Commit Graph

196 Commits

Author SHA1 Message Date
Neo Zhang Jianyu
acdd712929 fix script issues in MD file (#538) 2024-08-13 09:20:30 +08:00
xiguiw
c297155bea Pass OLLAMA_MODEL env to docker container (#571)
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
2024-08-12 16:42:50 +08:00
jotpalch
7a67298f19 chore: add support for .md file in file upload (#555)
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-08-12 14:24:16 +08:00
Dina Suehiro Jones
a5ed2233b5 Fix minor issue in ChatQnA Gaudi docker README (#567)
Signed-off-by: dmsuehir <dina.s.jones@intel.com>
2024-08-12 12:58:42 +08:00
chen, suyue
939502dba1 support multiple test cases for ChatQnA (#553)
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-08-12 00:26:01 +08:00
Ying Chun Guo
a072441c06 improve manifest chaqna test (#565)
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
2024-08-11 00:26:32 +08:00
Veenadhari Bedida
ed483719a8 Update ChatQnA readme with OpenShift instructions (#527)
* Update ChatQnA readme with OpenShift instructions

Signed-off-by: vbedida79 <veenadhari.bedida@intel.com>

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

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

---------

Signed-off-by: vbedida79 <veenadhari.bedida@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-08-09 15:13:12 +05:30
lkk
02a15366bc update chatqna dataprep-redis port (#557)
Co-authored-by: sdp <sdp@srf797636.jf.intel.com>
2024-08-08 22:23:32 +08:00
nithi-i
ad8ca8886e Fix typo {your_ip} to {host_ip} (#533)
Co-authored-by: Pratool Bharti <pratool.bharti@intel.com>
2024-08-08 10:11:48 +08:00
Letong Han
88eeb0d7e6 Remove LangSmith from Examples (#545)
Signed-off-by: letonghan <letong.han@intel.com>
2024-08-08 09:14:38 +08:00
ZePan110
7dd9952f5e Remove deprecated folder. (#536)
Signed-off-by: zepan <ze.pan@intel.com>
2024-08-07 10:26:23 +08:00
lvliang-intel
06c4484b88 Update guardrail dokcer file path (#531)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-08-06 17:34:52 +08:00
Letong Han
3913c7bb36 Refine docker_compose for dataprep param settings (#486)
* add TEI_ENDPOINT for dataprep

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

* add TEI_ENDPOINT for dataprep

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

* update ui test file

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

* add dataprep test into script

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

* refine e2e test of chatqna

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

* fix missing dockerfile path

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

* check test issue

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

* check dataprep log

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

* reverse codetrans

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

* cd log path

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

* add hf token in compose yaml

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

* add redis_host

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

* add upload link test

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

* re-format validate dataprep

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

* fix typo

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

* fix frontend env name

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

* fix ci issue

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

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-08-06 11:57:01 +08:00
Louie Tsai
70a50d8b78 Update README.md to notify two gaudi cards needed (#293)
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
2024-08-05 14:01:29 +08:00
David Kinder
4259240407 doc: missed an H1 in the middle of a doc (#498)
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-08-05 07:45:04 +08:00
ZePan110
ac89855ff8 Fix code scan warning (#473)
Signed-off-by: zepan <ze.pan@intel.com>
2024-08-02 09:31:30 +08:00
XinyaoWa
c71bc68c9c remove ray serve (#516)
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
2024-08-02 09:28:36 +08:00
WenjiaoYue
09a3196324 Added the ChatQnA delete feature, and updated the corresponding README (#471)
Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>
2024-07-31 09:33:09 +08:00
David Kinder
015a2b178b doc: fix markdown (#474)
* fix multiple H1 headings
* remove unnecessary use of HTML
* fix missing indents on ordered list content

Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Co-authored-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com>
2024-07-31 09:24:30 +08:00
lvliang-intel
1b3398902b Add Grafana dashboard support (#466)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-07-26 20:43:58 +08:00
Sihan Chen
8032ce60f6 add guardrails after LLM in ChatQnA (#456)
* add guardrails out

