github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-09-14 21:51:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add bge embbeding model (#479)

Browse Source 
1.add bge embedding model
2.getting start doc update
This commit is contained in:
magic.chen
2023-08-23 21:48:05 +08:00
committed by GitHub
parent 4ec47a5efd 4e3527e9d7
commit 1b9bb47ee2
6 changed files with 530 additions and 699 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.env.template
View File

@@ -50,6 +50,9 @@ QUANTIZE_8bit=True
#** EMBEDDING SETTINGS **#
#*******************************************************************#
EMBEDDING_MODEL=text2vec
#EMBEDDING_MODEL=m3e-large
#EMBEDDING_MODEL=bge-large-en
#EMBEDDING_MODEL=bge-large-zh
KNOWLEDGE_CHUNK_SIZE=500
KNOWLEDGE_SEARCH_TOP_SIZE=5
## EMBEDDING_TOKENIZER - Tokenizer to use for chunking large inputs

2
docs/conf.py
View File

@@ -14,7 +14,7 @@ project = "DB-GPT"
copyright = "2023, csunny"
author = "csunny"
version = "👏👏 0.3.5"
version = "👏👏 0.3.6"
html_title = project + " " + version
# -- General configuration ---------------------------------------------------

261
docs/getting_started/getting_started.md
View File

@@ -1,249 +1,38 @@
# Quickstart Guide
This tutorial gives you a quick walkthrough about use DB-GPT with you environment and data.
#### Welcome to DB-GPT!
## Installation
DB-GPT is an experimental open-source project that uses localized GPT large models to interact with your data and
environment. With this solution, you can be assured that there is no risk of data leakage, and your data is 100% private
and secure.
To get started, install DB-GPT with the following steps.
Our vision is to make it easier and more convenient to build applications around databases and llm.
### 1. Hardware Requirements
As our project has the ability to achieve ChatGPT performance of over 85%, there are certain hardware requirements. However, overall, the project can be deployed and used on consumer-grade graphics cards. The specific hardware requirements for deployment are as follows:
## What can I do with DB-GPT?
| GPU | VRAM Size | Performance |
| --------- | --------- | ------------------------------------------- |
| RTX 4090 | 24 GB | Smooth conversation inference |
| RTX 3090 | 24 GB | Smooth conversation inference, better than V100 |
| V100 | 16 GB | Conversation inference possible, noticeable stutter |
- Chat Data with your Datasource.
- Private domain knowledge question answering.
- Quickly provide private LLM Model deployment.
### 2. Install
## Usage with DB-GPT.
We use [Chroma embedding database](https://github.com/chroma-core/chroma) as the default for our vector database and use SQLite as the default for our database, so there is no need for special installation. If you choose to connect to other databases, you can follow our tutorial for installation and configuration.
For the entire installation process of DB-GPT, we use the miniconda3 virtual environment. Create a virtual environment and install the Python dependencies.
- Follow DB-GPT
application [install tutorial](https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html).
- Follow
DB-GPT [application usage](https://db-gpt.readthedocs.io/en/latest/getting_started/application/chatdb/chatdb.html).
```bash
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
```bash
python -m spacy download zh_core_web_sm
```
If you encounter any issues while using DB-GPT (whether it's during installation or usage), you can refer to
the [FAQ](https://db-gpt.readthedocs.io/en/latest/getting_started/faq/deploy/deploy_faq.html) section for assistance.
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
## 🗺️ Ecosystem
```{tip}
Notice make sure you have install git-lfs
```
- Github: https://github.com/eosphoros-ai/DB-GPT
- PyPi:
- DB-GPT: https://pypi.org/simple/db-gpt.
```bash
git clone https://huggingface.co/lmsys/vicuna-13b-v1.5
git clone https://huggingface.co/Tribbiani/vicuna-13b
git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
git clone https://huggingface.co/THUDM/chatglm2-6b
```
## Associated projects
The model files are large and will take a long time to download. During the download, let's configure the .env file, which needs to be copied and created from the .env.template
```{tip}
cp .env.template .env
```
You can configure basic parameters in the .env file, for example setting LLM_MODEL to the model to be used
([Vicuna-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) based on llama-2 has been released, we recommend you set `LLM_MODEL=vicuna-13b-v1.5` to try this model)
### 3. Run
You can refer to this document to obtain the Vicuna weights: [Vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-weights) .
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.
set .env configuration set your vector store type, eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > 2.1)
1.Run db-gpt server
```bash
$ python pilot/server/dbgpt_server.py
```
Open http://localhost:5000 with your browser to see the product.
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.
2.execute dbgpt_server.py in light mode
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
```
### 4. Docker (Experimental)
#### 4.1 Building Docker image
```bash
$ bash docker/build_all_images.sh
```
Review images by listing them:
```bash
$ docker images|grep "eosphorosai/dbgpt"
```
Output should look something like the following:
```
eosphorosai/dbgpt-allinone latest 349d49726588 27 seconds ago 15.1GB
eosphorosai/dbgpt latest eb3cdc5b4ead About a minute ago 14.5GB
```
`eosphorosai/dbgpt` is the base image, which contains the project's base dependencies and a sqlite database. `eosphorosai/dbgpt-allinone` build from `eosphorosai/dbgpt`, which contains a mysql database.
You can pass some parameters to docker/build_all_images.sh.
```bash
$ bash docker/build_all_images.sh \
--base-image nvidia/cuda:11.8.0-devel-ubuntu22.04 \
--pip-index-url https://pypi.tuna.tsinghua.edu.cn/simple \
--language zh
```
You can execute the command `bash docker/build_all_images.sh --help` to see more usage.
#### 4.2. Run all in one docker container
**Run with local model and SQLite database**
```bash
$ docker run --gpus all -d \
-p 5000:5000 \
-e LOCAL_DB_TYPE=sqlite \
-e LOCAL_DB_PATH=data/default_sqlite.db \
-e LLM_MODEL=vicuna-13b \
-e LANGUAGE=zh \
-v /data/models:/app/models \
--name dbgpt \
eosphorosai/dbgpt
```
Open http://localhost:5000 with your browser to see the product.
- `-e LLM_MODEL=vicuna-13b`, means we use vicuna-13b as llm model, see /pilot/configs/model_config.LLM_MODEL_CONFIG
- `-v /data/models:/app/models`, means we mount the local model file directory `/data/models` to the docker container directory `/app/models`, please replace it with your model file directory.
You can see log with command:
```bash
$ docker logs dbgpt -f
```
**Run with local model and MySQL database**
```bash
$ docker run --gpus all -d -p 3306:3306 \
-p 5000:5000 \
-e LOCAL_DB_HOST=127.0.0.1 \
-e LOCAL_DB_PASSWORD=aa123456 \
-e MYSQL_ROOT_PASSWORD=aa123456 \
-e LLM_MODEL=vicuna-13b \
-e LANGUAGE=zh \
-v /data/models:/app/models \
--name dbgpt \
eosphorosai/dbgpt-allinone
```
**Run with openai interface**
```bash
$ PROXY_API_KEY="You api key"
$ PROXY_SERVER_URL="https://api.openai.com/v1/chat/completions"
$ docker run --gpus all -d -p 3306:3306 \
-p 5000:5000 \
-e LOCAL_DB_HOST=127.0.0.1 \
-e LOCAL_DB_PASSWORD=aa123456 \
-e MYSQL_ROOT_PASSWORD=aa123456 \
-e LLM_MODEL=proxyllm \
-e PROXY_API_KEY=$PROXY_API_KEY \
-e PROXY_SERVER_URL=$PROXY_SERVER_URL \
-e LANGUAGE=zh \
-v /data/models/text2vec-large-chinese:/app/models/text2vec-large-chinese \
--name dbgpt \
eosphorosai/dbgpt-allinone
```
- `-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, fastchat interface...)
- `-v /data/models/text2vec-large-chinese:/app/models/text2vec-large-chinese`, means we mount the local text2vec model to the docker container.
#### 4.3. Run with docker compose
```bash
$ docker compose up -d
```
Output should look something like the following:
```
[+] Building 0.0s (0/0)
[+] Running 2/2
✔ Container db-gpt-db-1 Started 0.4s
✔ Container db-gpt-webserver-1 Started
```
You can see log with command:
```bash
$ docker logs db-gpt-webserver-1 -f
```
Open http://localhost:5000 with your browser to see the product.
You can open docker-compose.yml in the project root directory to see more details.
### 5. Multiple GPUs
DB-GPT will use all available gpu by default. And you can modify the setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file to use the specific gpu IDs.
Optionally, you can also specify the gpu ID to use before the starting command, as shown below:
````shell
# Specify 1 gpu
CUDA_VISIBLE_DEVICES=0 python3 pilot/server/dbgpt_server.py
# Specify 4 gpus
CUDA_VISIBLE_DEVICES=3,4,5,6 python3 pilot/server/dbgpt_server.py
````
You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to configure the maximum memory used by each GPU.
### 6. Not Enough Memory
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).
Here are some of the VRAM size usage of the models we tested in some common scenarios.
| Model | Quantize | VRAM Size |
| --------- | --------- | --------- |
| vicuna-7b-v1.5 | 4-bit | 8 GB |
| vicuna-7b-v1.5 | 8-bit | 12 GB |
| vicuna-13b-v1.5 | 4-bit | 12 GB |
| vicuna-13b-v1.5 | 8-bit | 20 GB |
| llama-2-7b | 4-bit | 8 GB |
| llama-2-7b | 8-bit | 12 GB |
| llama-2-13b | 4-bit | 12 GB |
| llama-2-13b | 8-bit | 20 GB |
| llama-2-70b | 4-bit | 48 GB |
| llama-2-70b | 8-bit | 80 GB |
| baichuan-7b | 4-bit | 8 GB |
| baichuan-7b | 8-bit | 12 GB |
| baichuan-13b | 4-bit | 12 GB |
| baichuan-13b | 8-bit | 20 GB |
- 🧪 DB-GPT-Hub: https://github.com/eosphoros-ai/DB-GPT-Hub | an experimental project to implement Text-to-SQL parsing
using LLMs
- 🏡 DB-GPT-Web: https://github.com/eosphoros-ai/DB-GPT-Web | Web application for DB-GPT.
- 🚀 DB-GPT-Plugins: https://github.com/eosphoros-ai/DB-GPT-Web | DB-GPT Plugins Repo, Which support AutoGPT plugin.

955
docs/locales/zh_CN/LC_MESSAGES/getting_started/getting_started.po
View File

@@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 0.3.0\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"POT-Creation-Date: 2023-08-23 17:00+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,492 +19,117 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/getting_started.md:1 70e40ad608d54bcfae6faf0437c09b6f
#: ../../getting_started/getting_started.md:1 f5e3f55f96de414183847de3e1eb0a75
msgid "Quickstart Guide"
msgstr "使用指南"
#: ../../getting_started/getting_started.md:3 c22ff099d6e940f7938dcea0e2265f11
#: ../../getting_started/getting_started.md:3 39ac3167d0044868b9d9efca953e73c5
msgid "Welcome to DB-GPT!"
msgstr "欢迎来到DB-GPT!"
#: ../../getting_started/getting_started.md:5 bdc699f3da554c6eb46eba0636fe7bda
msgid ""
"This tutorial gives you a quick walkthrough about use DB-GPT with you "
"environment and data."
msgstr "本教程为您提供了关于如何使用DB-GPT的使用指南。"
"DB-GPT is an experimental open-source project that uses localized GPT "
"large models to interact with your data and environment. With this "
"solution, you can be assured that there is no risk of data leakage, and "
"your data is 100% private and secure."
msgstr ""
"随着大模型的发布迭代，大模型变得越来越智能，在使用大模型的过程当中，遇到极大的数据安全与隐私挑战。在利用大模型能力的过程中我们的私密数据跟环境需要掌握自己的手里，完全可控，避免任何的数据隐私泄露以及安全风险。基于此"
"，我们发起了DB-GPT项目，为所有以数据库为基础的场景，构建一套完整的私有大模型解决方案。 "
"此方案因为支持本地部署，所以不仅仅可以应用于独立私有环境，而且还可以根据业务模块独立部署隔离，让大模型的能力绝对私有、安全、可控。"
#: ../../getting_started/getting_started.md:5 dc717e76b3194a85ac5b9e8a4479b197
msgid "Installation"
msgstr "安装"
#: ../../getting_started/getting_started.md:7 a1d30c3d01b94310b89fae16ac581157
msgid "To get started, install DB-GPT with the following steps."
