From f7a7f8aa3f8aeaa95cb0ddcde9b9f701698d2b85 Mon Sep 17 00:00:00 2001 From: bjzhjing Date: Tue, 12 Nov 2024 09:54:05 +0800 Subject: [PATCH 1/6] Fix typo (#1117) Signed-off-by: Cathy Zhang --- .../benchmark/performance/kubernetes/intel/gaudi/README.md | 4 ++-- .../kubernetes/intel/gaudi/generate_helm_values.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md index 6497828fe..d667727f4 100644 --- a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md +++ b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md @@ -100,12 +100,12 @@ python deploy.py --uninstall #### Case 2: Baseline Deployment without Rerank ```bash -python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2 +python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2 ``` #### Case 3: Tuned Deployment with Rerank ```bash -python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2 --with-rerank --tuned +python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2 --with-rerank --tuned ``` ## Benchmark diff --git a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py index bcaba6b3f..b28881800 100644 --- a/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py +++ b/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py @@ -99,7 +99,7 @@ def generate_helm_values(with_rerank, num_nodes, hf_token, model_dir, node_selec }, {"name": "teirerank", "resources": {"limits": {"habana.ai/gaudi": 1}}} if with_rerank else None, {"name": "tgi", "resources": {"limits": {"habana.ai/gaudi": 1}}}, - {"name": "retriever", "resources": {"requests": {"cpu": "8", "memory": "8000Mi"}}}, + {"name": "retriever-usvc", "resources": {"requests": {"cpu": "8", "memory": "8000Mi"}}}, ] # Filter out any None values directly as part of initialization From 1ff85f6a852785a3abad7a5b286e020592dfd2b7 Mon Sep 17 00:00:00 2001 From: lvliang-intel Date: Tue, 12 Nov 2024 14:38:22 +0800 Subject: [PATCH 2/6] Upgrade TGI Gaudi version to v2.0.6 (#1088) Signed-off-by: lvliang-intel Co-authored-by: chen, suyue --- .../docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml | 2 +- AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- AudioQnA/kubernetes/intel/README_gmc.md | 2 +- .../intel/hpu/gaudi/manifest/audioqna.yaml | 2 +- AudioQnA/tests/test_compose_on_gaudi.sh | 2 +- AudioQnA/tests/test_compose_on_xeon.sh | 2 +- .../docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- AvatarChatbot/tests/test_compose_on_gaudi.sh | 2 +- AvatarChatbot/tests/test_compose_on_xeon.sh | 2 +- ChatQnA/benchmark/accuracy/README.md | 2 +- .../eight_gaudi/oob_eight_gaudi_with_rerank.yaml | 2 +- .../four_gaudi/oob_four_gaudi_with_rerank.yaml | 2 +- .../single_gaudi/oob_single_gaudi_with_rerank.yaml | 2 +- .../two_gaudi/oob_two_gaudi_with_rerank.yaml | 2 +- .../eight_gaudi/oob_eight_gaudi_without_rerank.yaml | 2 +- .../four_gaudi/oob_four_gaudi_without_rerank.yaml | 2 +- .../oob_single_gaudi_without_rerank.yaml | 2 +- .../two_gaudi/oob_two_gaudi_without_rerank.yaml | 2 +- .../eight_gaudi/eight_gaudi_with_rerank.yaml | 2 +- .../four_gaudi/tuned_four_gaudi_with_rerank.yaml | 2 +- .../single_gaudi/tuned_single_gaudi_with_rerank.yaml | 2 +- .../two_gaudi/tuned_two_gaudi_with_rerank.yaml | 2 +- .../tuned_eight_gaudi_without_rerank.yaml | 2 +- .../four_gaudi/tuned_four_gaudi_without_rerank.yaml | 2 +- .../tuned_single_gaudi_without_rerank.yaml | 2 +- .../two_gaudi/tuned_two_gaudi_without_rerank.yaml | 2 +- ChatQnA/chatqna.yaml | 2 +- ChatQnA/docker_compose/intel/hpu/gaudi/README.md | 4 ++-- ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- .../intel/hpu/gaudi/compose_guardrails.yaml | 4 ++-- .../intel/hpu/gaudi/compose_without_rerank.yaml | 2 +- .../intel/hpu/gaudi/how_to_validate_service.md | 12 ++++++------ ChatQnA/kubernetes/intel/README_gmc.md | 2 +- .../intel/hpu/gaudi/manifest/chatqna-guardrails.yaml | 7 ++++++- .../kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml | 2 +- ChatQnA/tests/test_compose_guardrails_on_gaudi.sh | 2 +- ChatQnA/tests/test_compose_on_gaudi.sh | 2 +- ChatQnA/tests/test_compose_vllm_on_xeon.sh | 2 +- .../tests/test_compose_without_rerank_on_gaudi.sh | 2 +- ChatQnA/tests/test_compose_without_rerank_on_xeon.sh | 2 +- CodeGen/codegen.yaml | 2 +- CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- .../kubernetes/intel/hpu/gaudi/manifest/codegen.yaml | 2 +- CodeGen/tests/test_compose_on_gaudi.sh | 2 +- CodeTrans/codetrans.yaml | 2 +- .../docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- .../intel/hpu/gaudi/manifest/codetrans.yaml | 2 +- CodeTrans/tests/test_compose_on_gaudi.sh | 2 +- DocSum/docker_compose/intel/hpu/gaudi/README.md | 4 ++-- DocSum/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- DocSum/docsum.yaml | 2 +- DocSum/kubernetes/intel/README_gmc.md | 2 +- .../kubernetes/intel/hpu/gaudi/manifest/docsum.yaml | 2 +- DocSum/tests/test_compose_on_gaudi.sh | 2 +- FaqGen/benchmark/accuracy/launch_tgi.sh | 2 +- FaqGen/docker_compose/intel/hpu/gaudi/README.md | 4 ++-- FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- FaqGen/faqgen.yaml | 2 +- .../kubernetes/intel/hpu/gaudi/manifest/faqgen.yaml | 2 +- FaqGen/tests/test_compose_on_gaudi.sh | 2 +- GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- GraphRAG/tests/test_compose.sh | 2 +- .../docker_compose/intel/hpu/gaudi/README.md | 4 ++-- .../docker_compose/intel/hpu/gaudi/compose.yaml | 6 +++++- MultimodalQnA/tests/test_compose_on_gaudi.sh | 2 +- .../docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- SearchQnA/tests/test_compose_on_gaudi.sh | 2 +- .../docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- .../intel/hpu/gaudi/manifest/translation.yaml | 2 +- Translation/tests/test_compose_on_gaudi.sh | 2 +- Translation/translation.yaml | 2 +- VisualQnA/docker_compose/intel/hpu/gaudi/README.md | 4 ++-- .../docker_compose/intel/hpu/gaudi/compose.yaml | 2 +- VisualQnA/tests/test_compose_on_gaudi.sh | 2 +- 74 files changed, 94 insertions(+), 85 deletions(-) diff --git a/AgentQnA/docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml b/AgentQnA/docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml index cd5dd202d..59c5671e1 100644 --- a/AgentQnA/docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml +++ b/AgentQnA/docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml @@ -3,7 +3,7 @@ services: tgi-server: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-server ports: - "8085:80" diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml index c3f885fce..b536522c4 100644 --- a/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -51,7 +51,7 @@ services: environment: TTS_ENDPOINT: ${TTS_ENDPOINT} tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "3006:80" diff --git a/AudioQnA/kubernetes/intel/README_gmc.md b/AudioQnA/kubernetes/intel/README_gmc.md index 30d879e19..767fdf366 100644 --- a/AudioQnA/kubernetes/intel/README_gmc.md +++ b/AudioQnA/kubernetes/intel/README_gmc.md @@ -25,7 +25,7 @@ The AudioQnA uses the below prebuilt images if you choose a Xeon deployment Should you desire to use the Gaudi accelerator, two alternate images are used for the embedding and llm services. For Gaudi: -- tgi-service: ghcr.io/huggingface/tgi-gaudi:2.0.5 +- tgi-service: ghcr.io/huggingface/tgi-gaudi:2.0.6 - whisper-gaudi: opea/whisper-gaudi:latest - speecht5-gaudi: opea/speecht5-gaudi:latest diff --git a/AudioQnA/kubernetes/intel/hpu/gaudi/manifest/audioqna.yaml b/AudioQnA/kubernetes/intel/hpu/gaudi/manifest/audioqna.yaml index 2d0c567e3..6659a7811 100644 --- a/AudioQnA/kubernetes/intel/hpu/gaudi/manifest/audioqna.yaml +++ b/AudioQnA/kubernetes/intel/hpu/gaudi/manifest/audioqna.yaml @@ -271,7 +271,7 @@ spec: - envFrom: - configMapRef: name: audio-qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 name: llm-dependency-deploy-demo securityContext: capabilities: diff --git a/AudioQnA/tests/test_compose_on_gaudi.sh b/AudioQnA/tests/test_compose_on_gaudi.sh index 69270736d..e626b2671 100644 --- a/AudioQnA/tests/test_compose_on_gaudi.sh +++ b/AudioQnA/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="audioqna whisper-gaudi asr llm-tgi speecht5-gaudi tts" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/AudioQnA/tests/test_compose_on_xeon.sh b/AudioQnA/tests/test_compose_on_xeon.sh index b36b5c7de..926a51a33 100644 --- a/AudioQnA/tests/test_compose_on_xeon.sh +++ b/AudioQnA/tests/test_compose_on_xeon.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="audioqna whisper asr llm-tgi speecht5 tts" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml b/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml index 06a7e4e05..298149ef1 100644 --- a/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml @@ -54,7 +54,7 @@ services: environment: TTS_ENDPOINT: ${TTS_ENDPOINT} tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "3006:80" diff --git a/AvatarChatbot/tests/test_compose_on_gaudi.sh b/AvatarChatbot/tests/test_compose_on_gaudi.sh index ebb185120..ae404b236 100755 --- a/AvatarChatbot/tests/test_compose_on_gaudi.sh +++ b/AvatarChatbot/tests/test_compose_on_gaudi.sh @@ -29,7 +29,7 @@ function build_docker_images() { service_list="avatarchatbot whisper-gaudi asr llm-tgi speecht5-gaudi tts wav2lip-gaudi animation" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/AvatarChatbot/tests/test_compose_on_xeon.sh b/AvatarChatbot/tests/test_compose_on_xeon.sh index 1b1780a1b..2bed682cf 100755 --- a/AvatarChatbot/tests/test_compose_on_xeon.sh +++ b/AvatarChatbot/tests/test_compose_on_xeon.sh @@ -29,7 +29,7 @@ function build_docker_images() { service_list="avatarchatbot whisper asr llm-tgi speecht5 tts wav2lip animation" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/ChatQnA/benchmark/accuracy/README.md b/ChatQnA/benchmark/accuracy/README.md index 0cfae4564..c07313948 100644 --- a/ChatQnA/benchmark/accuracy/README.md +++ b/ChatQnA/benchmark/accuracy/README.md @@ -48,7 +48,7 @@ To setup a LLM model, we can use [tgi-gaudi](https://github.com/huggingface/tgi- docker run -p {your_llm_port}:80 --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HF_TOKEN={your_hf_token} --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.1 --model-id mistralai/Mixtral-8x7B-Instruct-v0.1 --max-input-tokens 2048 --max-total-tokens 4096 --sharded true --num-shard 2 # for better performance, set `PREFILL_BATCH_BUCKET_SIZE`, `BATCH_BUCKET_SIZE`, `max-batch-total-tokens`, `max-batch-prefill-tokens` -docker run -p {your_llm_port}:80 --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HF_TOKEN={your_hf_token} -e PREFILL_BATCH_BUCKET_SIZE=1 -e BATCH_BUCKET_SIZE=8 --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.5 --model-id mistralai/Mixtral-8x7B-Instruct-v0.1 --max-input-tokens 2048 --max-total-tokens 4096 --sharded true --num-shard 2 --max-batch-total-tokens 65536 --max-batch-prefill-tokens 2048 +docker run -p {your_llm_port}:80 --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HF_TOKEN={your_hf_token} -e PREFILL_BATCH_BUCKET_SIZE=1 -e BATCH_BUCKET_SIZE=8 --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id mistralai/Mixtral-8x7B-Instruct-v0.1 --max-input-tokens 2048 --max-total-tokens 4096 --sharded true --num-shard 2 --max-batch-total-tokens 65536 --max-batch-prefill-tokens 2048 ``` ### Prepare Dataset diff --git a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/eight_gaudi/oob_eight_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/eight_gaudi/oob_eight_gaudi_with_rerank.yaml index 8e74fe6ad..6198e2fac 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/eight_gaudi/oob_eight_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/eight_gaudi/oob_eight_gaudi_with_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml index 95f00644c..9c04cfc06 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml index 4fb165707..30df76b97 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml index 0d379f5b5..54cefbaf9 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/eight_gaudi/oob_eight_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/eight_gaudi/oob_eight_gaudi_without_rerank.yaml index 42e9ed4d4..91554a812 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/eight_gaudi/oob_eight_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/eight_gaudi/oob_eight_gaudi_without_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml index 0338a8768..7b81e252a 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml index 9d423ffaf..61346908f 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml index f405bcce6..72ada0191 100644 --- a/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/oob/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml @@ -237,7 +237,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/eight_gaudi/eight_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/eight_gaudi/eight_gaudi_with_rerank.yaml index 9b47fa0be..80122d731 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/eight_gaudi/eight_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/eight_gaudi/eight_gaudi_with_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml index 813a8e44c..970d2652a 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml index 32e5bd884..a38294b3b 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml index 055f66f0d..e6f94894c 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/eight_gaudi/tuned_eight_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/eight_gaudi/tuned_eight_gaudi_without_rerank.yaml index 5d6793cd9..365cd5ab5 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/eight_gaudi/tuned_eight_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/eight_gaudi/tuned_eight_gaudi_without_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml index 0cfb09b0f..6af61b1ff 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml index a9f7e4639..dc56cc96f 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml index a072d36ff..f14ebc215 100644 --- a/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml +++ b/ChatQnA/benchmark/performance-deprecated/tuned/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml @@ -255,7 +255,7 @@ spec: envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent name: llm-dependency-deploy ports: diff --git a/ChatQnA/chatqna.yaml b/ChatQnA/chatqna.yaml index e8a2d2735..89aac8aa8 100644 --- a/ChatQnA/chatqna.yaml +++ b/ChatQnA/chatqna.yaml @@ -38,7 +38,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/README.md b/ChatQnA/docker_compose/intel/hpu/gaudi/README.md index 02620ea7b..ad56d525a 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/README.md @@ -192,7 +192,7 @@ For users in China who are unable to download models directly from Huggingface, export HF_TOKEN=${your_hf_token} export HF_ENDPOINT="https://hf-mirror.com" model_name="Intel/neural-chat-7b-v3-3" - docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.5 --model-id $model_name --max-input-tokens 1024 --max-total-tokens 2048 + docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id $model_name --max-input-tokens 1024 --max-total-tokens 2048 ``` 2. Offline @@ -206,7 +206,7 @@ For users in China who are unable to download models directly from Huggingface, ```bash export HF_TOKEN=${your_hf_token} export model_path="/path/to/model" - docker run -p 8008:80 -v $model_path:/data --name tgi_service --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.5 --model-id /data --max-input-tokens 1024 --max-total-tokens 2048 + docker run -p 8008:80 -v $model_path:/data --name tgi_service --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id /data --max-input-tokens 1024 --max-total-tokens 2048 ``` ### Setup Environment Variables diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml index a47575b31..0658c0c2f 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -78,7 +78,7 @@ services: MAX_WARMUP_SEQUENCE_LENGTH: 512 command: --model-id ${RERANK_MODEL_ID} --auto-truncate tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8005:80" diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml index 570d689c2..79cf3f371 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml @@ -26,7 +26,7 @@ services: TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} tgi-guardrails-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-guardrails-server ports: - "8088:80" @@ -117,7 +117,7 @@ services: MAX_WARMUP_SEQUENCE_LENGTH: 512 command: --model-id ${RERANK_MODEL_ID} --auto-truncate tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8008:80" diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml index 9117a13a6..524b44c1a 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml @@ -57,7 +57,7 @@ services: HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} restart: unless-stopped tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8005:80" diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md b/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md index 7448ae625..9214960c2 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md @@ -48,16 +48,16 @@ f810f3b4d329 opea/embedding-tei:latest "python e 2fa17d84605f opea/dataprep-redis:latest "python prepare_doc_…" 2 minutes ago Up 2 minutes 0.0.0.0:6007->6007/tcp, :::6007->6007/tcp dataprep-redis-server 69e1fb59e92c opea/retriever-redis:latest "/home/user/comps/re…" 2 minutes ago Up 2 minutes 0.0.0.0:7000->7000/tcp, :::7000->7000/tcp retriever-redis-server 313b9d14928a opea/reranking-tei:latest "python reranking_te…" 2 minutes ago Up 2 minutes 0.0.0.0:8000->8000/tcp, :::8000->8000/tcp reranking-tei-gaudi-server -05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.5 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-gaudi-server +05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.6 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-gaudi-server 174bd43fa6b5 ghcr.io/huggingface/tei-gaudi:latest "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8090->80/tcp, :::8090->80/tcp tei-embedding-gaudi-server 74084469aa33 redis/redis-stack:7.2.0-v9 "/entrypoint.sh" 2 minutes ago Up 2 minutes 0.0.0.0:6379->6379/tcp, :::6379->6379/tcp, 0.0.0.0:8001->8001/tcp, :::8001->8001/tcp redis-vector-db 88399dbc9e43 ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8808->80/tcp, :::8808->80/tcp tei-reranking-gaudi-server ``` -In this case, `ghcr.io/huggingface/tgi-gaudi:2.0.5` Existed. +In this case, `ghcr.io/huggingface/tgi-gaudi:2.0.6` Existed. ``` -05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.5 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-gaudi-server +05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.6 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-gaudi-server ``` Next we can check the container logs to get to know what happened during the docker start. @@ -68,7 +68,7 @@ Check the log of container by: `docker logs -t` -View the logs of `ghcr.io/huggingface/tgi-gaudi:2.0.5` +View the logs of `ghcr.io/huggingface/tgi-gaudi:2.0.6` `docker logs 05c40b636239 -t` @@ -97,7 +97,7 @@ So just make sure the devices are available. Here is another failure example: ``` -f7a08f9867f9 ghcr.io/huggingface/tgi-gaudi:2.0.5 "text-generation-lau…" 16 seconds ago Exited (2) 14 seconds ago tgi-gaudi-server +f7a08f9867f9 ghcr.io/huggingface/tgi-gaudi:2.0.6 "text-generation-lau…" 16 seconds ago Exited (2) 14 seconds ago tgi-gaudi-server ``` Check the log by `docker logs f7a08f9867f9 -t`. @@ -114,7 +114,7 @@ View the docker input parameters in `./ChatQnA/docker_compose/intel/hpu/gaudi/co ``` tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8008:80" diff --git a/ChatQnA/kubernetes/intel/README_gmc.md b/ChatQnA/kubernetes/intel/README_gmc.md index 860bae720..a2ffed26b 100644 --- a/ChatQnA/kubernetes/intel/README_gmc.md +++ b/ChatQnA/kubernetes/intel/README_gmc.md @@ -25,7 +25,7 @@ Should you desire to use the Gaudi accelerator, two alternate images are used fo For Gaudi: - tei-embedding-service: ghcr.io/huggingface/tei-gaudi:latest -- tgi-service: gghcr.io/huggingface/tgi-gaudi:2.0.5 +- tgi-service: gghcr.io/huggingface/tgi-gaudi:2.0.6 > [NOTE] > Please refer to [Xeon README](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker_compose/intel/cpu/xeon/README.md) or [Gaudi README](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker_compose/intel/hpu/gaudi/README.md) to build the OPEA images. These too will be available on Docker Hub soon to simplify use. diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml index cd40efed1..b2cc29e89 100644 --- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml +++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml @@ -1103,7 +1103,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: Always volumeMounts: - mountPath: /data @@ -1184,8 +1184,13 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault +<<<<<<< HEAD + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" + imagePullPolicy: IfNotPresent +======= image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" imagePullPolicy: Always +>>>>>>> e3187be819ad088c24bf1b2cbb419255af0f2be3 volumeMounts: - mountPath: /data name: model-volume diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml index 1c80ca5af..72ba1ded9 100644 --- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml +++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml @@ -924,7 +924,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: Always volumeMounts: - mountPath: /data diff --git a/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh b/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh index fcc3f8041..79871e10a 100644 --- a/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh +++ b/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="chatqna-guardrails chatqna-ui dataprep-redis retriever-redis guardrails-tgi nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/tei-gaudi:latest diff --git a/ChatQnA/tests/test_compose_on_gaudi.sh b/ChatQnA/tests/test_compose_on_gaudi.sh index 1d5b8bc8a..204ad3039 100644 --- a/ChatQnA/tests/test_compose_on_gaudi.sh +++ b/ChatQnA/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="chatqna chatqna-ui dataprep-redis retriever-redis nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/tei-gaudi:latest diff --git a/ChatQnA/tests/test_compose_vllm_on_xeon.sh b/ChatQnA/tests/test_compose_vllm_on_xeon.sh index b664a6af8..f53fd3aea 100644 --- a/ChatQnA/tests/test_compose_vllm_on_xeon.sh +++ b/ChatQnA/tests/test_compose_vllm_on_xeon.sh @@ -23,7 +23,7 @@ function build_docker_images() { service_list="chatqna chatqna-ui dataprep-redis retriever-redis vllm nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker images && sleep 1s diff --git a/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh b/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh index 22c5e8c94..0a59eabf7 100644 --- a/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh +++ b/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="chatqna-without-rerank chatqna-ui dataprep-redis retriever-redis nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/tei-gaudi:latest diff --git a/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh b/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh index b0ffc22bc..89b492261 100644 --- a/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh +++ b/ChatQnA/tests/test_compose_without_rerank_on_xeon.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="chatqna-without-rerank chatqna-ui chatqna-conversation-ui dataprep-redis retriever-redis nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker images && sleep 1s diff --git a/CodeGen/codegen.yaml b/CodeGen/codegen.yaml index 95f2d78e6..8dc864f6f 100644 --- a/CodeGen/codegen.yaml +++ b/CodeGen/codegen.yaml @@ -6,7 +6,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml index 153b9f59a..92b70b099 100644 --- a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8028:80" diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml index b506d17d4..dc032cd25 100644 --- a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml +++ b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml @@ -405,7 +405,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/CodeGen/tests/test_compose_on_gaudi.sh b/CodeGen/tests/test_compose_on_gaudi.sh index ec1658314..f90e0aaa4 100644 --- a/CodeGen/tests/test_compose_on_gaudi.sh +++ b/CodeGen/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="codegen codegen-ui llm-tgi" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/CodeTrans/codetrans.yaml b/CodeTrans/codetrans.yaml index 9d7f70b4e..c36259978 100644 --- a/CodeTrans/codetrans.yaml +++ b/CodeTrans/codetrans.yaml @@ -6,7 +6,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml index 09b82ed3f..2f87d10c2 100644 --- a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: codetrans-tgi-service ports: - "8008:80" diff --git a/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml b/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml index 076104e77..a2efecf44 100644 --- a/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml +++ b/CodeTrans/kubernetes/intel/hpu/gaudi/manifest/codetrans.yaml @@ -405,7 +405,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/CodeTrans/tests/test_compose_on_gaudi.sh b/CodeTrans/tests/test_compose_on_gaudi.sh index 884f2dffa..c6e8b8c9b 100644 --- a/CodeTrans/tests/test_compose_on_gaudi.sh +++ b/CodeTrans/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="codetrans codetrans-ui llm-tgi nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/DocSum/docker_compose/intel/hpu/gaudi/README.md b/DocSum/docker_compose/intel/hpu/gaudi/README.md index cf655dd08..6882f0eba 100644 --- a/DocSum/docker_compose/intel/hpu/gaudi/README.md +++ b/DocSum/docker_compose/intel/hpu/gaudi/README.md @@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally. This step can be ignored As TGI Gaudi has been officially published as a Docker image, we simply need to pull it: ```bash -docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 +docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 ``` ### 2. Build LLM Image @@ -53,7 +53,7 @@ docker build -t opea/docsum-react-ui:latest --build-arg BACKEND_SERVICE_ENDPOINT Then run the command `docker images`, you will have the following Docker Images: -1. `ghcr.io/huggingface/tgi-gaudi:2.0.5` +1. `ghcr.io/huggingface/tgi-gaudi:2.0.6` 2. `opea/llm-docsum-tgi:latest` 3. `opea/docsum:latest` 4. `opea/docsum-ui:latest` diff --git a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml index ec9a2b355..71c52b40a 100644 --- a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8008:80" diff --git a/DocSum/docsum.yaml b/DocSum/docsum.yaml index bc87bc5b4..9e9936ff4 100644 --- a/DocSum/docsum.yaml +++ b/DocSum/docsum.yaml @@ -6,7 +6,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/DocSum/kubernetes/intel/README_gmc.md b/DocSum/kubernetes/intel/README_gmc.md index 6046ca4dc..00e9d8e1b 100644 --- a/DocSum/kubernetes/intel/README_gmc.md +++ b/DocSum/kubernetes/intel/README_gmc.md @@ -9,7 +9,7 @@ The DocSum application is defined as a Custom Resource (CR) file that the above The DocSum pipeline uses prebuilt images. The Xeon version uses the prebuilt image `llm-docsum-tgi:latest` which internally leverages the the image `ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the -service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.5`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use `Intel/neural-chat-7b-v3-3`. +service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.6`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use `Intel/neural-chat-7b-v3-3`. [NOTE] Refer to [Docker Xeon README](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/docker_compose/intel/cpu/xeon/README.md) or diff --git a/DocSum/kubernetes/intel/hpu/gaudi/manifest/docsum.yaml b/DocSum/kubernetes/intel/hpu/gaudi/manifest/docsum.yaml index 5c10f3c76..7ab1df9b1 100644 --- a/DocSum/kubernetes/intel/hpu/gaudi/manifest/docsum.yaml +++ b/DocSum/kubernetes/intel/hpu/gaudi/manifest/docsum.yaml @@ -405,7 +405,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh index 305b56d5d..12a6a8861 100644 --- a/DocSum/tests/test_compose_on_gaudi.sh +++ b/DocSum/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="docsum docsum-ui llm-docsum-tgi" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/FaqGen/benchmark/accuracy/launch_tgi.sh b/FaqGen/benchmark/accuracy/launch_tgi.sh index a504f2a41..1a1d23ee8 100644 --- a/FaqGen/benchmark/accuracy/launch_tgi.sh +++ b/FaqGen/benchmark/accuracy/launch_tgi.sh @@ -19,7 +19,7 @@ docker run -it --rm \ --ipc=host \ -e HTTPS_PROXY=$https_proxy \ -e