Merge branch 'main' into TY_08_DEV_NEW

# Conflicts:
#	requirements.txt
This commit is contained in:
yhjun1026
2023-08-18 10:44:36 +08:00
82 changed files with 4473 additions and 521 deletions

View File

@@ -22,7 +22,7 @@ WEB_SERVER_PORT=7860
#** LLM MODELS **#
#*******************************************************************#
# LLM_MODEL, see /pilot/configs/model_config.LLM_MODEL_CONFIG
LLM_MODEL=vicuna-13b
LLM_MODEL=vicuna-13b-v1.5
MODEL_SERVER=http://127.0.0.1:8000
LIMIT_MODEL_CONCURRENCY=5
MAX_POSITION_EMBEDDINGS=4096
@@ -37,6 +37,14 @@ QUANTIZE_8bit=True
## "PROXYLLM_BACKEND" is the model they actually deploy. We can use "PROXYLLM_BACKEND" to load the prompt of the corresponding scene.
# PROXYLLM_BACKEND=
### You can configure parameters for a specific model with {model name}_{config key}=xxx
### See /pilot/model/parameter.py
## prompt template for current model
# llama_cpp_prompt_template=vicuna_v1.1
## llama-2-70b must be 8
# llama_cpp_n_gqa=8
## Model path
# llama_cpp_model_path=/data/models/TheBloke/vicuna-7B-v1.5-GGML/vicuna-7b-v1.5.ggmlv3.q4_0.bin
#*******************************************************************#
#** EMBEDDING SETTINGS **#
@@ -65,18 +73,6 @@ LOCAL_DB_TYPE=sqlite
# LOCAL_DB_HOST=127.0.0.1
# LOCAL_DB_PORT=3306
### MILVUS
## MILVUS_ADDR - Milvus remote address (e.g. localhost:19530)
## MILVUS_USERNAME - username for your Milvus database
## MILVUS_PASSWORD - password for your Milvus database
## MILVUS_SECURE - True to enable TLS. (Default: False)
## Setting MILVUS_ADDR to a `https://` URL will override this setting.
## MILVUS_COLLECTION - Milvus collection, change it if you want to start a new memory and retain the old memory.
# MILVUS_ADDR=localhost:19530
# MILVUS_USERNAME=
# MILVUS_PASSWORD=
# MILVUS_SECURE=
# MILVUS_COLLECTION=dbgpt
#*******************************************************************#
#** COMMANDS **#

View File

@@ -145,19 +145,19 @@ The core capabilities mainly consist of the following parts:
## Image
🌐 [AutoDL Image](https://www.codewithgpu.com/i/csunny/DB-GPT/dbgpt-0.3.1-v2)
## Install
[Quickstart](https://db-gpt.readthedocs.io/en/latest/getting_started/getting_started.html)
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black)
![macOS](https://img.shields.io/badge/mac%20os-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0)
[**Quickstart**](https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html)
### Language Switching
In the .env configuration file, modify the LANGUAGE parameter to switch to different languages. The default is English (Chinese: zh, English: en, other languages to be added later).
### Platform Deployment
- autodl
[autodl image](https://www.codewithgpu.com/i/csunny/DB-GPT/csunny-db-gpt). You can refer to the image instructions to build from scratch, or use `docker pull` to obtain the shared image, follow the instructions in the document to operate. If you have any questions, please leave a comment.
## Usage Instructions
- [Multi LLMs Usage](https://db-gpt.readthedocs.io/en/latest/modules/llms.html)
- [Create your own knowledge repository](https://db-gpt.readthedocs.io/en/latest/modules/knowledge.html)
If nltk-related errors occur during the use of the knowledge base, you need to install the nltk toolkit. For more details, please refer to: [nltk documents](https://www.nltk.org/data.html)
Run the Python interpreter and type the commands:

View File

@@ -148,25 +148,29 @@ DB-GPT基于 [FastChat](https://github.com/lm-sys/FastChat) 构建大模型运
- [DB-GPT-Web](https://github.com/csunny/DB-GPT-Web) 多端交互前端界面
## Image
🌐 [AutoDL镜像](https://www.codewithgpu.com/i/csunny/DB-GPT/dbgpt-0.3.1-v2)
🌐 [阿里云镜像](http://dbgpt.site/web/#/p/dc4bb97e0bc15302dbf3a5d5571142dd)
## 安装
[快速开始](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/getting_started/getting_started.html)
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black)
![macOS](https://img.shields.io/badge/mac%20os-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0)
[**快速开始
**](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/getting_started/install/deploy/deploy.html)
### 多语言切换
在.env 配置文件当中修改LANGUAGE参数来切换使用不同的语言默认是英文(中文zh, 英文en, 其他语言待补充)
### 平台部署
- autodl
[autodl镜像](https://www.codewithgpu.com/i/csunny/DB-GPT/csunny-db-gpt),从头搭建可参考镜像说明,或通过`docker pull`获取共享镜像,按照文档中的说明操作即可,若有问题,欢迎评论。
在.env 配置文件当中修改LANGUAGE参数来切换使用不同的语言默认是英文(中文zh, 英文en, 其他语言待补充)
## 使用说明
### 多模型使用
[使用指南](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/modules/llms.html)
[使用指南](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/modules/llms.html)
如果在使用知识库时遇到与nltk相关的错误您需要安装nltk工具包。更多详情请参见[nltk文档](https://www.nltk.org/data.html)
Run the Python interpreter and type the commands:

BIN
assets/DB-GPT-Product.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 210 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 301 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 201 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 263 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 514 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 153 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 131 KiB

BIN
assets/chat_data/img.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 140 KiB

BIN
assets/kbqa/begin_chat.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 189 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 52 KiB

BIN
assets/kbqa/document.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 95 KiB

BIN
assets/kbqa/embedding.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 81 KiB

BIN
assets/kbqa/prompt.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 175 KiB

BIN
assets/kbqa/tasks.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 87 KiB

BIN
assets/kbqa/upload.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

BIN
assets/llm/dbgpt_llm.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 260 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 259 KiB

After

Width:  |  Height:  |  Size: 136 KiB

View File

@@ -11,38 +11,48 @@ ARG LANGUAGE="en"
ARG PIP_INDEX_URL="https://pypi.org/simple"
ENV PIP_INDEX_URL=$PIP_INDEX_URL
# COPY only requirements.txt first to leverage Docker cache
COPY ./requirements.txt /tmp/requirements.txt
WORKDIR /app
RUN pip3 install --upgrade pip -i $PIP_INDEX_URL \
&& (if [ "${BUILD_LOCAL_CODE}" = "false" ]; \
# if not build local code, clone latest code from git, and rename to /app, TODO: download by version, like: https://github.com/eosphoros-ai/DB-GPT/archive/refs/tags/$DBGPT_VERSION.zip
then git clone https://github.com/eosphoros-ai/DB-GPT.git /app \
&& cp /app/requirements.txt /tmp/requirements.txt; \
fi;) \
&& pip3 install -r /tmp/requirements.txt -i $PIP_INDEX_URL --no-cache-dir \
&& rm /tmp/requirements.txt
RUN (if [ "${LANGUAGE}" = "zh" ]; \
&& (if [ "${LANGUAGE}" = "zh" ]; \
# language is zh, download zh_core_web_sm from github
then wget https://github.com/explosion/spacy-models/releases/download/zh_core_web_sm-3.5.0/zh_core_web_sm-3.5.0-py3-none-any.whl -O /tmp/zh_core_web_sm-3.5.0-py3-none-any.whl \
&& pip3 install /tmp/zh_core_web_sm-3.5.0-py3-none-any.whl -i $PIP_INDEX_URL \
&& rm /tmp/zh_core_web_sm-3.5.0-py3-none-any.whl; \
# not zh, download directly
else python3 -m spacy download zh_core_web_sm; \
fi;) \
fi;)
RUN mkdir -p /app
# COPY only requirements.txt first to leverage Docker cache
COPY ./requirements.txt /app/requirements.txt
COPY ./setup.py /app/setup.py
COPY ./README.md /app/README.md
WORKDIR /app
# RUN pip3 install --upgrade pip -i $PIP_INDEX_URL \
# && (if [ "${BUILD_LOCAL_CODE}" = "false" ]; \
# # if not build local code, clone latest code from git, and rename to /app, TODO: download by version, like: https://github.com/eosphoros-ai/DB-GPT/archive/refs/tags/$DBGPT_VERSION.zip
# then git clone https://github.com/eosphoros-ai/DB-GPT.git /app \
# && cp /app/requirements.txt /tmp/requirements.txt; \
# fi;) \
# && pip3 install -r /tmp/requirements.txt -i $PIP_INDEX_URL --no-cache-dir \
# && rm /tmp/requirements.txt
RUN pip3 install -i $PIP_INDEX_URL .
# ENV CMAKE_ARGS="-DLLAMA_CUBLAS=ON -DLLAMA_AVX2=OFF -DLLAMA_F16C=OFF -DLLAMA_FMA=OFF"
# ENV FORCE_CMAKE=1
RUN pip3 install -i $PIP_INDEX_URL .[llama_cpp] \
&& rm -rf `pip3 cache dir`
ARG BUILD_LOCAL_CODE="false"
# COPY the rest of the app
COPY . /tmp/app
COPY . /app
# TODONeed to find a better way to determine whether to build docker image with local code.
RUN (if [ "${BUILD_LOCAL_CODE}" = "true" ]; \
then mv /tmp/app / && rm -rf /app/logs && rm -rf /app/pilot/data && rm -rf /app/pilot/message; \
else rm -rf /tmp/app; \
then rm -rf /app/logs && rm -rf /app/pilot/data && rm -rf /app/pilot/message; \
fi;)
ARG LOAD_EXAMPLES="true"

View File

@@ -0,0 +1,20 @@
Applications
==================================
DB-GPT product is a Web application that you can chat database, chat knowledge, text2dashboard.
.. image:: https://github.com/eosphoros-ai/DB-GPT/assets/13723926/f6564da2-bed3-43ad-9659-d00e0eeb255b
- Chat DB
- Chat Knowledge
- Dashboard
- Plugins
.. toctree::
:maxdepth: 2
:caption: Application
:name: chatdb
:hidden:
./application/chatdb/chatdb.md
./application/kbqa/kbqa.md

View File

@@ -0,0 +1,19 @@
ChatData & ChatDB
==================================
ChatData generates SQL from natural language and executes it. ChatDB involves conversing with metadata from the Database, including metadata about databases, tables, and fields.![db plugins demonstration](../../../../assets/chat_data/chat_data.jpg)
### 1.Choose Datasource
If you are using DB-GPT for the first time, you need to add a data source and set the relevant connection information for the data source.
#### 1.1 Datasource management
![db plugins demonstration](../../../../assets/chat_data/db_entry.png)
#### 1.2 Connection management
![db plugins demonstration](../../../../assets/chat_data/db_connect.png)
#### 1.3 Add Datasource
![db plugins demonstration](../../../../assets/chat_data/add_datasource.png)
### 2.ChatData
After successfully setting up the data source, you can start conversing with the database. You can ask it to generate SQL for you or inquire about relevant information on the database's metadata.
![db plugins demonstration](../../../../assets/chat_data/chatdata_eg.png)
### 3.ChatDB
![db plugins demonstration](../../../../assets/chat_data/chatdb_eg.png)

View File

@@ -0,0 +1,80 @@
KBQA
==================================
DB-GPT supports a knowledge question-answering module, which aims to create an intelligent expert in the field of databases and provide professional knowledge-based answers to database practitioners.
![chat_knowledge](../../../../assets/chat_knowledge.png)
## KBQA abilities
```{admonition} KBQA abilities
* Knowledge Space.
* Multi Source Knowledge Source Embedding.
* Embedding Argument Adjust
* Chat Knowledge
* Multi Vector DB
```
## Steps to KBQA In DB-GPT
#### 1.Create Knowledge Space
If you are using Knowledge Space for the first time, you need to create a Knowledge Space and set your name, owner, description.
![create_space](../../../../assets/kbqa/create_space.png)
#### 2.Create Knowledge Document
DB-GPT now support Multi Knowledge Source, including Text, WebUrl, and Document(PDF, Markdown, Word, PPT, HTML and CSV).
After successfully uploading a document for translation, the backend system will automatically read and split and chunk the document, and then import it into the vector database. Alternatively, you can manually synchronize the document. You can also click on details to view the specific document slicing content.
##### 2.1 Choose Knowledge Type:
![document](../../../../assets/kbqa/document.jpg)
##### 2.2 Upload Document:
![upload](../../../../assets/kbqa/upload.jpg)
#### 3.Chat With Knowledge
![upload](../../../../assets/kbqa/begin_chat.jpg)
#### 4.Adjust Space arguments
Each knowledge space supports argument customization, including the relevant arguments for vector retrieval and the arguments for knowledge question-answering prompts.
##### 4.1 Embedding
Embedding Argument
![upload](../../../../assets/kbqa/embedding.png)
```{tip} Embedding arguments
* topk:the top k vectors based on similarity score.
* recall_score:set a threshold score for the retrieval of similar vectors.
* recall_type:recall type.
* model:A model used to create vector representations of text or other data.
* chunk_size:The size of the data chunks used in processing.
* chunk_overlap:The amount of overlap between adjacent data chunks.
```
##### 4.2 Prompt
Prompt Argument
![upload](../../../../assets/kbqa/prompt.png)
```{tip} Prompt arguments
* scene:A contextual parameter used to define the setting or environment in which the prompt is being used.
* template:A pre-defined structure or format for the prompt, which can help ensure that the AI system generates responses that are consistent with the desired style or tone.
* max_token:The maximum number of tokens or words allowed in a prompt.
```
#### 5.Change Vector Database
```{admonition} Vector Store SETTINGS
#### Chroma
* VECTOR_STORE_TYPE=Chroma
#### MILVUS
* VECTOR_STORE_TYPE=Milvus
* MILVUS_URL=127.0.0.1
* MILVUS_PORT=19530
* MILVUS_USERNAME
* MILVUS_PASSWORD
* MILVUS_SECURE=
#### WEAVIATE
* WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
```