msgstr "请按照以下步骤安装DB-GPT"
#: ../../getting_started/getting_started.md:9 bab013745cb24538ac568b97045b72cc
msgid "1. Hardware Requirements"
msgstr "1. 硬件要求"
#: ../../getting_started/getting_started.md:10 7dd84870db394338a5c7e63b171207e0
#: ../../getting_started/getting_started.md:7 7d1a79640331431e85d5c54075dca1fd
msgid ""
"As our project has the ability to achieve ChatGPT performance of over "
"85%, there are certain hardware requirements. However, overall, the "
"project can be deployed and used on consumer-grade graphics cards. The "
"specific hardware requirements for deployment are as follows:"
msgstr "由于我们的项目有能力达到85%以上的ChatGPT性能，所以对硬件有一定的要求。但总体来说，我们在消费级的显卡上即可完成项目的部署使用，具体部署的硬件说明如下:"
"Our vision is to make it easier and more convenient to build applications"
" around databases and llm."
msgstr "我们的愿景是让围绕数据库构建大模型应用更简单，更方便。"
#: ../../getting_started/getting_started.md 055d07f830c54303a0b5596601c58870
msgid "GPU"
msgstr "GPU"
#: ../../getting_started/getting_started.md:9 f400d65e13e0405d8aea576c02a7b02a
msgid "What can I do with DB-GPT?"
msgstr "通过DB-GPT我能做什么"
#: ../../getting_started/getting_started.md
#: ../../getting_started/getting_started.md:50 7323cee42940438b8a0752d3c2355e59
#: e3fc2c10f81b4fe2ac0bfd9fe78feed9
msgid "VRAM Size"
msgstr "显存大小"
#: ../../getting_started/getting_started.md:10 2b161262a21b474ca7c191ed0f9ab6b0
msgid "Chat Data with your Datasource."
msgstr "和自己的数据聊天，进行数据分析"
#: ../../getting_started/getting_started.md 68831daf63f14dcd92088dd6c866f110
msgid "Performance"
msgstr "显存大小"
#: ../../getting_started/getting_started.md:11 0f1322f19cea45768b5bde4448dfea5e
msgid "Private domain knowledge question answering."
msgstr "私有领域的知识问答"
#: ../../getting_started/getting_started.md 8a7197a5e92c40a9ba160b43656983d2
msgid "RTX 4090"
msgstr "RTX 4090"
#: ../../getting_started/getting_started.md:12 9dc0e76f46c64304aabb80fcf4a2a3f2
msgid "Quickly provide private LLM Model deployment."
msgstr "快速构建私有大模型部署"
#: ../../getting_started/getting_started.md 69b2bfdec17e43fbb57f47e3e10a5f5a
#: 81d0c2444bbb4a2fb834a628689e4b68
msgid "24 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:14 ad5daeae9621455ba447735fd55648cc
msgid "Usage with DB-GPT."
msgstr "DB-GPT使用姿势."
#: ../../getting_started/getting_started.md 49b65b0eaffb41d78a1227bcc3e836e0
msgid "Smooth conversation inference"
msgstr "可以流畅的进行对话推理，无卡顿"
#: ../../getting_started/getting_started.md:15 870d82fd402444aab3028764607ff468
msgid ""
"Follow DB-GPT application [install tutorial](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html)."
msgstr ""
"先安装部署应用[安装教程](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html)."
#: ../../getting_started/getting_started.md 527def44c8b24e4bbe589d110bd43e91
msgid "RTX 3090"
msgstr "RTX 3090"
#: ../../getting_started/getting_started.md ad9666e0521c4ef0ad19c2e224daecda
msgid "Smooth conversation inference, better than V100"
msgstr "可以流畅进行对话推理，有卡顿感，但好于V100"
#: ../../getting_started/getting_started.md c090521969f042398236f6d04b017295
msgid "V100"
msgstr "V100"
#: ../../getting_started/getting_started.md 60605e0de3fc494cbb7199cef8f831ad
msgid "16 GB"
msgstr "16 GB"
#: ../../getting_started/getting_started.md b82747aee44e444984565aab0faa2a64
msgid "Conversation inference possible, noticeable stutter"
msgstr "可以进行对话推理，有明显卡顿"
#: ../../getting_started/getting_started.md:18 b9df8ec7b2c34233b28db81f3c90f8c7
msgid "2. Install"
msgstr "2. 安装"
#: ../../getting_started/getting_started.md:20 bd0f0159a49b4493ab387e124fef15fa
#: ../../getting_started/getting_started.md:16 c7806bcd1b9a43eda8a86402f9903dfe
#, fuzzy
msgid ""
"We use [Chroma embedding database](https://github.com/chroma-core/chroma)"
" as the default for our vector database and use SQLite as the default for"
" our database, so there is no need for special installation. If you "
"choose to connect to other databases, you can follow our tutorial for "
"installation and configuration. For the entire installation process of "
"DB-GPT, we use the miniconda3 virtual environment. Create a virtual "
"environment and install the Python dependencies."
"Follow DB-GPT [application usage](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/application/chatdb/chatdb.html)."
msgstr ""
"向量数据库我们默认使用的是Chroma内存数据库，所以无需特殊安装，如果有需要连接其他的同学，可以按照我们的教程进行安装配置。整个DB-"
"GPT的安装过程，我们使用的是miniconda3的虚拟环境。创建虚拟环境，并安装python依赖包"
"先安装部署应用[安装教程](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html)."
#: ../../getting_started/getting_started.md:29 bc8f2ee7894b4cad858d5e2cfbee10a9
msgid "Before use DB-GPT Knowledge Management"
msgstr "使用知识库管理功能之前"
#: ../../getting_started/getting_started.md:34 03e1652f724946ec8d01a97811883b5f
#: ../../getting_started/getting_started.md:18 5dd30b81ed39476f871ed31edd01c043
msgid ""
"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"
"If you encounter any issues while using DB-GPT (whether it's during "
"installation or usage), you can refer to the [FAQ](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/faq/deploy/deploy_faq.html) "
"section for assistance."
msgstr ""
"环境安装完成后，我们必须在DB-"
"GPT项目中创建一个新文件夹\"models\"，然后我们可以把从huggingface下载的所有模型放到这个目录下。"
"如果你在使用DB-GPT过程中遇到什么问题(无论是安装还是使用)，可以查看[FAQ](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/faq/deploy/deploy_faq.html)\""
#: ../../getting_started/getting_started.md:37 e26a827f1d5b4d2cbf92b42bce461082
#, fuzzy
msgid "Notice make sure you have install git-lfs"
msgstr "确保你已经安装了git-lfs"
#: ../../getting_started/getting_started.md:21 c6202be38f3641098eedca1ef31665b3
msgid "🗺️ 生态"
msgstr "🗺️ 生态"
#: ../../getting_started/getting_started.md:48 af91349fe332472ca7a2e592a0c582f7
#: ../../getting_started/getting_started.md:23 d55c843f8a044e099e61a86ef5a70eaf
msgid "Github: https://github.com/eosphoros-ai/DB-GPT"
msgstr "Github: https://github.com/eosphoros-ai/DB-GPT"
#: ../../getting_started/getting_started.md:24 7e279ce6cce346ecb3e58537f2d8ca24
msgid "PyPi:"
msgstr "PyPi:"
#: ../../getting_started/getting_started.md:25 ca92a6bc95c94996b4e672be7ee43f1b
msgid "DB-GPT: https://pypi.org/simple/db-gpt."
msgstr "DB-GPT: https://pypi.org/simple/db-gpt."
