From 26a0099352c20c8cd1424a01de629a3d26802b48 Mon Sep 17 00:00:00 2001 From: Xinyao Wang Date: Fri, 10 Jan 2025 21:32:22 +0800 Subject: [PATCH] align docsum endpoint Signed-off-by: Xinyao Wang --- DocSum/docker_compose/amd/gpu/rocm/README.md | 2 +- DocSum/docker_compose/intel/cpu/xeon/README.md | 2 +- DocSum/docker_compose/intel/hpu/gaudi/README.md | 2 +- DocSum/docsum.py | 2 +- DocSum/kubernetes/gmc/docsum_gaudi.yaml | 2 +- DocSum/kubernetes/gmc/docsum_xeon.yaml | 2 +- DocSum/tests/test_compose_on_gaudi.sh | 2 +- DocSum/tests/test_compose_on_rocm.sh | 2 +- DocSum/tests/test_compose_on_xeon.sh | 2 +- ProductivitySuite/docker_compose/intel/cpu/xeon/README.md | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) diff --git a/DocSum/docker_compose/amd/gpu/rocm/README.md b/DocSum/docker_compose/amd/gpu/rocm/README.md index 9925096b66..b45a496755 100644 --- a/DocSum/docker_compose/amd/gpu/rocm/README.md +++ b/DocSum/docker_compose/amd/gpu/rocm/README.md @@ -127,7 +127,7 @@ docker compose up -d 2. LLM Microservice ```bash - curl http://${host_ip}:9000/v1/chat/docsum \ + curl http://${host_ip}:9000/v1/docsum \ -X POST \ -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \ -H 'Content-Type: application/json' diff --git a/DocSum/docker_compose/intel/cpu/xeon/README.md b/DocSum/docker_compose/intel/cpu/xeon/README.md index 11c1d6091e..9465c0c976 100644 --- a/DocSum/docker_compose/intel/cpu/xeon/README.md +++ b/DocSum/docker_compose/intel/cpu/xeon/README.md @@ -140,7 +140,7 @@ You will have the following Docker Images: 2. LLM Microservice ```bash - curl http://${host_ip}:9000/v1/chat/docsum \ + curl http://${host_ip}:9000/v1/docsum \ -X POST \ -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \ -H 'Content-Type: application/json' diff --git a/DocSum/docker_compose/intel/hpu/gaudi/README.md b/DocSum/docker_compose/intel/hpu/gaudi/README.md index d2a4516747..d150b3f28e 100644 --- a/DocSum/docker_compose/intel/hpu/gaudi/README.md +++ b/DocSum/docker_compose/intel/hpu/gaudi/README.md @@ -132,7 +132,7 @@ You will have the following Docker Images: 2. LLM Microservice ```bash - curl http://${host_ip}:9000/v1/chat/docsum \ + curl http://${host_ip}:9000/v1/docsum \ -X POST \ -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \ -H 'Content-Type: application/json' diff --git a/DocSum/docsum.py b/DocSum/docsum.py index d1689d92a0..1d71f24ad1 100644 --- a/DocSum/docsum.py +++ b/DocSum/docsum.py @@ -146,7 +146,7 @@ def add_remote_service(self): name="llm", host=LLM_SERVICE_HOST_IP, port=LLM_SERVICE_PORT, - endpoint="/v1/chat/docsum", + endpoint="/v1/docsum", use_remote_service=True, service_type=ServiceType.LLM, ) diff --git a/DocSum/kubernetes/gmc/docsum_gaudi.yaml b/DocSum/kubernetes/gmc/docsum_gaudi.yaml index 9b7a1ef30f..66c55ae92b 100644 --- a/DocSum/kubernetes/gmc/docsum_gaudi.yaml +++ b/DocSum/kubernetes/gmc/docsum_gaudi.yaml @@ -23,7 +23,7 @@ spec: internalService: serviceName: docsum-llm-uservice config: - endpoint: /v1/chat/docsum + endpoint: /v1/docsum PORT: "9009" TGI_LLM_ENDPOINT: tgi-gaudi-svc - name: TgiGaudi diff --git a/DocSum/kubernetes/gmc/docsum_xeon.yaml b/DocSum/kubernetes/gmc/docsum_xeon.yaml index 09a72e0f1f..26fe2980f2 100644 --- a/DocSum/kubernetes/gmc/docsum_xeon.yaml +++ b/DocSum/kubernetes/gmc/docsum_xeon.yaml @@ -23,7 +23,7 @@ spec: internalService: serviceName: docsum-llm-uservice config: - endpoint: /v1/chat/docsum + endpoint: /v1/docsum PORT: "9009" TGI_LLM_ENDPOINT: tgi-svc - name: Tgi diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh index ae6cdf0ecd..10e4d0c9fa 100644 --- a/DocSum/tests/test_compose_on_gaudi.sh +++ b/DocSum/tests/test_compose_on_gaudi.sh @@ -157,7 +157,7 @@ function validate_microservices() { # llm microservice validate_services_json \ - "${host_ip}:9000/v1/chat/docsum" \ + "${host_ip}:9000/v1/docsum" \ "data: " \ "llm-docsum-tgi" \ "llm-docsum-gaudi-server" \ diff --git a/DocSum/tests/test_compose_on_rocm.sh b/DocSum/tests/test_compose_on_rocm.sh index 13b20b6fc9..dc0baa26cb 100644 --- a/DocSum/tests/test_compose_on_rocm.sh +++ b/DocSum/tests/test_compose_on_rocm.sh @@ -137,7 +137,7 @@ function validate_microservices() { # llm microservice validate_services \ - "${host_ip}:9000/v1/chat/docsum" \ + "${host_ip}:9000/v1/docsum" \ "data: " \ "docsum-llm-server" \ "docsum-llm-server" \ diff --git a/DocSum/tests/test_compose_on_xeon.sh b/DocSum/tests/test_compose_on_xeon.sh index 2c58b0afe1..d353fcefdb 100644 --- a/DocSum/tests/test_compose_on_xeon.sh +++ b/DocSum/tests/test_compose_on_xeon.sh @@ -159,7 +159,7 @@ function validate_microservices() { # llm microservice validate_services_json \ - "${host_ip}:9000/v1/chat/docsum" \ + "${host_ip}:9000/v1/docsum" \ "data: " \ "llm-docsum-tgi" \ "llm-docsum-server" \ diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md index da1e79688a..8faa43e3c2 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md @@ -293,7 +293,7 @@ Please refer to **[keycloak_setup_guide](keycloak_setup_guide.md)** for more det 10. DocSum LLM Microservice ```bash - curl http://${host_ip}:9003/v1/chat/docsum\ + curl http://${host_ip}:9003/v1/docsum\ -X POST \ -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5"}' \ -H 'Content-Type: application/json'