View File

@@ -0,0 +1,22 @@
FAQ
==================================
DB-GPT product is a Web application that you can chat database, chat knowledge, text2dashboard.
.. image:: ./assets/DB-GPT-Product.jpg
- deploy
- llm
- chatdb
- kbqa
.. toctree::
:maxdepth: 2
:caption: Deloy
:name: deploy
:hidden:
./faq/deploy/deploy_faq.md
./faq/llm/llm_faq.md
./faq/chatdb/chatdb_faq.md
./faq/kbqa/kbqa_faq.md

View File

@@ -0,0 +1,10 @@
Chat DB FAQ
==================================
##### Q1: What difference between ChatData and ChatDB
ChatData generates SQL from natural language and executes it. ChatDB involves conversing with metadata from the Database, including metadata about databases, tables, and fields.
##### Q2: The suitable llm model currently supported for text-to-SQL is?
Now vicunna-13b-1.5 and llama2-70b is more suitable for text-to-SQL.
##### Q3: How to fine-tune Text-to-SQL in DB-GPT
there is another github project for Text-to-SQL fine-tune (https://github.com/eosphoros-ai/DB-GPT-Hub)

View File

@@ -0,0 +1,33 @@
Installation FAQ
==================================
##### Q1: execute `pip install -r requirements.txt` 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
```
or
```bash
# tsinghua
$ pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
```
or
```bash
# aliyun
$ pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/
```
##### Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to open database file
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.

View File

@@ -0,0 +1,58 @@
KBQA FAQ
==================================
##### Q1: text2vec-large-chinese not found
make sure you have download text2vec-large-chinese embedding model in right way
```tip
centos:yum install git-lfs
ubuntu:apt-get install git-lfs -y
macos:brew install git-lfs
```
```bash
cd models
git lfs clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
```
##### Q2:How to change Vector DB Type in DB-GPT.
Update .env file and set VECTOR_STORE_TYPE.
DB-GPT currently support Chroma(Default), Milvus(>2.1), Weaviate vector database.
If you want to change vector db, Update your .env, set your vector store type, VECTOR_STORE_TYPE=Chroma (now only support Chroma and Milvus(>2.1), if you set Milvus, please set MILVUS_URL and MILVUS_PORT)
If you want to support more vector db, you can integrate yourself.[how to integrate](https://db-gpt.readthedocs.io/en/latest/modules/vector.html)
```commandline
#*******************************************************************#
#** VECTOR STORE SETTINGS **#
#*******************************************************************#
VECTOR_STORE_TYPE=Chroma
#MILVUS_URL=127.0.0.1
#MILVUS_PORT=19530
#MILVUS_USERNAME
#MILVUS_PASSWORD
#MILVUS_SECURE=
#WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
```
##### Q3:When I use vicuna-13b, found some illegal character like this.
<p align="left">
<img src="https://github.com/eosphoros-ai/DB-GPT/assets/13723926/088d1967-88e3-4f72-9ad7-6c4307baa2f8" width="800px" />
</p>
Set KNOWLEDGE_SEARCH_TOP_SIZE smaller or set KNOWLEDGE_CHUNK_SIZE smaller, and reboot server.
##### Q4:space add error (pymysql.err.OperationalError) (1054, "Unknown column 'knowledge_space.context' in 'field list'")
1.shutdown dbgpt_server(ctrl c)
2.add column context for table knowledge_space
```commandline
mysql -h127.0.0.1 -uroot -paa12345678
```
3.execute sql ddl
```commandline
mysql> use knowledge_management;
mysql> ALTER TABLE knowledge_space ADD COLUMN context TEXT COMMENT "arguments context";
```
4.restart dbgpt serve

View File

@@ -0,0 +1,40 @@
LLM USE FAQ
==================================
##### Q1:how to use openai chatgpt service
change your LLM_MODEL
````shell
LLM_MODEL=proxyllm
````
set your OPENAPI KEY
````shell
PROXY_API_KEY={your-openai-sk}
PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
````
make sure your openapi API_KEY is available
##### Q2 how to use MultiGPUs
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.
##### Q3 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).

View File

@@ -0,0 +1,25 @@
Install
==================================
DB-GPT product is a Web application that you can chat database, chat knowledge, text2dashboard.
.. image:: ./assets/DB-GPT-Product.jpg
- deploy
- docker
- docker_compose
- environment
- deploy_faq
.. toctree::
:maxdepth: 2
:caption: Install
:name: deploy
:hidden:
./install/deploy/deploy.md
./install/docker/docker.md
./install/docker_compose/docker_compose.md
./install/llm/llm.rst
./install/environment/environment.md
./install/faq/deploy_faq.md

View File

@@ -0,0 +1,146 @@
# Installation From Source
This tutorial gives you a quick walkthrough about use DB-GPT with you environment and data.
## Installation
To get started, install DB-GPT with the following steps.
### 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:
| 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 |
| T4 | 16 GB | Conversation inference possible, noticeable stutter |
if your VRAM Size is not enough, DB-GPT supported 8-bit quantization and 4-bit quantization.
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 |
### 2. Install
```bash
git clone https://github.com/eosphoros-ai/DB-GPT.git
```
We use Sqlite as default database, so there is no need for database 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.
[How to install Miniconda](https://docs.conda.io/en/latest/miniconda.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
```bash
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
```{tip}
Notice make sure you have install git-lfs
centos:yum install git-lfs
ubuntu:app-get install git-lfs
macos:brew install git-lfs
```
```bash
cd DB-GPT
mkdir models and cd models
#### llm model
git clone https://huggingface.co/lmsys/vicuna-13b-v1.5
or
git clone https://huggingface.co/THUDM/chatglm2-6b
#### embedding model
git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
or
git clone https://huggingface.co/moka-ai/m3e-large
```
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
if you want to use openai llm service, see [LLM Use FAQ](https://db-gpt.readthedocs.io/en/latest/getting_started/faq/llm/llm_faq.html)
```{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
1.Run db-gpt server
```bash
$ python pilot/server/dbgpt_server.py
```
Open http://localhost:5000 with your browser to see the product.
```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_SERVEReg: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
```
### 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.
### 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).

View File

@@ -0,0 +1,87 @@
Docker Install
==================================
### Docker (Experimental)
#### 1. Building Docker image
```bash
$ bash docker/build_all_images.sh
```
Review images by listing them:
```bash
$ docker images|grep db-gpt
```
Output should look something like the following:
```
db-gpt-allinone latest e1ffd20b85ac 45 minutes ago 14.5GB
db-gpt latest e36fb0cca5d9 3 hours ago 14GB
```
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.
#### 2. Run all in one docker container
**Run with local model**
```bash
$ docker run --gpus "device=0" -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 db-gpt-allinone \
db-gpt-allinone
```
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 db-gpt-allinone -f
```
**Run with openai interface**
```bash
$ PROXY_API_KEY="You api key"
$ PROXY_SERVER_URL="https://api.openai.com/v1/chat/completions"
$ docker run --gpus "device=0" -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 db-gpt-allinone \
db-gpt-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.
Open http://localhost:5000 with your browser to see the product.

View File

@@ -0,0 +1,26 @@
Docker Compose
==================================
#### 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.

View File

@@ -0,0 +1,122 @@
Environment Parameter
==================================
```{admonition} LLM MODEL Config
LLM Model Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG
* LLM_MODEL=vicuna-13b
MODEL_SERVER_ADDRESS
* MODEL_SERVER=http://127.0.0.1:8000
LIMIT_MODEL_CONCURRENCY
* LIMIT_MODEL_CONCURRENCY=5
MAX_POSITION_EMBEDDINGS
* MAX_POSITION_EMBEDDINGS=4096
QUANTIZE_QLORA
* QUANTIZE_QLORA=True
QUANTIZE_8bit
* QUANTIZE_8bit=True
```
```{admonition} LLM PROXY Settings
OPENAI Key
* PROXY_API_KEY={your-openai-sk}
* PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
from https://bard.google.com/ f12-> application-> __Secure-1PSID
* BARD_PROXY_API_KEY={your-bard-token}
```
```{admonition} DATABASE SETTINGS
### SQLite database (Current default database)
* LOCAL_DB_PATH=data/default_sqlite.db
* LOCAL_DB_TYPE=sqlite # Database Type default:sqlite
### MYSQL database
* LOCAL_DB_TYPE=mysql
* LOCAL_DB_USER=root
* LOCAL_DB_PASSWORD=aa12345678
* LOCAL_DB_HOST=127.0.0.1
* LOCAL_DB_PORT=3306
```
```{admonition} EMBEDDING SETTINGS
EMBEDDING MODEL Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG
* EMBEDDING_MODEL=text2vec
Embedding Chunk size, default 500
* KNOWLEDGE_CHUNK_SIZE=500
Embedding Chunk Overlap, default 100
* KNOWLEDGE_CHUNK_OVERLAP=100
embeding recall top k,5
* KNOWLEDGE_SEARCH_TOP_SIZE=5
embeding recall max token ,2000
* KNOWLEDGE_SEARCH_MAX_TOKEN=5
```
```{admonition} Vector Store SETTINGS
#### Chroma
* VECTOR_STORE_TYPE=Chroma
#### MILVUS
* VECTOR_STORE_TYPE=Milvus
* MILVUS_URL=127.0.0.1
* MILVUS_PORT=19530
* MILVUS_USERNAME
* MILVUS_PASSWORD
* MILVUS_SECURE=
#### WEAVIATE
* VECTOR_STORE_TYPE=Weaviate
* WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
```
```{admonition} Vector Store SETTINGS
#### Chroma
* VECTOR_STORE_TYPE=Chroma
#### MILVUS
* VECTOR_STORE_TYPE=Milvus
* MILVUS_URL=127.0.0.1
* MILVUS_PORT=19530
* MILVUS_USERNAME
* MILVUS_PASSWORD
* MILVUS_SECURE=
#### WEAVIATE
* WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
```
```{admonition} Multi-GPU Setting
See https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/
If CUDA_VISIBLE_DEVICES is not configured, all available gpus will be used
* CUDA_VISIBLE_DEVICES=0
Optionally, you can also specify the gpu ID to use before the starting command
* CUDA_VISIBLE_DEVICES=3,4,5,6
You can configure the maximum memory used by each GPU.
* MAX_GPU_MEMORY=16Gib
```
```{admonition} Other Setting
#### Language Settings(influence prompt language)
* LANGUAGE=en
* LANGUAGE=zh
```

View File

@@ -0,0 +1,80 @@
### 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).
## Running llama.cpp
### Preparing Model Files
To use llama.cpp, you need to prepare a ggml format model file, and there are two common ways to obtain it, you can choose either:
1. Download a pre-converted model file.
Suppose you want to use [Vicuna 7B v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5), you can download the file already converted from [TheBloke/vicuna-7B-v1.5-GGML](https://huggingface.co/TheBloke/vicuna-7B-v1.5-GGML), only one file is needed. Download it to the `models` directory and rename it to `ggml-model-q4_0.bin`.
```bash
wget https://huggingface.co/TheBloke/vicuna-7B-v1.5-GGML/resolve/main/vicuna-7b-v1.5.ggmlv3.q4_K_M.bin -O models/ggml-model-q4_0.bin
```
2. Convert It Yourself
You can convert the model file yourself according to the instructions in [llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp#prepare-data--run), and put the converted file in the models directory and rename it to `ggml-model-q4_0.bin`.