#: ../../getting_started/getting_started.md:27 cc44973d1a78434fa3dfe511618b08d9
msgid "Associated projects"
msgstr "关联的项目"
#: ../../getting_started/getting_started.md:30 93b80349645943b38d16afd80ee076da
msgid ""
"The model files are large and will take a long time to download. During "
"the download, let's configure the .env file, which needs to be copied and"
" created from the .env.template"
msgstr "模型文件很大，需要很长时间才能下载。在下载过程中，让我们配置.env文件，它需要从。env.template中复制和创建。"
"🧪 DB-GPT-Hub: https://github.com/eosphoros-ai/DB-GPT-Hub | an "
"experimental project to implement Text-to-SQL parsing using LLMs"
msgstr "🧪 DB-GPT-Hub: https://github.com/eosphoros-ai/DB-GPT-Hub | 基于开源大模型的Text-to-SQL实验性项目"
#: ../../getting_started/getting_started.md:51 84d2d93130034c2f94f4d0bebcc2b0d2
msgid "cp .env.template .env"
msgstr "cp .env.template .env"
#: ../../getting_started/getting_started.md:54 b3adfec002354f00baba9c43a1a3e381
#: ../../getting_started/getting_started.md:31 2c061d9eee624a4b994bb6af3361591b
msgid ""
"You can configure basic parameters in the .env file, for example setting "
"LLM_MODEL to the model to be used"
msgstr "您可以在.env文件中配置基本参数，例如将LLM_MODEL设置为要使用的模型。"
"🏡 DB-GPT-Web: https://github.com/eosphoros-ai/DB-GPT-Web | Web "
"application for DB-GPT."
msgstr "🏡 DB-GPT-Web: https://github.com/eosphoros-ai/DB-GPT-Web | Web "
"应用 for DB-GPT."
#: ../../getting_started/getting_started.md:56 1b11268133c0440cb3c26981f5d0c1fe
#: ../../getting_started/getting_started.md:32 6564f208ecd04a3fae6dd5f12cfbad12
msgid ""
"([Vicuna-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) based on "
"llama-2 has been released, we recommend you set `LLM_MODEL=vicuna-"
"13b-v1.5` to try this model)"
msgstr ""
#: ../../getting_started/getting_started.md:58 511d47f08bab42e0bd3f34df58c5a822
msgid "3. Run"
msgstr "3. 运行"
#: ../../getting_started/getting_started.md:59 eba1922d852b4d548370884987237c09
msgid ""
"You can refer to this document to obtain the Vicuna weights: "
"[Vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-"
"weights) ."
msgstr ""
"关于基础模型, 可以根据[Vicuna](https://github.com/lm-"
"sys/FastChat/blob/main/README.md#model-weights) 合成教程进行合成。"
#: ../../getting_started/getting_started.md:61 bb51e0506f4e44c3a4daf1d0fbd5a4ef
msgid ""
"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."
msgstr ""
"如果此步有困难的同学，也可以直接使用[此链接](https://huggingface.co/Tribbiani/vicuna-"
"7b)上的模型进行替代。"
#: ../../getting_started/getting_started.md:63 0d532891bd754e78a6390fcc97d0f59d
msgid ""
"set .env configuration set your vector store type, "
"eg:VECTOR_STORE_TYPE=Chroma, now we support Chroma and Milvus(version > "
"2.1)"
msgstr ""
"在.env文件设置向量数据库环境变量，eg:VECTOR_STORE_TYPE=Chroma, 目前我们支持了 Chroma and "
"Milvus(version >2.1) "
#: ../../getting_started/getting_started.md:66 8beb3199650e4d2b8f567d0de20e2cb6
#, fuzzy
msgid "1.Run db-gpt server"
msgstr "运行模型服务"
#: ../../getting_started/getting_started.md:71
#: ../../getting_started/getting_started.md:131
#: ../../getting_started/getting_started.md:200
#: 41984cf5289f4cefbead6b84fb011e92 5c3eb807af36425a8b0620705fc9c4e9
#: 7c420ffa305d4eb1a052b25101e80011
#, fuzzy
msgid "Open http://localhost:5000 with your browser to see the product."
msgstr "打开浏览器访问http://localhost:5000"
#: ../../getting_started/getting_started.md:73 802ca13fbe0542a19258d40c08da509e
msgid ""
"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. 2.execute dbgpt_server.py in light mode"
msgstr "如果你想访问外部的大模型服务，1.需要在.env文件设置模型名和外部模型服务地址。2.使用light模式启动服务"
#: ../../getting_started/getting_started.md:76 7808d30d1642422fbed42f1929e37343
#, fuzzy
msgid ""
"If you want to learn about dbgpt-webui, read https://github./csunny/DB-"
"GPT/tree/new-page-framework/datacenter"
msgstr ""
"如果你想了解DB-GPT前端服务，访问https://github.com/csunny/DB-GPT/tree/new-page-"
"framework/datacenter"
#: ../../getting_started/getting_started.md:82 094ed036720c406c904c8a9ca6e7b8ae
msgid "4. Docker (Experimental)"
msgstr "4. Docker (Experimental)"
#: ../../getting_started/getting_started.md:84 9428d68d1eef42c28bf33d9bd7022c85
msgid "4.1 Building Docker image"
msgstr "4.1 Building Docker image"
#: ../../getting_started/getting_started.md:90 16bfb175a85c455e847c3cafe2d94ce1
msgid "Review images by listing them:"
msgstr "Review images by listing them:"
#: ../../getting_started/getting_started.md:96
#: ../../getting_started/getting_started.md:186
#: 46438a8f73f344ca84f5c77c8fe7434b eaca8cbd8bdd4c03863ef5ea218218b1
msgid "Output should look something like the following:"
msgstr "Output should look something like the following:"
#: ../../getting_started/getting_started.md:103
#: 47d72ad65ce0455ca0d85580eb0db619
msgid ""
"`eosphorosai/dbgpt` is the base image, which contains the project's base "
"dependencies and a sqlite database. `eosphorosai/dbgpt-allinone` build "
"from `eosphorosai/dbgpt`, which contains a mysql database."
msgstr ""
#: ../../getting_started/getting_started.md:105
#: 980f39c088564de288cab120a4004d53
msgid "You can pass some parameters to docker/build_all_images.sh."
msgstr "You can pass some parameters to docker/build_all_images.sh."