HTTP_PROXY=$https_proxy \ - ghcr.io/huggingface/tgi-gaudi:2.0.5 \ + ghcr.io/huggingface/tgi-gaudi:2.0.6 \ --model-id $model_name \ --max-input-tokens $max_input_tokens \ --max-total-tokens $max_total_tokens \ diff --git a/FaqGen/docker_compose/intel/hpu/gaudi/README.md b/FaqGen/docker_compose/intel/hpu/gaudi/README.md index 548a94e16..b157106bf 100644 --- a/FaqGen/docker_compose/intel/hpu/gaudi/README.md +++ b/FaqGen/docker_compose/intel/hpu/gaudi/README.md @@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally. This step can be ignored As TGI Gaudi has been officially published as a Docker image, we simply need to pull it: ```bash -docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 +docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 ``` ### 2. Build LLM Image @@ -53,7 +53,7 @@ docker build -t opea/faqgen-react-ui:latest --build-arg https_proxy=$https_proxy Then run the command `docker images`, you will have the following Docker Images: -1. `ghcr.io/huggingface/tgi-gaudi:2.0.5` +1. `ghcr.io/huggingface/tgi-gaudi:2.0.6` 2. `opea/llm-faqgen-tgi:latest` 3. `opea/faqgen:latest` 4. `opea/faqgen-ui:latest` diff --git a/FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml b/FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml index 1ee36bd30..1416019b1 100644 --- a/FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8008:80" diff --git a/FaqGen/faqgen.yaml b/FaqGen/faqgen.yaml index 8d354871e..5b924a38e 100644 --- a/FaqGen/faqgen.yaml +++ b/FaqGen/faqgen.yaml @@ -6,7 +6,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/FaqGen/kubernetes/intel/hpu/gaudi/manifest/faqgen.yaml b/FaqGen/kubernetes/intel/hpu/gaudi/manifest/faqgen.yaml index 2703cbc4e..a9b8ef199 100644 --- a/FaqGen/kubernetes/intel/hpu/gaudi/manifest/faqgen.yaml +++ b/FaqGen/kubernetes/intel/hpu/gaudi/manifest/faqgen.yaml @@ -47,7 +47,7 @@ spec: value: 'true' - name: FLASH_ATTENTION_RECOMPUTE value: 'true' - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 imagePullPolicy: IfNotPresent securityContext: capabilities: diff --git a/FaqGen/tests/test_compose_on_gaudi.sh b/FaqGen/tests/test_compose_on_gaudi.sh index 161c1e2a7..6eb229ca7 100644 --- a/FaqGen/tests/test_compose_on_gaudi.sh +++ b/FaqGen/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="faqgen faqgen-ui llm-faqgen-tgi" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml b/GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml index b03cba56a..2cedab39e 100644 --- a/GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml @@ -40,7 +40,7 @@ services: ipc: host command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate tgi-gaudi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "6005:80" diff --git a/GraphRAG/tests/test_compose.sh b/GraphRAG/tests/test_compose.sh index 0fc227830..72b77b642 100755 --- a/GraphRAG/tests/test_compose.sh +++ b/GraphRAG/tests/test_compose.sh @@ -23,7 +23,7 @@ function build_docker_images() { service_list="graphrag dataprep-neo4j-llamaindex retriever-neo4j-llamaindex chatqna-gaudi-ui-server chatqna-gaudi-nginx-server" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull neo4j:latest docker images && sleep 1s diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md index 6d6ca88ff..9e7db70b7 100644 --- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md @@ -80,7 +80,7 @@ docker build --no-cache -t opea/retriever-multimodal-redis:latest --build-arg ht Build TGI Gaudi image ```bash -docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 +docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 ``` Build lvm-tgi microservice image @@ -118,7 +118,7 @@ Then run the command `docker images`, you will have the following 8 Docker Image 1. `opea/dataprep-multimodal-redis:latest` 2. `opea/lvm-tgi:latest` -3. `ghcr.io/huggingface/tgi-gaudi:2.0.5` +3. `ghcr.io/huggingface/tgi-gaudi:2.0.6` 4. `opea/retriever-multimodal-redis:latest` 5. `opea/embedding-multimodal:latest` 6. `opea/embedding-multimodal-bridgetower:latest` diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml index e66aea1f0..ddaf2b09d 100644 --- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -69,7 +69,7 @@ services: INDEX_NAME: ${INDEX_NAME} restart: unless-stopped tgi-gaudi: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-llava-gaudi-server ports: - "8399:80" @@ -84,6 +84,10 @@ services: PREFILL_BATCH_BUCKET_SIZE: 1 BATCH_BUCKET_SIZE: 1 MAX_BATCH_TOTAL_TOKENS: 4096 + ENABLE_HPU_GRAPH: true + LIMIT_HPU_GRAPH: true + USE_FLASH_ATTENTION: true + FLASH_ATTENTION_RECOMPUTE: true runtime: habana cap_add: - SYS_NICE diff --git a/MultimodalQnA/tests/test_compose_on_gaudi.sh b/MultimodalQnA/tests/test_compose_on_gaudi.sh index 3b629f52b..5ac1228db 100644 --- a/MultimodalQnA/tests/test_compose_on_gaudi.sh +++ b/MultimodalQnA/tests/test_compose_on_gaudi.sh @@ -25,7 +25,7 @@ function build_docker_images() { service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-tgi dataprep-multimodal-redis" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml index 5ade94cc1..a2f4cda83 100644 --- a/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -80,7 +80,7 @@ services: HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} restart: unless-stopped tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "3006:80" diff --git a/SearchQnA/tests/test_compose_on_gaudi.sh b/SearchQnA/tests/test_compose_on_gaudi.sh index cefadaa88..fee28643e 100644 --- a/SearchQnA/tests/test_compose_on_gaudi.sh +++ b/SearchQnA/tests/test_compose_on_gaudi.sh @@ -23,7 +23,7 @@ function build_docker_images() { docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker pull ghcr.io/huggingface/tei-gaudi:latest docker images && sleep 1s } diff --git a/Translation/docker_compose/intel/hpu/gaudi/compose.yaml b/Translation/docker_compose/intel/hpu/gaudi/compose.yaml index c470c441a..eabae1321 100644 --- a/Translation/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/Translation/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-gaudi-server ports: - "8008:80" diff --git a/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml b/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml index a1da33b79..25e39a700 100644 --- a/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml +++ b/Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml @@ -362,7 +362,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "ghcr.io/huggingface/tgi-gaudi:2.0.5" + image: "ghcr.io/huggingface/tgi-gaudi:2.0.6" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/Translation/tests/test_compose_on_gaudi.sh b/Translation/tests/test_compose_on_gaudi.sh index 9515c95af..fad64f5ba 100644 --- a/Translation/tests/test_compose_on_gaudi.sh +++ b/Translation/tests/test_compose_on_gaudi.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="translation translation-ui llm-tgi nginx" docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } diff --git a/Translation/translation.yaml b/Translation/translation.yaml index 882eca8e2..f3a07da96 100644 --- a/Translation/translation.yaml +++ b/Translation/translation.yaml @@ -6,7 +6,7 @@ opea_micro_services: tgi-service: host: ${TGI_SERVICE_IP} ports: ${TGI_SERVICE_PORT} - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 volumes: - "./data:/data" runtime: habana diff --git a/VisualQnA/docker_compose/intel/hpu/gaudi/README.md b/VisualQnA/docker_compose/intel/hpu/gaudi/README.md index 84783353a..abb341f28 100644 --- a/VisualQnA/docker_compose/intel/hpu/gaudi/README.md +++ b/VisualQnA/docker_compose/intel/hpu/gaudi/README.md @@ -18,7 +18,7 @@ docker build --no-cache -t opea/nginx:latest --build-arg https_proxy=$https_prox ### 2. Pull TGI Gaudi Image ```bash -docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 +docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 ``` ### 3. Build MegaService Docker Image @@ -43,7 +43,7 @@ docker build --no-cache -t opea/visualqna-ui:latest --build-arg https_proxy=$htt Then run the command `docker images`, you will have the following 5 Docker Images: -1. `ghcr.io/huggingface/tgi-gaudi:2.0.5` +1. `ghcr.io/huggingface/tgi-gaudi:2.0.6` 2. `opea/lvm-tgi:latest` 3. `opea/visualqna:latest` 4. `opea/visualqna-ui:latest` diff --git a/VisualQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/VisualQnA/docker_compose/intel/hpu/gaudi/compose.yaml index 45732e832..bd587aa6f 100644 --- a/VisualQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/VisualQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -3,7 +3,7 @@ services: llava-tgi-service: - image: ghcr.io/huggingface/tgi-gaudi:2.0.5 + image: ghcr.io/huggingface/tgi-gaudi:2.0.6 container_name: tgi-llava-gaudi-server ports: - "8399:80" diff --git a/VisualQnA/tests/test_compose_on_gaudi.sh b/VisualQnA/tests/test_compose_on_gaudi.sh index a489a2c7a..15f9fe7f2 100644 --- a/VisualQnA/tests/test_compose_on_gaudi.sh +++ b/VisualQnA/tests/test_compose_on_gaudi.sh @@ -21,7 +21,7 @@ function build_docker_images() { echo "Build all the images with --no-cache, check docker_image_build.log for details..." docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5 + docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 docker images && sleep 1s } From 0d52c2f00396db03bb6259cd006bd1a9e8045c70 Mon Sep 17 00:00:00 2001 From: pallavijaini0525 <112209032+pallavijaini0525@users.noreply.github.com> Date: Tue, 12 Nov 2024 17:32:37 -0800 Subject: [PATCH 3/6] Pinecone update to Readme and docker compose for ChatQnA (#540) Signed-off-by: pallavi jaini Signed-off-by: AI Workloads Signed-off-by: Pallavi Jaini Signed-off-by: Pallavi Jaini Signed-off-by: root Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: AI Workloads Co-authored-by: Pallavi Jaini Co-authored-by: root Co-authored-by: chen, suyue --- .../intel/cpu/xeon/README_pinecone.md | 382 ++++++++++++++++++ .../intel/cpu/xeon/compose_pinecone.yaml | 151 +++++++ ChatQnA/docker_image_build/build.yaml | 12 + .../tests/test_compose_pinecone_on_xeon.sh | 233 +++++++++++ 4 files changed, 778 insertions(+) create mode 100644 ChatQnA/docker_compose/intel/cpu/xeon/README_pinecone.md create mode 100644 ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml create mode 100755 ChatQnA/tests/test_compose_pinecone_on_xeon.sh diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README_pinecone.md b/ChatQnA/docker_compose/intel/cpu/xeon/README_pinecone.md new file mode 100644 index 000000000..f730a91ae --- /dev/null +++ b/ChatQnA/docker_compose/intel/cpu/xeon/README_pinecone.md @@ -0,0 +1,382 @@ +# Build Mega Service of ChatQnA (with Pinecone) on Xeon + +This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on Intel Xeon server. The steps include Docker image creation, container deployment via Docker Compose, and service execution to integrate microservices such as `embedding`, `retriever`, `rerank`, and `llm`. We will publish the Docker images to Docker Hub soon, it will simplify the deployment process for this service. + +## 🚀 Apply Xeon Server on AWS + +To apply a Xeon server on AWS, start by creating an AWS account if you don't have one already. Then, head to the [EC2 Console](https://console.aws.amazon.com/ec2/v2/home) to begin the process. Within the EC2 service, select the Amazon EC2 M7i or M7i-flex instance type to leverage the power of 4th Generation Intel Xeon Scalable processors. These instances are optimized for high-performance computing and demanding workloads. + +For detailed information about these instance types, you can refer to this [link](https://aws.amazon.com/ec2/instance-types/m7i/). Once you've chosen the appropriate instance type, proceed with configuring your instance settings, including network configurations, security groups, and storage options. + +After launching your instance, you can connect to it using SSH (for Linux instances) or Remote Desktop Protocol (RDP) (for Windows instances). From there, you'll have full access to your Xeon server, allowing you to install, configure, and manage your applications as needed. + +**Certain ports in the EC2 instance need to opened up in the security group, for the microservices to work with the curl commands** + +> See one example below. Please open up these ports in the EC2 instance based on the IP addresses you want to allow + +``` + +data_prep_service +===================== +Port 6007 - Open to 0.0.0.0/0 +Port 6008 - Open to 0.0.0.0/0 + +tei_embedding_service +===================== +Port 6006 - Open to 0.0.0.0/0 + +embedding +========= +Port 6000 - Open to 0.0.0.0/0 + +retriever +========= +Port 7000 - Open to 0.0.0.0/0 + +tei_xeon_service +================ +Port 8808 - Open to 0.0.0.0/0 + +reranking +========= +Port 8000 - Open to 0.0.0.0/0 + +tgi-service +=========== +Port 9009 - Open to 0.0.0.0/0 + +llm +=== +Port 9000 - Open to 0.0.0.0/0 + +chaqna-xeon-backend-server +========================== +Port 8888 - Open to 0.0.0.0/0 + +chaqna-xeon-ui-server +===================== +Port 5173 - Open to 0.0.0.0/0 +``` + +## 🚀 Build Docker Images + +First of all, you need to build Docker Images locally and install the python package of it. + +```bash +git clone https://github.com/opea-project/GenAIComps.git +cd GenAIComps +``` + +### 1. Build Embedding Image + +```bash +docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/tei/langchain/Dockerfile . +``` + +### 2. Build Retriever Image + +```bash +docker build --no-cache -t opea/retriever-pinecone:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/pinecone/langchain/Dockerfile . +``` + +### 3. Build Rerank Image + +```bash +docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/Dockerfile . +``` + +### 4. Build LLM Image + +```bash +docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile . +``` + +### 5. Build Dataprep Image + +```bash +docker build --no-cache -t opea/dataprep-pinecone:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/pinecone/langchain/Dockerfile . +cd .. +``` + +### 6. Build MegaService Docker Image + +To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `chatqna.py` Python script. Build MegaService Docker image via below command: + +```bash +git clone https://github.com/opea-project/GenAIExamples.git +cd GenAIExamples/ChatQnA/docker +docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile . +cd ../../.. +``` + +### 7. Build