Merge remote-tracking branch 'origin/main' into dbgpt_api

docs/getting_started/faq/deploy/deploy_faq.md

@@ -2,26 +2,26 @@ Installation FAQ
 ==================================
 
 
-##### Q1: execute `pip install -r requirements.txt` error, found some package cannot find correct version.
+##### Q1: execute `pip install -e .` error, found some package cannot find correct version.
 change the pip source.
 
 ```bash
 # pypi
-$ pip install -r requirements.txt -i https://pypi.python.org/simple
+$ pip install -e . -i https://pypi.python.org/simple
 ```
 
 or
 
 ```bash
 # tsinghua
-$ pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
+$ pip install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple/
 ```
 
 or
 
 ```bash
 # aliyun
-$ pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/
+$ pip install -e . -i http://mirrors.aliyun.com/pypi/simple/
 ```
 
 ##### Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to open database file 
@@ -29,5 +29,20 @@ $ pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/
 make sure you pull latest code or create directory with mkdir pilot/data
 
 ##### Q3: The model keeps getting killed.
+
 your GPU VRAM size is not enough, try replace your hardware or replace other llms.
 
+##### Q4: How to access website on the public network
+
+You can try to use gradio's [network](https://github.com/gradio-app/gradio/blob/main/gradio/networking.py) to achieve.
+```python
+import secrets
+from gradio import networking
+token=secrets.token_urlsafe(32)
+local_port=5000
+url = networking.setup_tunnel('0.0.0.0', local_port, token)
+print(f'Public url: {url}')
+time.sleep(60 * 60 * 24)
+```
+
+Open `url` with your browser to see the website.

docs/getting_started/install/deploy/deploy.md

@@ -49,7 +49,7 @@ For the entire installation process of DB-GPT, we use the miniconda3 virtual env
 python>=3.10
 conda create -n dbgpt_env python=3.10
 conda activate dbgpt_env
-pip install -r requirements.txt
+pip install -e .
 ```
 Before use DB-GPT Knowledge
 ```bash
@@ -97,15 +97,20 @@ You can configure basic parameters in the .env file, for example setting LLM_MOD
 
 ### 3. Run
 
+**(Optional) load examples into SQLlite**
+```bash
+bash ./scripts/examples/load_examples.sh
+```
+
 1.Run db-gpt server 
 
 ```bash
-$ python pilot/server/dbgpt_server.py
+python pilot/server/dbgpt_server.py
 ```
 
 Open http://localhost:5000 with your browser to see the product.
 
-```tip
+```{tip}
 If you want to access an external LLM service, you need to
 
 1.set the variables LLM_MODEL=YOUR_MODEL_NAME, MODEL_SERVER=YOUR_MODEL_SERVER（eg:http://localhost:5000） in the .env file.
@@ -116,7 +121,7 @@ If you want to access an external LLM service, you need to
 If you want to learn about dbgpt-webui, read https://github./csunny/DB-GPT/tree/new-page-framework/datacenter
 
 ```bash
-$ python pilot/server/dbgpt_server.py --light
+python pilot/server/dbgpt_server.py --light
 ```
 
 ### Multiple GPUs
@@ -141,6 +146,4 @@ DB-GPT supported 8-bit quantization and 4-bit quantization.
 
 You can modify the setting `QUANTIZE_8bit=True` or `QUANTIZE_4bit=True` in `.env` file to use quantization(8-bit quantization is enabled by default).
 
-Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit quantization can run with 48 GB of VRAM.
-
-Note: you need to install the latest dependencies according to [requirements.txt](https://github.com/eosphoros-ai/DB-GPT/blob/main/requirements.txt).
+Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit quantization can run with 48 GB of VRAM.

docs/getting_started/install/llm/llama/llama_cpp.md

@@ -1,6 +1,8 @@
-### llama.cpp
+llama.cpp
+==================================
 
-DB-GPT is now supported by [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) through [llama.cpp](https://github.com/ggerganov/llama.cpp).
+
+DB-GPT already supports [llama.cpp](https://github.com/ggerganov/llama.cpp) via [llama-cpp-python](https://github.com/abetlen/llama-cpp-python).
 
 ## Running llama.cpp