### Installing Dependencies
llama.cpp is an optional dependency in DB-GPT, and you can manually install it using the following command:
```bash
pip install -e ".[llama_cpp]"
```
### Modifying the Configuration File
Next, you can directly modify your `.env` file to enable llama.cpp.
```env
LLM_MODEL=llama-cpp
llama_cpp_prompt_template=vicuna_v1.1
```
Then you can run it according to [Run](https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run).
### More Configurations
In DB-GPT, the model configuration can be done through `{model name}_{config key}`.
| Environment Variable Key | default | Prompt Template Name|
|----------|-----------| ----------- |
| llama_cpp_prompt_template | None | Prompt template name, now support: `zero_shot, vicuna_v1.1, llama-2,baichuan-chat`, If None, the prompt template is automatically determined from model path。 |
| llama_cpp_model_path | None | Model path |
| llama_cpp_n_gpu_layers | 1000000000 |Number of layers to offload to the GPU, Set this to 1000000000 to offload all layers to the GPU. If your GPU VRAM is not enough, you can set a low number, eg: `10` |
| llama_cpp_n_threads | None | Number of threads to use. If None, the number of threads is automatically determined |
| llama_cpp_n_batch | 512 | Maximum number of prompt tokens to batch together when calling llama_eval |
| llama_cpp_n_gqa | None | Grouped-query attention. Must be 8 for llama-2 70b.|
| llama_cpp_rms_norm_eps | 5e-06 | 5e-6 is a good value for llama-2 models.|
| llama_cpp_cache_capacity | None | Maximum cache capacity. Examples: 2000MiB, 2GiB |
| llama_cpp_prefer_cpu | False | If a GPU is available, it will be preferred by default, unless prefer_cpu=False is configured. |
## GPU Acceleration
GPU acceleration is supported by default. If you encounter any issues, you can uninstall the dependent packages with the following command:
```bash
pip uninstall -y llama-cpp-python llama_cpp_python_cuda
```
Then install `llama-cpp-python` according to the instructions in [llama-cpp-python](https://github.com/abetlen/llama-cpp-python/blob/main/README.md).
### Mac Usage
Special attention, if you are using Apple Silicon (M1) Mac, it is highly recommended to install arm64 architecture python support, for example:
```bash
wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-MacOSX-arm64.sh
bash Miniforge3-MacOSX-arm64.sh
```
### Windows Usage
The use under the Windows platform has not been rigorously tested and verified, and you are welcome to use it. If you have any problems, you can create an [issue](https://github.com/eosphoros-ai/DB-GPT/issues) or [contact us](https://github.com/eosphoros-ai/DB-GPT/tree/main#contact-information) directly.

View File

@@ -0,0 +1,30 @@
LLM Usage
==================================
DB-GPT provides a management and deployment solution for multiple models. This chapter mainly discusses how to deploy different models.
.. image:: https://github.com/eosphoros-ai/DB-GPT/assets/13723926/a0d0840f-570a-4409-bb7d-bec6535a5f62
Multi LLMs Support, Supports multiple large language models, currently supporting
- 🔥 Vicuna-v1.5(7b,13b)
- 🔥 llama-2(7b,13b,70b)
- WizardLM-v1.2(13b)
- Vicuna (7b,13b)
- ChatGLM-6b (int4,int8)
- ChatGLM2-6b (int4,int8)
- guanaco(7b,13b,33b)
- Gorilla(7b,13b)
- Baichuan(7b,13b)
- OpenAI
- llama_cpp
- quantization
.. toctree::
:maxdepth: 2
:caption: LLM Usage
:name: llama_cpp
:hidden:
./llama/llama_cpp.md
./quantization/quantization.md

View File

@@ -0,0 +1,2 @@
quantization
==================================

View File

@@ -1,4 +1,4 @@
# Installation
# Python SDK
DB-GPT provides a third-party Python API package that you can integrate into your own code.
### Installation from Pip

View File

@@ -6,19 +6,18 @@ This is a collection of DB-GPT tutorials on Medium.
DB-GPT is divided into several functions, including chat with knowledge base, execute SQL, chat with database, and execute plugins.
### Introduction
#### youtube
[What is DB-GPT](https://www.youtube.com/watch?v=QszhVJerc0I)
### Knowledge
[How to deploy DB-GPT step by step](https://www.youtube.com/watch?v=OJGU4fQCqPs)
[How to Create your own knowledge repository](https://db-gpt.readthedocs.io/en/latest/modules/knownledge.html)
![Add new Knowledge demonstration](../../assets/new_knownledge.gif)
#### bilibili
[What is DB-GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?spm_id_from=333.788&vd_source=7792e22c03b7da3c556a450eb42c8a0f)
[How to deploy DB-GPT step by step](https://www.bilibili.com/video/BV1mu411Y7ve/?spm_id_from=pageDriver&vd_source=7792e22c03b7da3c556a450eb42c8a0f)
### SQL Generation
![sql generation demonstration](../../assets/demo_en.gif)
### SQL Execute
![sql execute demonstration](../../assets/auto_sql_en.gif)
### Plugins
![db plugins demonstration](../../assets/dashboard.png)

View File

@@ -47,10 +47,12 @@ Getting Started
:caption: Getting Started
:hidden:
getting_started/getting_started.md
getting_started/install.rst
getting_started/application.md
getting_started/installation.md
getting_started/concepts.md
getting_started/tutorials.md
getting_started/faq.rst
Modules
@@ -130,32 +132,6 @@ Reference
./reference.md
FAQ
-----------
| DB-GPT FAQ.
.. toctree::
:maxdepth: 1
:caption: FAQ
:name: FAQ
:hidden:
./faq.md
Ecosystem
----------
| Guides for how other companies/products can be used with DB-GPT
.. toctree::
:maxdepth: 1
:glob:
:caption: Ecosystem
:name: ecosystem
:hidden
./ecosystem.md
Resources
----------

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: 2023-08-10 16:40+0800\n"
"POT-Creation-Date: 2023-08-17 21:23+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,85 +19,84 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../faq.md:1 c4b5b298c447462ba7aaffd954549def
#: ../../faq.md:1 a39cbc25271841d79095c1557a817a76
msgid "FAQ"
msgstr "FAQ"
msgstr ""
#: ../../faq.md:2 533e388b78594244aa0acbf2b0263f60
#: ../../faq.md:2 b08ce199a11b4d309142866a637bc3d0
msgid "Q1: text2vec-large-chinese not found"
msgstr "Q1: text2vec-large-chinese not found"
msgstr ""
#: ../../faq.md:4 e1c7e28c60f24f7a983f30ee43bad32e
#: ../../faq.md:4 754a61fa05a846f4847bd988c4049ceb
msgid ""
"A1: make sure you have download text2vec-large-chinese embedding model in"
" right way"
msgstr "按照正确的姿势下载text2vec-large-chinese模型"
msgstr ""
#: ../../faq.md:16 7cbfd6629267423a879735dd0dbba24e
#: ../../faq.md:16 5a3d32eacdd94f59bb4039c3d6380fc9
msgid ""
"Q2: execute `pip install -r requirements.txt` error, found some package "
"cannot find correct version."
msgstr "执行`pip install -r requirements.txt`报错"
msgstr ""
#: ../../faq.md:19 a2bedf7cf2984d35bc9e3edffd9cb991
#: ../../faq.md:19 54b322726a074d6d9c1a957310774aba
msgid "A2: change the pip source."
msgstr "修改pip源"
msgstr ""
#: ../../faq.md:26 ../../faq.md:33 307385dc581841148bad0dfa95541722
#: 55a9cd0665e74b47bac71e652a80c8bd
#: ../../faq.md:26 ../../faq.md:33 0c238f86900243e5b5e9a49e4ef37063
#: 245e48f636524172b1b9ba4144946007
msgid "or"
msgstr ""
msgstr ""
#: ../../faq.md:41 8ec34a9f22744313825bd53e90e86695
#: ../../faq.md:41 f2f7025f324c4065abf244a3adb4e4f6
msgid "Q3:Access denied for user 'root@localhost'(using password :NO)"
msgstr ""
msgstr ""
#: ../../faq.md:43 85d67326827145859f5af707c96c852f
#: ../../faq.md:43 f14fd1c2d2ed454491e0a876fd2971a4
msgid "A3: make sure you have installed mysql instance in right way"
msgstr "按照正确姿势安装mysql"
msgstr ""
#: ../../faq.md:45 c51cffb2777c49c6b15485e6151f8b70
#: ../../faq.md:45 6d499bfb6c0142ec838f68696f793c3d
msgid "Docker:"
msgstr "Docker:"
msgstr ""
#: ../../faq.md:49 09f16d57dbeb4f34a1274b2ac52aacf5
#: ../../faq.md:49 71137fe8a30d42e7943dd2a4402b2094
msgid "Normal: [download mysql instance](https://dev.mysql.com/downloads/mysql/)"
msgstr "[download mysql instance](https://dev.mysql.com/downloads/mysql/)"
msgstr ""
#: ../../faq.md:52 ab730de8f02f4cb895510a52ca90c02f
#: ../../faq.md:52 ec5d5f79cbe54328902e6e9b820276e7
msgid "Q4:When I use openai(MODEL_SERVER=proxyllm) to chat"
msgstr "使用openai-chatgpt模型时(MODEL_SERVER=proxyllm)"
msgstr ""
#: ../../faq.md:57 8308cf21e0654e5798c9a2638b8565ec
#: ../../faq.md:58 d2cbee8bbfd54b4b853ccbdbf1c30c97
msgid "A4: make sure your openapi API_KEY is available"
msgstr "确认openapi API_KEY是否可用"
msgstr ""
#: ../../faq.md:59 ff6361a5438943c2b9e613aa9e2322bf
#: ../../faq.md:60 c506819975c841468af1899730df3ed1
msgid "Q5:When I Chat Data and Chat Meta Data, I found the error"
msgstr "Chat Data and Chat Meta Data报如下错"
#: ../../faq.md:64 1a89acc3bf074b77b9e44d20f9b9c3cb
#: ../../faq.md:67 af52123acad74c28a50f93d53da6afa9
msgid "A5: you have not create your database and table"
msgstr "需要创建自己的数据库"
#: ../../faq.md:65 e7d63e2aa0d24c5d90dd1865753c7d52
#: ../../faq.md:68 05bf6d858df44157bfb5480f9e8759fb
msgid "1.create your database."
msgstr "1.先创建数据库"
#: ../../faq.md:71 8b0de08106a144b98538b12bc671cbb2
#: ../../faq.md:74 363d4fbb2a474c64a54c2659844596b5
msgid "2.create table {$your_table} and insert your data. eg:"
msgstr "然后创建数据表,模拟数据"
#: ../../faq.md:85 abb226843354448a925de4deb52db555
#: ../../faq.md:88 5f3a9b9d7e6f444a87deb17b5a1a45af
msgid "Q6:How to change Vector DB Type in DB-GPT."
msgstr ""
#: ../../faq.md:87 cc80165e2f6b46a28e53359ea7b3e0af
#: ../../faq.md:90 ee1d4dfa813942e1a3d1219f21bc041f
msgid "A6: Update .env file and set VECTOR_STORE_TYPE."
msgstr ""
#: ../../faq.md:88 d30fa1e2fdd94e00a72ef247af41fb43
#, fuzzy
#: ../../faq.md:91 71e9e9905bdb46e1925f66a6c12a6afd
msgid ""
"DB-GPT currently support Chroma(Default), Milvus(>2.1), Weaviate vector "
"database. If you want to change vector db, Update your .env, set your "
@@ -106,48 +105,144 @@ msgid ""
"If you want to support more vector db, you can integrate yourself.[how to"
" integrate](https://db-gpt.readthedocs.io/en/latest/modules/vector.html)"
msgstr ""
"DB-GPT当前支持Chroma(默认),如果你想替换向量数据库,需要更新.env文件VECTOR_STORE_TYPE=Chroma (now"
" only support Chroma, Milvus Weaviate, if you set Milvus(>2.1), please "
"set MILVUS_URL and "
"MILVUS_PORT)。如果当前支持向量数据库无法满足你的需求,可以集成使用自己的向量数据库。[怎样集成](https://db-"
"gpt.readthedocs.io/en/latest/modules/vector.html)"
#: ../../faq.md:104 bed01b4f96e04f61aa536cf615254c87
#, fuzzy
#: ../../faq.md:107 d6c4ed8ff8244aa8aef6ea8d8f0a5555
msgid "Q7:When I use vicuna-13b, found some illegal character like this."
msgstr "使用vicuna-13b知识库问答出现乱码"
msgstr ""
#: ../../faq.md:109 1ea68292da6d46a89944212948d1719d
#, fuzzy
#: ../../faq.md:112 911a5051c37244e1b6ea9d3b1bd1fd97
msgid ""
"A7: set KNOWLEDGE_SEARCH_TOP_SIZE smaller or set KNOWLEDGE_CHUNK_SIZE "
"smaller, and reboot server."
msgstr "将KNOWLEDGE_SEARCH_TOP_SIZE和KNOWLEDGE_CHUNK_SIZE设置小点然后重启"
msgstr ""
#: ../../faq.md:111 256b58e3749a4a17acbc456c71581597
#: ../../faq.md:114 0566430bbc0541709ed60b81c7372175
msgid ""
"Q8:space add error (pymysql.err.OperationalError) (1054, \"Unknown column"
" 'knowledge_space.context' in 'field list'\")"
msgstr "Q8:space add error (pymysql.err.OperationalError) (1054, \"Unknown column"
" 'knowledge_space.context' in 'field list'\")"
msgstr ""
#: ../../faq.md:114 febe9ec0c51b4e10b3a2bb0aece94e7c
#: ../../faq.md:117 37419da934b44575bd39bcffffa81482
msgid "A8:"
msgstr "A8:"
msgstr ""
#: ../../faq.md:115 d713a368fe8147feb6db8f89938f3dcd
#: ../../faq.md:118 1c5f46dbccc342329b544ac174a79994
msgid "1.shutdown dbgpt_server(ctrl c)"
msgstr ""