UI Docker Image + +Build frontend Docker image via below command: + +```bash +cd GenAIExamples/ChatQnA/docker/ui/ +docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile . +cd ../../../.. +``` + +### 8. Build Conversational React UI Docker Image (Optional) + +Build frontend Docker image that enables Conversational experience with ChatQnA megaservice via below command: + +**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable** + +```bash +cd GenAIExamples/ChatQnA/docker/ui/ +export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna" +export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep" +export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file" +docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT --build-arg DATAPREP_SERVICE_ENDPOINT=$DATAPREP_SERVICE_ENDPOINT --build-arg DATAPREP_GET_FILE_ENDPOINT=$DATAPREP_GET_FILE_ENDPOINT -f ./docker/Dockerfile.react . +cd ../../../.. +``` + +Then run the command `docker images`, you will have the following 7 Docker Images: + +1. `opea/dataprep-pinecone:latest` +2. `opea/embedding-tei:latest` +3. `opea/retriever-pinecone:latest` +4. `opea/reranking-tei:latest` +5. `opea/llm-tgi:latest` +6. `opea/chatqna:latest` +7. `opea/chatqna-ui:latest` + +## 🚀 Start Microservices + +### Setup Environment Variables + +Since the `compose_pinecone.yaml` will consume some environment variables, you need to setup them in advance as below. + +**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable** + +> Change the External_Public_IP below with the actual IPV4 value + +``` +export host_ip="External_Public_IP" +``` + +**Export the value of your Huggingface API token to the `your_hf_api_token` environment variable** + +> Change the Your_Huggingface_API_Token below with tyour actual Huggingface API Token value + +``` +export your_hf_api_token="Your_Huggingface_API_Token" +``` + +**Append the value of the public IP address to the no_proxy list** + +``` +export your_no_proxy=${your_no_proxy},"External_Public_IP" +``` + +\*\*Get the PINECONE_API_KEY and the INDEX_NAME + +``` +export pinecone_api_key=${api_key} +export pinecone_index_name=${pinecone_index} +``` + +```bash +export no_proxy=${your_no_proxy} +export http_proxy=${your_http_proxy} +export https_proxy=${your_http_proxy} +export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" +export RERANK_MODEL_ID="BAAI/bge-reranker-base" +export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" +export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" +export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" +export TGI_LLM_ENDPOINT="http://${host_ip}:9009" +export PINECONE_API_KEY=${pinecone_api_key} +export PINECONE_INDEX_NAME=${pinecone_index_name} +export INDEX_NAME=${pinecone_index_name} +export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} +export MEGA_SERVICE_HOST_IP=${host_ip} +export EMBEDDING_SERVICE_HOST_IP=${host_ip} +export RETRIEVER_SERVICE_HOST_IP=${host_ip} +export RERANK_SERVICE_HOST_IP=${host_ip} +export LLM_SERVICE_HOST_IP=${host_ip} +export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna" +export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep" +export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file" +export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete_file" +``` + +Note: Please replace with `host_ip` with you external IP address, do not use localhost. + +### Start all the services Docker Containers + +> Before running the docker compose command, you need to be in the folder that has the docker compose yaml file + +```bash +cd GenAIExamples/ChatQnA/docker/xeon/ +docker compose -f compose_pinecone.yaml up -d +``` + +### Validate Microservices + +1. TEI Embedding Service + +```bash +curl ${host_ip}:6006/embed \ + -X POST \ + -d '{"inputs":"What is Deep Learning?"}' \ + -H 'Content-Type: application/json' +``` + +2. Embedding Microservice + +```bash +curl http://${host_ip}:6000/v1/embeddings\ + -X POST \ + -d '{"text":"hello"}' \ + -H 'Content-Type: application/json' +``` + +3. Retriever Microservice + To validate the retriever microservice, you need to generate a mock embedding vector of length 768 in Python script: + +```Python +import random +embedding = [random.uniform(-1, 1) for _ in range(768)] +print(embedding) +``` + +Then substitute your mock embedding vector for the `${your_embedding}` in the following cURL command: + +```bash +curl http://${host_ip}:7000/v1/retrieval \ + -X POST \ + -d '{"text":"What is the revenue of Nike in 2023?","embedding":"'"${your_embedding}"'"}' \ + -H 'Content-Type: application/json' +``` + +4. TEI Reranking Service + +```bash +curl http://${host_ip}:8808/rerank \ + -X POST \ + -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \ + -H 'Content-Type: application/json' +``` + +5. Reranking Microservice + +```bash +curl http://${host_ip}:8000/v1/reranking\ + -X POST \ + -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \ + -H 'Content-Type: application/json' +``` + +6. TGI Service + +```bash +curl http://${host_ip}:9009/generate \ + -X POST \ + -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \ + -H 'Content-Type: application/json' +``` + +7. LLM Microservice + +```bash +curl http://${host_ip}:9000/v1/chat/completions\ + -X POST \ + -d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":true}' \ + -H 'Content-Type: application/json' +``` + +8. MegaService + +```bash +curl http://${host_ip}:8888/v1/chatqna -H "Content-Type: application/json" -d '{ + "messages": "What is the revenue of Nike in 2023?" + }' +``` + +9. Dataprep Microservice（Optional） + +If you want to update the default knowledge base, you can use the following commands: + +Update Knowledge Base via Local File Upload: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F "files=@./nke-10k-2023.pdf" +``` + +This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment. + +Add Knowledge Base via HTTP Links: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F 'link_list=["https://opea.dev"]' +``` + +This command updates a knowledge base by submitting a list of HTTP links for processing. + +Also, you are able to get the file list that you uploaded: + +```bash +curl -X POST "http://${host_ip}:6008/v1/dataprep/get_file" \ + -H "Content-Type: application/json" +``` + +## Enable LangSmith for Monotoring Application (Optional) + +LangSmith offers tools to debug, evaluate, and monitor language models and intelligent agents. It can be used to assess benchmark data for each microservice. Before launching your services with `docker compose -f compose_pinecone.yaml up -d`, you need to enable LangSmith tracing by setting the `LANGCHAIN_TRACING_V2` environment variable to true and configuring your LangChain API key. + +Here's how you can do it: + +1. Install the latest version of LangSmith: + +```bash +pip install -U langsmith +``` + +2. Set the necessary environment variables: + +```bash +export LANGCHAIN_TRACING_V2=true +export LANGCHAIN_API_KEY=ls_... +``` + +## 🚀 Launch the UI + +To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below: + +```yaml + chaqna-gaudi-ui-server: + image: opea/chatqna-ui:latest + ... + ports: + - "80:5173" +``` + +## 🚀 Launch the Conversational UI (react) + +To access the Conversational UI frontend, open the following URL in your browser: http://{host_ip}:5174. By default, the UI runs on port 80 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below: + +```yaml + chaqna-xeon-conversation-ui-server: + image: opea/chatqna-conversation-ui:latest + ... + ports: + - "80:80" +``` + +![project-screenshot](../../../../assets/img/chat_ui_init.png) + +Here is an example of running ChatQnA: + +![project-screenshot](../../../../assets/img/chat_ui_response.png) + +Here is an example of running ChatQnA with Conversational UI (React): + +![project-screenshot](../../../../assets/img/conversation_ui_response.png) diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml new file mode 100644 index 000000000..f42fd6fd2 --- /dev/null +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml @@ -0,0 +1,151 @@ + +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +version: "3.8" + +services: + dataprep-pinecone-service: + image: ${REGISTRY:-opea}/dataprep-pinecone:${TAG:-latest} + container_name: dataprep-pinecone-server + depends_on: + - tei-embedding-service + ports: + - "6007:6007" + - "6008:6008" + - "6009:6009" + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + PINECONE_API_KEY: ${PINECONE_API_KEY} + PINECONE_INDEX_NAME: ${PINECONE_INDEX_NAME} + TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80 + LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} + HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + tei-embedding-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 + container_name: tei-embedding-server + ports: + - "6006:80" + volumes: + - "./data:/data" + shm_size: 1g + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate + retriever: + image: ${REGISTRY:-opea}/retriever-pinecone:${TAG:-latest} + container_name: retriever-pinecone-server + ports: + - "7000:7000" + ipc: host + environment: + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + PINECONE_API_KEY: ${PINECONE_API_KEY} + INDEX_NAME: ${PINECONE_INDEX_NAME} + PINECONE_INDEX_NAME: ${PINECONE_INDEX_NAME} + LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} + TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80 + HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + restart: unless-stopped + tei-reranking-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 + container_name: tei-reranking-server + ports: + - "8808:80" + volumes: + - "./data:/data" + shm_size: 1g + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + HF_HUB_DISABLE_PROGRESS_BARS: 1 + HF_HUB_ENABLE_HF_TRANSFER: 0 + command: --model-id ${RERANK_MODEL_ID} --auto-truncate + tgi-service: + image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu + container_name: tgi-service + ports: + - "9009:80" + volumes: + - "./data:/data" + shm_size: 1g + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + HF_HUB_DISABLE_PROGRESS_BARS: 1 + HF_HUB_ENABLE_HF_TRANSFER: 0 + command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 + chatqna-xeon-backend-server: + image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} + container_name: chatqna-xeon-backend-server + depends_on: + - tei-embedding-service + - dataprep-pinecone-service + - retriever + - tei-reranking-service + - tgi-service + ports: + - "8888:8888" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + - MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server + - EMBEDDING_SERVER_HOST_IP=tei-embedding-service + - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80} + - RETRIEVER_SERVICE_HOST_IP=retriever + - RERANK_SERVER_HOST_IP=tei-reranking-service + - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80} + - LLM_SERVER_HOST_IP=tgi-service + - LLM_SERVER_PORT=${LLM_SERVER_PORT:-80} + - LOGFLAG=${LOGFLAG} + - LLM_MODEL=${LLM_MODEL_ID} + ipc: host + restart: always + chatqna-xeon-ui-server: + image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest} + container_name: chatqna-xeon-ui-server + depends_on: + - chatqna-xeon-backend-server + ports: + - "5173:5173" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + ipc: host + restart: always + chatqna-xeon-nginx-server: + image: ${REGISTRY:-opea}/nginx:${TAG:-latest} + container_name: chatqna-xeon-nginx-server + depends_on: + - chatqna-xeon-backend-server + - chatqna-xeon-ui-server + ports: + - "${NGINX_PORT:-80}:80" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + - FRONTEND_SERVICE_IP=chatqna-xeon-ui-server + - FRONTEND_SERVICE_PORT=5173 + - BACKEND_SERVICE_NAME=chatqna + - BACKEND_SERVICE_IP=chatqna-xeon-backend-server + - BACKEND_SERVICE_PORT=8888 + - DATAPREP_SERVICE_IP=dataprep-pinecone-service + - DATAPREP_SERVICE_PORT=6007 + ipc: host + restart: always + +networks: + default: + driver: bridge diff --git a/ChatQnA/docker_image_build/build.yaml b/ChatQnA/docker_image_build/build.yaml index b84fa0796..7be5141ea 100644 --- a/ChatQnA/docker_image_build/build.yaml +++ b/ChatQnA/docker_image_build/build.yaml @@ -53,6 +53,12 @@ services: dockerfile: comps/retrievers/qdrant/haystack/Dockerfile extends: chatqna image: ${REGISTRY:-opea}/retriever-qdrant:${TAG:-latest} + retriever-pinecone: + build: + context: GenAIComps + dockerfile: comps/retrievers/pinecone/langchain/Dockerfile + extends: chatqna + image: ${REGISTRY:-opea}/retriever-pinecone:${TAG:-latest} reranking-tei: build: context: GenAIComps @@ -89,6 +95,12 @@ services: dockerfile: comps/dataprep/qdrant/langchain/Dockerfile extends: chatqna image: ${REGISTRY:-opea}/dataprep-qdrant:${TAG:-latest} + dataprep-pinecone: + build: + context: GenAIComps + dockerfile: comps/dataprep/pinecone/langchain/Dockerfile + extends: chatqna + image: ${REGISTRY:-opea}/dataprep-pinecone:${TAG:-latest} guardrails-tgi: build: context: GenAIComps diff --git a/ChatQnA/tests/test_compose_pinecone_on_xeon.sh b/ChatQnA/tests/test_compose_pinecone_on_xeon.sh new file mode 100755 index 000000000..a95b90c16 --- /dev/null +++ b/ChatQnA/tests/test_compose_pinecone_on_xeon.sh @@ -0,0 +1,233 @@ +#!