Commit Graph

  • a1712035a4 Block links that require real person verification (#897) ZePan110 2024-11-13 21:43:20 +08:00
  • e879366cf8 Multiple models support for LLM TGI (#835) sgurunat 2024-11-13 14:41:43 +05:30
  • 9e471a9ecc Block links that require real person verification (#896) ZePan110 2024-11-13 16:42:57 +08:00
  • 393367e9f1 Fix left issue of tgi version update (#1121) chen, suyue 2024-11-13 15:42:42 +08:00
  • 550325d8cb vLLM support for DocSum (#885) sgurunat 2024-11-13 12:50:15 +05:30
  • f5c60f10b1 vLLM support for FAQGen (#884) sgurunat 2024-11-13 11:47:49 +05:30
  • baafa402c2 Add support for Audio and Video summarization to Docsum (#865) Mustafa 2024-11-12 21:51:45 -08:00
  • 7adbba6add Enable vLLM Profiling for ChatQnA (#1124) Louie Tsai 2024-11-12 19:26:31 -08:00
  • 3b106c82ef Replace HTTP "inprogress" gauge with megaservice "request_pending" one (#864) Eero Tamminen 2024-11-13 03:52:24 +02:00
  • 2d0eea90d2 quick fix (#894) ZePan110 2024-11-13 09:41:02 +08:00
  • f1594cb54f Fix missing end of file chars (#874) Abolfazl Shahbazi 2024-11-12 17:34:03 -08:00
  • 0d52c2f003 Pinecone update to Readme and docker compose for ChatQnA (#540) pallavijaini0525 2024-11-12 17:32:37 -08:00
  • e39b08f3d0 agent short & long term memory with langgraph. (#851) lkk 2024-11-12 17:28:37 +08:00
  • 24b9f03f48 vLLM support for Codegen (#886) sgurunat 2024-11-12 12:53:31 +05:30
  • 23c99c1170 Combine CI/CD docker compose. (#861) ZePan110 2024-11-12 15:15:21 +08:00
  • 1ff85f6a85 Upgrade TGI Gaudi version to v2.0.6 (#1088) lvliang-intel 2024-11-12 14:38:22 +08:00
  • 37f35140cc Add DPO support in finetuning microservice (#857) XinyuYe-Intel 2024-11-12 11:35:03 +08:00
  • f7a7f8aa3f Fix typo (#1117) bjzhjing 2024-11-12 09:54:05 +08:00
  • e3187be819 Update ChatQnA manifests using always pull image policy (#1100) lvliang-intel 2024-11-11 14:37:14 +08:00
  • abd9d12937 Fix non stream case (#1115) Sihan Chen 2024-11-11 14:18:42 +08:00
  • a7353bbaa4 Refine performance directory (#1017) bjzhjing 2024-11-11 13:58:46 +08:00
  • aa314f6757 [Readme] Update ChatQnA Readme for LLM Endpoint (#1086) Letong Han 2024-11-11 13:53:06 +08:00
  • 91940b8058 Merge branch 'main' of https://github.com/opea-project/GenAIExamples into reorg_helm_chart reorg_helm_chart letonghan 2024-11-11 13:49:52 +08:00
  • 3744bb8c1b Fix docSum ui error in accessing parsed files (#1079) WenjiaoYue 2024-11-11 09:10:12 +08:00
  • 9a50131d69 Enable bash scr to to be path-independent using $0 to address ERROR: failed to solve: failed to read dockerfile: open Dockerfile.intel_hpu: no such file or director when following README (#808) qgao007 2024-11-08 13:04:06 -07:00
  • 82801d0121 image build bug fix (#1105) chen, suyue 2024-11-08 23:54:32 +08:00
  • 52757b382c Enable Intel ARC gpu test for vllm openvino. (#856) senhui2intel 2024-11-08 22:38:27 +08:00
  • f7026773b8 [ChatQnA] Fix the no_proxy setting for gpu example (#1078) Wang, Kai Lawrence 2024-11-08 22:27:51 +08:00
  • edc09ece5c ProductivitySuite: Fix typo in README (#1083) Hoong Tee, Yeoh 2024-11-08 22:26:32 +08:00
  • dfed2aead2 Bump gradio from 5.0.0 to 5.5.0 in /MultimodalQnA/ui/gradio (#1080) dependabot[bot] 2024-11-08 22:24:36 +08:00
  • 049517f977 Improve the robustness of links check workflow (#1096) ZePan110 2024-11-08 22:19:52 +08:00
  • ee83a6d5b4 opt CI to skip none MD and RST files (#1098) Neo Zhang Jianyu 2024-11-08 22:07:17 +08:00