#: ../../getting_started/getting_started.md:113
#: fad33767622f4b639881c4124bdc92cc
msgid ""
"You can execute the command `bash docker/build_all_images.sh --help` to "
"see more usage."
msgstr ""
"You can execute the command `bash docker/build_all_images.sh --help` to "
"see more usage."
#: ../../getting_started/getting_started.md:115
#: 878bb7ecfbe74a96bf42adef951bec44
msgid "4.2. Run all in one docker container"
msgstr "4.2. Run all in one docker container"
#: ../../getting_started/getting_started.md:117
#: 2e8279c88e814e8db5dc16d4b05c62e1
#, fuzzy
msgid "**Run with local model and SQLite database**"
msgstr "**Run with local model**"
#: ../../getting_started/getting_started.md:134
#: fb87d01dc56c48ac937b537dcc29627c
msgid ""
"`-e LLM_MODEL=vicuna-13b`, means we use vicuna-13b as llm model, see "
"/pilot/configs/model_config.LLM_MODEL_CONFIG"
msgstr ""
"`-e LLM_MODEL=vicuna-13b`, means we use vicuna-13b as llm model, see "
"/pilot/configs/model_config.LLM_MODEL_CONFIG"
#: ../../getting_started/getting_started.md:135
#: b2517db39b0b473ab4f302a925d86879
msgid ""
"`-v /data/models:/app/models`, means we mount the local model file "
"directory `/data/models` to the docker container directory `/app/models`,"
" please replace it with your model file directory."
msgstr ""
"`-v /data/models:/app/models`, means we mount the local model file "
"directory `/data/models` to the docker container directory `/app/models`,"
" please replace it with your model file directory."
#: ../../getting_started/getting_started.md:137
#: ../../getting_started/getting_started.md:194
#: 140b925a0e5b4daeb6880fef503d6aac 67636495385943e3b81af74b5433c74b
msgid "You can see log with command:"
msgstr "You can see log with command:"
#: ../../getting_started/getting_started.md:143
#: 4ba6f304021746f6aa63fe196e752092
#, fuzzy
msgid "**Run with local model and MySQL database**"
msgstr "**Run with local model**"
#: ../../getting_started/getting_started.md:158
#: 4f2fc76b150b4f248356418cf0183c83
msgid "**Run with openai interface**"
msgstr "**Run with openai interface**"
#: ../../getting_started/getting_started.md:177
#: ed6edd5016444324a98200f054c7d2a5
msgid ""
"`-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, "
"fastchat interface...)"
msgstr ""
"`-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, "
"fastchat interface...)"
#: ../../getting_started/getting_started.md:178
#: 7bc17c46292f43c488dcec172c835d49
msgid ""
"`-v /data/models/text2vec-large-chinese:/app/models/text2vec-large-"
"chinese`, means we mount the local text2vec model to the docker "
"container."
msgstr ""
"`-v /data/models/text2vec-large-chinese:/app/models/text2vec-large-"
"chinese`, means we mount the local text2vec model to the docker "
"container."
#: ../../getting_started/getting_started.md:180
#: 257860df855843eb85383478d2e8baca
msgid "4.3. Run with docker compose"
msgstr ""
#: ../../getting_started/getting_started.md:202
#: 143be856423e412c8605488c0e50d2dc
msgid ""
"You can open docker-compose.yml in the project root directory to see more"
" details."
msgstr ""
"You can open docker-compose.yml in the project root directory to see more"
" details."
#: ../../getting_started/getting_started.md:205
#: 0dd3dc0d7a7f4565a041ab5855808fd3
msgid "5. Multiple GPUs"
msgstr "5. Multiple GPUs"
#: ../../getting_started/getting_started.md:207
#: 65b1d32a91634c069a80269c44728727
msgid ""
"DB-GPT will use all available gpu by default. And you can modify the "
"setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file to use the specific gpu"
" IDs."
msgstr ""
"DB-GPT will use all available gpu by default. And you can modify the "
"setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file to use the specific gpu"
" IDs."
#: ../../getting_started/getting_started.md:209
#: 1ef71b0a976640319211a245943d99d5
msgid ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command, as shown below:"
msgstr ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command, as shown below:"
#: ../../getting_started/getting_started.md:219
#: efbc9ca4b8f44b219460577b691d2c0a
msgid ""
"You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to "
"configure the maximum memory used by each GPU."
msgstr ""
#: ../../getting_started/getting_started.md:221
#: c80f5e6d2a6042ad9ac0ef320cc6d987
msgid "6. Not Enough Memory"
msgstr ""
#: ../../getting_started/getting_started.md:223
#: b8151a333f804489ad6a2b59e739a8ed
msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
msgstr ""
#: ../../getting_started/getting_started.md:225
#: be32dacd8bb84a19985417bd1b78db0f
msgid ""
"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)."
msgstr ""
#: ../../getting_started/getting_started.md:227
#: 247509e1392e4b4a8d8cdc59f2f94d37
msgid ""
"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."
msgstr ""
"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."
#: ../../getting_started/getting_started.md:229
#: 4e8def991b8a491c83c29214e5f80669
msgid ""
"Note: you need to install the latest dependencies according to "
"[requirements.txt](https://github.com/eosphoros-ai/DB-"
"GPT/blob/main/requirements.txt)."
msgstr ""
"Note: you need to install the latest dependencies according to "
"[requirements.txt](https://github.com/eosphoros-ai/DB-"
"GPT/blob/main/requirements.txt)."
#: ../../getting_started/getting_started.md:232
#: 85f7bb08aa714f5db6db00d905dd9dc8
msgid ""
"Here are some of the VRAM size usage of the models we tested in some "
"common scenarios."
msgstr ""
"Here are some of the VRAM size usage of the models we tested in some "
"common scenarios."
