feat:update spark connection

docs/getting_started/application/chatdb/chatdb.md

@@ -35,6 +35,7 @@ now DB-GPT support Datasource Type
 * DuckDB
 * Clickhouse
 * Mssql
+* Spark
 ```
 
 ### 2.ChatData

docs/getting_started/faq/deploy/deploy_faq.md

@@ -80,4 +80,16 @@ Download and install `Microsoft C++ Build Tools` from [visual-cpp-build-tools](h
 ```
 
 1. Install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive)
-2. Reinstall PyTorch [start-locally](https://pytorch.org/get-started/locally/#start-locally) with CUDA support.
+2. Reinstall PyTorch [start-locally](https://pytorch.org/get-started/locally/#start-locally) with CUDA support.
+
+##### Q7: ImportError: cannot import name 'PersistentClient' from 'chromadb'.
+
+```commandline
+pip install chromadb==0.4.10
+```
+
+##### Q8: pydantic.error_wrappers.ValidationError:1 validation error for HuggingFaceEmbeddings.model_kwargs extra not permitted
+
+```commandline
+pip install langchain>=0.0.286
+```

docs/getting_started/faq/llm/llm_faq.md

@@ -86,8 +86,9 @@ pip install -e "pip install -e ".[default]"
 ##### Q8 When starting the worker_manager on a cloud server and registering it with the controller, it is noticed that the worker's exposed IP is a private IP instead of a public IP, which leads to the inability to access the service.
 
 ```commandline
+
 --worker_register_host  public_ip     The ip address of current worker to register
-                                  to ModelController. If None, the address is
+                                to ModelController. If None, the address is
                                   automatically determined
 ```