  • 09980b5355 opt CI to skip none MD and RST files (#873) Neo Zhang Jianyu 2024-11-08 22:07:10 +08:00
  • e2bdd19fd4 update faqGen ui response (#1091) WenjiaoYue 2024-11-08 21:29:52 +08:00
  • c9088eb824 Add EdgeCraftRag as a GenAIExample (#1072) Zhu Yongbo 2024-11-08 21:07:24 +08:00
  • 75eb864d78 update llm endpoint validation commands (#869) Letong Han 2024-11-08 19:45:06 +08:00
  • 9c3023a12e Fix faq ut bug (#1097) XinyaoWa 2024-11-08 16:27:00 +08:00
  • 7d779513f5 add docsum helm charts letonghan 2024-11-08 16:04:29 +08:00
  • ca6a4e3609 Remove health check log (#853) dolpher 2024-11-08 15:54:58 +08:00
  • bbc95bb708 MultimodalQnA Image and Audio Support Phase 1 (#1071) Melanie Hart Buehler 2024-11-07 23:54:49 -08:00
  • 46ff36c008 Fixed the issue of asynchronous call failure for MosecEmbeddings (#871) Yao Qing 2024-11-08 15:54:16 +08:00
  • dd9623d3d5 Add new image repo clone. (#1093) ZePan110 2024-11-08 15:27:42 +08:00
  • ef507ce6fa fix doc format issue (#870) Neo Zhang Jianyu 2024-11-08 14:58:35 +08:00
  • c0109da594 fix module id xuehao/check_idle_devices Sun, Xuehao 2024-11-08 14:43:13 +08:00
  • a2b9d95f86 Add vLLM ARC support with OpenVINO backend (#641) Li Gang 2024-11-08 14:13:06 +08:00
  • 4c27a3d30c Align faqgen to form input (#1089) XinyaoWa 2024-11-08 13:32:26 +08:00
  • 617e119f67 Remove useless vllm ray (#859) XinyaoWa 2024-11-08 13:04:19 +08:00
  • 40386d9bd6 remove vllm-on-ray (#1084) XinyaoWa 2024-11-08 13:01:48 +08:00
  • 3401db2032 fix list_service method not returning expected response (#787) (#788) Isaac Ng 2024-11-08 12:14:17 +08:00
  • fe97e88c7a Add CI case to check online doc building, not update online doc (#1087) Neo Zhang Jianyu 2024-11-08 11:57:01 +08:00
  • 5eca5da368 Add CI case to check online doc building, not update online doc (#867) Neo Zhang Jianyu 2024-11-08 11:56:46 +08:00
  • 453ff726a6 support faqgen upload file in UI (#866) XinyaoWa 2024-11-08 11:54:04 +08:00
  • 78d8276325 [Dataprep] Fix Delete Bug (#863) Letong Han 2024-11-08 11:00:49 +08:00
  • 29ef64269a MultimodalQnA Image and Audio Support Phase 1 (#852) Melanie Hart Buehler 2024-11-07 18:19:46 -08:00
  • 11d8b24c8a ProductivitySuite: Update TGI CPU image version to 2.4.0 (#1062) Hoong Tee, Yeoh 2024-11-08 09:50:11 +08:00
  • 4635a927fa Make embedding run on CPU for aligning with Gaudi performance benchmark (#1057) lvliang-intel 2024-11-07 17:39:34 +08:00
  • 786cabe57d align vllm hpu version to latest vllm-fork (#860) XinyaoWa 2024-11-07 14:14:58 +08:00
  • 1da44d99a1 Remove debug outputs (#1085) ZePan110 2024-11-07 14:11:46 +08:00
  • e9b164505e align vllm hpu version to latest vllm-fork (#1061) XinyaoWa 2024-11-07 14:08:56 +08:00
  • 6263b517b9 [Doc] Add steps to deploy opea services using minikube (#1058) Arthur Leung 2024-11-07 00:57:34 -05:00
  • 618f45bab1 Upgrade habana docker version to 1.18.0 (#854) lvliang-intel 2024-11-07 11:28:48 +08:00
  • 2de7c0ba89 Enhance CI hardware list detect (#1077) chen, suyue 2024-11-07 09:38:19 +08:00
  • 518cdfb6e3 add dynamic batching embedding/reranking (#774) Sihan Chen 2024-11-06 16:13:36 +08:00
  • ebd2ab0222 Update tuned_single_gaudi_with_rerank.yaml helmcharts_vllm Zhenzhong1 2024-11-06 16:00:41 +08:00
  • 29e3595982 fix Sun, Xuehao 2024-11-06 12:20:39 +08:00
  • 47b72ea4cb Add script to get idle device Sun, Xuehao 2024-11-06 11:25:17 +08:00
  • a8e5adc4d0 [Exporter Tool] Updated exporter tool for docker compose and k8s manifests. (#813) Yao Qing 2024-11-06 10:34:04 +08:00
