(improvement)(chat) Remove langchain4j configuration file and perform all configuration for the large model through the UI interface. (#1442)

launchers/standalone/src/test/resources/application-local.yaml

@@ -11,7 +11,4 @@ spring:
   h2:
     console:
       path: /h2-console/semantic
-      enabled: true
-  config:
-    import:
-      - classpath:langchain4j-local.yaml
+      enabled: true

launchers/standalone/src/test/resources/langchain4j-local.yaml

@@ -1,42 +0,0 @@
-langchain4j:
-  # Replace `open_ai` with ollama/zhipu/azure/dashscope as needed.
-  # Note:
-  # 1. `open_ai` is commonly used to connect to cloud-based models;
-  # 2. `ollama` is commonly used to connect to local models.
-  open-ai:
-    chat-model:
-      # It is recommended to replace with your API key in production.
-      # 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}
-
-  #    embedding-model:
-  #      base-url: https://api.openai.com/v1
-  #      api-key: demo
-  #      model-name: text-embedding-3-small
-  #      timeout: PT60S
-
-  in-memory:
-    embedding-model:
-      model-name: bge-small-zh
-
-    embedding-store:
-      persist-path: /tmp
-
-#  chroma:
-#    embedding-store:
-#      baseUrl: http://0.0.0.0:8000
-#      timeout: 120s
-
-#  milvus:
-#    embedding-store:
-#      host: localhost
-#      port: 2379
-#      uri: http://0.0.0.0:19530
-#      token: demo
-#      dimension: 512
-#      timeout: 120s