github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-09-11 13:58:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc:readme and tutorial for DB-GPT

Browse Source
This commit is contained in:
aries_ckt
2023-06-30 18:10:31 +08:00
parent 6becd9746e
commit 185d8f2976
6 changed files with 161 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
docs/getting_started/getting_started.md
View File

@@ -30,10 +30,16 @@ python>=3.10
conda create -n dbgpt_env python=3.10
conda activate dbgpt_env
pip install -r requirements.txt
```
Before use DB-GPT Knowledge Management
```
python -m spacy download zh_core_web_sm
```
Once the environment is installed, we have to create a new folder "models" in the DB-GPT project, and then we can put all the models downloaded from huggingface in this directory
make sure you have install git-lfs
```
git clone https://huggingface.co/Tribbiani/vicuna-13b
git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
@@ -54,20 +60,30 @@ You can refer to this document to obtain the Vicuna weights: [Vicuna](https://gi
If you have difficulty with this step, you can also directly use the model from [this link](https://huggingface.co/Tribbiani/vicuna-7b) as a replacement.
1. Run server
1. prepare server sql script
```bash
$ python pilot/server/llmserver.py
mysql> CREATE DATABASE knowledge_management;
mysql> use knowledge_management;
mysql> source ./assets/schema/knowledge_management.sql
```
set .env configuration set your vector store type, eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > 2.1)
Starting `llmserver.py` with the following command will result in a relatively stable Python service with multiple processes.
```bash
$ gunicorn llmserver:app -w 4 -k uvicorn.workers.UvicornWorker -b 0.0.0.0:8000 &
```
Run gradio webui
2. Run db-gpt server
```bash
$ python pilot/server/webserver.py
$ python pilot/server/dbgpt_server.py
```
Notice: the webserver need to connect llmserver, so you need change the .env file. change the MODEL_SERVER = "http://127.0.0.1:8000" to your address. It's very important.
3. Run new webui
```bash
$ cd datacenter
$ npm i
$ npm run dev
```
Notice: make sure node.js is the latest version, learn more about db-gt webui,
read https://github.com/csunny/DB-GPT/tree/new-page-framework/datacenter
Open http://localhost:3000 with your browser to see the result.