/bin/bash +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +set -e +IMAGE_REPO=${IMAGE_REPO:-"opea"} +IMAGE_TAG=${IMAGE_TAG:-"latest"} +echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}" +echo "TAG=IMAGE_TAG=${IMAGE_TAG}" +export REGISTRY=${IMAGE_REPO} +export TAG=${IMAGE_TAG} + +WORKPATH=$(dirname "$PWD") +LOG_PATH="$WORKPATH/tests" +ip_address=$(hostname -I | awk '{print $1}') + +function build_docker_images() { + cd $WORKPATH/docker_image_build + git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../ + + echo "Build all the images with --no-cache, check docker_image_build.log for details..." + service_list="chatqna chatqna-ui dataprep-pinecone retriever-pinecone nginx" + docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log + + docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu + docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 + + docker images && sleep 1s +} + +function start_services() { + cd $WORKPATH/docker_compose/intel/cpu/xeon/ + export no_proxy=${no_proxy},${ip_address} + export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" + export RERANK_MODEL_ID="BAAI/bge-reranker-base" + export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct" + export PINECONE_API_KEY=${PINECONE_KEY_LANGCHAIN_TEST} + export PINECONE_INDEX_NAME="langchain-test" + export INDEX_NAME="langchain-test" + export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} + + # Start Docker Containers + docker compose -f compose_pinecone.yaml up -d > ${LOG_PATH}/start_services_with_compose.log + + n=0 + until [[ "$n" -ge 500 ]]; do + docker logs tgi-service > ${LOG_PATH}/tgi_service_start.log + if grep -q Connected ${LOG_PATH}/tgi_service_start.log; then + break + fi + sleep 1s + n=$((n+1)) + done +} + +function validate_service() { + local URL="$1" + local EXPECTED_RESULT="$2" + local SERVICE_NAME="$3" + local DOCKER_NAME="$4" + local INPUT_DATA="$5" + + if [[ $SERVICE_NAME == *"dataprep_upload_file"* ]]; then + cd $LOG_PATH + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./dataprep_file.txt' -H 'Content-Type: multipart/form-data' "$URL") + elif [[ $SERVICE_NAME == *"dataprep_del"* ]]; then + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d '{"file_path": "all"}' -H 'Content-Type: application/json' "$URL") + else + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL") + fi + HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://') + RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g') + + docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log + + + # check response status + if [ "$HTTP_STATUS" -ne "200" ]; then + echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS" + exit 1 + else + echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..." + fi + echo "Response" + echo $RESPONSE_BODY + echo "Expected Result" + echo $EXPECTED_RESULT + # check response body + if [[ "$RESPONSE_BODY" != *"$EXPECTED_RESULT"* ]]; then + echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY" + exit 1 + else + echo "[ $SERVICE_NAME ] Content is as expected." + fi + + sleep 1s +} + +function validate_microservices() { + # Check if the microservices are running correctly. + + # tei for embedding service + validate_service \ + "${ip_address}:6006/embed" \ + "[[" \ + "tei-embedding" \ + "tei-embedding-server" \ + '{"inputs":"What is Deep Learning?"}' + + sleep 1m # retrieval can't curl as expected, try to wait for more time + + # test /v1/dataprep/delete_file + validate_service \ + "http://${ip_address}:6009/v1/dataprep/delete_file" \ + '{"status":true}' \ + "dataprep_del" \ + "dataprep-pinecone-server" + + + # test /v1/dataprep upload file + echo "Deep learning is a subset of machine learning that utilizes neural networks with multiple layers to analyze various levels of abstract data representations. It enables computers to identify patterns and make decisions with minimal human intervention by learning from large amounts of data." > $LOG_PATH/dataprep_file.txt + validate_service \ + "http://${ip_address}:6007/v1/dataprep" \ + "Data preparation succeeded" \ + "dataprep_upload_file" \ + "dataprep-pinecone-server" + + + # retrieval microservice + test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)") + validate_service \ + "${ip_address}:7000/v1/retrieval" \ + " " \ + "retrieval" \ + "retriever-pinecone-server" \ + "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}" + + # tei for rerank microservice + echo "Validating reranking service" + validate_service \ + "${ip_address}:8808/rerank" \ + '{"index":1,"score":' \ + "tei-rerank" \ + "tei-reranking-server" \ + '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' + + + # tgi for llm service + echo "Validating llm service" + validate_service \ + "${ip_address}:9009/generate" \ + "generated_text" \ + "tgi-llm" \ + "tgi-service" \ + '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' + +} + +function validate_megaservice() { + # Curl the Mega Service + validate_service \ + "${ip_address}:8888/v1/chatqna" \ + "data: " \ + "chatqna-megaservice" \ + "chatqna-xeon-backend-server" \ + '{"messages": "What is the revenue of Nike in 2023?"}' + +} + +function validate_frontend() { + echo "[ TEST INFO ]: --------- frontend test started ---------" + cd $WORKPATH/ui/svelte + local conda_env_name="OPEA_e2e" + export PATH=${HOME}/miniforge3/bin/:$PATH + if conda info --envs | grep -q "$conda_env_name"; then + echo "$conda_env_name exist!" + else + conda create -n ${conda_env_name} python=3.12 -y + fi + source activate ${conda_env_name} + echo "[ TEST INFO ]: --------- conda env activated ---------" + + sed -i "s/localhost/$ip_address/g" playwright.config.ts + + conda install -c conda-forge nodejs -y + npm install && npm ci && npx playwright install --with-deps + node -v && npm -v && pip list + + exit_status=0 + npx playwright test || exit_status=$? + + if [ $exit_status -ne 0 ]; then + echo "[TEST INFO]: ---------frontend test failed---------" + exit $exit_status + else + echo "[TEST INFO]: ---------frontend test passed---------" + fi +} + +function stop_docker() { + echo "In stop docker" + echo $WORKPATH + cd $WORKPATH/docker_compose/intel/cpu/xeon/ + docker compose -f compose_pinecone.yaml down +} + +function main() { + + stop_docker + + if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi + + start_time=$(date +%s) + start_services + end_time=$(date +%s) + duration=$((end_time-start_time)) + echo "Mega service start duration is $duration s" && sleep 1s + + if [ "${mode}" == "perf" ]; then + python3 $WORKPATH/tests/chatqna_benchmark.py + elif [ "${mode}" == "" ]; then + validate_microservices + echo "==== microservices validated ====" + validate_megaservice + echo "==== megaservice validated ====" + fi + + stop_docker + echo y | docker system prune + +} + +main From 7adbba6add38fbd32d4a44dd5dbfd2992c6eb3d7 Mon Sep 17 00:00:00 2001 From: Louie Tsai Date: Tue, 12 Nov 2024 19:26:31 -0800 Subject: [PATCH 4/6] Enable vLLM Profiling for ChatQnA (#1124) --- .../docker_compose/intel/cpu/xeon/README.md | 51 +++++++++++++++++++ .../intel/cpu/xeon/compose_vllm.yaml | 1 + 2 files changed, 52 insertions(+) diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md index 990cb3537..49a7bf168 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/README.md +++ b/ChatQnA/docker_compose/intel/cpu/xeon/README.md @@ -432,6 +432,57 @@ curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \ -H "Content-Type: application/json" ``` + +### Profile Microservices + +To further analyze MicroService Performance, users could follow the instructions to profile MicroServices. + +#### 1. vLLM backend Service + Users could follow previous section to testing vLLM microservice or ChatQnA MegaService. + By default, vLLM profiling is not enabled. Users could start and stop profiling by following commands. + + ##### Start vLLM profiling + + ```bash + curl http://${host_ip}:9009/start_profile \ + -H "Content-Type: application/json" \ + -d '{"model": "Intel/neural-chat-7b-v3-3"}' + ``` + Users would see below docker logs from vllm-service if profiling is started correctly. + ```bash + INFO api_server.py:361] Starting profiler... + INFO api_server.py:363] Profiler started. + INFO: x.x.x.x:35940 - "POST /start_profile HTTP/1.1" 200 OK + ``` + After vLLM profiling is started, users could start asking questions and get responses from vLLM MicroService + or ChatQnA MicroService. + + ##### Stop vLLM profiling + By following command, users could stop vLLM profliing and generate a *.pt.trace.json.gz file as profiling result + under /mnt folder in vllm-service docker instance. + ```bash + # vLLM Service + curl http://${host_ip}:9009/stop_profile \ + -H "Content-Type: application/json" \ + -d '{"model": "Intel/neural-chat-7b-v3-3"}' + ``` + Users would see below docker logs from vllm-service if profiling is stopped correctly. + ```bash + INFO api_server.py:368] Stopping profiler... + INFO api_server.py:370] Profiler stopped. + INFO: x.x.x.x:41614 - "POST /stop_profile HTTP/1.1" 200 OK + ``` + After vllm profiling is stopped, users could use below command to get the *.pt.trace.json.gz file under /mnt folder. + ```bash + docker cp vllm-service:/mnt/ . + ``` + + ##### Check profiling result + Open a web browser and type "chrome://tracing" or "ui.perfetto.dev", and then load the json.gz file, you should be able + to see the vLLM profiling result as below diagram. +![image](https://github.com/user-attachments/assets/55c7097e-5574-41dc-97a7-5e87c31bc286) + + ## 🚀 Launch the UI ### Launch with origin port diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_vllm.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_vllm.yaml index 6e9d9ac20..3735b75f0 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_vllm.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_vllm.yaml @@ -86,6 +86,7 @@ services: https_proxy: ${https_proxy} HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} LLM_MODEL_ID: ${LLM_MODEL_ID} + VLLM_TORCH_PROFILER_DIR: "/mnt" command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80 chatqna-xeon-backend-server: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} From 393367e9f103326a74a58a58a1cb9db7403306d6 Mon Sep 17 00:00:00 2001 From: "chen, suyue" Date: Wed, 13 Nov 2024 15:42:42 +0800 Subject: [PATCH 5/6] Fix left issue of tgi version update (#1121) Signed-off-by: chensuyue Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> --- .../intel/hpu/gaudi/compose.yaml | 10 +- AvatarChatbot/tests/test_compose_on_gaudi.sh | 12 +-- .../docker_compose/intel/cpu/xeon/README.md | 93 ++++++++++--------- 3 files changed, 59 insertions(+), 56 deletions(-) diff --git a/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml b/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml index 298149ef1..2003bb4a9 100644 --- a/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml @@ -15,7 +15,7 @@ services: no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy} - HABANA_VISIBLE_MODULES: all + HABANA_VISIBLE_DEVICES: all OMPI_MCA_btl_vader_single_copy_mechanism: none runtime: habana cap_add: @@ -39,7 +39,7 @@ services: no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy} - HABANA_VISIBLE_MODULES: all + HABANA_VISIBLE_DEVICES: all OMPI_MCA_btl_vader_single_copy_mechanism: none runtime: habana cap_add: @@ -67,7 +67,7 @@ services: HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HF_HUB_DISABLE_PROGRESS_BARS: 1 HF_HUB_ENABLE_HF_TRANSFER: 0 - HABANA_VISIBLE_MODULES: all + HABANA_VISIBLE_DEVICES: all OMPI_MCA_btl_vader_single_copy_mechanism: none ENABLE_HPU_GRAPH: true LIMIT_HPU_GRAPH: true @@ -105,7 +105,7 @@ services: no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy} - HABANA_VISIBLE_MODULES: all + HABANA_VISIBLE_DEVICES: all OMPI_MCA_btl_vader_single_copy_mechanism: none DEVICE: ${DEVICE} INFERENCE_MODE: ${INFERENCE_MODE} @@ -132,7 +132,7 @@ services: no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy} - HABANA_VISIBLE_MODULES: all + HABANA_VISIBLE_DEVICES: all OMPI_MCA_btl_vader_single_copy_mechanism: none WAV2LIP_ENDPOINT: ${WAV2LIP_ENDPOINT} runtime: habana diff --git a/AvatarChatbot/tests/test_compose_on_gaudi.sh b/AvatarChatbot/tests/test_compose_on_gaudi.sh index ae404b236..aab0e3b68 100755 --- a/AvatarChatbot/tests/test_compose_on_gaudi.sh +++ b/AvatarChatbot/tests/test_compose_on_gaudi.sh @@ -74,7 +74,7 @@ function start_services() { export FPS=10 # Start Docker Containers - docker compose up -d + docker compose up -d > ${LOG_PATH}/start_services_with_compose.log n=0 until [[ "$n" -ge 100 ]]; do @@ -86,7 +86,6 @@ function start_services() { n=$((n+1)) done - # sleep 5m echo "All services are up and running" sleep 5s } @@ -99,6 +98,7 @@ function validate_megaservice() { if [[ $result == *"mp4"* ]]; then echo "Result correct." else + echo "Result wrong, print docker logs." docker logs whisper-service > $LOG_PATH/whisper-service.log docker logs asr-service > $LOG_PATH/asr-service.log docker logs speecht5-service > $LOG_PATH/speecht5-service.log @@ -107,19 +107,13 @@ function validate_megaservice() { docker logs llm-tgi-gaudi-server > $LOG_PATH/llm-tgi-gaudi-server.log docker logs wav2lip-service > $LOG_PATH/wav2lip-service.log docker logs animation-gaudi-server > $LOG_PATH/animation-gaudi-server.log - - echo "Result wrong." + echo "Exit test." exit 1 fi } -#function validate_frontend() { - -#} - - function stop_docker() { cd $WORKPATH/docker_compose/intel/hpu/gaudi docker compose down diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md index 49a7bf168..8396df454 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/README.md +++ b/ChatQnA/docker_compose/intel/cpu/xeon/README.md @@ -432,57 +432,66 @@ curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \ -H "Content-Type: application/json" ``` - ### Profile Microservices -To further analyze MicroService Performance, users could follow the instructions to profile MicroServices. +To further analyze MicroService Performance, users could follow the instructions to profile MicroServices. #### 1. vLLM backend Service - Users could follow previous section to testing vLLM microservice or ChatQnA MegaService. - By default, vLLM profiling is not enabled. Users could start and stop profiling by following commands. - ##### Start vLLM profiling +Users could follow previous section to testing vLLM microservice or ChatQnA MegaService. + By default, vLLM profiling is not enabled. Users could start and stop profiling by following commands. - ```bash - curl http://${host_ip}:9009/start_profile \ - -H "Content-Type: application/json" \ - -d '{"model": "Intel/neural-chat-7b-v3-3"}' - ``` - Users would see below docker logs from vllm-service if profiling is started correctly. - ```bash - INFO api_server.py:361] Starting profiler... - INFO api_server.py:363] Profiler started. - INFO: x.x.x.x:35940 - "POST /start_profile HTTP/1.1" 200 OK - ``` - After vLLM profiling is started, users could start asking questions and get responses from vLLM MicroService - or ChatQnA MicroService. - - ##### Stop vLLM profiling - By following command, users could stop vLLM profliing and generate a *.pt.trace.json.gz file as profiling result - under /mnt folder in vllm-service docker instance. - ```bash - # vLLM Service - curl