#: ../../getting_started/getting_started.md:50 165d0902ed064bbaa8b0bbe84befe139
msgid "Model"
msgstr "Model"
#: ../../getting_started/getting_started.md:50 d077bca9cada4a9b89037ef5ab494c26
msgid "Quantize"
msgstr "Quantize"
#: ../../getting_started/getting_started.md:50 42723863614e42b1aa6c664bfd197474
#: b71ce0c19de7471787cbbc09d6137a4b
msgid "vicuna-7b-v1.5"
msgstr "vicuna-7b-v1.5"
#: ../../getting_started/getting_started.md:50 2654d358528a48e38bec445644ffd20a
#: 2ad34cd14f54422491464967331d83fc 3b42a055e72847ec99d8d131fa9f5f84
#: 6641e98d9bed44ee853fe7a11263a88b a69801bc92f143aa9e0818886ef6eade
#: daa418b33705484ba944b0d92981a501 fc26bd1dace2432ca64b99ca16c2c80f
msgid "4-bit"
msgstr "4-bit"
#: ../../getting_started/getting_started.md:50 1688f8a0972c4026abf69b5186d92137
#: 683de09d524a4084bcdad1a184206f87 74586e40b480444591dc884e7f3f683f
#, fuzzy
msgid "8 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:50 13aa8cac7a784ad1a1b58b166be99711
#: 32633a38c1f44aac92f9647ee7867cd1 3b7fea4236174e2bb33894fd8234eddb
#: 3b8104af560e41f285d9c433e19f6cb7 5862f0c57e2c411dada47fe71f6a74bd
#: 6425f53f197742c8b3153a79cf4a220a d1fa83af3a884714a72f7a0af5f3be23
msgid "8-bit"
msgstr "8-bit"
#: ../../getting_started/getting_started.md:50 107ed4fb15c44cb5bb7020a8092f7341
#: 1d1791894226418ea623abdecd3107ba 1fdc42ef874f4022be31df7696e6a5de
#: 718c49ddac8e4086a75cdbba166dc3cb 99404c8333974ae7a1e68885f4471b32
#: da59674e4418488583cf4865545ad752
#, fuzzy
msgid "12 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:50 79bf82a6dc9f4c22af779be4b1d2d13c
#: b5bde8f01fc343baa567806fd53070dc
msgid "vicuna-13b-v1.5"
msgstr "vicuna-13b-v1.5"
#: ../../getting_started/getting_started.md:50 362720115dd64143a214b3b9d3069512
#: e0545557159b44dea0522a1848170216 e3c6ab8f25bc4adbae3b3087716a1efe
#, fuzzy
msgid "20 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:50 295fd7d6e6c846748a1f2c82f8c79ba0
#: 55efa8e8e4e74efc865df87fcfade84d
msgid "llama-2-7b"
msgstr "llama-2-7b"
#: ../../getting_started/getting_started.md:50 15b1e541bdac43fda1dcccf2aaeaa40f
#: 5785954810bc45369ed1745f5c503c9c
msgid "llama-2-13b"
msgstr "llama-2-13b"
#: ../../getting_started/getting_started.md:50 185892d421684c1b903c04ea9b6653d7
#: d7970a5fe574434798d72427436c82d5
msgid "llama-2-70b"
msgstr "llama-2-70b"
#: ../../getting_started/getting_started.md:50 f732a7f73a504bd1b56b42dab1114d04
#, fuzzy
msgid "48 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:50 04642b0dd4bc4563a45c6d15fa1d8f07
#, fuzzy
msgid "80 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:50 b9c4d8b71b1e4185bab24a857433f884
#: fc1b1927cc344e2e91bb7047c79ad227
msgid "baichuan-7b"
msgstr ""
#: ../../getting_started/getting_started.md:50 c92417b527a04d82ac9caa837884113c
#: dc17ae982c154b988433a0c623301bcb
msgid "baichuan-13b"
msgstr "baichuan-13b"
"🚀 DB-GPT-Plugins: https://github.com/eosphoros-ai/DB-GPT-Web | DB-GPT "
"Plugins Repo, Which support AutoGPT plugin."
msgstr "🚀 DB-GPT-Plugins: https://github.com/eosphoros-ai/DB-GPT-Web | DB-GPT "
"Plugins Repo, Which support AutoGPT plugin."
#~ msgid "4.2. Run with docker compose"
#~ msgstr "4.2. Run with docker compose"
@@ -519,3 +144,411 @@ msgstr "baichuan-13b"
#~ msgid "prepare server sql script"
#~ msgstr "准备db-gpt server sql脚本"
#~ msgid ""
#~ "This tutorial gives you a quick "
#~ "walkthrough about use DB-GPT with "
#~ "you environment and data."
#~ msgstr "本教程为您提供了关于如何使用DB-GPT的使用指南。"
#~ msgid "Installation"
#~ msgstr "安装"
#~ msgid "To get started, install DB-GPT with the following steps."
#~ msgstr "请按照以下步骤安装DB-GPT"
#~ msgid "1. Hardware Requirements"
#~ msgstr "1. 硬件要求"
#~ msgid ""
#~ "As our project has the ability to"
#~ " achieve ChatGPT performance of over "
#~ "85%, there are certain hardware "
#~ "requirements. However, overall, the project"
#~ " can be deployed and used on "
#~ "consumer-grade graphics cards. The specific"
#~ " hardware requirements for deployment are"
#~ " as follows:"
#~ msgstr "由于我们的项目有能力达到85%以上的ChatGPT性能，所以对硬件有一定的要求。但总体来说，我们在消费级的显卡上即可完成项目的部署使用，具体部署的硬件说明如下:"
#~ msgid "GPU"
#~ msgstr "GPU"
#~ msgid "VRAM Size"
#~ msgstr "显存大小"
#~ msgid "Performance"
#~ msgstr "显存大小"
#~ msgid "RTX 4090"
#~ msgstr "RTX 4090"
#~ msgid "24 GB"
#~ msgstr "24 GB"
#~ msgid "Smooth conversation inference"
#~ msgstr "可以流畅的进行对话推理，无卡顿"
#~ msgid "RTX 3090"
#~ msgstr "RTX 3090"
#~ msgid "Smooth conversation inference, better than V100"
#~ msgstr "可以流畅进行对话推理，有卡顿感，但好于V100"
#~ msgid "V100"
#~ msgstr "V100"
#~ msgid "16 GB"
#~ msgstr "16 GB"
#~ msgid "Conversation inference possible, noticeable stutter"
#~ msgstr "可以进行对话推理，有明显卡顿"
#~ msgid "2. Install"
#~ msgstr "2. 安装"
#~ msgid ""
#~ "We use [Chroma embedding "
#~ "database](https://github.com/chroma-core/chroma) as "
#~ "the default for our vector database "
#~ "and use SQLite as the default for"
#~ " our database, so there is no "
#~ "need for special installation. If you"
#~ " choose to connect to other "
#~ "databases, you can follow our tutorial"
#~ " for installation and configuration. For"
#~ " the entire installation process of "
#~ "DB-GPT, we use the miniconda3 virtual"
#~ " environment. Create a virtual environment"
#~ " and install the Python dependencies."