#: ../../faq.md:117 4c6ad307caff4b57bb6c7085cc42fb64
#: ../../faq.md:120 35bb76e9d9ec4230a8fab9aed475a4d7
msgid "2.add column context for table knowledge_space"
msgstr "2.add column context for table knowledge_space"
msgstr ""
#: ../../faq.md:121 a3f955c090be4163bdb934eb32c25fd5
#: ../../faq.md:124 e198605e42d4452680359487abc349a3
msgid "3.execute sql ddl"
msgstr "3.执行 sql ddl"
msgstr ""
#: ../../faq.md:126 1861332d1c0342e2b968732fba55fa54
#: ../../faq.md:129 88495f3e66c448faab9f06c4c5cd27ef
msgid "4.restart dbgpt server"
msgstr "4.重启 dbgpt server"
msgstr ""
#~ msgid "FAQ"
#~ msgstr "FAQ"
#~ msgid "Q1: text2vec-large-chinese not found"
#~ msgstr "Q1: text2vec-large-chinese not found"
#~ msgid ""
#~ "A1: make sure you have download "
#~ "text2vec-large-chinese embedding model in"
#~ " right way"
#~ msgstr "按照正确的姿势下载text2vec-large-chinese模型"
#~ msgid ""
#~ "Q2: execute `pip install -r "
#~ "requirements.txt` error, found some package"
#~ " cannot find correct version."
#~ msgstr "执行`pip install -r requirements.txt`报错"
#~ msgid "A2: change the pip source."
#~ msgstr "修改pip源"
#~ msgid "or"
#~ msgstr "或"
#~ msgid "Q3:Access denied for user 'root@localhost'(using password :NO)"
#~ msgstr "或"
#~ msgid "A3: make sure you have installed mysql instance in right way"
#~ msgstr "按照正确姿势安装mysql"
#~ msgid "Docker:"
#~ msgstr "Docker:"
#~ msgid ""
#~ "Normal: [download mysql "
#~ "instance](https://dev.mysql.com/downloads/mysql/)"
#~ msgstr "[download mysql instance](https://dev.mysql.com/downloads/mysql/)"
#~ msgid "Q4:When I use openai(MODEL_SERVER=proxyllm) to chat"
#~ msgstr "使用openai-chatgpt模型时(MODEL_SERVER=proxyllm)"
#~ msgid "A4: make sure your openapi API_KEY is available"
#~ msgstr "确认openapi API_KEY是否可用"
#~ msgid "Q6:How to change Vector DB Type in DB-GPT."
#~ msgstr ""
#~ msgid "A6: Update .env file and set VECTOR_STORE_TYPE."
#~ msgstr ""
#~ msgid ""
#~ "DB-GPT currently support Chroma(Default), "
#~ "Milvus(>2.1), Weaviate vector database. If "
#~ "you want to change vector db, "
#~ "Update your .env, set your vector "
#~ "store type, VECTOR_STORE_TYPE=Chroma (now only"
#~ " support Chroma and Milvus(>2.1), if "
#~ "you set Milvus, please set MILVUS_URL"
#~ " and MILVUS_PORT) If you want to "
#~ "support more vector db, you can "
#~ "integrate yourself.[how to integrate](https://db-"
#~ "gpt.readthedocs.io/en/latest/modules/vector.html)"
#~ msgstr ""
#~ "DB-"
#~ "GPT当前支持Chroma(默认),如果你想替换向量数据库,需要更新.env文件VECTOR_STORE_TYPE=Chroma "
#~ "(now only support Chroma, Milvus "
#~ "Weaviate, if you set Milvus(>2.1), "
#~ "please set MILVUS_URL and "
#~ "MILVUS_PORT)。如果当前支持向量数据库无法满足你的需求,可以集成使用自己的向量数据库。[怎样集成](https://db-"
#~ "gpt.readthedocs.io/en/latest/modules/vector.html)"
#~ msgid "Q7:When I use vicuna-13b, found some illegal character like this."
#~ msgstr "使用vicuna-13b知识库问答出现乱码"
#~ msgid ""
#~ "A7: set KNOWLEDGE_SEARCH_TOP_SIZE smaller or"
#~ " set KNOWLEDGE_CHUNK_SIZE smaller, and "
#~ "reboot server."
#~ msgstr "将KNOWLEDGE_SEARCH_TOP_SIZE和KNOWLEDGE_CHUNK_SIZE设置小点然后重启"
#~ msgid ""
#~ "Q8:space add error (pymysql.err.OperationalError)"
#~ " (1054, \"Unknown column "
#~ "'knowledge_space.context' in 'field list'\")"
#~ msgstr ""
#~ "Q8:space add error (pymysql.err.OperationalError)"
#~ " (1054, \"Unknown column "
#~ "'knowledge_space.context' in 'field list'\")"
#~ msgid "A8:"
#~ msgstr "A8:"
#~ msgid "1.shutdown dbgpt_server(ctrl c)"
#~ msgstr ""
#~ msgid "2.add column context for table knowledge_space"
#~ msgstr "2.add column context for table knowledge_space"
#~ msgid "3.execute sql ddl"
#~ msgstr "3.执行 sql ddl"
#~ msgid "4.restart dbgpt server"
#~ msgstr "4.重启 dbgpt server"

View File

@@ -0,0 +1,51 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/application.rst:13
msgid "Application"
msgstr "应用"
#: ../../getting_started/application.rst:2 4de9609785bc406aa6f3965f057f90d8
msgid "Applications"
msgstr "应用"
#: ../../getting_started/application.rst:3 1ef4f6d81f7c4a2f9ee330fc890017dd
msgid ""
"DB-GPT product is a Web application that you can chat database, chat "
"knowledge, text2dashboard."
msgstr "DB-GPT是一个可以和数据库对话知识问答智能报表的web应用"
#: ../../getting_started/application.rst:8 0451376d435b47bfa7b3f81c87683610
msgid "Chat DB"
msgstr "Chat DB"
#: ../../getting_started/application.rst:9 4b1372dd4ae34881891c1dbcd83b92bf
msgid "Chat Knowledge"
msgstr "知识问答"
#: ../../getting_started/application.rst:10 d8807a357f1144ccba933338cd0f619a
msgid "Dashboard"
msgstr "Dashboard"
#: ../../getting_started/application.rst:11 f6a5806d4f0d4271bb0964935d9c2ff3
msgid "Plugins"
msgstr "Plugins"

View File

@@ -0,0 +1,118 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/application/chatdb/chatdb.md:1
#: e3984d7305214fc59fc356bd2e382543
msgid "ChatData & ChatDB"
msgstr "ChatData & ChatDB"
#: ../../getting_started/application/chatdb/chatdb.md:3
#: e74daab738984be990aaa21ab5af7046
msgid ""
"ChatData generates SQL from natural language and executes it. ChatDB "
"involves conversing with metadata from the Database, including metadata "
"about databases, tables, and fields.![db plugins "
"demonstration](../../../../assets/chat_data/chat_data.jpg)"
msgstr "ChatData 是会将自然语言生成SQL并将其执行。ChatDB是与Database里面的元数据包括库、表、字段的元数据进行对话.![db plugins "
"demonstration](../../../../assets/chat_data/chat_data.jpg)"
#: ../../getting_started/application/chatdb/chatdb.md:3
#: ../../getting_started/application/chatdb/chatdb.md:7
#: ../../getting_started/application/chatdb/chatdb.md:9
#: ../../getting_started/application/chatdb/chatdb.md:11
#: ../../getting_started/application/chatdb/chatdb.md:13
#: ../../getting_started/application/chatdb/chatdb.md:17
#: 109d4292c91f4ca5a6b682189f10620a 23b1865780a24ad2b765196faff15550
#: 3c87a8907e854e5d9a61b1ef658e5935 40eefe75a51e4444b1e4b67bdddc6da9
#: 73eee6111545418e8f9ae533a255d589 876ee62e4e404da6b5d6c5cba0259e5c
msgid "db plugins demonstration"
msgstr "db plugins demonstration"
#: ../../getting_started/application/chatdb/chatdb.md:4
#: a760078b833e434681da72c87342083f
msgid "1.Choose Datasource"
msgstr "1.Choose Datasource"
#: ../../getting_started/application/chatdb/chatdb.md:5
#: b68ac469c7d34026b1cb8b587a446737
msgid ""
"If you are using DB-GPT for the first time, you need to add a data source"
" and set the relevant connection information for the data source."
msgstr "如果你是第一次使用DB-GPT, 首先需要添加数据源,设置数据源的相关连接信息"
#: ../../getting_started/application/chatdb/chatdb.md:6
#: 8edecf9287ce4077a984617f0a06e30c
msgid "1.1 Datasource management"
msgstr "1.1 Datasource management"
#: ../../getting_started/application/chatdb/chatdb.md:7
#: af7b5d2f6c9b4666a3466fed05968258
msgid "![db plugins demonstration](../../../../assets/chat_data/db_entry.png)"
msgstr "![db plugins demonstration](../../../../assets/chat_data/db_entry.png)"
#: ../../getting_started/application/chatdb/chatdb.md:8
#: f7d49ffe448d49169713452f54b3437c
msgid "1.2 Connection management"
msgstr "1.2 Connection管理"
#: ../../getting_started/application/chatdb/chatdb.md:9
#: 109a8c9da05d4ec7a80ae1665b8d48bb
msgid "![db plugins demonstration](../../../../assets/chat_data/db_connect.png)"
msgstr "![db plugins demonstration](../../../../assets/chat_data/db_connect.png)"
#: ../../getting_started/application/chatdb/chatdb.md:10
#: ac283fff85bf41efbd2cfeeda5980f9a
msgid "1.3 Add Datasource"
msgstr "1.3 添加Datasource"
#: ../../getting_started/application/chatdb/chatdb.md:11
#: a25dec01f4824bfe88cc801c93bb3e3b
msgid ""
"![db plugins "
"demonstration](../../../../assets/chat_data/add_datasource.png)"
msgstr "![db plugins "
"demonstration](../../../../assets/chat_data/add_datasource.png)"
#: ../../getting_started/application/chatdb/chatdb.md:12
#: 4751d6d3744148cab130a901594f673a
msgid "2.ChatData"
msgstr "2.ChatData"
#: ../../getting_started/application/chatdb/chatdb.md:13
#: bad82b572ba34ffb8669f0f8ff9b0a05
msgid ""
"After successfully setting up the data source, you can start conversing "
"with the database. You can ask it to generate SQL for you or inquire "
"about relevant information on the database's metadata. ![db plugins "
"demonstration](../../../../assets/chat_data/chatdata_eg.png)"
msgstr "设置数据源成功后就可以和数据库进行对话了。你可以让它帮你生成SQL也可以和问它数据库元数据的相关信息。 ![db plugins "
"demonstration](../../../../assets/chat_data/chatdata_eg.png)"
#: ../../getting_started/application/chatdb/chatdb.md:16
#: 0bf9c5a2f3764b36abc82102c53d3cd4
msgid "3.ChatDB"
msgstr "3.ChatDB"
#: ../../getting_started/application/chatdb/chatdb.md:17
#: f06e7583c2484a959c1681b1db0acfaa
msgid "![db plugins demonstration](../../../../assets/chat_data/chatdb_eg.png)"
msgstr "![db plugins demonstration](../../../../assets/chat_data/chatdb_eg.png)"

View File

@@ -0,0 +1,21 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"

View File

@@ -0,0 +1,318 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/application/kbqa/kbqa.md:1
#: a06d9329c98f44ffaaf6fc09ba53d97e
msgid "KBQA"
msgstr ""
#: ../../getting_started/application/kbqa/kbqa.md:3
#: bb6943c115754b1fafb7467313100753
msgid ""
"DB-GPT supports a knowledge question-answering module, which aims to "
"create an intelligent expert in the field of databases and provide "
"professional knowledge-based answers to database practitioners."
msgstr " DB-GPT支持知识问答模块知识问答的初衷是打造DB领域的智能专家为数据库从业人员解决专业的知识问题回答"
#: ../../getting_started/application/kbqa/kbqa.md:5
#: a13ac963479e4d4fbcbcc4fec7863274
msgid "![chat_knowledge](../../../../assets/chat_knowledge.png)"
msgstr "![chat_knowledge](../../../../assets/chat_knowledge.png)"
#: ../../getting_started/application/kbqa/kbqa.md:5
#: f4db3a8d04634059a74be1b2b3c948ef
msgid "chat_knowledge"
msgstr "chat_knowledge"
#: ../../getting_started/application/kbqa/kbqa.md:7
#: ../../getting_started/application/kbqa/kbqa.md:10
#: 86856cce95c845eb83ed44d8713b0ef6 f787e9ad9f7444a5923fe3476ab4d287
msgid "KBQA abilities"
msgstr "KBQA现有能力"
#: ../../getting_started/application/kbqa/kbqa.md:11
#: df1c88b28a2d46b2b3f5fae1caec000e
msgid "Knowledge Space."
msgstr "知识空间"
#: ../../getting_started/application/kbqa/kbqa.md:12
#: 7f6c99d0c1394f08b246daa1343c24b2
msgid "Multi Source Knowledge Source Embedding."
msgstr "多数据源Embedding"
#: ../../getting_started/application/kbqa/kbqa.md:13
#: 3c1274c3e65f426bbee219227f681e27
msgid "Embedding Argument Adjust"
msgstr "Embedding参数自定义"
#: ../../getting_started/application/kbqa/kbqa.md:14
#: 52fb29f7ee8745e6b78145f5be23b8ce
msgid "Chat Knowledge"
msgstr "知识问答"
#: ../../getting_started/application/kbqa/kbqa.md:15
#: 83e427c46d844c6a9bb5954342ae7c42
msgid "Multi Vector DB"
msgstr "多向量数据库管理"
#: ../../getting_started/application/kbqa/kbqa.md:19
#: 07c1e189d0f84db69b6a51cf23ede7dc
msgid "Steps to KBQA In DB-GPT"
msgstr "怎样一步一步使用KBQA"
#: ../../getting_started/application/kbqa/kbqa.md:21
#: 36e4195e5c3a4bedb7d11243e5705f0a
msgid "1.Create Knowledge Space"
msgstr "1.首先创建知识空间"
#: ../../getting_started/application/kbqa/kbqa.md:22
#: 5c92d41df2b04374a6c7ce40308f738b
msgid ""
"If you are using Knowledge Space for the first time, you need to create a"
" Knowledge Space and set your name, owner, description. "
"![create_space](../../../../assets/kbqa/create_space.png)"
msgstr "如果你是第一次使用,先创建知识空间,指定名字,拥有者和描述信息"
#: ../../getting_started/application/kbqa/kbqa.md:22
#: c5f6e842be384977be1bd667b1e0ab5d
msgid "create_space"
msgstr "create_space"
#: ../../getting_started/application/kbqa/kbqa.md:27