http://${host_ip}:9009/stop_profile \ - -H "Content-Type: application/json" \ - -d '{"model": "Intel/neural-chat-7b-v3-3"}' - ``` - Users would see below docker logs from vllm-service if profiling is stopped correctly. - ```bash - INFO api_server.py:368] Stopping profiler... - INFO api_server.py:370] Profiler stopped. - INFO: x.x.x.x:41614 - "POST /stop_profile HTTP/1.1" 200 OK - ``` - After vllm profiling is stopped, users could use below command to get the *.pt.trace.json.gz file under /mnt folder. - ```bash - docker cp vllm-service:/mnt/ . - ``` +##### Start vLLM profiling + +```bash +curl http://${host_ip}:9009/start_profile \ + -H "Content-Type: application/json" \ + -d '{"model": "Intel/neural-chat-7b-v3-3"}' +``` + +Users would see below docker logs from vllm-service if profiling is started correctly. + +```bash +INFO api_server.py:361] Starting profiler... +INFO api_server.py:363] Profiler started. +INFO: x.x.x.x:35940 - "POST /start_profile HTTP/1.1" 200 OK +``` + +After vLLM profiling is started, users could start asking questions and get responses from vLLM MicroService + or ChatQnA MicroService. + +##### Stop vLLM profiling + +By following command, users could stop vLLM profliing and generate a \*.pt.trace.json.gz file as profiling result + under /mnt folder in vllm-service docker instance. + +```bash +# vLLM Service +curl http://${host_ip}:9009/stop_profile \ + -H "Content-Type: application/json" \ + -d '{"model": "Intel/neural-chat-7b-v3-3"}' +``` + +Users would see below docker logs from vllm-service if profiling is stopped correctly. + +```bash +INFO api_server.py:368] Stopping profiler... +INFO api_server.py:370] Profiler stopped. +INFO: x.x.x.x:41614 - "POST /stop_profile HTTP/1.1" 200 OK +``` + +After vllm profiling is stopped, users could use below command to get the \*.pt.trace.json.gz file under /mnt folder. + +```bash +docker cp vllm-service:/mnt/ . +``` + +##### Check profiling result - ##### Check profiling result - Open a web browser and type "chrome://tracing" or "ui.perfetto.dev", and then load the json.gz file, you should be able - to see the vLLM profiling result as below diagram. +Open a web browser and type "chrome://tracing" or "ui.perfetto.dev", and then load the json.gz file, you should be able + to see the vLLM profiling result as below diagram. ![image](https://github.com/user-attachments/assets/55c7097e-5574-41dc-97a7-5e87c31bc286) - ## 🚀 Launch the UI ### Launch with origin port From b5f95f735e4839126b63787da44e719412323ba5 Mon Sep 17 00:00:00 2001 From: Abolfazl Shahbazi <12436063+ashahba@users.noreply.github.com> Date: Wed, 13 Nov 2024 09:40:53 -0800 Subject: [PATCH 6/6] Fix missing end of file chars (#1106) Signed-off-by: Abolfazl Shahbazi <12436063+ashahba@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> --- .github/code_spell_ignore.txt | 2 +- .github/license_template.txt | 2 +- .gitignore | 2 +- .prettierignore | 2 +- AudioQnA/ui/docker/Dockerfile | 2 +- AudioQnA/ui/svelte/src/app.postcss | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/1.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/2.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/3.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/4.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/5.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/stop-recording.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/upload.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/voice.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOff.svg | 2 +- AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOn.svg | 2 +- AvatarChatbot/.gitignore | 2 +- ChatQnA/ui/docker/Dockerfile | 2 +- ChatQnA/ui/docker/Dockerfile.react | 2 +- ChatQnA/ui/react/.env | 2 +- ChatQnA/ui/react/.env.production | 2 +- ChatQnA/ui/react/nginx.conf | 2 +- ChatQnA/ui/react/public/vite.svg | 2 +- ChatQnA/ui/react/src/assets/react.svg | 2 +- ChatQnA/ui/react/src/components/Conversation/DataSource.tsx | 2 +- ChatQnA/ui/react/src/components/UserInfoModal/UserInfoModal.tsx | 2 +- ChatQnA/ui/svelte/src/app.postcss | 2 +- ChatQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg | 2 +- ChatQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg | 2 +- ChatQnA/ui/svelte/tests/test_file.txt | 2 +- CodeGen/ui/docker/Dockerfile | 2 +- CodeGen/ui/docker/Dockerfile.react | 2 +- CodeGen/ui/react/.env | 2 +- CodeGen/ui/react/.env.production | 2 +- CodeGen/ui/react/nginx.conf | 2 +- .../ui/react/src/components/Shared/CodeRender/CodeRender.tsx | 2 +- CodeGen/ui/react/src/components/Shared/Markdown/Markdown.tsx | 2 +- CodeGen/ui/svelte/.prettierrc | 2 +- CodeGen/ui/svelte/src/app.postcss | 2 +- CodeTrans/ui/docker/Dockerfile | 2 +- DBQnA/ui/react/nginx.conf | 2 +- DBQnA/ui/react/src/logo.svg | 2 +- DBQnA/ui/react/src/main.tsx | 2 +- DocSum/ui/docker/Dockerfile | 2 +- DocSum/ui/docker/Dockerfile.react | 2 +- DocSum/ui/react/.env | 2 +- DocSum/ui/react/nginx.conf | 2 +- DocSum/ui/react/src/components/DocSum/DocSum.tsx | 2 +- DocSum/ui/react/src/components/DocSum/FileUpload.tsx | 2 +- DocSum/ui/react/src/components/Shared/CodeRender/CodeRender.tsx | 2 +- DocSum/ui/react/src/components/Shared/Markdown/Markdown.tsx | 2 +- EdgeCraftRAG/Dockerfile | 2 +- EdgeCraftRAG/edgecraftrag/prompt_template/default_prompt.txt | 2 +- EdgeCraftRAG/ui/docker/Dockerfile.ui | 2 +- FaqGen/ui/docker/Dockerfile | 2 +- FaqGen/ui/docker/Dockerfile.react | 2 +- FaqGen/ui/react/nginx.conf | 2 +- FaqGen/ui/react/public/vite.svg | 2 +- FaqGen/ui/react/src/assets/react.svg | 2 +- FaqGen/ui/react/src/components/FaqGen/FaqGen.tsx | 2 +- FaqGen/ui/react/src/components/FaqGen/FileUpload.tsx | 2 +- FaqGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx | 2 +- FaqGen/ui/react/src/components/Shared/Markdown/Markdown.tsx | 2 +- GraphRAG/ui/docker/Dockerfile | 2 +- GraphRAG/ui/docker/Dockerfile.react | 2 +- GraphRAG/ui/react/.env | 2 +- GraphRAG/ui/react/.env.production | 2 +- GraphRAG/ui/react/nginx.conf | 2 +- GraphRAG/ui/react/public/vite.svg | 2 +- GraphRAG/ui/react/src/assets/react.svg | 2 +- GraphRAG/ui/react/src/components/Conversation/DataSource.tsx | 2 +- .../ui/react/src/components/UserInfoModal/UserInfoModal.tsx | 2 +- GraphRAG/ui/svelte/src/app.postcss | 2 +- GraphRAG/ui/svelte/src/lib/assets/voice/svg/paste.svg | 2 +- GraphRAG/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg | 2 +- GraphRAG/ui/svelte/tests/test_file.txt | 2 +- LICENSE | 2 +- ProductivitySuite/ui/docker/Dockerfile.react | 2 +- ProductivitySuite/ui/react/.env.production | 2 +- ProductivitySuite/ui/react/nginx.conf | 2 +- ProductivitySuite/ui/react/src/assets/react.svg | 2 +- .../ui/react/src/components/Conversation/DataSource.tsx | 2 +- .../ui/react/src/components/Conversation/PromptTemplate.tsx | 2 +- .../ui/react/src/components/Conversation/settings.tsx | 2 +- ProductivitySuite/ui/react/src/components/DocSum/DocSum.tsx | 2 +- ProductivitySuite/ui/react/src/components/DocSum/FileUpload.tsx | 2 +- ProductivitySuite/ui/react/src/components/FaqGen/FaqGen.tsx | 2 +- ProductivitySuite/ui/react/src/components/FaqGen/FileUpload.tsx | 2 +- .../ui/react/src/components/Shared/CodeRender/CodeRender.tsx | 2 +- .../ui/react/src/components/Shared/Markdown/Markdown.tsx | 2 +- SearchQnA/ui/docker/Dockerfile | 2 +- SearchQnA/ui/svelte/.env | 2 +- SearchQnA/ui/svelte/src/app.postcss | 2 +- SearchQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg | 2 +- SearchQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg | 2 +- Text2Image/ui/docker/Dockerfile | 2 +- Text2Image/ui/svelte/src/app.postcss | 2 +- Translation/ui/svelte/.env | 2 +- VideoQnA/ui/docker/Dockerfile | 2 +- VisualQnA/ui/docker/Dockerfile | 2 +- VisualQnA/ui/svelte/.env | 2 +- VisualQnA/ui/svelte/src/app.postcss | 2 +- VisualQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg | 2 +- VisualQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg | 2 +- 104 files changed, 104 insertions(+), 104 deletions(-) diff --git a/.github/code_spell_ignore.txt b/.github/code_spell_ignore.txt index 047d573d2..4566d4f3a 100644 --- a/.github/code_spell_ignore.txt +++ b/.github/code_spell_ignore.txt @@ -1,2 +1,2 @@ ModelIn -modelin \ No newline at end of file +modelin diff --git a/.github/license_template.txt b/.github/license_template.txt index b43bb9dc8..a0410374d 100644 --- a/.github/license_template.txt +++ b/.github/license_template.txt @@ -1,2 +1,2 @@ Copyright (C) 2024 Intel Corporation -SPDX-License-Identifier: Apache-2.0 \ No newline at end of file +SPDX-License-Identifier: Apache-2.0 diff --git a/.gitignore b/.gitignore index 3a5650d21..8b736f831 100644 --- a/.gitignore +++ b/.gitignore @@ -5,4 +5,4 @@ **/playwright/.cache/ **/test-results/ -__pycache__/ \ No newline at end of file +__pycache__/ diff --git a/.prettierignore b/.prettierignore index 0978a006b..4ab09a93b 100644 --- a/.prettierignore +++ b/.prettierignore @@ -1 +1 @@ -**/kubernetes/ \ No newline at end of file +**/kubernetes/ diff --git a/AudioQnA/ui/docker/Dockerfile b/AudioQnA/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/AudioQnA/ui/docker/Dockerfile +++ b/AudioQnA/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/AudioQnA/ui/svelte/src/app.postcss b/AudioQnA/ui/svelte/src/app.postcss index c3e0519c6..4b957234d 100644 --- a/AudioQnA/ui/svelte/src/app.postcss +++ b/AudioQnA/ui/svelte/src/app.postcss @@ -79,4 +79,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/1.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/1.svg index 38adea6ff..71ac8d5fc 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/1.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/1.svg @@ -89,4 +89,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/2.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/2.svg index 0e6150e4a..95d405658 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/2.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/2.svg @@ -89,4 +89,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/3.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/3.svg index 3ed7f7fc5..310d437e5 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/3.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/3.svg @@ -76,4 +76,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/4.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/4.svg index 2b34e86b0..f3281671d 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/4.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/4.svg @@ -76,4 +76,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/5.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/5.svg index 718f3b304..8a5864192 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/5.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/5.svg @@ -89,4 +89,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/stop-recording.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/stop-recording.svg index 4f4e638ba..82e497ab0 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/stop-recording.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/stop-recording.svg @@ -3,4 +3,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/upload.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/upload.svg index 55790f05f..5264818eb 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/upload.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/upload.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voice.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voice.svg index 0cc1d520e..2d1375e1a 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voice.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voice.svg @@ -6,4 +6,4 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOff.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOff.svg index 8161062a4..fe9b59ee8 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOff.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOff.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOn.svg b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOn.svg index aeb96fabe..eca1441d1 100644 --- a/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOn.svg +++ b/AudioQnA/ui/svelte/src/lib/assets/icons/svg/voiceOn.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/AvatarChatbot/.gitignore b/AvatarChatbot/.gitignore index d7593f774..84dc2308b 100644 --- a/AvatarChatbot/.gitignore +++ b/AvatarChatbot/.gitignore @@ -5,4 +5,4 @@ docker_compose/intel/cpu/xeon/data docker_compose/intel/hpu/gaudi/data inputs/ -outputs/ \ No newline at end of file +outputs/ diff --git a/ChatQnA/ui/docker/Dockerfile b/ChatQnA/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/ChatQnA/ui/docker/Dockerfile +++ b/ChatQnA/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/ChatQnA/ui/docker/Dockerfile.react b/ChatQnA/ui/docker/Dockerfile.react index 49bc13124..18afc393a 100644 --- a/ChatQnA/ui/docker/Dockerfile.react +++ b/ChatQnA/ui/docker/Dockerfile.react @@ -18,4 +18,4 @@ COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html COPY ./react/env.sh /docker-entrypoint.d/env.sh COPY ./react/nginx.conf /etc/nginx/conf.d/default.conf -RUN chmod +x /docker-entrypoint.d/env.sh \ No newline at end of file +RUN chmod +x /docker-entrypoint.d/env.sh diff --git a/ChatQnA/ui/react/.env b/ChatQnA/ui/react/.env index e5d52f421..ae0bd3732 100644 --- a/ChatQnA/ui/react/.env +++ b/ChatQnA/ui/react/.env @@ -1,2 +1,2 @@ VITE_BACKEND_SERVICE_ENDPOINT=http://backend_address:8888/v1/chatqna -VITE_DATA_PREP_SERVICE_URL=http://backend_address:6007/v1/dataprep \ No newline at end of file +VITE_DATA_PREP_SERVICE_URL=http://backend_address:6007/v1/dataprep diff --git a/ChatQnA/ui/react/.env.production b/ChatQnA/ui/react/.env.production index a46e1e385..9922d6012 100644 --- a/ChatQnA/ui/react/.env.production +++ b/ChatQnA/ui/react/.env.production @@ -1,2 +1,2 @@ VITE_BACKEND_SERVICE_ENDPOINT=APP_BACKEND_SERVICE_ENDPOINT -VITE_DATA_PREP_SERVICE_URL=APP_DATA_PREP_SERVICE_URL \ No newline at end of file +VITE_DATA_PREP_SERVICE_URL=APP_DATA_PREP_SERVICE_URL diff --git a/ChatQnA/ui/react/nginx.conf b/ChatQnA/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/ChatQnA/ui/react/nginx.conf +++ b/ChatQnA/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/ChatQnA/ui/react/public/vite.svg b/ChatQnA/ui/react/public/vite.svg index e7b8dfb1b..ee9fadaf9 100644 --- a/ChatQnA/ui/react/public/vite.svg +++ b/ChatQnA/ui/react/public/vite.