大改，未验证

.env

@@ -48,7 +48,7 @@ LLM_API_KEY=sk-Gce85QLROESeOWf3icd2mQnYHOrmMYojwVPQ0AubMjGQ5ZE2
 LLM_BASE_URL=https://gemini.jeason.online/v1
 
 # The specific model to use, e.g., "qwen-plus-latest", "gpt-3.5-turbo", "claude-3-sonnet-20240229"
-LLM_MODEL=gemini-2.5-flash
+LLM_MODEL=mimo-v2-flash
 
 # The temperature for the model's responses (0.0 to 2.0).
 LLM_TEMPERATURE=0.7
@@ -123,3 +123,13 @@ REDIS_DEFAULT_TTL=3600
 
 # Enable Redis cache (set to False to disable caching)
 REDIS_ENABLED=True
+
+
+# ============================================================================
+# EMBEDDING CONFIGURATION (知识库向量检索 - 本地模型)
+# ============================================================================
+# 暂时禁用，等有合适的 embedding API 或服务器资源时再启用
+EMBEDDING_ENABLED=False
+EMBEDDING_MODEL=BAAI/bge-small-zh-v1.5
+EMBEDDING_DIMENSION=512
+EMBEDDING_SIMILARITY_THRESHOLD=0.5