#: c98434920955416ca5273892f9086bc5
msgid "2.Create Knowledge Document"
msgstr "2.上传知识"
#: ../../getting_started/application/kbqa/kbqa.md:28
#: d63f798e8270455587d1afd98c72e995
msgid ""
"DB-GPT now support Multi Knowledge Source, including Text, WebUrl, and "
"Document(PDF, Markdown, Word, PPT, HTML and CSV). After successfully "
"uploading a document for translation, the backend system will "
"automatically read and split and chunk the document, and then import it "
"into the vector database. Alternatively, you can manually synchronize the"
" document. You can also click on details to view the specific document "
"slicing content."
msgstr "DB-GPT支持多数据源包括Text纯文本, WebUrl和Document(PDF, Markdown, Word, PPT, HTML and CSV)。上传文档成功后后台会自动将文档内容进行读取,切片,然后导入到向量数据库中,当然你也可以手动进行同步,你也可以点击详情查看具体的文档切片内容"
#: ../../getting_started/application/kbqa/kbqa.md:30
#: 18becde7bdc34e9cb7017ff7711d1634
msgid "2.1 Choose Knowledge Type:"
msgstr "2.1 选择知识类型"
#: ../../getting_started/application/kbqa/kbqa.md:31
#: 755dfd18812249e591647d233ec9253b
msgid "![document](../../../../assets/kbqa/document.jpg)"
msgstr "![document](../../../../assets/kbqa/document.jpg)"
#: ../../getting_started/application/kbqa/kbqa.md:31
#: 10faa2236fa84dc284f7ce6d68acc43c
msgid "document"
msgstr "document"
#: ../../getting_started/application/kbqa/kbqa.md:33
#: 04449bfa78b14d1cb42c1259f67531d1
msgid "2.2 Upload Document:"
msgstr "2.2上传文档"
#: ../../getting_started/application/kbqa/kbqa.md:34
#: de14e2d7a6c54623bfc8af2fc6e20c62
msgid "![upload](../../../../assets/kbqa/upload.jpg)"
msgstr "![upload](../../../../assets/kbqa/upload.jpg)"
#: ../../getting_started/application/kbqa/kbqa.md:34
#: ../../getting_started/application/kbqa/kbqa.md:38
#: ../../getting_started/application/kbqa/kbqa.md:43
#: ../../getting_started/application/kbqa/kbqa.md:56
#: 0e3ab13b9d064b238fba283d6f466051 65ea0b9b43ef4c64897a6e65781129c7
#: cb65cb968a91492d9526f47e74b179e1 f0ff29911159497fb542942b6deb6972
msgid "upload"
msgstr "upload"
#: ../../getting_started/application/kbqa/kbqa.md:37
#: 77d936d2502f41feb2721da86cc1ebb1
msgid "3.Chat With Knowledge"
msgstr "3.知识问答"
#: ../../getting_started/application/kbqa/kbqa.md:38
#: ae72c3236e564949b142a945f3474425
msgid "![upload](../../../../assets/kbqa/begin_chat.jpg)"
msgstr "![upload](../../../../assets/kbqa/begin_chat.jpg)"
#: ../../getting_started/application/kbqa/kbqa.md:40
#: b9d701985d404a9196bb896718f41e36
msgid "4.Adjust Space arguments"
msgstr "4.调整知识参数"
#: ../../getting_started/application/kbqa/kbqa.md:41
#: 6155bbf401ef44ea8d761c83ae5ceb9a
msgid ""
"Each knowledge space supports argument customization, including the "
"relevant arguments for vector retrieval and the arguments for knowledge "
"question-answering prompts."
msgstr "每一个知识空间都支持参数自定义, 包括向量召回的相关参数以及知识问答Promp参数"
#: ../../getting_started/application/kbqa/kbqa.md:42
#: b9ac70b5ee99435a962dcb040b5ba4fc
msgid "4.1 Embedding"
msgstr "4.1 Embedding"
#: ../../getting_started/application/kbqa/kbqa.md:43
#: 0ca2398756924828a904921456b863b5
msgid "Embedding Argument ![upload](../../../../assets/kbqa/embedding.png)"
msgstr "Embedding Argument ![upload](../../../../assets/kbqa/embedding.png)"
#: ../../getting_started/application/kbqa/kbqa.md:47
#: e8b3e973e3b940e4bbf3180b7d6057ec
msgid "Embedding arguments"
msgstr "Embedding arguments"
#: ../../getting_started/application/kbqa/kbqa.md:48
#: 1cff4790d546455abeca725ae8b53c0d
msgid "topk:the top k vectors based on similarity score."
msgstr "topk:相似性检索出tok条文档"
#: ../../getting_started/application/kbqa/kbqa.md:49
#: 525aaa02028b4900919526290b6da9ef
msgid "recall_score:set a threshold score for the retrieval of similar vectors."
msgstr "recall_score:向量检索相关度衡量指标分数"
#: ../../getting_started/application/kbqa/kbqa.md:50
#: dead3b559b134e52a3cf38e29b1982e1
msgid "recall_type:recall type."
msgstr "recall_type:召回类型"
#: ../../getting_started/application/kbqa/kbqa.md:51
#: 7c48de3186a14fcf96ee2bc6d715bd4c
msgid "model:A model used to create vector representations of text or other data."
msgstr "model:embdding模型"
#: ../../getting_started/application/kbqa/kbqa.md:52
#: 875ba3d051b847a5b3357a4eef583c0a
msgid "chunk_size:The size of the data chunks used in processing."
msgstr "chunk_size:文档切片阈值大小"
#: ../../getting_started/application/kbqa/kbqa.md:53
#: e43f2bb091594532ba69ed3e3a385cdd
msgid "chunk_overlap:The amount of overlap between adjacent data chunks."
msgstr "chunk_overlap:文本块之间的最大重叠量。保留一些重叠可以保持文本块之间的连续性(例如使用滑动窗口)"
#: ../../getting_started/application/kbqa/kbqa.md:55
#: e21e19688fa042a4b60860ffa6bcf119
msgid "4.2 Prompt"
msgstr "4.2 Prompt"
#: ../../getting_started/application/kbqa/kbqa.md:56
#: 00f0bddcd9174b7a84a25b7fe6d286e9
msgid "Prompt Argument ![upload](../../../../assets/kbqa/prompt.png)"
msgstr "Prompt Argument ![upload](../../../../assets/kbqa/prompt.png)"
#: ../../getting_started/application/kbqa/kbqa.md:60
#: d5ff2b76a04949708b3c9050db647927
msgid "Prompt arguments"
msgstr "Prompt arguments"
#: ../../getting_started/application/kbqa/kbqa.md:61
#: 817a8744378546a2b049f44793b4554b
msgid ""
"scene:A contextual parameter used to define the setting or environment in"
" which the prompt is being used."
msgstr "scene:上下文环境的场景定义"
#: ../../getting_started/application/kbqa/kbqa.md:62
#: 5330c26a4fc34ff6ba5fea1910cfbdc0
msgid ""
"template:A pre-defined structure or format for the prompt, which can help"
" ensure that the AI system generates responses that are consistent with "
"the desired style or tone."
msgstr ""
"template:预定义的提示结构或格式可以帮助确保AI系统生成与所期望的风格或语气一致的回复。"
#: ../../getting_started/application/kbqa/kbqa.md:63
#: a34cd8248e6b44228868c2a02e12466f
msgid "max_token:The maximum number of tokens or words allowed in a prompt."
msgstr "max_token: prompt token最大值"
#: ../../getting_started/application/kbqa/kbqa.md:65
#: 7da49aac293f462b9e3968fa1493dba1
msgid "5.Change Vector Database"
msgstr "5.Change Vector Database"
#: ../../getting_started/application/kbqa/kbqa.md:67
#: 680bfb451eb040e0aa55f8faa12bb75a
msgid "Vector Store SETTINGS"
msgstr "Vector Store SETTINGS"
#: ../../getting_started/application/kbqa/kbqa.md:68
#: 32820ae6807840119a786e92124ad209
msgid "Chroma"
msgstr "Chroma"
#: ../../getting_started/application/kbqa/kbqa.md:69
#: 7573aa05bc914fc2993b2531475b3b99
msgid "VECTOR_STORE_TYPE=Chroma"
msgstr "VECTOR_STORE_TYPE=Chroma"
#: ../../getting_started/application/kbqa/kbqa.md:70
#: cc2c5521ba6e417eb5b3cf96375c2a08
msgid "MILVUS"
msgstr "MILVUS"
#: ../../getting_started/application/kbqa/kbqa.md:71
#: fc5dfa54c8a24b069e2709c309e43faa
msgid "VECTOR_STORE_TYPE=Milvus"
msgstr "VECTOR_STORE_TYPE=Milvus"
#: ../../getting_started/application/kbqa/kbqa.md:72
#: 8661384f0c4a40a0b79fad94bbee1792
msgid "MILVUS_URL=127.0.0.1"
msgstr "MILVUS_URL=127.0.0.1"
#: ../../getting_started/application/kbqa/kbqa.md:73
#: 2035d343d34f47fa9fa84eb841afa2f8
msgid "MILVUS_PORT=19530"
msgstr "MILVUS_PORT=19530"
#: ../../getting_started/application/kbqa/kbqa.md:74
#: e0d8bd8d1dfb425bb50d5c8bf4a134ab
msgid "MILVUS_USERNAME"
msgstr "MILVUS_USERNAME"
#: ../../getting_started/application/kbqa/kbqa.md:75
#: dec547e6b4354c71857fa7c92c08bfa6
msgid "MILVUS_PASSWORD"
msgstr "MILVUS_PASSWORD"
#: ../../getting_started/application/kbqa/kbqa.md:76
#: 9ad3f325f79e49309bd3419f48015e90
msgid "MILVUS_SECURE="
msgstr "MILVUS_SECURE="
#: ../../getting_started/application/kbqa/kbqa.md:78
#: f6e15bf479da496fbcdf7621bad4dda8
msgid "WEAVIATE"
msgstr "WEAVIATE"
#: ../../getting_started/application/kbqa/kbqa.md:79
#: f7838d5de0a9452486adceb3a26369ee
msgid "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
msgstr "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.networkc"

View File

@@ -0,0 +1,51 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/faq.rst:13
msgid "Deloy"
msgstr "Deloy"
#: ../../getting_started/faq.rst:2 136e86216b564bcb91709d97ae03013c
msgid "FAQ"
msgstr "FAQ"
#: ../../getting_started/faq.rst:3 9350e190f83648248a4e53a4703529a0
msgid ""
"DB-GPT product is a Web application that you can chat database, chat "
"knowledge, text2dashboard."
msgstr ""
#: ../../getting_started/faq.rst:8 c4d7887a869f48ddb1819a5df9206005
msgid "deploy"
msgstr "deploy"
#: ../../getting_started/faq.rst:9 3859638a380043dfa466d6f9c593ff14
msgid "llm"
msgstr "llm"
#: ../../getting_started/faq.rst:10 2039dce8389d4f9fb8fb7a8afa393809
msgid "chatdb"
msgstr "chatdb"
#: ../../getting_started/faq.rst:11 24a115044f984a71a83dea6000a98de8
msgid "kbqa"
msgstr "kbqa"

View File

@@ -0,0 +1,61 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 23:15+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/faq/chatdb/chatdb_faq.md:1
#: ffd1abb6b8f34e53a8ed83ede845b141
msgid "Chat DB FAQ"
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:3
#: 2467f6603ab341bbb1ce17f75dc06e5e
msgid "Q1: What difference between ChatData and ChatDB"
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:4
#: 6e47803e92064e379a1bb74e2b3d347a
msgid ""
"ChatData generates SQL from natural language and executes it. ChatDB "
"involves conversing with metadata from the Database, including metadata "
"about databases, tables, and fields."
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:6
#: fa3eef15697f43db963f6c875e85323b
msgid "Q2: The suitable llm model currently supported for text-to-SQL is?"
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:7
#: 47f36a0a48c045269bcf790873d55f8c
msgid "Now vicunna-13b-1.5 and llama2-70b is more suitable for text-to-SQL."
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:9
#: 9f5ef9a05fac4eb3b27875171ec4e763
msgid "Q3: How to fine-tune Text-to-SQL in DB-GPT"
msgstr ""
#: ../../getting_started/faq/chatdb/chatdb_faq.md:10
#: c9b6f6e969e04805a59d9ccabc03c0b8
msgid ""
"there is another github project for Text-to-SQL fine-tune "
"(https://github.com/eosphoros-ai/DB-GPT-Hub)"
msgstr ""

View File

@@ -0,0 +1,86 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 23:15+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/faq/deploy/deploy_faq.md:1
#: 6aa73265a43d4e6ea287e6265ef4efe5
msgid "Installation FAQ"
msgstr "Installation FAQ"
#: ../../getting_started/faq/deploy/deploy_faq.md:5
#: 4efe241d5e724db5ab22548cfb88f8b6
msgid ""
"Q1: execute `pip install -r requirements.txt` error, found some package "
"cannot find correct version."
msgstr "Q1: execute `pip install -r requirements.txt` error, found some package "
"cannot find correct version."
#: ../../getting_started/faq/deploy/deploy_faq.md:6
#: e837e10bdcfa49cebb71b32eece4831b
msgid "change the pip source."
msgstr "替换pip源."
#: ../../getting_started/faq/deploy/deploy_faq.md:13
#: ../../getting_started/faq/deploy/deploy_faq.md:20
#: 84310ec0c54e4a02949da2e0b35c8c7d e8a7a8b38b7849b88c14fb6d647f9b63
msgid "or"
msgstr "或者"
#: ../../getting_started/faq/deploy/deploy_faq.md:27
#: 87797a5dafef47c8884f6f1be9a1fbd2
msgid ""
"Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to"
" open database file"
msgstr "Q2: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to"
" open database file"
#: ../../getting_started/faq/deploy/deploy_faq.md:29
#: bc96b22e201c47ec999c8d98227a956d
msgid "make sure you pull latest code or create directory with mkdir pilot/data"
msgstr "make sure you pull latest code or create directory with mkdir pilot/data"
#: ../../getting_started/faq/deploy/deploy_faq.md:31
#: d7938f1c70a64efa9948080a6d416964