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/ChatQnA/ui/react/src/assets/react.svg b/ChatQnA/ui/react/src/assets/react.svg index 6c87de9bb..8e0e0f15c 100644 --- a/ChatQnA/ui/react/src/assets/react.svg +++ b/ChatQnA/ui/react/src/assets/react.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/ChatQnA/ui/react/src/components/Conversation/DataSource.tsx b/ChatQnA/ui/react/src/components/Conversation/DataSource.tsx index cb7b326c9..6f1b2ab06 100644 --- a/ChatQnA/ui/react/src/components/Conversation/DataSource.tsx +++ b/ChatQnA/ui/react/src/components/Conversation/DataSource.tsx @@ -68,4 +68,4 @@ export default function DataSource({ opened, onClose }: Props) { ) -} \ No newline at end of file +} diff --git a/ChatQnA/ui/react/src/components/UserInfoModal/UserInfoModal.tsx b/ChatQnA/ui/react/src/components/UserInfoModal/UserInfoModal.tsx index 4d54180a4..4540bd4c9 100644 --- a/ChatQnA/ui/react/src/components/UserInfoModal/UserInfoModal.tsx +++ b/ChatQnA/ui/react/src/components/UserInfoModal/UserInfoModal.tsx @@ -45,4 +45,4 @@ const UserInfoModal = () => { ) } -export default UserInfoModal \ No newline at end of file +export default UserInfoModal diff --git a/ChatQnA/ui/svelte/src/app.postcss b/ChatQnA/ui/svelte/src/app.postcss index 1bb14630c..963bbca4e 100644 --- a/ChatQnA/ui/svelte/src/app.postcss +++ b/ChatQnA/ui/svelte/src/app.postcss @@ -83,4 +83,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/ChatQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg b/ChatQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg index 9fe89acc1..8910f0ea6 100644 --- a/ChatQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg +++ b/ChatQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/ChatQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg b/ChatQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg index 362a6994e..9a77286a8 100644 --- a/ChatQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg +++ b/ChatQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/ChatQnA/ui/svelte/tests/test_file.txt b/ChatQnA/ui/svelte/tests/test_file.txt index 93fc5da94..bfbd73c1c 100644 --- a/ChatQnA/ui/svelte/tests/test_file.txt +++ b/ChatQnA/ui/svelte/tests/test_file.txt @@ -101,4 +101,4 @@ Terms of Use Privacy Sitemap Copyright © 2003 - 2023. All rights reserved. -CTATECH-PROD2 \ No newline at end of file +CTATECH-PROD2 diff --git a/CodeGen/ui/docker/Dockerfile b/CodeGen/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/CodeGen/ui/docker/Dockerfile +++ b/CodeGen/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/CodeGen/ui/docker/Dockerfile.react b/CodeGen/ui/docker/Dockerfile.react index 49bc13124..18afc393a 100644 --- a/CodeGen/ui/docker/Dockerfile.react +++ b/CodeGen/ui/docker/Dockerfile.react @@ -18,4 +18,4 @@ COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html COPY ./react/env.sh /docker-entrypoint.d/env.sh COPY ./react/nginx.conf /etc/nginx/conf.d/default.conf -RUN chmod +x /docker-entrypoint.d/env.sh \ No newline at end of file +RUN chmod +x /docker-entrypoint.d/env.sh diff --git a/CodeGen/ui/react/.env b/CodeGen/ui/react/.env index c5a7e3cad..3ce78a405 100644 --- a/CodeGen/ui/react/.env +++ b/CodeGen/ui/react/.env @@ -1 +1 @@ -VITE_CODE_GEN_URL=http://ip_address:7778/v1/codegen \ No newline at end of file +VITE_CODE_GEN_URL=http://ip_address:7778/v1/codegen diff --git a/CodeGen/ui/react/.env.production b/CodeGen/ui/react/.env.production index d3851cd49..8e99e67f9 100644 --- a/CodeGen/ui/react/.env.production +++ b/CodeGen/ui/react/.env.production @@ -1 +1 @@ -VITE_CODE_GEN_URL=APP_CODE_GEN_URL \ No newline at end of file +VITE_CODE_GEN_URL=APP_CODE_GEN_URL diff --git a/CodeGen/ui/react/nginx.conf b/CodeGen/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/CodeGen/ui/react/nginx.conf +++ b/CodeGen/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/CodeGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx b/CodeGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx index 479034cec..a21f7acc5 100644 --- a/CodeGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx +++ b/CodeGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx @@ -49,4 +49,4 @@ const CodeRender = ({ cleanCode, language, inline }:CodeRenderProps) => { } -export default CodeRender; \ No newline at end of file +export default CodeRender; diff --git a/CodeGen/ui/react/src/components/Shared/Markdown/Markdown.tsx b/CodeGen/ui/react/src/components/Shared/Markdown/Markdown.tsx index 6331c6d08..2726e14b2 100644 --- a/CodeGen/ui/react/src/components/Shared/Markdown/Markdown.tsx +++ b/CodeGen/ui/react/src/components/Shared/Markdown/Markdown.tsx @@ -59,4 +59,4 @@ const Markdown = ({ content }: MarkdownProps) => { />) } -export default Markdown; \ No newline at end of file +export default Markdown; diff --git a/CodeGen/ui/svelte/.prettierrc b/CodeGen/ui/svelte/.prettierrc index 3b2006102..d146ee2b2 100644 --- a/CodeGen/ui/svelte/.prettierrc +++ b/CodeGen/ui/svelte/.prettierrc @@ -10,4 +10,4 @@ } } ] -} \ No newline at end of file +} diff --git a/CodeGen/ui/svelte/src/app.postcss b/CodeGen/ui/svelte/src/app.postcss index fa2438088..ae1c1623f 100644 --- a/CodeGen/ui/svelte/src/app.postcss +++ b/CodeGen/ui/svelte/src/app.postcss @@ -113,4 +113,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/CodeTrans/ui/docker/Dockerfile b/CodeTrans/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/CodeTrans/ui/docker/Dockerfile +++ b/CodeTrans/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/DBQnA/ui/react/nginx.conf b/DBQnA/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/DBQnA/ui/react/nginx.conf +++ b/DBQnA/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/DBQnA/ui/react/src/logo.svg b/DBQnA/ui/react/src/logo.svg index 9dfc1c058..716947603 100644 --- a/DBQnA/ui/react/src/logo.svg +++ b/DBQnA/ui/react/src/logo.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/DBQnA/ui/react/src/main.tsx b/DBQnA/ui/react/src/main.tsx index a6695d54e..7f3e44154 100644 --- a/DBQnA/ui/react/src/main.tsx +++ b/DBQnA/ui/react/src/main.tsx @@ -10,4 +10,4 @@ ReactDOM.createRoot(document.getElementById("root")!).render( -) \ No newline at end of file +) diff --git a/DocSum/ui/docker/Dockerfile b/DocSum/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/DocSum/ui/docker/Dockerfile +++ b/DocSum/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/DocSum/ui/docker/Dockerfile.react b/DocSum/ui/docker/Dockerfile.react index aa8f3fe78..945886465 100644 --- a/DocSum/ui/docker/Dockerfile.react +++ b/DocSum/ui/docker/Dockerfile.react @@ -21,4 +21,4 @@ EXPOSE 80 COPY --from=vite-app /usr/app/react/nginx.conf /etc/nginx/conf.d/default.conf COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html -ENTRYPOINT ["nginx", "-g", "daemon off;"] \ No newline at end of file +ENTRYPOINT ["nginx", "-g", "daemon off;"] diff --git a/DocSum/ui/react/.env b/DocSum/ui/react/.env index 88e4996a2..b25495154 100644 --- a/DocSum/ui/react/.env +++ b/DocSum/ui/react/.env @@ -1 +1 @@ -VITE_DOC_SUM_URL=http://backend_address:8888/v1/docsum \ No newline at end of file +VITE_DOC_SUM_URL=http://backend_address:8888/v1/docsum diff --git a/DocSum/ui/react/nginx.conf b/DocSum/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/DocSum/ui/react/nginx.conf +++ b/DocSum/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/DocSum/ui/react/src/components/DocSum/DocSum.tsx b/DocSum/ui/react/src/components/DocSum/DocSum.tsx index 9e7472c65..2fa9fd4a3 100644 --- a/DocSum/ui/react/src/components/DocSum/DocSum.tsx +++ b/DocSum/ui/react/src/components/DocSum/DocSum.tsx @@ -150,4 +150,4 @@ const DocSum = () => { ) } -export default DocSum \ No newline at end of file +export default DocSum diff --git a/DocSum/ui/react/src/components/DocSum/FileUpload.tsx b/DocSum/ui/react/src/components/DocSum/FileUpload.tsx index baa77670c..1790cfb16 100644 --- a/DocSum/ui/react/src/components/DocSum/FileUpload.tsx +++ b/DocSum/ui/react/src/components/DocSum/FileUpload.tsx @@ -64,4 +64,4 @@ export function FileUpload(props: Partial) { ); -} \ No newline at end of file +} diff --git a/DocSum/ui/react/src/components/Shared/CodeRender/CodeRender.tsx b/DocSum/ui/react/src/components/Shared/CodeRender/CodeRender.tsx index 479034cec..a21f7acc5 100644 --- a/DocSum/ui/react/src/components/Shared/CodeRender/CodeRender.tsx +++ b/DocSum/ui/react/src/components/Shared/CodeRender/CodeRender.tsx @@ -49,4 +49,4 @@ const CodeRender = ({ cleanCode, language, inline }:CodeRenderProps) => { } -export default CodeRender; \ No newline at end of file +export default CodeRender; diff --git a/DocSum/ui/react/src/components/Shared/Markdown/Markdown.tsx b/DocSum/ui/react/src/components/Shared/Markdown/Markdown.tsx index dc4b2d308..77471cd19 100644 --- a/DocSum/ui/react/src/components/Shared/Markdown/Markdown.tsx +++ b/DocSum/ui/react/src/components/Shared/Markdown/Markdown.tsx @@ -55,4 +55,4 @@ const Markdown = ({ content }: MarkdownProps) => { />) } -export default Markdown; \ No newline at end of file +export default Markdown; diff --git a/EdgeCraftRAG/Dockerfile b/EdgeCraftRAG/Dockerfile index a15136464..3c9711dea 100644 --- a/EdgeCraftRAG/Dockerfile +++ b/EdgeCraftRAG/Dockerfile @@ -25,4 +25,4 @@ USER user RUN echo 'ulimit -S -n 999999' >> ~/.bashrc -ENTRYPOINT ["python", "chatqna.py"] \ No newline at end of file +ENTRYPOINT ["python", "chatqna.py"] diff --git a/EdgeCraftRAG/edgecraftrag/prompt_template/default_prompt.txt b/EdgeCraftRAG/edgecraftrag/prompt_template/default_prompt.txt index aa57e6059..800d1fa2f 100644 --- a/EdgeCraftRAG/edgecraftrag/prompt_template/default_prompt.txt +++ b/EdgeCraftRAG/edgecraftrag/prompt_template/default_prompt.txt @@ -5,4 +5,4 @@ <|im_start|>System: Pay attention to your formatting of response. If you need to reference content from context, try to keep the formatting.<|im_end|> <|im_start|>System: Try to summarize from the context, do some reasoning before response, then response. Make sure your response is logically sound and self-consistent.<|im_end|> -<|im_start|>{input} \ No newline at end of file +<|im_start|>{input} diff --git a/EdgeCraftRAG/ui/docker/Dockerfile.ui b/EdgeCraftRAG/ui/docker/Dockerfile.ui index d8e5eec8e..46a14a6e9 100644 --- a/EdgeCraftRAG/ui/docker/Dockerfile.ui +++ b/EdgeCraftRAG/ui/docker/Dockerfile.ui @@ -20,4 +20,4 @@ USER user RUN echo 'ulimit -S -n 999999' >> ~/.bashrc -ENTRYPOINT ["python", "ecragui.py"] \ No newline at end of file +ENTRYPOINT ["python", "ecragui.py"] diff --git a/FaqGen/ui/docker/Dockerfile b/FaqGen/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/FaqGen/ui/docker/Dockerfile +++ b/FaqGen/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/FaqGen/ui/docker/Dockerfile.react b/FaqGen/ui/docker/Dockerfile.react index 4e29136a6..734c6ba1d 100644 --- a/FaqGen/ui/docker/Dockerfile.react +++ b/FaqGen/ui/docker/Dockerfile.react @@ -17,4 +17,4 @@ EXPOSE 80 COPY --from=vite-app /usr/app/react/nginx.conf /etc/nginx/conf.d/default.conf COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html -ENTRYPOINT ["nginx", "-g", "daemon off;"] \ No newline at end of file +ENTRYPOINT ["nginx", "-g", "daemon off;"] diff --git a/FaqGen/ui/react/nginx.conf b/FaqGen/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/FaqGen/ui/react/nginx.conf +++ b/FaqGen/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/FaqGen/ui/react/public/vite.svg b/FaqGen/ui/react/public/vite.svg index e7b8dfb1b..ee9fadaf9 100644 --- a/FaqGen/ui/react/public/vite.svg +++ b/FaqGen/ui/react/public/vite.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/FaqGen/ui/react/src/assets/react.svg b/FaqGen/ui/react/src/assets/react.svg index 6c87de9bb..8e0e0f15c 100644 --- a/FaqGen/ui/react/src/assets/react.svg +++ b/FaqGen/ui/react/src/assets/react.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/FaqGen/ui/react/src/components/FaqGen/FaqGen.tsx b/FaqGen/ui/react/src/components/FaqGen/FaqGen.tsx index ca731cbf8..74f52d3ef 100644 --- a/FaqGen/ui/react/src/components/FaqGen/FaqGen.tsx +++ b/FaqGen/ui/react/src/components/FaqGen/FaqGen.tsx @@ -164,4 +164,4 @@ const FaqGen = () => { ) } -export default FaqGen; \ No newline at end of file +export default FaqGen; diff --git a/FaqGen/ui/react/src/components/FaqGen/FileUpload.tsx b/FaqGen/ui/react/src/components/FaqGen/FileUpload.tsx index 914ac8724..aa5d84a00 100644 --- a/FaqGen/ui/react/src/components/FaqGen/FileUpload.tsx +++ b/FaqGen/ui/react/src/components/FaqGen/FileUpload.tsx @@ -76,4 +76,4 @@ export function FileUpload(props: Partial) { ); -} \ No newline at end of file +} diff --git a/FaqGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx b/FaqGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx index 479034cec..a21f7acc5 100644 --- a/FaqGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx +++ b/FaqGen/ui/react/src/components/Shared/CodeRender/CodeRender.tsx @@ -49,4 +49,4 @@ const CodeRender = ({ cleanCode, language, inline }:CodeRenderProps) => { } -export default CodeRender; \ No newline at end of file +export default CodeRender; diff --git a/FaqGen/ui/react/src/components/Shared/Markdown/Markdown.tsx b/FaqGen/ui/react/src/components/Shared/Markdown/Markdown.tsx index 64f624bc6..653ac4b02 100644 --- a/FaqGen/ui/react/src/components/Shared/Markdown/Markdown.tsx +++ b/FaqGen/ui/react/src/components/Shared/Markdown/Markdown.tsx @@ -58,4 +58,4 @@ const Markdown = ({ content }: MarkdownProps) => { />) } -export default Markdown; \ No newline at end of file +export default Markdown; diff --git a/GraphRAG/ui/docker/Dockerfile b/GraphRAG/ui/docker/Dockerfile index ef034e67c..c609e0d64 100644 --- a/GraphRAG/ui/docker/Dockerfile +++ b/GraphRAG/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/GraphRAG/ui/docker/Dockerfile.react b/GraphRAG/ui/docker/Dockerfile.react index 9c4eff842..a92dba7d8 100644 --- a/GraphRAG/ui/docker/Dockerfile.react +++ b/GraphRAG/ui/docker/Dockerfile.react @@ -16,4 +16,4 @@ COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html COPY ./react/env.sh /docker-entrypoint.d/env.sh COPY ./react/nginx.conf /etc/nginx/conf.d/default.conf -RUN chmod +x /docker-entrypoint.d/env.sh \ No newline at end of file +RUN chmod +x /docker-entrypoint.d/env.sh diff --git a/GraphRAG/ui/react/.env b/GraphRAG/ui/react/.env index e5d52f421..ae0bd3732 100644 --- a/GraphRAG/ui/react/.env +++ b/GraphRAG/ui/react/.env @@ -1,2 +1,2 @@ VITE_BACKEND_SERVICE_ENDPOINT=http://backend_address:8888/v1/chatqna -VITE_DATA_PREP_SERVICE_URL=http://backend_address:6007/v1/dataprep \ No newline at end of file +VITE_DATA_PREP_SERVICE_URL=http://backend_address:6007/v1/dataprep diff --git a/GraphRAG/ui/react/.env.production b/GraphRAG/ui/react/.env.production index a46e1e385..9922d6012 100644 --- a/GraphRAG/ui/react/.env.production +++ b/GraphRAG/ui/react/.env.production @@ -1,2 +1,2 @@ VITE_BACKEND_SERVICE_ENDPOINT=APP_BACKEND_SERVICE_ENDPOINT -VITE_DATA_PREP_SERVICE_URL=APP_DATA_PREP_SERVICE_URL \ No newline at end of file +VITE_DATA_PREP_SERVICE_URL=APP_DATA_PREP_SERVICE_URL diff --git a/GraphRAG/ui/react/nginx.conf b/GraphRAG/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/GraphRAG/ui/react/nginx.conf +++ b/GraphRAG/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/GraphRAG/ui/react/public/vite.svg b/GraphRAG/ui/react/public/vite.svg index e7b8dfb1b..ee9fadaf9 100644 --- a/GraphRAG/ui/react/public/vite.svg +++ b/GraphRAG/ui/react/public/vite.