diff --git a/assembly/bin/supersonic-build.sh b/assembly/bin/supersonic-build.sh index 39fd75a7e..05d7df6b8 100755 --- a/assembly/bin/supersonic-build.sh +++ b/assembly/bin/supersonic-build.sh @@ -15,7 +15,7 @@ fi function buildJavaService { model_name=$1 echo "starting building supersonic-${model_name} service" - mvn -f $projectDir/launchers/${model_name} clean package -DskipTests + mvn -f $projectDir clean package -DskipTests if [ $? -ne 0 ]; then echo "Failed to build backend Java modules." exit 1 @@ -72,7 +72,7 @@ elif [ "$service" == "webapp" ]; then buildWebapp target_path=$projectDir/launchers/$STANDALONE_SERVICE/target/classes tar xvf $projectDir/webapp/supersonic-webapp.tar.gz -C $target_path - mv $target_path/supersonic_webapp $target_path/webapp + mv $target_path/supersonic-webapp $target_path/webapp else buildJavaService $service buildWebapp diff --git a/assembly/bin/supersonic-daemon.sh b/assembly/bin/supersonic-daemon.sh index 7e7dbbdac..618fe5229 100755 --- a/assembly/bin/supersonic-daemon.sh +++ b/assembly/bin/supersonic-daemon.sh @@ -1,9 +1,12 @@ #!/usr/bin/env bash sbinDir=$(cd "$(dirname "$0")"; pwd) -chmod +x $sbinDir/supersonic-common.sh source $sbinDir/supersonic-common.sh +set -a +source $sbinDir/../conf/supersonic-env.sh +set +a + command=$1 service=$2 if [ -z "$service" ]; then diff --git a/headless/python/config/config_parse.py b/headless/python/config/config_parse.py index 7ce6ec4f3..521d8faeb 100644 --- a/headless/python/config/config_parse.py +++ b/headless/python/config/config_parse.py @@ -1,5 +1,4 @@ # -*- coding:utf-8 -*- -import os import configparser import os @@ -8,6 +7,12 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.append(os.path.dirname(os.path.abspath(__file__))) +class EnvInterpolation(configparser.BasicInterpolation): + """Interpolation which expands environment variables in values.""" + + def before_get(self, parser, section, option, value, defaults): + value = super().before_get(parser, section, option, value, defaults) + return os.path.expandvars(value) def type_convert(input_str: str): try: @@ -16,13 +21,13 @@ def type_convert(input_str: str): return input_str -PROJECT_DIR_PATH = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) +PROJECT_DIR_PATH = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) config_dir = "config" -CONFIG_DIR_PATH = os.path.join(PROJECT_DIR_PATH, config_dir) +CONFIG_DIR_PATH = os.path.join(PROJECT_DIR_PATH, config_dir) config_file = "run_config.ini" config_path = os.path.join(CONFIG_DIR_PATH, config_file) -config = configparser.ConfigParser() +config = configparser.ConfigParser(interpolation=EnvInterpolation()) config.read(config_path) log_dir = "log" @@ -77,5 +82,3 @@ def type_convert(input_str: str): print(f"ACT_MIN_WINDOWN_SIZE: {ACT_MIN_WINDOWN_SIZE}") print(f"ACT_MAX_WINDOWN_SIZE: {ACT_MAX_WINDOWN_SIZE}") print(f"LOG_FILE_PATH: {LOG_FILE_PATH}") - - \ No newline at end of file diff --git