Refine docker_compose for dataprep param settings (#486)

* add TEI_ENDPOINT for dataprep Signed-off-by: letonghan <letong.han@intel.com> * add TEI_ENDPOINT for dataprep Signed-off-by: letonghan <letong.han@intel.com> * update ui test file Signed-off-by: letonghan <letong.han@intel.com> * add dataprep test into script Signed-off-by: letonghan <letong.han@intel.com> * refine e2e test of chatqna Signed-off-by: letonghan <letong.han@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix missing dockerfile path Signed-off-by: letonghan <letong.han@intel.com> * check test issue Signed-off-by: letonghan <letong.han@intel.com> * check dataprep log Signed-off-by: letonghan <letong.han@intel.com> * reverse codetrans Signed-off-by: letonghan <letong.han@intel.com> * cd log path Signed-off-by: letonghan <letong.han@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add hf token in compose yaml Signed-off-by: letonghan <letong.han@intel.com> * add redis_host Signed-off-by: letonghan <letong.han@intel.com> * add upload link test Signed-off-by: letonghan <letong.han@intel.com> * re-format validate dataprep Signed-off-by: letonghan <letong.han@intel.com> * fix typo Signed-off-by: letonghan <letong.han@intel.com> * fix frontend env name Signed-off-by: letonghan <letong.han@intel.com> * fix ci issue Signed-off-by: letonghan <letong.han@intel.com> --------- Signed-off-by: letonghan <letong.han@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
opea-project · Aug 6, 2024 · 3913c7b · 3913c7b
1 parent abc02e1
commit 3913c7b
Show file tree

Hide file tree

Showing 10 changed files with 183 additions and 64 deletions.
diff --git a/ChatQnA/docker/gaudi/compose.yaml b/ChatQnA/docker/gaudi/compose.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -26,6 +27,8 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
   tei-embedding-service:
     image: opea/tei-gaudi:latest
     container_name: tei-embedding-gaudi-server

diff --git a/ChatQnA/docker/gaudi/compose_guardrails.yaml b/ChatQnA/docker/gaudi/compose_guardrails.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -26,6 +27,7 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tgi-guardrails-service:
     image: ghcr.io/huggingface/tgi-gaudi:2.0.1
     container_name: tgi-guardrails-server

diff --git a/ChatQnA/docker/gaudi/compose_vllm.yaml b/ChatQnA/docker/gaudi/compose_vllm.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -26,6 +27,7 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tei-embedding-service:
     image: opea/tei-gaudi:latest
     container_name: tei-embedding-gaudi-server

diff --git a/ChatQnA/docker/gaudi/compose_vllm_ray.yaml b/ChatQnA/docker/gaudi/compose_vllm_ray.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -26,6 +27,7 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tei-embedding-service:
     image: opea/tei-gaudi:latest
     container_name: tei-embedding-gaudi-server

diff --git a/ChatQnA/docker/gpu/compose.yaml b/ChatQnA/docker/gpu/compose.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -25,7 +26,10 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
+      REDIS_HOST: ${REDIS_HOST}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server

diff --git a/ChatQnA/docker/xeon/compose.yaml b/ChatQnA/docker/xeon/compose.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -25,7 +26,10 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
+      REDIS_HOST: ${REDIS_HOST}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
@@ -154,6 +158,7 @@ services:
       - redis-vector-db
       - tei-embedding-service
       - embedding
+      - dataprep-redis-service
       - retriever
       - tei-reranking-service
       - reranking

diff --git a/ChatQnA/docker/xeon/docker_compose_qdrant.yaml b/ChatQnA/docker/xeon/docker_compose_qdrant.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-qdrant-server
     depends_on:
       - qdrant-vector-db
+      - tei-embedding-service
     ports:
       - "6000:6000"
     environment:
@@ -25,6 +26,7 @@ services:
       QDRANT: ${host_ip}
       QDRANT_PORT: 6333
       COLLECTION_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
     container_name: tei-embedding-server

diff --git a/ChatQnA/docker/xeon/docker_compose_vllm.yaml b/ChatQnA/docker/xeon/docker_compose_vllm.yaml
@@ -16,6 +16,7 @@ services:
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
+      - tei-embedding-service
     ports:
       - "6007:6007"
       - "6008:6008"
@@ -26,6 +27,7 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
     container_name: tei-embedding-server

diff --git a/ChatQnA/tests/test_chatqna_on_gaudi.sh b/ChatQnA/tests/test_chatqna_on_gaudi.sh
@@ -52,6 +52,7 @@ function start_services() {
     export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
     export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
     export REDIS_URL="redis://${ip_address}:6379"
+    export REDIS_HOST=${ip_address}
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export MEGA_SERVICE_HOST_IP=${ip_address}
@@ -61,6 +62,8 @@ function start_services() {
     export LLM_SERVICE_HOST_IP=${ip_address}
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
     export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
+    export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get_file"
+    export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
 