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/GraphRAG/ui/react/src/assets/react.svg b/GraphRAG/ui/react/src/assets/react.svg index 6c87de9bb..8e0e0f15c 100644 --- a/GraphRAG/ui/react/src/assets/react.svg +++ b/GraphRAG/ui/react/src/assets/react.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/GraphRAG/ui/react/src/components/Conversation/DataSource.tsx b/GraphRAG/ui/react/src/components/Conversation/DataSource.tsx index cb7b326c9..6f1b2ab06 100644 --- a/GraphRAG/ui/react/src/components/Conversation/DataSource.tsx +++ b/GraphRAG/ui/react/src/components/Conversation/DataSource.tsx @@ -68,4 +68,4 @@ export default function DataSource({ opened, onClose }: Props) { ) -} \ No newline at end of file +} diff --git a/GraphRAG/ui/react/src/components/UserInfoModal/UserInfoModal.tsx b/GraphRAG/ui/react/src/components/UserInfoModal/UserInfoModal.tsx index 4d54180a4..4540bd4c9 100644 --- a/GraphRAG/ui/react/src/components/UserInfoModal/UserInfoModal.tsx +++ b/GraphRAG/ui/react/src/components/UserInfoModal/UserInfoModal.tsx @@ -45,4 +45,4 @@ const UserInfoModal = () => { ) } -export default UserInfoModal \ No newline at end of file +export default UserInfoModal diff --git a/GraphRAG/ui/svelte/src/app.postcss b/GraphRAG/ui/svelte/src/app.postcss index 1bb14630c..963bbca4e 100644 --- a/GraphRAG/ui/svelte/src/app.postcss +++ b/GraphRAG/ui/svelte/src/app.postcss @@ -83,4 +83,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/GraphRAG/ui/svelte/src/lib/assets/voice/svg/paste.svg b/GraphRAG/ui/svelte/src/lib/assets/voice/svg/paste.svg index 9fe89acc1..8910f0ea6 100644 --- a/GraphRAG/ui/svelte/src/lib/assets/voice/svg/paste.svg +++ b/GraphRAG/ui/svelte/src/lib/assets/voice/svg/paste.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/GraphRAG/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg b/GraphRAG/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg index 362a6994e..9a77286a8 100644 --- a/GraphRAG/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg +++ b/GraphRAG/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/GraphRAG/ui/svelte/tests/test_file.txt b/GraphRAG/ui/svelte/tests/test_file.txt index 93fc5da94..bfbd73c1c 100644 --- a/GraphRAG/ui/svelte/tests/test_file.txt +++ b/GraphRAG/ui/svelte/tests/test_file.txt @@ -101,4 +101,4 @@ Terms of Use Privacy Sitemap Copyright © 2003 - 2023. All rights reserved. -CTATECH-PROD2 \ No newline at end of file +CTATECH-PROD2 diff --git a/LICENSE b/LICENSE index 2bb9ad240..d9a10c0d8 100644 --- a/LICENSE +++ b/LICENSE @@ -173,4 +173,4 @@ incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. - END OF TERMS AND CONDITIONS \ No newline at end of file + END OF TERMS AND CONDITIONS diff --git a/ProductivitySuite/ui/docker/Dockerfile.react b/ProductivitySuite/ui/docker/Dockerfile.react index f023b7afb..4c4d72761 100644 --- a/ProductivitySuite/ui/docker/Dockerfile.react +++ b/ProductivitySuite/ui/docker/Dockerfile.react @@ -18,4 +18,4 @@ COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html COPY ./react/env.sh /docker-entrypoint.d/env.sh COPY ./react/nginx.conf /etc/nginx/conf.d/default.conf -RUN chmod +x /docker-entrypoint.d/env.sh \ No newline at end of file +RUN chmod +x /docker-entrypoint.d/env.sh diff --git a/ProductivitySuite/ui/react/.env.production b/ProductivitySuite/ui/react/.env.production index a7b38a272..f881c388c 100644 --- a/ProductivitySuite/ui/react/.env.production +++ b/ProductivitySuite/ui/react/.env.production @@ -13,4 +13,4 @@ VITE_CHAT_HISTORY_CREATE_ENDPOINT=APP_CHAT_HISTORY_CREATE_ENDPOINT VITE_CHAT_HISTORY_GET_ENDPOINT=APP_CHAT_HISTORY_GET_ENDPOINT VITE_CHAT_HISTORY_DELETE_ENDPOINT=APP_CHAT_HISTORY_DELETE_ENDPOINT VITE_PROMPT_SERVICE_GET_ENDPOINT=APP_PROMPT_SERVICE_GET_ENDPOINT -VITE_PROMPT_SERVICE_CREATE_ENDPOINT=APP_PROMPT_SERVICE_CREATE_ENDPOINT \ No newline at end of file +VITE_PROMPT_SERVICE_CREATE_ENDPOINT=APP_PROMPT_SERVICE_CREATE_ENDPOINT diff --git a/ProductivitySuite/ui/react/nginx.conf b/ProductivitySuite/ui/react/nginx.conf index 00433fcda..01aef1275 100644 --- a/ProductivitySuite/ui/react/nginx.conf +++ b/ProductivitySuite/ui/react/nginx.conf @@ -17,4 +17,4 @@ server { expires 1d; } } -} \ No newline at end of file +} diff --git a/ProductivitySuite/ui/react/src/assets/react.svg b/ProductivitySuite/ui/react/src/assets/react.svg index 6c87de9bb..8e0e0f15c 100644 --- a/ProductivitySuite/ui/react/src/assets/react.svg +++ b/ProductivitySuite/ui/react/src/assets/react.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/ProductivitySuite/ui/react/src/components/Conversation/DataSource.tsx b/ProductivitySuite/ui/react/src/components/Conversation/DataSource.tsx index cc273aa83..72575af06 100644 --- a/ProductivitySuite/ui/react/src/components/Conversation/DataSource.tsx +++ b/ProductivitySuite/ui/react/src/components/Conversation/DataSource.tsx @@ -90,4 +90,4 @@ export default function DataSource() { ) -} \ No newline at end of file +} diff --git a/ProductivitySuite/ui/react/src/components/Conversation/PromptTemplate.tsx b/ProductivitySuite/ui/react/src/components/Conversation/PromptTemplate.tsx index 4acb55743..723e1c429 100644 --- a/ProductivitySuite/ui/react/src/components/Conversation/PromptTemplate.tsx +++ b/ProductivitySuite/ui/react/src/components/Conversation/PromptTemplate.tsx @@ -28,4 +28,4 @@ function PromptTemplate({setPrompt}:PromptTemplateProps) { ) } -export default PromptTemplate \ No newline at end of file +export default PromptTemplate diff --git a/ProductivitySuite/ui/react/src/components/Conversation/settings.tsx b/ProductivitySuite/ui/react/src/components/Conversation/settings.tsx index 61fd87e9b..bb9468413 100644 --- a/ProductivitySuite/ui/react/src/components/Conversation/settings.tsx +++ b/ProductivitySuite/ui/react/src/components/Conversation/settings.tsx @@ -45,4 +45,4 @@ function Settings() { ) } -export default Settings \ No newline at end of file +export default Settings diff --git a/ProductivitySuite/ui/react/src/components/DocSum/DocSum.tsx b/ProductivitySuite/ui/react/src/components/DocSum/DocSum.tsx index 9e7472c65..2fa9fd4a3 100644 --- a/ProductivitySuite/ui/react/src/components/DocSum/DocSum.tsx +++ b/ProductivitySuite/ui/react/src/components/DocSum/DocSum.tsx @@ -150,4 +150,4 @@ const DocSum = () => { ) } -export default DocSum \ No newline at end of file +export default DocSum diff --git a/ProductivitySuite/ui/react/src/components/DocSum/FileUpload.tsx b/ProductivitySuite/ui/react/src/components/DocSum/FileUpload.tsx index 914ac8724..aa5d84a00 100644 --- a/ProductivitySuite/ui/react/src/components/DocSum/FileUpload.tsx +++ b/ProductivitySuite/ui/react/src/components/DocSum/FileUpload.tsx @@ -76,4 +76,4 @@ export function FileUpload(props: Partial) { ); -} \ No newline at end of file +} diff --git a/ProductivitySuite/ui/react/src/components/FaqGen/FaqGen.tsx b/ProductivitySuite/ui/react/src/components/FaqGen/FaqGen.tsx index ca731cbf8..74f52d3ef 100644 --- a/ProductivitySuite/ui/react/src/components/FaqGen/FaqGen.tsx +++ b/ProductivitySuite/ui/react/src/components/FaqGen/FaqGen.tsx @@ -164,4 +164,4 @@ const FaqGen = () => { ) } -export default FaqGen; \ No newline at end of file +export default FaqGen; diff --git a/ProductivitySuite/ui/react/src/components/FaqGen/FileUpload.tsx b/ProductivitySuite/ui/react/src/components/FaqGen/FileUpload.tsx index 914ac8724..aa5d84a00 100644 --- a/ProductivitySuite/ui/react/src/components/FaqGen/FileUpload.tsx +++ b/ProductivitySuite/ui/react/src/components/FaqGen/FileUpload.tsx @@ -76,4 +76,4 @@ export function FileUpload(props: Partial) { ); -} \ No newline at end of file +} diff --git a/ProductivitySuite/ui/react/src/components/Shared/CodeRender/CodeRender.tsx b/ProductivitySuite/ui/react/src/components/Shared/CodeRender/CodeRender.tsx index 479034cec..a21f7acc5 100644 --- a/ProductivitySuite/ui/react/src/components/Shared/CodeRender/CodeRender.tsx +++ b/ProductivitySuite/ui/react/src/components/Shared/CodeRender/CodeRender.tsx @@ -49,4 +49,4 @@ const CodeRender = ({ cleanCode, language, inline }:CodeRenderProps) => { } -export default CodeRender; \ No newline at end of file +export default CodeRender; diff --git a/ProductivitySuite/ui/react/src/components/Shared/Markdown/Markdown.tsx b/ProductivitySuite/ui/react/src/components/Shared/Markdown/Markdown.tsx index 6331c6d08..2726e14b2 100644 --- a/ProductivitySuite/ui/react/src/components/Shared/Markdown/Markdown.tsx +++ b/ProductivitySuite/ui/react/src/components/Shared/Markdown/Markdown.tsx @@ -59,4 +59,4 @@ const Markdown = ({ content }: MarkdownProps) => { />) } -export default Markdown; \ No newline at end of file +export default Markdown; diff --git a/SearchQnA/ui/docker/Dockerfile b/SearchQnA/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/SearchQnA/ui/docker/Dockerfile +++ b/SearchQnA/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/SearchQnA/ui/svelte/.env b/SearchQnA/ui/svelte/.env index 89db8c467..49f7b9dd5 100644 --- a/SearchQnA/ui/svelte/.env +++ b/SearchQnA/ui/svelte/.env @@ -1 +1 @@ -BACKEND_BASE_URL = 'http://backend_address:3008/v1/searchqna' \ No newline at end of file +BACKEND_BASE_URL = 'http://backend_address:3008/v1/searchqna' diff --git a/SearchQnA/ui/svelte/src/app.postcss b/SearchQnA/ui/svelte/src/app.postcss index 1bb14630c..963bbca4e 100644 --- a/SearchQnA/ui/svelte/src/app.postcss +++ b/SearchQnA/ui/svelte/src/app.postcss @@ -83,4 +83,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/SearchQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg b/SearchQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg index 9fe89acc1..8910f0ea6 100644 --- a/SearchQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg +++ b/SearchQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/SearchQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg b/SearchQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg index 362a6994e..9a77286a8 100644 --- a/SearchQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg +++ b/SearchQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/Text2Image/ui/docker/Dockerfile b/Text2Image/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/Text2Image/ui/docker/Dockerfile +++ b/Text2Image/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/Text2Image/ui/svelte/src/app.postcss b/Text2Image/ui/svelte/src/app.postcss index 1bb14630c..963bbca4e 100644 --- a/Text2Image/ui/svelte/src/app.postcss +++ b/Text2Image/ui/svelte/src/app.postcss @@ -83,4 +83,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/Translation/ui/svelte/.env b/Translation/ui/svelte/.env index 4df683237..fdb106b4b 100644 --- a/Translation/ui/svelte/.env +++ b/Translation/ui/svelte/.env @@ -1 +1 @@ -BASE_URL = 'http://10.7.5.135:8888/v1/translation' \ No newline at end of file +BASE_URL = 'http://10.7.5.135:8888/v1/translation' diff --git a/VideoQnA/ui/docker/Dockerfile b/VideoQnA/ui/docker/Dockerfile index 7220b28ac..dcd029a0b 100644 --- a/VideoQnA/ui/docker/Dockerfile +++ b/VideoQnA/ui/docker/Dockerfile @@ -18,4 +18,4 @@ EXPOSE 5173 HEALTHCHECK CMD curl --fail http://localhost:5173/_stcore/health -ENTRYPOINT ["streamlit", "run", "ui.py", "--server.port=5173", "--server.address=0.0.0.0"] \ No newline at end of file +ENTRYPOINT ["streamlit", "run", "ui.py", "--server.port=5173", "--server.address=0.0.0.0"] diff --git a/VisualQnA/ui/docker/Dockerfile b/VisualQnA/ui/docker/Dockerfile index ac2bb7da3..1d5115f4b 100644 --- a/VisualQnA/ui/docker/Dockerfile +++ b/VisualQnA/ui/docker/Dockerfile @@ -23,4 +23,4 @@ RUN npm run build EXPOSE 5173 # Run the front-end application in preview mode -CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] \ No newline at end of file +CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"] diff --git a/VisualQnA/ui/svelte/.env b/VisualQnA/ui/svelte/.env index e3086b4e0..ce3ce4033 100644 --- a/VisualQnA/ui/svelte/.env +++ b/VisualQnA/ui/svelte/.env @@ -1 +1 @@ -BACKEND_BASE_URL = '/v1/visualqna' \ No newline at end of file +BACKEND_BASE_URL = '/v1/visualqna' diff --git a/VisualQnA/ui/svelte/src/app.postcss b/VisualQnA/ui/svelte/src/app.postcss index 1bb14630c..963bbca4e 100644 --- a/VisualQnA/ui/svelte/src/app.postcss +++ b/VisualQnA/ui/svelte/src/app.postcss @@ -83,4 +83,4 @@ a.btn { .w-12\/12 { width: 100% -} \ No newline at end of file +} diff --git a/VisualQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg b/VisualQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg index 9fe89acc1..8910f0ea6 100644 --- a/VisualQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg +++ b/VisualQnA/ui/svelte/src/lib/assets/voice/svg/paste.svg @@ -1 +1 @@ - \ No newline at end of file + diff --git a/VisualQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg b/VisualQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg index 362a6994e..9a77286a8 100644 --- a/VisualQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg +++ b/VisualQnA/ui/svelte/src/lib/assets/voice/svg/uploadFile.svg @@ -1 +1 @@ - \ No newline at end of file +