From 6730b242cc5367206d79bd10cef73ec8ac3694ea Mon Sep 17 00:00:00 2001 From: Zhenzhong1 <109137058+Zhenzhong1@users.noreply.github.com> Date: Wed, 4 Sep 2024 19:50:46 +0800 Subject: [PATCH] [ChatQnA] Update retrieval & dataprep manifests (#717) * modify tgi hyperparameters * upgrade tgi 2.0.1 to 2.0.4 * Update dataprep-microservice_run.yaml * Update retrieval-microservice_run.yaml * Update retrieval-microservice_run.yaml * Update dataprep-microservice_run.yaml * Update dataprep-microservice_run.yaml * Update dataprep-microservice_run.yaml * Update retrieval-microservice_run.yaml * Update retrieval-microservice_run.yaml --- .../four_gaudi/dataprep-microservice_run.yaml | 5 +++++ ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml | 2 +- .../four_gaudi/retrieval-microservice_run.yaml | 10 ++++++++++ .../single_gaudi/dataprep-microservice_run.yaml | 5 +++++ ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml | 2 +- .../single_gaudi/retrieval-microservice_run.yaml | 10 ++++++++++ .../benchmark/two_gaudi/dataprep-microservice_run.yaml | 5 +++++ ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml | 2 +- .../two_gaudi/retrieval-microservice_run.yaml | 10 ++++++++++ 9 files changed, 48 insertions(+), 3 deletions(-) diff --git a/ChatQnA/benchmark/four_gaudi/dataprep-microservice_run.yaml b/ChatQnA/benchmark/four_gaudi/dataprep-microservice_run.yaml index 14fae684c..4c71df7ce 100644 --- a/ChatQnA/benchmark/four_gaudi/dataprep-microservice_run.yaml +++ b/ChatQnA/benchmark/four_gaudi/dataprep-microservice_run.yaml @@ -35,6 +35,11 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT - name: INDEX_NAME valueFrom: configMapKeyRef: diff --git a/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml index 127160e33..6903ee506 100644 --- a/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml +++ b/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml @@ -25,7 +25,7 @@ spec: - envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.1 + image: ghcr.io/huggingface/tgi-gaudi:2.0.4 name: llm-dependency-deploy-demo securityContext: capabilities: diff --git a/ChatQnA/benchmark/four_gaudi/retrieval-microservice_run.yaml b/ChatQnA/benchmark/four_gaudi/retrieval-microservice_run.yaml index 72a087dc5..25314a782 100644 --- a/ChatQnA/benchmark/four_gaudi/retrieval-microservice_run.yaml +++ b/ChatQnA/benchmark/four_gaudi/retrieval-microservice_run.yaml @@ -35,6 +35,16 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_EMBEDDING_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT + - name: HUGGINGFACEHUB_API_TOKEN + valueFrom: + configMapKeyRef: + name: qna-config + key: HUGGINGFACEHUB_API_TOKEN - name: INDEX_NAME valueFrom: configMapKeyRef: diff --git a/ChatQnA/benchmark/single_gaudi/dataprep-microservice_run.yaml b/ChatQnA/benchmark/single_gaudi/dataprep-microservice_run.yaml index 14fae684c..4c71df7ce 100644 --- a/ChatQnA/benchmark/single_gaudi/dataprep-microservice_run.yaml +++ b/ChatQnA/benchmark/single_gaudi/dataprep-microservice_run.yaml @@ -35,6 +35,11 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT - name: INDEX_NAME valueFrom: configMapKeyRef: diff --git a/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml index ae30c6a21..6de12aa6d 100644 --- a/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml +++ b/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml @@ -25,7 +25,7 @@ spec: - envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.1 + image: ghcr.io/huggingface/tgi-gaudi:2.0.4 name: llm-dependency-deploy-demo securityContext: capabilities: diff --git a/ChatQnA/benchmark/single_gaudi/retrieval-microservice_run.yaml b/ChatQnA/benchmark/single_gaudi/retrieval-microservice_run.yaml index 40040ee5b..298abd73a 100644 --- a/ChatQnA/benchmark/single_gaudi/retrieval-microservice_run.yaml +++ b/ChatQnA/benchmark/single_gaudi/retrieval-microservice_run.yaml @@ -35,6 +35,16 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_EMBEDDING_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT + - name: HUGGINGFACEHUB_API_TOKEN + valueFrom: + configMapKeyRef: + name: qna-config + key: HUGGINGFACEHUB_API_TOKEN - name: INDEX_NAME valueFrom: configMapKeyRef: diff --git a/ChatQnA/benchmark/two_gaudi/dataprep-microservice_run.yaml b/ChatQnA/benchmark/two_gaudi/dataprep-microservice_run.yaml index 14fae684c..4c71df7ce 100644 --- a/ChatQnA/benchmark/two_gaudi/dataprep-microservice_run.yaml +++ b/ChatQnA/benchmark/two_gaudi/dataprep-microservice_run.yaml @@ -35,6 +35,11 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT - name: INDEX_NAME valueFrom: configMapKeyRef: diff --git a/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml index 4d9988441..550e338e1 100644 --- a/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml +++ b/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml @@ -25,7 +25,7 @@ spec: - envFrom: - configMapRef: name: qna-config - image: ghcr.io/huggingface/tgi-gaudi:2.0.1 + image: ghcr.io/huggingface/tgi-gaudi:2.0.4 name: llm-dependency-deploy-demo securityContext: capabilities: diff --git a/ChatQnA/benchmark/two_gaudi/retrieval-microservice_run.yaml b/ChatQnA/benchmark/two_gaudi/retrieval-microservice_run.yaml index b9654d3e3..b6799fc60 100644 --- a/ChatQnA/benchmark/two_gaudi/retrieval-microservice_run.yaml +++ b/ChatQnA/benchmark/two_gaudi/retrieval-microservice_run.yaml @@ -35,6 +35,16 @@ spec: configMapKeyRef: name: qna-config key: REDIS_URL + - name: TEI_EMBEDDING_ENDPOINT + valueFrom: + configMapKeyRef: + name: qna-config + key: TEI_EMBEDDING_ENDPOINT + - name: HUGGINGFACEHUB_API_TOKEN + valueFrom: + configMapKeyRef: + name: qna-config + key: HUGGINGFACEHUB_API_TOKEN - name: INDEX_NAME valueFrom: configMapKeyRef: