Skip to content

Commit 6730b24

Browse files
authored
[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
1 parent 4a51874 commit 6730b24

9 files changed

+48
-3
lines changed

ChatQnA/benchmark/four_gaudi/dataprep-microservice_run.yaml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,11 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
3843
- name: INDEX_NAME
3944
valueFrom:
4045
configMapKeyRef:

ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ spec:
2525
- envFrom:
2626
- configMapRef:
2727
name: qna-config
28-
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
28+
image: ghcr.io/huggingface/tgi-gaudi:2.0.4
2929
name: llm-dependency-deploy-demo
3030
securityContext:
3131
capabilities:

ChatQnA/benchmark/four_gaudi/retrieval-microservice_run.yaml

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,16 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_EMBEDDING_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
43+
- name: HUGGINGFACEHUB_API_TOKEN
44+
valueFrom:
45+
configMapKeyRef:
46+
name: qna-config
47+
key: HUGGINGFACEHUB_API_TOKEN
3848
- name: INDEX_NAME
3949
valueFrom:
4050
configMapKeyRef:

ChatQnA/benchmark/single_gaudi/dataprep-microservice_run.yaml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,11 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
3843
- name: INDEX_NAME
3944
valueFrom:
4045
configMapKeyRef:

ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ spec:
2525
- envFrom:
2626
- configMapRef:
2727
name: qna-config
28-
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
28+
image: ghcr.io/huggingface/tgi-gaudi:2.0.4
2929
name: llm-dependency-deploy-demo
3030
securityContext:
3131
capabilities:

ChatQnA/benchmark/single_gaudi/retrieval-microservice_run.yaml

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,16 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_EMBEDDING_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
43+
- name: HUGGINGFACEHUB_API_TOKEN
44+
valueFrom:
45+
configMapKeyRef:
46+
name: qna-config
47+
key: HUGGINGFACEHUB_API_TOKEN
3848
- name: INDEX_NAME
3949
valueFrom:
4050
configMapKeyRef:

ChatQnA/benchmark/two_gaudi/dataprep-microservice_run.yaml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,11 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
3843
- name: INDEX_NAME
3944
valueFrom:
4045
configMapKeyRef:

ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ spec:
2525
- envFrom:
2626
- configMapRef:
2727
name: qna-config
28-
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
28+
image: ghcr.io/huggingface/tgi-gaudi:2.0.4
2929
name: llm-dependency-deploy-demo
3030
securityContext:
3131
capabilities:

ChatQnA/benchmark/two_gaudi/retrieval-microservice_run.yaml

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,16 @@ spec:
3535
configMapKeyRef:
3636
name: qna-config
3737
key: REDIS_URL
38+
- name: TEI_EMBEDDING_ENDPOINT
39+
valueFrom:
40+
configMapKeyRef:
41+
name: qna-config
42+
key: TEI_EMBEDDING_ENDPOINT
43+
- name: HUGGINGFACEHUB_API_TOKEN
44+
valueFrom:
45+
configMapKeyRef:
46+
name: qna-config
47+
key: HUGGINGFACEHUB_API_TOKEN
3848
- name: INDEX_NAME
3949
valueFrom:
4050
configMapKeyRef:

0 commit comments

Comments
 (0)