msgid "Q3: The model keeps getting killed."
msgstr "Q3: The model keeps getting killed."
#: ../../getting_started/faq/deploy/deploy_faq.md:32
#: b072386586a64b2289c0fcdf6857b2b7
msgid ""
"your GPU VRAM size is not enough, try replace your hardware or replace "
"other llms."
msgstr "GPU显存不够, 增加显存或者换一个显存小的模型"
#~ msgid ""
#~ "Q2: When use Mysql, Access denied "
#~ "for user 'root@localhost'(using password :NO)"
#~ msgstr ""
#~ msgid "A3: make sure you have installed mysql instance in right way"
#~ msgstr ""
#~ msgid "Docker:"
#~ msgstr ""
#~ msgid ""
#~ "Normal: [download mysql "
#~ "instance](https://dev.mysql.com/downloads/mysql/)"
#~ msgstr ""

View File

@@ -0,0 +1,98 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/faq/kbqa/kbqa_faq.md:1
#: bce4fd8751dd49bb8ab89a651094cfe1
msgid "KBQA FAQ"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:4
#: c9714f70a03f422fae7bdb2b3b3c8be5
msgid "Q1: text2vec-large-chinese not found"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:6
#: 1c56b9081adb46b29063947659e67083
msgid ""
"make sure you have download text2vec-large-chinese embedding model in "
"right way"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:18
#: 39763bdbc6824675b293f0f219fc05bb
msgid "Q2:How to change Vector DB Type in DB-GPT."
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:20
#: 225cc6e5b6944ce3b675845aa93afb66
msgid "Update .env file and set VECTOR_STORE_TYPE."
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:22
#: 5ad12db4aed44f4890911b5aea9529ce
msgid ""
"DB-GPT currently support Chroma(Default), Milvus(>2.1), Weaviate vector "
"database. If you want to change vector db, Update your .env, set your "
"vector store type, VECTOR_STORE_TYPE=Chroma (now only support Chroma and "
"Milvus(>2.1), if you set Milvus, please set MILVUS_URL and MILVUS_PORT) "
"If you want to support more vector db, you can integrate yourself.[how to"
" integrate](https://db-gpt.readthedocs.io/en/latest/modules/vector.html)"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:38
#: f8dd19ff86244cc7be91b7ab9190baeb
msgid "Q3:When I use vicuna-13b, found some illegal character like this."
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:43
#: ec4a69476d4e4e4d92619ade829c2b39
msgid ""
"Set KNOWLEDGE_SEARCH_TOP_SIZE smaller or set KNOWLEDGE_CHUNK_SIZE "
"smaller, and reboot server."
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:45
#: 5b039a860c0b4cb088d042467ad2a49c
msgid ""
"Q4:space add error (pymysql.err.OperationalError) (1054, \"Unknown column"
" 'knowledge_space.context' in 'field list'\")"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:47
#: bafac5e248894263a77ab688922df520
msgid "1.shutdown dbgpt_server(ctrl c)"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:49
#: 8ff5ca901f684e8ebe951f8c053ab925
msgid "2.add column context for table knowledge_space"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:53
#: ea9f945678aa426894f0a12013f8fe5c
msgid "3.execute sql ddl"
msgstr ""
#: ../../getting_started/faq/kbqa/kbqa_faq.md:58
#: 1a7941f2f1e94d359095e92b470ee02c
msgid "4.restart dbgpt serve"
msgstr ""

View File

@@ -0,0 +1,92 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/faq/llm/llm_faq.md:1 f79c82f385904385b08618436e600d9f
msgid "LLM USE FAQ"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:3 1fc802fa69224062b02403bc35084c18
msgid "Q1:how to use openai chatgpt service"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:4 9094902d148a4cc99fe72aa0e41062ae
msgid "change your LLM_MODEL"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:9 07073eb8d9eb4988a3b035666c63d3fb
msgid "set your OPENAPI KEY"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:15 a71bb0d1181e47368a286b5694a00056
msgid "make sure your openapi API_KEY is available"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:17 789b003864824970923bac474a9ab0cd
msgid "Q2 how to use MultiGPUs"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:18 4be3dd71a8654202a210bcb11c50cc79
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 ""
#: ../../getting_started/faq/llm/llm_faq.md:20 3a00c5fff666451cacda7f9af37564b9
msgid ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command, as shown below:"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:30 7fef386f3a3443569042e7d8b9a3ff15
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/faq/llm/llm_faq.md:32 d75d440da8ab49a3944c3a456db25bee
msgid "Q3 Not Enough Memory"
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:34 2a2cd59382e149ffb623cb3d42754dca
msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
msgstr ""
#: ../../getting_started/faq/llm/llm_faq.md:36 755131812baa4f5a99b706849459e10a
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/faq/llm/llm_faq.md:38 b85424bc11134af985f687d8ee8d2c9f
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 ""
#: ../../getting_started/faq/llm/llm_faq.md:40 b6e4db679636492c9e4170a33fd6f638
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 ""

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: 2023-08-10 16:38+0800\n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,29 +19,29 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/getting_started.md:1 b5ce6e0075114e669c78cda63f22dfe6
#: ../../getting_started/getting_started.md:1 70e40ad608d54bcfae6faf0437c09b6f
msgid "Quickstart Guide"
msgstr "使用指南"
#: ../../getting_started/getting_started.md:3 caf6a35c0ddc43199750b2faae2bf95d
#: ../../getting_started/getting_started.md:3 c22ff099d6e940f7938dcea0e2265f11
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。"
#: ../../getting_started/getting_started.md:5 338aae168e63461f84c8233c4cbf4bcc
#: ../../getting_started/getting_started.md:5 dc717e76b3194a85ac5b9e8a4479b197
msgid "Installation"
msgstr "安装"
#: ../../getting_started/getting_started.md:7 62519550906f4fdb99aad61502e7a5e6
#: ../../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 f9072092ebf24ebc893604ca86116cd3
#: ../../getting_started/getting_started.md:9 bab013745cb24538ac568b97045b72cc
msgid "1. Hardware Requirements"
msgstr "1. 硬件要求"
#: ../../getting_started/getting_started.md:10 071c54f9a38e4ef5bb5dcfbf7d4a6004
#: ../../getting_started/getting_started.md:10 7dd84870db394338a5c7e63b171207e0
msgid ""
"As our project has the ability to achieve ChatGPT performance of over "
"85%, there are certain hardware requirements. However, overall, the "
@@ -49,86 +49,76 @@ msgid ""
"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:"
#: ../../getting_started/getting_started.md 4757df7812c64eb4b511aa3b8950c899
#: ../../getting_started/getting_started.md 055d07f830c54303a0b5596601c58870
msgid "GPU"
msgstr "GPU"
#: ../../getting_started/getting_started.md
#: ../../getting_started/getting_started.md:60 8f316fbd032f474b88d823978d134328
#: cb3d34d1ed074e1187b60c6f74cf1468
#: ../../getting_started/getting_started.md:50 7323cee42940438b8a0752d3c2355e59
#: e3fc2c10f81b4fe2ac0bfd9fe78feed9
msgid "VRAM Size"
msgstr "显存大小"
#: ../../getting_started/getting_started.md ac41e6ccf820424b9c497156a317287d
#: ../../getting_started/getting_started.md 68831daf63f14dcd92088dd6c866f110
msgid "Performance"
msgstr "显存大小"
#: ../../getting_started/getting_started.md 3ca06ce116754dde958ba21beaedac6f
#: ../../getting_started/getting_started.md 8a7197a5e92c40a9ba160b43656983d2
msgid "RTX 4090"
msgstr "RTX 4090"
#: ../../getting_started/getting_started.md 54e3410cc9a241098ae4412356a89f02
#: e3f31b30c4c84b45bc63b0ea193d0ed1
#: ../../getting_started/getting_started.md 69b2bfdec17e43fbb57f47e3e10a5f5a
#: 81d0c2444bbb4a2fb834a628689e4b68
msgid "24 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md ff0c37e041a848899b1c3a63bab43404
#: ../../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 09120e60cfc640e182e8069a372038cc
#: ../../getting_started/getting_started.md 527def44c8b24e4bbe589d110bd43e91
msgid "RTX 3090"
msgstr "RTX 3090"
#: ../../getting_started/getting_started.md 0545dfec3b6d47e1bffc87301a0f05b3
#: ../../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 d41078c0561f47a981a488eb4b9c7a54
#: ../../getting_started/getting_started.md c090521969f042398236f6d04b017295
msgid "V100"
msgstr "V100"
#: ../../getting_started/getting_started.md 6aefb19420f4452999544a0da646f067
#: ../../getting_started/getting_started.md 60605e0de3fc494cbb7199cef8f831ad
msgid "16 GB"
msgstr "16 GB"
#: ../../getting_started/getting_started.md 8e06966b88234f4898729750d724e272
#: ../../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 113957ae638e4799a47e58a2ca259ce8
#: ../../getting_started/getting_started.md:18 b9df8ec7b2c34233b28db81f3c90f8c7
msgid "2. Install"
msgstr "2. 安装"
#: ../../getting_started/getting_started.md:20 e068b950171f4c48a9e125ece31f75b9
#: ../../getting_started/getting_started.md:20 bd0f0159a49b4493ab387e124fef15fa
#, fuzzy
msgid ""
"1.This project relies on a local MySQL database service, which you need "
"to install locally. We recommend using Docker for installation."
msgstr "本项目依赖一个本地的 MySQL 数据库服务,你需要本地安装,推荐直接使用 Docker 安装。"
#: ../../getting_started/getting_started.md:24 f115b61438ad403aaaae0fc4970a982b
msgid "prepare server sql script"
msgstr "准备db-gpt server sql脚本"
#: ../../getting_started/getting_started.md:29 c5f707269582464e92e5fd57365f5a51
msgid ""
"We use [Chroma embedding database](https://github.com/chroma-core/chroma)"
" as the default for our vector 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."
" 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"
#: ../../getting_started/getting_started.md:38 377381c76f32409298f4184f23653205
#: ../../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:44 62e7e96a18ca495595b3dfab97ca387e
#: ../../getting_started/getting_started.md:34 03e1652f724946ec8d01a97811883b5f
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 "
@@ -137,40 +127,40 @@ 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。"
#: ../../getting_started/getting_started.md:47 e34d946ab06e47dba81cf50348987594
#: ../../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:58 07149cfac5314daabbd37dc1cef82905
#: ../../getting_started/getting_started.md:48 af91349fe332472ca7a2e592a0c582f7
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。"
#: ../../getting_started/getting_started.md:61 b8da240286e04573a2d731d228fbdb1e
#: ../../getting_started/getting_started.md:51 84d2d93130034c2f94f4d0bebcc2b0d2
msgid "cp .env.template .env"
msgstr "cp .env.template .env"
#: ../../getting_started/getting_started.md:64 c2b05910bba14e5b9b49f8ad8c436412
#: ../../getting_started/getting_started.md:54 b3adfec002354f00baba9c43a1a3e381
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。"
#: ../../getting_started/getting_started.md:66 4af57c4cbf4744a8af83083d051098b3
#: ../../getting_started/getting_started.md:56 1b11268133c0440cb3c26981f5d0c1fe
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:68 62287c3828ba48c4871dd831af7d819a
#: ../../getting_started/getting_started.md:58 511d47f08bab42e0bd3f34df58c5a822
msgid "3. Run"
msgstr "3. 运行"
#: ../../getting_started/getting_started.md:69 7a04f6c514c34d87a03b105de8a03f0b
#: ../../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-"
@@ -179,7 +169,7 @@ 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:71 72c9ad9d95c34b42807ed0a1e46adb73
#: ../../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 "