#~ msgstr ""
#~ "向量数据库我们默认使用的是Chroma内存数据库，所以无需特殊安装，如果有需要连接其他的同学，可以按照我们的教程进行安装配置"
#~ "。整个DB-GPT的安装过程，我们使用的是miniconda3的虚拟环境。创建虚拟环境，并安装python依赖包"
#~ msgid "Before use DB-GPT Knowledge Management"
#~ msgstr "使用知识库管理功能之前"
#~ msgid ""
#~ "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"
#~ msgstr ""
#~ "环境安装完成后，我们必须在DB-"
#~ "GPT项目中创建一个新文件夹\"models\"，然后我们可以把从huggingface下载的所有模型放到这个目录下。"
#~ msgid "Notice make sure you have install git-lfs"
#~ msgstr "确保你已经安装了git-lfs"
#~ msgid ""
#~ "The model files are large and will"
#~ " take a long time to download. "
#~ "During the download, let's configure the"
#~ " .env file, which needs to be "
#~ "copied and created from the "
#~ ".env.template"
#~ msgstr "模型文件很大，需要很长时间才能下载。在下载过程中，让我们配置.env文件，它需要从。env.template中复制和创建。"
#~ msgid "cp .env.template .env"
#~ msgstr "cp .env.template .env"
#~ msgid ""
#~ "You can configure basic parameters in"
#~ " the .env file, for example setting"
#~ " LLM_MODEL to the model to be "
#~ "used"
#~ msgstr "您可以在.env文件中配置基本参数，例如将LLM_MODEL设置为要使用的模型。"
#~ msgid ""
#~ "([Vicuna-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) "
#~ "based on llama-2 has been released, "
#~ "we recommend you set `LLM_MODEL=vicuna-"
#~ "13b-v1.5` to try this model)"
#~ msgstr ""
#~ msgid "3. Run"
#~ msgstr "3. 运行"
#~ msgid ""
#~ "You can refer to this document to"
#~ " obtain the Vicuna weights: "
#~ "[Vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md"
#~ "#model-weights) ."
#~ msgstr ""
#~ "关于基础模型, 可以根据[Vicuna](https://github.com/lm-"
#~ "sys/FastChat/blob/main/README.md#model-weights) 合成教程进行合成。"
#~ msgid ""
#~ "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."
#~ msgstr ""
#~ "如果此步有困难的同学，也可以直接使用[此链接](https://huggingface.co/Tribbiani/vicuna-"
#~ "7b)上的模型进行替代。"
#~ msgid ""
#~ "set .env configuration set your vector"
#~ " store type, eg:VECTOR_STORE_TYPE=Chroma, now "
#~ "we support Chroma and Milvus(version >"
#~ " 2.1)"
#~ msgstr ""
#~ "在.env文件设置向量数据库环境变量，eg:VECTOR_STORE_TYPE=Chroma, 目前我们支持了 "
#~ "Chroma and Milvus(version >2.1) "
#~ msgid "1.Run db-gpt server"
#~ msgstr "运行模型服务"
#~ msgid "Open http://localhost:5000 with your browser to see the product."
#~ msgstr "打开浏览器访问http://localhost:5000"
#~ msgid ""
#~ "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. 2.execute dbgpt_server.py "
#~ "in light mode"
#~ msgstr "如果你想访问外部的大模型服务，1.需要在.env文件设置模型名和外部模型服务地址。2.使用light模式启动服务"
#~ msgid ""
#~ "If you want to learn about "
#~ "dbgpt-webui, read https://github./csunny/DB-"
#~ "GPT/tree/new-page-framework/datacenter"
#~ msgstr ""
#~ "如果你想了解DB-GPT前端服务，访问https://github.com/csunny/DB-GPT/tree"
#~ "/new-page-framework/datacenter"
#~ msgid "4. Docker (Experimental)"
#~ msgstr "4. Docker (Experimental)"
#~ msgid "4.1 Building Docker image"
#~ msgstr "4.1 Building Docker image"
#~ msgid "Review images by listing them:"
#~ msgstr "Review images by listing them:"
#~ msgid "Output should look something like the following:"
#~ msgstr "Output should look something like the following:"
#~ msgid ""
#~ "`eosphorosai/dbgpt` is the base image, "
#~ "which contains the project's base "
#~ "dependencies and a sqlite database. "
#~ "`eosphorosai/dbgpt-allinone` build from "
#~ "`eosphorosai/dbgpt`, which contains a mysql"
#~ " database."
#~ msgstr ""
#~ msgid "You can pass some parameters to docker/build_all_images.sh."
#~ msgstr "You can pass some parameters to docker/build_all_images.sh."
#~ msgid ""
#~ "You can execute the command `bash "
#~ "docker/build_all_images.sh --help` to see more"
#~ " usage."
#~ msgstr ""
#~ "You can execute the command `bash "
#~ "docker/build_all_images.sh --help` to see more"
#~ " usage."
#~ msgid "4.2. Run all in one docker container"
#~ msgstr "4.2. Run all in one docker container"
#~ msgid "**Run with local model and SQLite database**"
#~ msgstr "**Run with local model**"
#~ msgid ""
#~ "`-e LLM_MODEL=vicuna-13b`, means we use"
#~ " vicuna-13b as llm model, see "
#~ "/pilot/configs/model_config.LLM_MODEL_CONFIG"
#~ msgstr ""
#~ "`-e LLM_MODEL=vicuna-13b`, means we use"
#~ " vicuna-13b as llm model, see "
#~ "/pilot/configs/model_config.LLM_MODEL_CONFIG"
#~ msgid ""
#~ "`-v /data/models:/app/models`, means we mount"
#~ " the local model file directory "
#~ "`/data/models` to the docker container "
#~ "directory `/app/models`, please replace it "
#~ "with your model file directory."
#~ msgstr ""
#~ "`-v /data/models:/app/models`, means we mount"
#~ " the local model file directory "
#~ "`/data/models` to the docker container "
#~ "directory `/app/models`, please replace it "
#~ "with your model file directory."
