新增工程数据

backend/app/settings.py

@@ -7,6 +7,8 @@ from llama_index.llms.xinference import Xinference
 from llama_index.llms.xinference.base import DEFAULT_XINFERENCE_TEMP
 
 from app.xinference.base import XinferenceEmbedding, XinferenceRerank
+from app.engine.loaders import getProjectInfos
+from app.api.routers.request.base import ProjectInfo
 
 
 def get_node_postprocessors():
@@ -53,7 +55,6 @@ def init_settings():
     Settings.chunk_size = int(os.getenv("CHUNK_SIZE", "1024"))
     Settings.chunk_overlap = int(os.getenv("CHUNK_OVERLAP", "20"))
 
-
 def init_ollama():
     # from llama_index.embeddings.ollama import OllamaEmbedding
     # from llama_index.llms.ollama.base import DEFAULT_REQUEST_TIMEOUT, Ollama
@@ -127,7 +128,6 @@ def init_dashscope():
     Settings.embed_model = DashScopeEmbedding(model_name=DashScopeTextEmbeddingModels.TEXT_EMBEDDING_V2,
                                               text_type=DashScopeTextEmbeddingType.TEXT_TYPE_QUERY)
 
-
 def init_azure_openai():
     # from llama_index.core.constants import DEFAULT_TEMPERATURE
     # from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
@@ -162,7 +162,6 @@ def init_azure_openai():
     # )
     pass
 
-
 def init_fastembed():
     """
     Use Qdrant Fastembed as the local embedding provider.
@@ -232,4 +231,11 @@ def init_mistral():
     #
     # Settings.llm = MistralAI(model=os.getenv("MODEL"))
     # Settings.embed_model = MistralAIEmbedding(model_name=os.getenv("EMBEDDING_MODEL"))
-    pass
+    pass
+
+def init_ProjectInfo():
+    prjObj = ProjectInfo()
+    prjInfos:list[tuple] = getProjectInfos()
+    for prjInfo in prjInfos:
+        prjObj.add(prjInfo['name'],prjInfo['flag'])
+