@@ -188,7 +178,7 @@ 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:73 889cf1a4dbd2422580fe59d9f3eab6bf
#: ../../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 > "
@@ -197,21 +187,21 @@ 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:76 28a2ec60d35c43edab71bac103ccb0e0
#: ../../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:81
#: ../../getting_started/getting_started.md:140
#: ../../getting_started/getting_started.md:194
#: 04ed6e8729604ee59edd16995301f0d5 225139430ee947cb8a191f1641f581b3
#: b33473644c124fdf9fe9912307cb6a9d
#: ../../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:83 8068aef8a84e46b59caf59de32ad6e2b
#: ../../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 "
@@ -219,7 +209,7 @@ msgid ""
"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:86 4a11e53950ac489a891ca8dc67c26ca0
#: ../../getting_started/getting_started.md:76 7808d30d1642422fbed42f1929e37343
#, fuzzy
msgid ""
"If you want to learn about dbgpt-webui, read https://github./csunny/DB-"
@@ -228,268 +218,304 @@ 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:92 6a2b09ea9ba64c879d3e7ca154d95095
#: ../../getting_started/getting_started.md:82 094ed036720c406c904c8a9ca6e7b8ae
msgid "4. Docker (Experimental)"
msgstr "4. Docker (Experimental)"
#: ../../getting_started/getting_started.md:94 5cef89f829ce4da299f9b430fd52c446
#: ../../getting_started/getting_started.md:84 9428d68d1eef42c28bf33d9bd7022c85
msgid "4.1 Building Docker image"
msgstr "4.1 Building Docker image"
#: ../../getting_started/getting_started.md:100
#: b3999a9169694b209bd4848c6458ff41
#: ../../getting_started/getting_started.md:90 16bfb175a85c455e847c3cafe2d94ce1
msgid "Review images by listing them:"
msgstr "Review images by listing them:"
#: ../../getting_started/getting_started.md:106
#: ../../getting_started/getting_started.md:180
#: 10486e7f872f4c13a384b75e564e37fe 5b142d0a103848fa82fafd40a557f998
#: ../../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:113
#: 83dd5525d0f7481fac57e5898605e7f3
#: ../../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:121
#: d5b916efd7b84972b68a4aa50ebc047c
#: ../../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 "
msgstr ""
"You can execute the command `bash docker/build_all_images.sh --help` to "
"see more usage."
#: ../../getting_started/getting_started.md:123
#: 0d01cafcfde04c92b4115d804dd9e912
#: ../../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:125
#: 90d49baea1d34f01a0db696fd567bfba
msgid "**Run with local model**"
#: ../../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:143
#: 422a237241014cac9917832ac053aed5
#: ../../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"
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:144
#: af5fb303a0c64567b9c82a3ce3b00aaa
#: ../../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 "
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:146
#: ../../getting_started/getting_started.md:188
#: 05652e117c3f4d3aaea0269f980cf975 3844ae7eeec54804b05bc8aea01c3e36
#: ../../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:152
#: 665aa47936aa40458fe33dd73c76513d
#: ../../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:171
#: 98d627b0f7f149dfb9c7365e3ba082a1
#: ../../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, "
msgstr ""
"`-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, "
"fastchat interface...)"
#: ../../getting_started/getting_started.md:172
#: b293dedb88034aaab9a3b740e82d7adc
#: ../../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-"
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:174
#: e48085324a324749af8a21bad8e7ca0e
#: ../../getting_started/getting_started.md:180
#: 257860df855843eb85383478d2e8baca
msgid "4.3. Run with docker compose"
msgstr ""
#: ../../getting_started/getting_started.md:196
#: a356d9ae292f4dc3913c5999e561d533
#: ../../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"
msgstr ""
"You can open docker-compose.yml in the project root directory to see more"
" details."
#: ../../getting_started/getting_started.md:199
#: 0c644409bce34bf4b898c26e24f7a1ac
#: ../../getting_started/getting_started.md:205
#: 0dd3dc0d7a7f4565a041ab5855808fd3
msgid "5. Multiple GPUs"
msgstr "5. Multiple GPUs"
#: ../../getting_started/getting_started.md:201
#: af435b17984341e5abfd2d9b64fbde20
#: ../../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 "
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:203
#: aac3e9cec74344fd963e2136a26384af
#: ../../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 "
msgstr ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command, as shown below:"
#: ../../getting_started/getting_started.md:213
#: 3351daf4f5a04b76bae2e9cd8740549e
#: ../../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:215
#: fabf9090b7c649b59b91742ba761339c
#: ../../getting_started/getting_started.md:221
#: c80f5e6d2a6042ad9ac0ef320cc6d987
msgid "6. Not Enough Memory"
msgstr ""
#: ../../getting_started/getting_started.md:217
#: d23322783fd34364acebe1679d7ca554
#: ../../getting_started/getting_started.md:223
#: b8151a333f804489ad6a2b59e739a8ed
msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
msgstr ""
#: ../../getting_started/getting_started.md:219
#: 8699aa0b5fe049099fb1e8038f9ad1ee
#: ../../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:221
#: b115800c207b49b39de5e1a548feff58
#: ../../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"
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:223
#: ae7146f0995d4eca9f775c39898d5313
#: ../../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 "
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:226
#: 58987c486d2641cda3180a77af26c56d
#: ../../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 "
msgstr ""
"Here are some of the VRAM size usage of the models we tested in some "
"common scenarios."
#: ../../getting_started/getting_started.md:60 4ca1a7e65f7e46c08ef12a1357f68817
#: ../../getting_started/getting_started.md:50 165d0902ed064bbaa8b0bbe84befe139
msgid "Model"
msgstr "Model"
#: ../../getting_started/getting_started.md:60 21ab5b38f81a49aeacadbcde55082adf
#: ../../getting_started/getting_started.md:50 d077bca9cada4a9b89037ef5ab494c26
msgid "Quantize"
msgstr "Quantize"
#: ../../getting_started/getting_started.md:60 a2ad84e7807c4d3ebc9d2f9aec323962
#: b4e2d7a107074e58b91b263d815b2936
#: ../../getting_started/getting_started.md:50 42723863614e42b1aa6c664bfd197474
#: b71ce0c19de7471787cbbc09d6137a4b
msgid "vicuna-7b-v1.5"
msgstr "vicuna-7b-v1.5"
#: ../../getting_started/getting_started.md:60 0134b7564c3f4cd9a605c3e7dabf5c78
#: 12a931b938ee4e938a4ed166532946e9 9cc80bc860c7430cbc2b4aff3c4c67d2
#: b34fb93b644a419d8073203a1a0091fc bb61c197b1c74eb2bf4e7e42ad05850d
#: e3ab5cabd6f54faa9de0ec6c334c0d44 f942635d6f5e483293833ac5f92b6ab9
#: ../../getting_started/getting_started.md:50 2654d358528a48e38bec445644ffd20a
#: 2ad34cd14f54422491464967331d83fc 3b42a055e72847ec99d8d131fa9f5f84
#: 6641e98d9bed44ee853fe7a11263a88b a69801bc92f143aa9e0818886ef6eade
#: daa418b33705484ba944b0d92981a501 fc26bd1dace2432ca64b99ca16c2c80f
msgid "4-bit"
msgstr "4-bit"
#: ../../getting_started/getting_started.md:60 a8556b0ec7b3488585efcdc2ba5e8565
#: afb4365dab1e4be18f486fafbd5c6256 b50b8bc0e8084e6ebe4f9678d1f2af9d
#: ../../getting_started/getting_started.md:50 1688f8a0972c4026abf69b5186d92137
#: 683de09d524a4084bcdad1a184206f87 74586e40b480444591dc884e7f3f683f
#, fuzzy
msgid "8 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:60 259b43952ea5424a970dfa29c84cc83d
#: 64c6a8282eaf4e229d4196ccdbc2527f 7a426b8af2a6406fa4144142450e392e
#: 8e5742b0c4b44bf6bd0536aade037671 a96071a0c713493fae2b381408ceaad3
#: dcd6861abd2049a38f32957dd16408ab f334903a72934a2a86c3b24920f8cfdb
#: ../../getting_started/getting_started.md:50 13aa8cac7a784ad1a1b58b166be99711
#: 32633a38c1f44aac92f9647ee7867cd1 3b7fea4236174e2bb33894fd8234eddb
#: 3b8104af560e41f285d9c433e19f6cb7 5862f0c57e2c411dada47fe71f6a74bd
#: 6425f53f197742c8b3153a79cf4a220a d1fa83af3a884714a72f7a0af5f3be23
msgid "8-bit"
msgstr "8-bit"
#: ../../getting_started/getting_started.md:60 09c7435ba68248bd885a41366a08f557
#: 328ad98c8cb94f9083e8b5f158d7c14e 633e1f6d17404732a0c2f1cdf04f6591
#: c351117229304ae88561cdd284a77f55 c77a5a73cde34e3195a6389fdd81deda
#: f28704154fad48a8a08e16e136877ca7
#: ../../getting_started/getting_started.md:50 107ed4fb15c44cb5bb7020a8092f7341
#: 1d1791894226418ea623abdecd3107ba 1fdc42ef874f4022be31df7696e6a5de
#: 718c49ddac8e4086a75cdbba166dc3cb 99404c8333974ae7a1e68885f4471b32
#: da59674e4418488583cf4865545ad752
#, fuzzy
msgid "12 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:60 63564bdcfa4249438d0245922068924f
#: 9ad1bc9af45b4f52a1a0a9e7c8d14cce
#: ../../getting_started/getting_started.md:50 79bf82a6dc9f4c22af779be4b1d2d13c
#: b5bde8f01fc343baa567806fd53070dc
msgid "vicuna-13b-v1.5"
msgstr "vicuna-13b-v1.5"
#: ../../getting_started/getting_started.md:60 0e05753ff4ec4c1a94fc68b63254115b
#: 68a9e76f2089461692c8f396774e7634 a3136e5685cf49c4adbf79224cb0eb7d
#: ../../getting_started/getting_started.md:50 362720115dd64143a214b3b9d3069512
#: e0545557159b44dea0522a1848170216 e3c6ab8f25bc4adbae3b3087716a1efe
#, fuzzy
msgid "20 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:60 173b58152fde49f4b3e03103323c4dd7
#: 7ab8309661024d1cb656911acb7b0d58
#: ../../getting_started/getting_started.md:50 295fd7d6e6c846748a1f2c82f8c79ba0
#: 55efa8e8e4e74efc865df87fcfade84d
msgid "llama-2-7b"
msgstr "llama-2-7b"
#: ../../getting_started/getting_started.md:60 069459a955274376a3d9a4021a032424
#: 619257e4671141488feb6e71bd002880
#: ../../getting_started/getting_started.md:50 15b1e541bdac43fda1dcccf2aaeaa40f
#: 5785954810bc45369ed1745f5c503c9c
msgid "llama-2-13b"
msgstr "llama-2-13b"
#: ../../getting_started/getting_started.md:60 ce39526cfbcc4c8c910928dc69293720
#: f5e3fb53bd964e328aac908ae6fc06a4
#: ../../getting_started/getting_started.md:50 185892d421684c1b903c04ea9b6653d7
#: d7970a5fe574434798d72427436c82d5
msgid "llama-2-70b"
msgstr "llama-2-70b"
#: ../../getting_started/getting_started.md:60 c09fb995952048d290dde484a0e09478
#: ../../getting_started/getting_started.md:50 f732a7f73a504bd1b56b42dab1114d04
#, fuzzy
msgid "48 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:60 4d9bc275dbc548918cda210f5f5d7722
#: ../../getting_started/getting_started.md:50 04642b0dd4bc4563a45c6d15fa1d8f07
#, fuzzy
msgid "80 GB"
msgstr "24 GB"
#: ../../getting_started/getting_started.md:60 962d13ed427041a19f20d9a1c8ca26ff
#: dedfece8bc8c4ffabf9cc7166e4ca4db
#: ../../getting_started/getting_started.md:50 b9c4d8b71b1e4185bab24a857433f884
#: fc1b1927cc344e2e91bb7047c79ad227
msgid "baichuan-7b"
msgstr ""
#: ../../getting_started/getting_started.md:60 43f629be73914d4cbb1d75c7a06f88e8
#: 5cba8d23c6e847579986b7019e073eaf
#: ../../getting_started/getting_started.md:50 c92417b527a04d82ac9caa837884113c
#: dc17ae982c154b988433a0c623301bcb
msgid "baichuan-13b"
msgstr "baichuan-13b"
#~ msgid "4.2. Run with docker compose"
#~ msgstr "4.2. Run with docker compose"
#~ msgid ""
#~ "1.This project relies on a local "
#~ "MySQL database service, which you need"
#~ " to install locally. We recommend "
#~ "using Docker for installation."
#~ msgstr "本项目依赖一个本地的 MySQL 数据库服务,你需要本地安装,推荐直接使用 Docker 安装。"
#~ msgid "prepare server sql script"
#~ msgstr "准备db-gpt server sql脚本"