#~ msgid "You can see log with command:"
#~ msgstr "You can see log with command:"
#~ msgid "**Run with local model and MySQL database**"
#~ msgstr "**Run with local model**"
#~ msgid "**Run with openai interface**"
#~ msgstr "**Run with openai interface**"
#~ msgid ""
#~ "`-e LLM_MODEL=proxyllm`, means we use "
#~ "proxy llm(openai interface, fastchat "
#~ "interface...)"
#~ msgstr ""
#~ "`-e LLM_MODEL=proxyllm`, means we use "
#~ "proxy llm(openai interface, fastchat "
#~ "interface...)"
#~ msgid ""
#~ "`-v /data/models/text2vec-large-chinese:/app/models"
#~ "/text2vec-large-chinese`, means we mount"
#~ " the local text2vec model to the "
#~ "docker container."
#~ msgstr ""
#~ "`-v /data/models/text2vec-large-chinese:/app/models"
#~ "/text2vec-large-chinese`, means we mount"
#~ " the local text2vec model to the "
#~ "docker container."
#~ msgid "4.3. Run with docker compose"
#~ msgstr ""
#~ msgid ""
#~ "You can open docker-compose.yml in "
#~ "the project root directory to see "
#~ "more details."
#~ msgstr ""
#~ "You can open docker-compose.yml in "
#~ "the project root directory to see "
#~ "more details."
#~ msgid "5. Multiple GPUs"
#~ msgstr "5. Multiple GPUs"
#~ msgid ""
#~ "DB-GPT will use all available gpu"
#~ " by default. And you can modify "
#~ "the setting `CUDA_VISIBLE_DEVICES=0,1` in "
#~ "`.env` file to use the specific "
#~ "gpu IDs."
#~ msgstr ""
#~ "DB-GPT will use all available gpu"
#~ " by default. And you can modify "
#~ "the setting `CUDA_VISIBLE_DEVICES=0,1` in "
#~ "`.env` file to use the specific "
#~ "gpu IDs."
#~ msgid ""
#~ "Optionally, you can also specify the "
#~ "gpu ID to use before the starting"
#~ " command, as shown below:"
#~ msgstr ""
#~ "Optionally, you can also specify the "
#~ "gpu ID to use before the starting"
#~ " command, as shown below:"
#~ msgid ""
#~ "You can modify the setting "
#~ "`MAX_GPU_MEMORY=xxGib` in `.env` file to "
#~ "configure the maximum memory used by "
#~ "each GPU."
#~ msgstr ""
#~ msgid "6. Not Enough Memory"
#~ msgstr ""
#~ msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
#~ msgstr ""
#~ msgid ""
#~ "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)."
#~ msgstr ""
#~ msgid ""
#~ "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."
#~ msgstr ""
#~ "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."
#~ msgid ""
#~ "Note: you need to install the "
#~ "latest dependencies according to "
#~ "[requirements.txt](https://github.com/eosphoros-ai/DB-"
#~ "GPT/blob/main/requirements.txt)."
#~ msgstr ""
#~ "Note: you need to install the "
#~ "latest dependencies according to "
#~ "[requirements.txt](https://github.com/eosphoros-ai/DB-"
#~ "GPT/blob/main/requirements.txt)."
#~ msgid ""
#~ "Here are some of the VRAM size "
#~ "usage of the models we tested in"
#~ " some common scenarios."
#~ msgstr ""
#~ "Here are some of the VRAM size "
#~ "usage of the models we tested in"
#~ " some common scenarios."
#~ msgid "Model"
#~ msgstr "Model"
#~ msgid "Quantize"
#~ msgstr "Quantize"
#~ msgid "vicuna-7b-v1.5"
#~ msgstr "vicuna-7b-v1.5"
#~ msgid "4-bit"
#~ msgstr "4-bit"
#~ msgid "8 GB"
#~ msgstr "24 GB"
#~ msgid "8-bit"
#~ msgstr "8-bit"
#~ msgid "12 GB"
#~ msgstr "24 GB"
#~ msgid "vicuna-13b-v1.5"
#~ msgstr "vicuna-13b-v1.5"
#~ msgid "20 GB"
#~ msgstr "24 GB"
#~ msgid "llama-2-7b"
#~ msgstr "llama-2-7b"
#~ msgid "llama-2-13b"
#~ msgstr "llama-2-13b"
#~ msgid "llama-2-70b"
#~ msgstr "llama-2-70b"
#~ msgid "48 GB"
#~ msgstr "24 GB"
#~ msgid "80 GB"
#~ msgstr "24 GB"
#~ msgid "baichuan-7b"
#~ msgstr ""
#~ msgid "baichuan-13b"
#~ msgstr "baichuan-13b"
#~ msgid ""
#~ "[应用使用教程](https://db-"
#~ "gpt.readthedocs.io/en/latest/getting_started/application/chatdb/chatdb.html)."
#~ msgstr ""

6
pilot/configs/model_config.py
View File

@@ -41,6 +41,12 @@ LLM_MODEL_CONFIG = {
"m3e-base": os.path.join(MODEL_PATH, "m3e-base"),
# https://huggingface.co/moka-ai/m3e-base
"m3e-large": os.path.join(MODEL_PATH, "m3e-large"),
# https://huggingface.co/BAAI/bge-large-en
"bge-large-en": os.path.join(MODEL_PATH, "bge-large-en"),
"bge-base-en": os.path.join(MODEL_PATH, "bge-base-en"),
# https://huggingface.co/BAAI/bge-large-zh
"bge-large-zh": os.path.join(MODEL_PATH, "bge-large-zh"),
"bge-base-zh": os.path.join(MODEL_PATH, "bge-base-zh"),
"sentence-transforms": os.path.join(MODEL_PATH, "all-MiniLM-L6-v2"),
"codegen2-1b": os.path.join(MODEL_PATH, "codegen2-1B"),
"codet5p-2b": os.path.join(MODEL_PATH, "codet5p-2b"),

2
setup.py
View File

@@ -347,7 +347,7 @@ init_install_requires()
setuptools.setup(
name="db-gpt",
packages=find_packages(exclude=("tests", "*.tests", "*.tests.*", "examples")),
version="0.3.5",
version="0.3.6",
author="csunny",
author_email="cfqcsunny@gmail.com",
description="DB-GPT is an experimental open-source project that uses localized GPT large models to interact with your data and environment."