  • 944ae47948 [ChatQnA] Fix the service connection issue on GPU and modify the emb backend (#1059) Wang, Kai Lawrence 2024-11-06 10:22:21 +08:00
  • b8948f248f fix format issue (#855) Neo Zhang Jianyu 2024-11-05 17:05:20 +08:00
  • 2d9aeb3715 fix wrong format which break online doc build (#1073) Neo Zhang Jianyu 2024-11-05 17:01:40 +08:00
  • a0921f127f [Doc] Fix broken build instruction (#1063) xiguiw 2024-11-05 13:35:12 +08:00
  • cf86aceb18 Update nightly image build jobs (#1070) chen, suyue 2024-11-05 09:14:44 +08:00
  • c2b7bd25d9 Use docker stop instead of docker compose stop to avoid container clean up issue (#1068) chen, suyue 2024-11-04 22:54:19 +08:00
  • 78331ee678 Add nightly image build and publish action (#1067) chen, suyue 2024-11-04 17:22:56 +08:00
  • 7f7ad0e256 Inject commit for the release docker image (#1060) ZePan110 2024-11-04 17:08:15 +08:00
  • c1c5798485 Add issue template (#785) Isaac Ng 2024-11-04 15:57:14 +08:00
  • acf07cd90d fix prometheus invalid metric name (#849) Sihan Chen 2024-11-04 12:00:02 +08:00
  • 0306c620b5 Update TGI CPU image to latest official release 2.4.0 (#1035) lvliang-intel 2024-11-04 11:28:43 +08:00
  • a6998a1dbd Add E2E Promeheus metrics to applications (#845) Eero Tamminen 2024-11-04 03:58:23 +02:00
  • 3372b9d480 update accuracy embedding endpoint for no wrapper (#1056) lkk 2024-11-04 09:18:49 +08:00
  • 5eb3d2869f Update AgentQnA example for v1.1 release (#885) minmin-intel 2024-11-03 17:17:19 -08:00
  • 7477e3b592 fix: Update pre-commit prettier mirror to running prettier in local #765 (#779) KS Foong 2024-11-03 23:36:03 +08:00
  • ced68e1834 Add performance benchmark scripts for 4 use cases. (#1052) Yi Yao 2024-11-03 12:41:02 +08:00
  • c8e363901a Update RAGAgentLlama and ReActLlama (#843) minmin-intel 2024-11-01 15:40:14 -07:00
  • 9f68bd394b enable parameter k to get web resources (#844) Letong Han 2024-11-01 15:58:36 +08:00
  • 6dbb0a7fd7 gpt-sovits: Run as normal user (#839) Lianhao Lu 2024-11-01 10:03:41 +08:00
  • bf5c391e47 Add Workflow Executor Example (#892) JoshuaL3000 2024-11-01 09:50:20 +08:00
  • c65d7d40fb fix vllm output in chatqna (#1038) XinyaoWa 2024-11-01 09:26:57 +08:00
  • 74df6bb728 Remote TGI/TGI services with OAuth Client Credentials authentication (#836) sgurunat 2024-10-31 18:08:48 +05:30
  • 9d124161e0 update action for CI (#1050) chen, suyue 2024-10-31 14:54:04 +08:00
  • 0f5a9c4a5e Fix ChatQnA manifest test issue on Xeon (#1044) chen, suyue 2024-10-31 14:23:17 +08:00
  • a65640b4a5 Graph rag (#1007) rbrugaro 2024-10-30 08:52:25 -07:00
  • d2e9c0a9dd Pinecone retriever index fix (#816) Dan 2024-10-30 08:35:16 -05:00
  • 9f692c4215 Fix web_retriever batch size issue (#834) Letong Han 2024-10-30 17:11:19 +08:00
  • 19330ea23f GraphRAG with llama-index (#793) rbrugaro 2024-10-29 22:45:44 -07:00
  • 7197286a14 Fix ChatQnA manifest default port issue (#1033) lvliang-intel 2024-10-30 11:52:04 +08:00
  • 960805a57b Adding audio and image/video files needed for loading the Gradio UI, and update the UI Python function (#1034) Chun Tao 2024-10-29 19:05:02 -07:00
  • 00abba253a Enable bf16 quantization of models, and fix resetting args.audio in the microservice between runs (#832) Chun Tao 2024-10-29 19:04:56 -07:00
  • 002f0e2b11 Update VisualQnA README.md for its workflow (#912) Louie Tsai 2024-10-29 18:27:22 -07:00
  • 2f1f80bbae fixed the issue of cm Zhenzhong1 2024-10-29 03:03:21 -07:00