diff --git a/yudao-module-llm/yudao-module-llm-biz/src/main/java/cn/iocoder/yudao/module/llm/service/basemodel/BaseModelTaskService.java b/yudao-module-llm/yudao-module-llm-biz/src/main/java/cn/iocoder/yudao/module/llm/service/basemodel/BaseModelTaskService.java index eca11d2d2..dbeafe0dc 100644 --- a/yudao-module-llm/yudao-module-llm-biz/src/main/java/cn/iocoder/yudao/module/llm/service/basemodel/BaseModelTaskService.java +++ b/yudao-module-llm/yudao-module-llm-biz/src/main/java/cn/iocoder/yudao/module/llm/service/basemodel/BaseModelTaskService.java @@ -4,9 +4,9 @@ import cn.iocoder.yudao.module.llm.controller.admin.basemodel.vo.BaseModelSaveRe import cn.iocoder.yudao.module.llm.dal.dataobject.basemodel.BaseModelDO; import cn.iocoder.yudao.module.llm.dal.dataobject.servername.ServerNameDO; import cn.iocoder.yudao.module.llm.dal.mysql.servername.ServerNameMapper; -import cn.iocoder.yudao.module.llm.enums.ModelDeployConstantEnum; import cn.iocoder.yudao.module.llm.handler.AigcCustomDateTimeDeserializer; import cn.iocoder.yudao.module.llm.service.basemodel.vo.ModelListRes; +import cn.iocoder.yudao.module.llm.service.http.FineTuningTaskHttpService; import cn.iocoder.yudao.module.llm.service.http.TrainHttpService; import cn.iocoder.yudao.module.llm.service.http.vo.AigcModelDeploySaveReq; import cn.iocoder.yudao.module.llm.service.http.vo.AigcModelDeployVO; @@ -43,7 +43,11 @@ public class BaseModelTaskService { @Resource ServerNameMapper serverNameMapper; + @Resource + private FineTuningTaskHttpService fineTuningTaskHttpService; + private static final String DEFAULT_MODEL_URL_SUFFIX = "/v1/chat/completions"; + // 减少维护 先注释掉 @Scheduled(cron ="0 0/1 * * * ?") public void synchronous() throws JsonProcessingException { @@ -73,7 +77,7 @@ public class BaseModelTaskService { // 构建查询参数并查询模型部署信息 String query = "?filter={\"id\":" + modelId + "}"; log.debug("正在查询模型部署信息，查询参数: {}", query); - String res = trainHttpService.modelTableQuery(new HashMap<>(), serverName.getHost(), "model_deploy", query); + String res = fineTuningTaskHttpService.modelTableQuery(new HashMap<>(), serverName.getHost(), "model_deploy", query); log.debug("模型部署信息查询成功。响应内容: {}", res); // 解析响应内容 diff --git a/yudao-server/src/main/resources/application-prod.yaml b/yudao-server/src/main/resources/application-prod.yaml index ed83d6f95..dd791ff57 100644 --- a/yudao-server/src/main/resources/application-prod.yaml +++ b/yudao-server/src/main/resources/application-prod.yaml @@ -249,23 +249,23 @@ llm: #################### 8123: RAG服务、训练集和标注相关API。 ################### ### RAG服务 #RAG健康检查 GET - rag_health: http://36.103.199.248:8123/health + rag_health: http://127.0.0.1:8123/health #上传并向量化 POST - rag_embed: http://36.103.199.248:8123/embed + rag_embed: http://127.0.0.1:8123/embed #获取所有向量id GET - rag_ids: http://36.103.199.248:8123/ids + rag_ids: http://127.0.0.1:8123/ids #根据id获取文档 GET - rag_documents: http://36.103.199.248:8123/documents + rag_documents: http://127.0.0.1:8123/documents #根据id删除文档 DEL - rag_documents_del: http://36.103.199.248:8123/documents + rag_documents_del: http://127.0.0.1:8123/documents #根据file_id检索向量 POST - rag_query: http://36.103.199.248:8123/query + rag_query: http://127.0.0.1:8123/query #支持多个文件id查询向量 GET - rag_query_multiple: http://36.103.199.248:8123/query_multiple + rag_query_multiple: http://127.0.0.1:8123/query_multiple # 知识库向量嵌入 - embed: http://36.103.199.248:8123/embed + embed: http://127.0.0.1:8123/embed # 知识库查询 - embed_query: http://36.103.199.248:8123/query + embed_query: http://127.0.0.1:8123/query #### LLM train and service api 训练集、标注相关API # 训练集列表 GET @@ -283,26 +283,28 @@ llm: #################### 9000: 大模型管理、微调任务、文件上传和模型部署相关API。 ################### # 大模型列表 GET - models_list: http://36.103.199.248:9000/api/models + models_list: http://127.0.0.1:9000/api/models # 登录 POST - login: http://36.103.199.248:9000/api/auth/login - account: http://36.103.199.248:9000/api/auth/account + login: http://127.0.0.1:9000/api/auth/login + account: http://127.0.0.1:9000/api/auth/account login_username: admin login_password: admin # 微调任务详情 GET - finetuning_detail: http://36.103.199.248:9000/api/finetuning + finetuning_detail: http://127.0.0.1:9000/api/finetuning # 微调任务取消 - finetuning_cancel: http://36.103.199.248:9000/api/finetuning/%s/cancel + finetuning_cancel: http://127.0.0.1:9000/api/finetuning/%s/cancel # 微调文件列表 GET - finetuning_file_list: http://36.103.199.248:9000/api/files?purpose=fine-tune + finetuning_file_list: http://127.0.0.1:9000/api/files?purpose=fine-tune # 模型部署 - model_create: http://36.103.199.248:9000/api/models + model_create: http://127.0.0.1:9000/api/models # aigc模型推理 - aigc_model_completions: http://36.103.199.248:9000/api/channels/chat/completions - # 微调文件上传 + aigc_model_completions: http://127.0.0.1:9000/api/channels/chat/completions + + #################### 5123: 微调任务、模型部署、文件管理、提示词优化、自动评估、文生图等API。 ################### - aigc_file_upload: /api/files # 创建微调任务 POST + # 微调文件上传 + aigc_file_upload: /api/files finetuning_create: /llm/finetuning # 日志获取 finetuning_log: /llm/get_log @@ -330,9 +332,9 @@ llm: #################### 30000: 大模型对话相关API。 ################### #### 大模型对话 # 模型列表 GET - base_model_list: http://36.103.199.248:30000/model/v1/models + base_model_list: http://127.0.0.1:30000/model/v1/models # 模型对话 POST - model_completions: http://36.103.199.248:30000/v1/chat/completions + model_completions: http://127.0.0.1:30000/v1/chat/completions #################### 48080: 应用和管理服务相关API。 ################### application_api: http://localhost:48080/admin-api/llm/application/api/apiKey/chat