* change name

* add env
2024-07-26 20:13:46 +08:00
Zhenzhong1
b61c2abd61 upload manifests (#454)
* uploadded manifests

* [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>
2024-07-26 20:12:54 +08:00
chen, suyue
965c13c556 rename docker compose.yaml (#446)
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-07-26 20:03:36 +08:00
David Kinder
8d0c8fb949 doc: fix missing title H1 heading (#458)
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Co-authored-by: Haihao Shen <haihao.shen@intel.com>
2024-07-26 09:32:54 +08:00
Letong Han
43bd8f2e4b Refine Example READMEs (#457)
* refine retrieval part in readmes

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

* unify command

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

---------

Signed-off-by: letonghan <letong.han@intel.com>
2024-07-25 11:36:47 +08:00
lvliang-intel
8b60948c7b Add auto truncate for embedding and rerank (#449)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-07-25 09:21:06 +08:00
WenjiaoYue
5984848bb0 update ChatQnA upload feature (#419)
Signed-off-by: Yue, Wenjiao <wenjiao.yue@intel.com>
2024-07-25 09:16:40 +08:00
lvliang-intel
f4b4ac0d3a Update TEI version v1.5 for better performance (#447)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-07-25 08:54:34 +08:00
gadmarkovits
c745641ba1 Added ChatQnA example using Qdrant retriever (#384)
* Added ChatQnA example using Qdrant retriever

Signed-off-by: gadmarkovits <gad.markovits@intel.com>

* Updated dockerfile path

Signed-off-by: gadmarkovits <gad.markovits@intel.com>

---------

Signed-off-by: gadmarkovits <gad.markovits@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-07-25 08:18:06 +08:00
Jaswanth Karani
1b48e54a3d code-gen-react-ui (#417)
* CodeGen: Manifest to deploy CodeGen with ReactUI into Kubernetes

Include manifest to deploy CodeGen pipeline with ReactUI into
Kubernetes. Include as well README file for the steps.

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* code-gen-react-ui

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* made changes as per PR suggestions

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

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

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

* updated readme

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

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

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

* update base image

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* updated codegn dockerfile react

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* updated wait time

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* updated as per PR comments

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* aded react ui in gaudi test file

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* fixed PR comments

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* added docker pull for text-generation-model

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

* removed unused files

Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>

---------

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>
Signed-off-by: jaswanth8888 <karani.jaswanth@gmail.com>
Co-authored-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-07-24 09:01:16 -07:00
WenjiaoYue
e371b1e9d4 Update REAME to be consistent with .env variables (#452)
* Update REAME to be consistent with .env variables

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

---------

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>
2024-07-24 15:34:11 +08:00
XinyaoWa
631d841119 Support vLLM/vLLM-on-Ray/Ray Serve for ChatQnA (#428)
* support vllm for chatqna

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add vllm-on-ray into ChatQnA

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* support ray serve in ChatQnA

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fix conflice

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* refine readme

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add UT for chatqna vllm

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add UT for ChatQnA Ray Serve

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add UT for chatqna vllm ray

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

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

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

* add vllm for chatqna on xeon

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* fix bug for vllm chatqna cpu

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

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

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

* add ut for chatqna vllm

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

---------

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-24 10:44:07 +08:00
Lianhao Lu
665c46ffae Update Kubernetes manifest files for deploying ChatQnA (#445)
Update Kubernetes manifest files for deploying ChatQnA without
GMC.

