
9657f7bc83 Update set_env.sh (#644) 2024-08-22 16:02:55 +08:00
chen, suyue
dfaf47978d optimize CI log format (#648) 
Signed-off-by: chensuyue <suyue.chen@intel.com>
 2024-08-22 15:08:59 +08:00
Zhenzhong1
e6b4fff05c Update the number of microservice replicas for OPEA v0.9 (#645) 2024-08-22 09:48:47 +08:00
lvliang-intel
a54ffd2c1e Support ChatQnA pipeline without rerank microservice (#643) 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
 2024-08-22 09:26:54 +08:00
chen, suyue
5d39506c5c Add env params for chatqna xeon test (#642) 
Signed-off-by: chensuyue <suyue.chen@intel.com>
 2024-08-21 22:53:32 +08:00
Lianhao Lu
771975510a chatqna k8s manifest: Fixed retriever-redis v0.9 image issue (#638) 
Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
 2024-08-21 22:24:29 +08:00
Sihan Chen
6674832162 fix tgi xeon tag (#641) 2024-08-21 22:17:07 +08:00
chen, suyue
db2d2bd1a1 fix chatqna guardrails (#615) 
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
 2024-08-20 22:15:23 +08:00
Zhenzhong1
ba78b4c994 update manifests for v0.9 (#632) 
* update model HF TOKEN variables & reranking name for v0.9
 2024-08-20 14:35:14 +08:00
Lianhao Lu
01c1b7504f Update K8S manifest for ChatQnA/CodeGen/CodeTrans/DocSum 
- Sync with docker-compose changes since v0.8 release

- Add K8S probes

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
 2024-08-20 10:45:15 +08:00
Ying Chun Guo
4fd3517f23 update benchmark manifest to fix errors (#626) 
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
 2024-08-19 21:59:26 +08:00
Zhenzhong1
08f57fa54a update manifests for v0.9 (#623) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-08-19 15:55:04 +08:00
lvliang-intel
b2771ad3f2 Using TGI official release docker image for intel cpu (#581) 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
 2024-08-18 17:17:44 +08:00
Ying Chun Guo
71363a6b9d change microservice tags in CD workflow (#612) 
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
 2024-08-16 21:57:28 +08:00
Letong Han
040d2b7fd9 update port for dataprep in set_env.sh (#606) 
Signed-off-by: letonghan <letong.han@intel.com>
 2024-08-16 18:15:33 +08:00