a/headless/python/config/run_config.ini b/headless/python/config/run_config.ini index 126697ed2..269292290 100644 --- a/headless/python/config/run_config.ini +++ b/headless/python/config/run_config.ini @@ -17,13 +17,11 @@ ACT_MAX_WINDOWN_SIZE = 10 [Text2Vec] HF_TEXT2VEC_MODEL_NAME = GanymedeNil/text2vec-large-chinese - [LLMProvider] LLM_PROVIDER_NAME = openai - [LLMModel] -MODEL_NAME = gpt-3.5-turbo -OPENAI_API_KEY = YOUR_API_KEY -OPENAI_API_BASE = http://YOUR_API_BASE -TEMPERATURE = 0.0 +OPENAI_API_KEY = ${OPENAI_API_KEY} +OPENAI_API_BASE = ${OPENAI_API_BASE} +MODEL_NAME = ${OPENAI_MODEL_NAME} +TEMPERATURE = ${OPENAI_TEMPERATURE} \ No newline at end of file diff --git a/launchers/standalone/src/main/resources/application-local.yaml b/launchers/standalone/src/main/resources/application-local.yaml index 3125fbae9..d755912b1 100644 --- a/launchers/standalone/src/main/resources/application-local.yaml +++ b/launchers/standalone/src/main/resources/application-local.yaml @@ -1,3 +1,10 @@ +server: + port: 9080 + compression: + enabled: true + min-response-size: 1024 + mime-types: application/javascript,application/json,application/xml,text/html,text/xml,text/plain,text/css,image/* + spring: h2: console: @@ -12,15 +19,8 @@ spring: username: root password: semantic -demo: - enabled: true - -server: - port: 9080 - compression: - enabled: true - min-response-size: 1024 - mime-types: application/javascript,application/json,application/xml,text/html,text/xml,text/plain,text/css,image/* +mybatis: + mapper-locations=classpath:mappers/custom/*.xml,classpath*:/mappers/*.xml authentication: enable: true @@ -31,6 +31,16 @@ authentication: header: key: Authorization +demo: + enabled: true + +query: + optimizer: + enable: true + +multi: + turn: false + time: threshold: 100 @@ -39,20 +49,19 @@ dimension: metric: topn: 20 -mybatis: - mapper-locations=classpath:mappers/custom/*.xml,classpath*:/mappers/*.xml - corrector: additional: information: true + pyllm: url: http://127.0.0.1:9092 - llm: parser: url: ${pyllm.url} + embedding: url: ${pyllm.url} + functionCall: url: ${pyllm.url} @@ -60,7 +69,6 @@ text2sql: example: num: 1 -#langchain4j config s2: langchain4j: #1.chat-model @@ -68,20 +76,21 @@ s2: provider: open_ai openai: # Replace with your LLM configs - # Note: Below API key `demo` is provided by langchain4j community which limits 1000 tokens per request. - base-url: https://api.openai.com/v1 - api-key: demo - model-name: gpt-3.5-turbo - temperature: 0.0 - timeout: PT60S + # Note: The default API key `demo` is provided by langchain4j community + # which limits 1000 tokens per request. + base-url: ${OPENAI_API_BASE:https://api.openai.com/v1} + api-key: ${OPENAI_API_KEY:demo} + model-name: ${OPENAI_MODEL_NAME:gpt-3.5-turbo} + temperature: ${OPENAI_TEMPERATURE:0.0} + timeout: ${OPENAI_TIMEOUT:PT60S} #2.embedding-model #2.1 in_memory(default) embedding-model: provider: in_process -# inProcess: -# modelPath: /data/model.onnx -# vocabularyPath: /data/onnx_vocab.txt -# shibing624/text2vec-base-chinese + # inProcess: + # modelPath: /data/model.onnx + # vocabularyPath: /data/onnx_vocab.txt + # shibing624/text2vec-base-chinese #2.2 open_ai # embedding-model: # provider: open_ai @@ -105,11 +114,4 @@ logging: inMemoryEmbeddingStore: persistent: - path: /tmp - -query: - optimizer: - enable: true -multi: - turn: false - num: 5 + path: /tmp \ No newline at end of file diff --git a/launchers/standalone/src/main/resources/rewrite_examplar.json b/launchers/standalone/src/main/resources/rewrite_examplar.json deleted file mode 100644 index 03166fb35..000000000 --- a/launchers/standalone/src/main/resources/rewrite_examplar.json +++ /dev/null @@ -1,122 +0,0 @@ -[ - { - "contextualQuestions": "[“近7天纯音乐的歌曲播放量 (补充信息:’ '纯音乐'‘是一个’语种‘。)”]", - "currentQuestion": "对比翻唱版呢 (补充信息:’ '翻唱版'‘是一个’歌曲版本‘。)", - "rewritingCurrentQuestion": "对比近7天翻唱版和纯音乐的歌曲播放量" - }, - { - "contextualQuestions": "[]", - "currentQuestion": "robinlee在内容库的访问次数 (补充信息:’ 'robinlee'‘是一个’用户名‘。)", - "rewritingCurrentQuestion": "robinlee在内容库的访问次数" - }, - { - "contextualQuestions": "[\"robinlee在内容库的访问次数 (补充信息:’ 'robinlee'‘是一个’用户名‘。)\"]", - "currentQuestion": "对比jackjchen呢？ (补充信息:’ 'jackjchen'‘是一个’用户名‘。)", - "rewritingCurrentQuestion": "robinlee对比jackjchen在内容库的访问次数" - }, - { - "contextualQuestions": "[\"robinlee在内容库的访问次数 (补充信息:’ 'robinlee'‘是一个’用户名‘。)\",\"对比jackjchen呢？ (补充信息:’ 'jackjchen'‘是一个’用户名‘。)\"]。", - "currentQuestion": "内容库近12个月访问人数按部门", - "rewritingCurrentQuestion": "内容库近12个月访问人数按部门" - }, - { - "contextualQuestions": "[\"robinlee在内容库的访问次数 (补充信息:’ 'robinlee'‘是一个’用户名‘。)\",\"对比jackjchen呢？ (补充信息:’ 'jackjchen'‘是一个’用户名‘。)\",\"内容库近12个月访问人数按部门\"]", - "currentQuestion": "访问次数呢？", - "rewritingCurrentQuestion": "内容库近12个月访问次数按部门" - }, - { - "contextualQuestions": "[]", - "currentQuestion": "近3天海田飞系MPPM结算播放份额 (补充信息:’'海田飞系'‘是一个’严选版权归属系‘)", - "rewritingCurrentQuestion": "近3天海田飞系MPPM结算播放份额" - }, - { - "contextualQuestions": "[\"近3天海田飞系MPPM结算播放份额(补充信息:’'海田飞系'‘是一个’严选版权归属系‘) \"]", - "currentQuestion": "近60天呢", - "rewritingCurrentQuestion": "近60天海田飞系MPPM结算播放份额" - }, - { - "contextualQuestions": "[\"近3天海田飞系MPPM结算播放份额(补充信息:’'海田飞系'‘是一个’严选版权归属系‘) \",\"近60天呢\"]", - "currentQuestion": "飞天系呢(补充信息:’'飞天系'‘是一个’严选版权归属系‘)", - "rewritingCurrentQuestion": "近60天飞天系MPPM结算播放份额" - }, - { - "contextualQuestions": "[“近90天袁亚伟播放量是多少 (补充信息:'袁亚伟'是一个歌手名)”]", - "currentQuestion": "平均值是多少", - "rewritingCurrentQuestion": "近90天袁亚伟播放量的平均值是多少" - }, - { - "contextualQuestions": "[“近90天袁亚伟播放量是多少 (补充信息:'袁亚伟'是一个歌手名)”,\"平均值是多少\",\"总和是多少\"]", - "currentQuestion": "总和是多少", - "rewritingCurrentQuestion": "近90天袁亚伟播放量的总和是多少" - }, - { - "contextualQuestions": "[\"播放量大于1万的歌曲有多少\"]", - "currentQuestion": "下载量大于10万的呢", - "rewritingCurrentQuestion": "下载量大于10万的歌曲有多少" - }, - { - "contextualQuestions": "[\"周杰伦2023年6月之后发布的歌曲有哪些(补充信息:'周杰伦'是一个歌手名)\"]", - "currentQuestion": "这些歌曲有哪些播放量大于500W的？", - "rewritingCurrentQuestion": "周杰伦2023年6月之后发布的歌曲，有哪些播放量大于500W的？" - }, - { - "contextualQuestions": "[“陈奕迅唱的所有的播放量大于20万的歌曲有哪些(补充信息:'陈奕迅'是一个歌手名)”]", - "currentQuestion": "大于100万的呢", - "rewritingCurrentQuestion": "陈奕迅唱的所有的播放量大于100万的歌曲有哪些" - }, - { - "contextualQuestions": "[“陈奕迅唱的所有的播放量大于20万的歌曲有哪些(补充信息:'陈奕迅'是一个歌手名)”,\"大于100万的呢\"]", - "currentQuestion": "周杰伦去年发布的歌曲有哪些(补充信息:'周杰伦'是一个歌手名)", - "rewritingCurrentQuestion": "周杰伦去年发布的歌曲有哪些" - }, - { - "contextualQuestions": "[“陈奕迅唱的所有的播放量大于20万的歌曲有哪些(补充信息:'陈奕迅'是一个歌手名)”,\"大于100万的呢\",\"周杰伦去年发布的歌曲有哪些(补充信息:'周杰伦'是一个歌手名)\"]", - "currentQuestion": "他今年发布的呢", - "rewritingCurrentQuestion": "周杰伦今年发布的歌曲有哪些" - }, - { - "contextualQuestions": "[“陈奕迅唱的所有的播放量大于20万的歌曲有哪些(补充信息:'陈奕迅'是一个歌手名)”,\"大于100万的呢\",\"周杰伦去年发布的歌曲有哪些(补充信息:'周杰伦'是一个歌手名)\",\"他今年发布的呢\"]", - "currentQuestion": "我想要近半年签约的播放量前十的歌手有哪些", - "rewritingCurrentQuestion": "我想要近半年签约的播放量前十的歌手有哪些" - }, - { - "contextualQuestions": "[]", - "currentQuestion": "最近一年发行的歌曲中，有哪些在近7天播放超过一千万的", - "rewritingCurrentQuestion": "最近一年发行的歌曲中，有哪些在近7天播放超过一千万的" - }, - { - "contextualQuestions": "[“最近一年发行的歌曲中，有哪些在近7天播放超过一千万的”]", - "currentQuestion": "今年以来呢？", - "rewritingCurrentQuestion": "今年以来发行的歌曲中，有哪些在近7天播放超过一千万的" - }, - { - "contextualQuestions": "[“最近一年发行的歌曲中，有哪些在近7天播放超过一千万的”,\"今年以来呢？\"]", - "currentQuestion": "2023年以来呢？", - "rewritingCurrentQuestion": "2023年以来发行的歌曲中，有哪些在近7天播放超过一千万的" - }, - { - "contextualQuestions": "[\"内容库近20天访问次数\"]", - "currentQuestion": "按部门看一下", - "rewritingCurrentQuestion": "内容库近20天按部门的访问次数" - }, - { - "contextualQuestions": "[\"内容库近20天访问次数\",\"按部门看一下\"]", - "currentQuestion": "按模块看一下", - "rewritingCurrentQuestion": "内容库近20天按模块的访问次数" - }, - { - "contextualQuestions": "[\"内容库近20天访问次数\",\"按部门看一下\",\"按模块看一下\"]", - "currentQuestion": "看一下技术部的 (补充信息:’'技术部'‘是一个’部门‘)", - "rewritingCurrentQuestion": "技术部在内容库近20天的访问次数" - }, - { - "contextualQuestions": "[\"内容库近20天访问次数\",\"按部门看一下\",\"按模块看一下\",\"看一下技术部的 (补充信息:’'技术部'‘是一个’部门‘)\"]", - "currentQuestion": "看一下产品部的 (补充信息:’'产品部'‘是一个’部门‘)", - "rewritingCurrentQuestion": "产品部在内容库近20天的访问次数" - }, - { - "contextualQuestions": "[\"内容库近20天访问次数\",\"按部门看一下\",\"按模块看一下\",\"看一下技术部的 (补充信息:’'技术部'‘是一个’部门‘)\",\"看一下产品部的 (补充信息:’'产品部'‘是一个’部门‘)\"]", - "currentQuestion": "对比一下技术部、产品部(补充信息:'技术部'、‘产品部’分别是一个’部门‘)", - "rewritingCurrentQuestion": "对比一下技术部、产品部在内容库近20天的访问次数" - } -] diff --git a/launchers/standalone/src/main/resources/supersonic-env.sh b/launchers/standalone/src/main/resources/supersonic-env.sh new file mode 100644 index 000000000..098ec75ab --- /dev/null +++ b/launchers/standalone/src/main/resources/supersonic-env.sh @@ -0,0 +1,10 @@ +#!/usr/bin/env bash + +# Replace with your LLM configs +# Note: The default API key `demo` is provided by langchain4j community +# which limits 1000 tokens per request. +OPENAI_API_BASE=https://api.openai.com/v1 +OPENAI_API_KEY=demo +OPENAI_MODEL_NAME=gpt-3.5-turbo +OPENAI_TEMPERATURE=0.0 +OPENAI_TIMEOUT=PT60S \ No newline at end of file