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
2024-07-24 09:59:38 +08:00
Lianhao Lu
6e797fae89 README for installing 4 worklods using helm chart (#431)
Add README to install the following workloads using helm chart:

- ChatQnA
- CodeGen
- CodeTrans
- DocSum

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
2024-07-24 09:46:03 +08:00
yang yuhan
b46ae8bdcc Fix a minor bug for chatqna in docker-compose (#442) (#443)
Embedding and reranking services failed to run on GPU H100.
Change the image tag and use CPU for these services. This PR will
fix #442

Signed-off-by: PeterYang12 <yuhan.yang@intel.com>
2024-07-24 08:41:47 +08:00
Steve Zhang
290a74fae9 Update all examples yaml files of GMC in GenAIExample (#436)
* Update all examples yaml files of GMC in GenAIExample.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
2024-07-23 16:40:51 +08:00
Letong Han
8ad7f36fe2 Update READMEs (#430)
* update readme gaudi part & add tei-gaudi params

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

* modify supported habana driver version

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

* update env set part

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

* add example for no_proxy

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

* add an example of public ip

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

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-23 15:25:02 +08:00
chen, suyue
bb42307af9 add docker compose yaml print for test (#433)
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-07-22 15:36:03 +08:00
chen, suyue
ee0dcb3d37 expand tgi connect timeout (#424)
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-07-18 21:28:48 +08:00
Letong Han
f732674b1e Refine README of Examples (#420)
* update chatqna readme and set env script

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

* update for comments

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

* add consume

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

* modify details

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

* update codegen readme

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

* add patch modifications

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

* update codegen readme

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

* update ui options

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

* udpate codetrans readme

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

* update docsum & searchqna readme

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>
2024-07-18 21:17:09 +08:00
Ruoyu Ying
d9946180a2 doc: fix minor issue in GMC doc (#383)
Signed-off-by: Ruoyu Ying <ruoyu.ying@intel.com>
2024-07-18 16:21:28 +08:00
ZePan110
11a56e09ef Adding Chatqna Benchmark Test (#404)
Signed-off-by: zepan <ze.pan@intel.com>
2024-07-18 16:03:29 +08:00
lvliang-intel
9551594164 Add guardrails in the ChatQnA pipeline (#407)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-07-17 21:09:54 +08:00
xiguiw
97da49f61e [Doc]Add ChatQnA Flow Chart (#398)
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
2024-07-16 21:05:56 +08:00
Sihan Chen
ba65415b78 Fix win PC issues (#399)
* change to LF

* add readme for windows pc

* add OLLAMA_MODEL param

* readme

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

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

* Update README.md

* Update docker_compose.yaml

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-15 17:11:49 +08:00
chen, suyue
3505bd25a4 update tgi-gaudi version (#389)
Signed-off-by: chensuyue <suyue.chen@intel.com>
Co-authored-by: Spycsh <sihan.chen@intel.com>
2024-07-12 15:01:03 +08:00
Malini Bhandaru
c37d9c82b0 Updated READMEs for kubernetes example pipelines (#353)
* Updated READMEs for kubernetes.
Signed-off-by: mkbhanda <malini.bhandaru@intel.com>

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

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

* Kubernetes related Readme.
Signed-off-by: mkbhanda <malini.bhandaru@intel.com>

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-10 09:03:08 +08:00
Yogesh Pandey
89ddec9b2d Updates for running ChatQnA + Conversational UI on Gaudi (#357)
* [pre-commit.ci] auto fixes from pre-commit.com hooks

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

* Added README and docker-compose updates for running chat Conversation on Gaudi

Signed-off-by: Yogesh Pandey <yogesh.pandey@intel.com>

* Updated tests

Signed-off-by: Yogesh Pandey <yogesh.pandey@intel.com>

* updates README and compose file as per review comments

Signed-off-by: Yogesh Pandey <yogesh.pandey@intel.com>

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

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

---------

Signed-off-by: Yogesh Pandey <yogesh.pandey@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-07-10 09:01:59 +08:00
lvliang-intel
d7a5b751d9 Update reranking microservice dockerfile path (#381)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-07-10 09:01:26 +08:00
Ying Chun Guo
15fc6f9711 Optimize gmc manifest e2e tests (#382)
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
2024-07-09 14:46:58 +08:00