@@ -93,104 +96,147 @@ function start_services() {
     done
 }
 
-function validate_services() {
+function validate_service() {
     local URL="$1"
     local EXPECTED_RESULT="$2"
     local SERVICE_NAME="$3"
     local DOCKER_NAME="$4"
     local INPUT_DATA="$5"
 
-    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
-    if [ "$HTTP_STATUS" -eq 200 ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+    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 [[ $SERVICE_NAME == *"dataprep_upload_link"* ]]; then
+        HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'link_list=["https://www.ces.tech/"]' "$URL")
+    elif [[ $SERVICE_NAME == *"dataprep_get"* ]]; then
+        HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' "$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')
 
-        local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+    docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
 
-        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
-            echo "[ $SERVICE_NAME ] Content is as expected."
-        else
-            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
-            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
-            exit 1
-        fi
-    else
+    # check response status
+    if [ "$HTTP_STATUS" -ne "200" ]; then
         echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
         exit 1
+    else
+        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+    fi
+    # check response body
+    if [[ "$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_services \
+    validate_service \
         "${ip_address}:8090/embed" \
-        "\[\[" \
+        "[[" \
         "tei-embedding" \
         "tei-embedding-gaudi-server" \
         '{"inputs":"What is Deep Learning?"}'
 
     # embedding microservice
-    validate_services \
+    validate_service \
         "${ip_address}:6000/v1/embeddings" \
-        '"text":"What is Deep Learning?","embedding":\[' \
-        "embedding" \
+        '"text":"What is Deep Learning?","embedding":[' \
+        "embedding-microservice" \
         "embedding-tei-server" \
         '{"text":"What is Deep Learning?"}'
 
     sleep 1m # retrieval can't curl as expected, try to wait for more time
 
+    # 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-redis-server"
+
+    # test /v1/dataprep upload link
+    validate_service \
+        "http://${ip_address}:6007/v1/dataprep" \
+        "Data preparation succeeded" \
+        "dataprep_upload_link" \
+        "dataprep-redis-server"
+
+    # test /v1/dataprep/get_file
+    validate_service \
+        "http://${ip_address}:6008/v1/dataprep/get_file" \
+        '{"name":' \
+        "dataprep_get" \
+        "dataprep-redis-server"
+
+    # test /v1/dataprep/delete_file
+    validate_service \
+        "http://${ip_address}:6009/v1/dataprep/delete_file" \
+        '{"status":true}' \
+        "dataprep_del" \
+        "dataprep-redis-server"
+
     # retrieval microservice
     test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
-    validate_services \
+    validate_service \
         "${ip_address}:7000/v1/retrieval" \
-        " " \
-        "retrieval" \
+        "retrieved_docs" \
+        "retrieval-microservice" \
         "retriever-redis-server" \
         "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
 
     # tei for rerank microservice
-    validate_services \
+    validate_service \
         "${ip_address}:8808/rerank" \
         '{"index":1,"score":' \
         "tei-rerank" \
         "tei-reranking-gaudi-server" \
         '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}'
 
     # rerank microservice
-    validate_services \
+    validate_service \
         "${ip_address}:8000/v1/reranking" \
         "Deep learning is..." \
-        "rerank" \
+        "rerank-microservice" \
         "reranking-tei-gaudi-server" \
         '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}'
 
     # tgi for llm service
-    validate_services \
+    validate_service \
         "${ip_address}:8008/generate" \
         "generated_text" \
         "tgi-llm" \
         "tgi-gaudi-server" \
         '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
 
     # llm microservice
-    validate_services \
+    validate_service \
         "${ip_address}:9000/v1/chat/completions" \
         "data: " \
-        "llm" \
+        "llm-microservice" \
         "llm-tgi-gaudi-server" \
         '{"query":"What is Deep Learning?"}'
 
 }
 
 function validate_megaservice() {
     # Curl the Mega Service
-    validate_services \
+    validate_service \
         "${ip_address}:8888/v1/chatqna" \
-        "billion" \
-        "mega-chatqna" \
+        "data: " \
+        "chatqna-megaservice" \
         "chatqna-gaudi-backend-server" \
         '{"messages": "What is the revenue of Nike in 2023?"}'
 
@@ -241,7 +287,7 @@ function main() {
     elif [ "${mode}" == "" ]; then
         validate_microservices
         validate_megaservice
-        # validate_frontend
+        validate_frontend
     fi
 
     stop_docker