View File

@@ -0,0 +1,52 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install.rst:2 ../../getting_started/install.rst:14
#: 2861085e63144eaca1bb825e5f05d089
msgid "Install"
msgstr "Install"
#: ../../getting_started/install.rst:3 01a6603d91fa4520b0f839379d4eda23
msgid ""
"DB-GPT product is a Web application that you can chat database, chat "
"knowledge, text2dashboard."
msgstr "DB-GPT 可以生成sql智能报表, 知识库问答的产品"
#: ../../getting_started/install.rst:8 beca85cddc9b4406aecf83d5dfcce1f7
msgid "deploy"
msgstr "部署"
#: ../../getting_started/install.rst:9 601e9b9eb91f445fb07d2f1c807f0370
msgid "docker"
msgstr "docker"
#: ../../getting_started/install.rst:10 6d1e094ac9284458a32a3e7fa6241c81
msgid "docker_compose"
msgstr "docker_compose"
#: ../../getting_started/install.rst:11 ff1d1c60bbdc4e8ca82b7a9f303dd167
msgid "environment"
msgstr "environment"
#: ../../getting_started/install.rst:12 33bfbe8defd74244bfc24e8fbfd640f6
msgid "deploy_faq"
msgstr "deploy_faq"

View File

@@ -0,0 +1,443 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-17 21:23+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/deploy/deploy.md:1
#: de0b03c3b94a4e2aad7d380f532b85c0
msgid "Installation From Source"
msgstr "源码安装"
#: ../../getting_started/install/deploy/deploy.md:3
#: 65a034e1a90f40bab24899be901cc97f
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。"
#: ../../getting_started/install/deploy/deploy.md:5
#: 33b15956f7ef446a9aa4cac014163884
msgid "Installation"
msgstr "安装"
#: ../../getting_started/install/deploy/deploy.md:7
#: ad64dc334e8e43bebc8873afb27f7b15
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/install/deploy/deploy.md:9
#: 33e12a5bef6c45dbb30fbffae556b664
msgid "1. Hardware Requirements"
msgstr "1. 硬件要求"
#: ../../getting_started/install/deploy/deploy.md:10
#: dfd3b7c074124de78169f34168b7c757
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:"
#: ../../getting_started/install/deploy/deploy.md
#: 3d4530d981bf4dbab815a11c74bfd897
msgid "GPU"
msgstr "GPU"
#: ../../getting_started/install/deploy/deploy.md
#: 348c8f9b734244258416ea2e11b76caa f2f5e55b8c9b4c7da0ac090e763a9f47
msgid "VRAM Size"
msgstr "显存"
#: ../../getting_started/install/deploy/deploy.md
#: 9e099897409f42339bc284c378318a72
msgid "Performance"
msgstr "Performance"
#: ../../getting_started/install/deploy/deploy.md
#: 65bd67a198a84a5399f4799b505e062c
msgid "RTX 4090"
msgstr "RTX 4090"
#: ../../getting_started/install/deploy/deploy.md
#: 75e7f58f8f5d42f081a3e4d2e51ccc18 d897e949b37344d084f6917b977bcceb
msgid "24 GB"
msgstr "24 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 9cba72a2be3c41bda797ff447b63e448
msgid "Smooth conversation inference"
msgstr "Smooth conversation inference"
#: ../../getting_started/install/deploy/deploy.md
#: 90ea71d2099c47acac027773e69d2b23
msgid "RTX 3090"
msgstr "RTX 3090"
#: ../../getting_started/install/deploy/deploy.md
#: 7dd339251a1a45be9a45e0bb30bd09f7
msgid "Smooth conversation inference, better than V100"
msgstr "Smooth conversation inference, better than V100"
#: ../../getting_started/install/deploy/deploy.md
#: 8abe188052464e6aa395392db834c842
msgid "V100"
msgstr "V100"
#: ../../getting_started/install/deploy/deploy.md
#: 0b5263806a19446991cbd59c0fec6ba7 d645833d7e854eab81102374bf3fb7d8
msgid "16 GB"
msgstr "16 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 83bb5f40fa7f4e9389ac6abdb6bbb285 f9e58862a0cb488194d7ad536f359f0d
msgid "Conversation inference possible, noticeable stutter"
msgstr "Conversation inference possible, noticeable stutter"
#: ../../getting_started/install/deploy/deploy.md
#: 281f7b3c9a9f450798e5cc7612ea3890
msgid "T4"
msgstr "T4"
#: ../../getting_started/install/deploy/deploy.md:19
#: 7276d432615040b3a9eea3f2c5764319
msgid ""
"if your VRAM Size is not enough, DB-GPT supported 8-bit quantization and "
"4-bit quantization."
msgstr "如果你的显存不够DB-GPT支持8-bit和4-bit量化版本"
#: ../../getting_started/install/deploy/deploy.md:21
#: f68d085e03d244ed9b5ccec347466889
msgid ""
"Here are some of the VRAM size usage of the models we tested in some "
"common scenarios."
msgstr "这里是量化版本的相关说明"
#: ../../getting_started/install/deploy/deploy.md
#: 8d397d7ee603448b97153192e6d3e372
msgid "Model"
msgstr "Model"
#: ../../getting_started/install/deploy/deploy.md
#: 4c789597627447278e89462690563faa
msgid "Quantize"
msgstr "Quantize"
#: ../../getting_started/install/deploy/deploy.md
#: a8d7c76224544ce69f376ac7cb2f5a3b dbf2beb53d7e491393b00848d63d7ffa
msgid "vicuna-7b-v1.5"
msgstr "vicuna-7b-v1.5"
#: ../../getting_started/install/deploy/deploy.md
#: 1bd5afee2af84597b5a423308e92362c 46d030b6ff1849ebb22b590e6978d914
#: 4cf8f3ebb0b743ffb2f1c123a25b75d0 6d96be424e6043daa2c02649894aa796
#: 83bb935f520c4c818bfe37e13034b2a7 92ba161085374917b7f82810b1a2bf00
#: ca5ccc49ba1046d2b4b13aaa7ceb62f5
msgid "4-bit"
msgstr "4-bit"
#: ../../getting_started/install/deploy/deploy.md
#: 1173b5ee04cb4686ba34a527bc618bdb 558136997f4d49998f2f4e6a9bb656b0
#: 8d203a9a70684cbaa9d937af8450847f
msgid "8 GB"
msgstr "8 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 033458b772e3493b80041122e067e194 0f3eda083eac4739b2cf7d21337b145e
#: 6404eaa486cf45a69a27b0f87a7f6302 8e850aa3acf14ab2b231be74ddb34e86
#: ba258645f41f47a693aacbbc0f38e981 df67cac599234c4ba667a9b40eb6d9bc
#: fc07aeb321434722a320fed0afe3ffb8
msgid "8-bit"
msgstr "8-bit"
#: ../../getting_started/install/deploy/deploy.md
#: 3ed2cb5787c14f268c446b03d5531233 68e7f0b0e8ad44ee86a86189bb3b553d
#: 8b4ea703d1df45c5be90d83c4723f16f cb606e0a458746fd86307c1e8aea08f1
#: d5da58dbde3c4bb4ac8b464a0a507c62 e8e140c610ec4971afe1b7ec2690382a
msgid "12 GB"
msgstr "12 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 512cd29c308c4d3ab66dbe63e7ea8f48 78f8307ab96c4245a1f09abcd714034c
msgid "vicuna-13b-v1.5"
msgstr "vicuna-13b-v1.5"
#: ../../getting_started/install/deploy/deploy.md
#: 48849903b3cb4888b6dd3d5efcbb24fb 83178c05f6cf431f82bb1d6d25b2645e
#: 979e3ab64df14753b0987bdd49bd5cc6
msgid "20 GB"
msgstr "20 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 0496046d1fb644c28361959b395231d7 3871c7c4432b4a15a9888586cdc70eda
msgid "llama-2-7b"
msgstr "llama-2-7b"
#: ../../getting_started/install/deploy/deploy.md
#: 0c7c632d7c4d44fabfeed58fcc13db8f 78ee1adc6a7e4fa188706a1d5356059f
msgid "llama-2-13b"
msgstr "llama-2-13b"
#: ../../getting_started/install/deploy/deploy.md
#: 15a9341d4a6649908ef88045edd0cb93 d385381b0b4d4eff96a93a9d299cf516
msgid "llama-2-70b"
msgstr "llama-2-70b"
#: ../../getting_started/install/deploy/deploy.md
#: de37a5c2b02a498b9344b24f626db9dc
msgid "48 GB"
msgstr "48 GB"
#: ../../getting_started/install/deploy/deploy.md
#: e897098f81314ce4bf729aee1de7354c
msgid "80 GB"
msgstr "80 GB"
#: ../../getting_started/install/deploy/deploy.md
#: 0782883260f840db8e8bf7c10b5ddf62 b03b5c9343454119ae11fcb2dedf9f90
msgid "baichuan-7b"
msgstr "baichuan-7b"
#: ../../getting_started/install/deploy/deploy.md
#: 008a7d56e8dc4242ae3503bbbf4db153 65ea9ba20adb45519d65da7b16069fa8
msgid "baichuan-13b"
msgstr "baichuan-13b"
#: ../../getting_started/install/deploy/deploy.md:40
#: 1e434048c4844cc1906d83dd68af6d8c
msgid "2. Install"
msgstr "2. Install"
#: ../../getting_started/install/deploy/deploy.md:45
#: c6190ea13c024ddcb8e45ea22a235c3b
msgid ""
"We use Sqlite as default database, so there is no need for database "
"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. [How to install "
"Miniconda](https://docs.conda.io/en/latest/miniconda.html)"
msgstr ""
"目前使用Sqlite作为默认数据库因此DB-"
"GPT快速部署不需要部署相关数据库服务。如果你想使用其他数据库需要先部署相关数据库服务。我们目前使用Miniconda进行python环境和包依赖管理[安装"
" Miniconda](https://docs.conda.io/en/latest/miniconda.html)"
#: ../../getting_started/install/deploy/deploy.md:54
#: ee1e44044b73460ea8cd2f6c2eb6100d
msgid "Before use DB-GPT Knowledge"
msgstr "在使用知识库之前"
#: ../../getting_started/install/deploy/deploy.md:60
#: 6a9ff4138c69429bb159bf452fa7ee55
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 "如果你已经安装好了环境需要创建models, 然后到huggingface官网下载模型"
#: ../../getting_started/install/deploy/deploy.md:63
#: 1299b19bd0f24cc896c59e2c8e7e656c
msgid "Notice make sure you have install git-lfs"
msgstr ""
#: ../../getting_started/install/deploy/deploy.md:65
#: 69b3433c8e5c4cbb960e0178bdd6ac97
msgid "centos:yum install git-lfs"
msgstr ""
#: ../../getting_started/install/deploy/deploy.md:67
#: 50e3cfee5fd5484bb063d41693ac75f0
msgid "ubuntu:app-get install git-lfs"
msgstr ""
#: ../../getting_started/install/deploy/deploy.md:69
#: 81c85ca1188b4ef5b94e0431c6309f9b
msgid "macos:brew install git-lfs"
msgstr ""
#: ../../getting_started/install/deploy/deploy.md:86
#: 9b503ea553a24d488e1c180bf30055ff
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。"
#: ../../getting_started/install/deploy/deploy.md:88
#: 643b6a27bc0f43ee9451d18d52a9a2eb
msgid ""
"if you want to use openai llm service, see [LLM Use FAQ](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/faq/llm/llm_faq.html)"
msgstr ""
"如果想使用openai大模型服务, 可以参考[LLM Use FAQ](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/faq/llm/llm_faq.html)"
#: ../../getting_started/install/deploy/deploy.md:91
#: cc869640e66949e99faa17b1098b1306
msgid "cp .env.template .env"
msgstr "cp .env.template .env"
#: ../../getting_started/install/deploy/deploy.md:94
#: 1b94ed0e469f413b8e9d0ff3cdabca33
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。"
#: ../../getting_started/install/deploy/deploy.md:96
#: 52cfa3636f2b4f949035d2d54b39a123
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 ""
"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。([Vicuna-v1.5](https://huggingface.co/lmsys"
"/vicuna-13b-v1.5) "
"目前Vicuna-v1.5模型(基于llama2)已经开源了我们推荐你使用这个模型通过设置LLM_MODEL=vicuna-13b-v1.5"
#: ../../getting_started/install/deploy/deploy.md:98
#: 491fd44ede1645a3a2db10097c10dbe8
msgid "3. Run"
msgstr "3. Run"
#: ../../getting_started/install/deploy/deploy.md:100
#: f66b8a2b18b34df5b3e74674b4a9d7a9
msgid "1.Run db-gpt server"
msgstr "1.Run db-gpt server"
#: ../../getting_started/install/deploy/deploy.md:105
#: b72283f0ffdc4ecbb4da5239be5fd126
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/install/deploy/deploy.md:116
#: 1fae8a8ce4184feba2d74f877a25d8d2
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web-ui, 请访问https://github./csunny/DB-GPT/tree/new-page-"
"framework/datacenter"
#: ../../getting_started/install/deploy/deploy.md:123
#: 573c0349bd2140e9bb356b53f1da6ee3
#, fuzzy
msgid "Multiple GPUs"
msgstr "4. Multiple GPUs"
#: ../../getting_started/install/deploy/deploy.md:125
#: af5d6a12ec954da19576decdf434df5d
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默认加载可利用的gpu你也可以通过修改 在`.env`文件 `CUDA_VISIBLE_DEVICES=0,1`来指定gpu IDs"
#: ../../getting_started/install/deploy/deploy.md:127
#: de96662007194418a2877cece51dc5cb
msgid ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command, as shown below:"
msgstr "你也可以指定gpu ID启动"
#: ../../getting_started/install/deploy/deploy.md:137
#: 9cb0ff253fb2428dbaec97570e5c4fa4
msgid ""
"You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to "
"configure the maximum memory used by each GPU."
msgstr "同时你可以通过在.env文件设置`MAX_GPU_MEMORY=xxGib`修改每个GPU的最大使用内存"
#: ../../getting_started/install/deploy/deploy.md:139
#: c708ee0a321444dd91be00cda469976c
#, fuzzy
msgid "Not Enough Memory"
msgstr "5. Not Enough Memory"
#: ../../getting_started/install/deploy/deploy.md:141
#: 760347ecf9a44d03a8e17cba153a2cc6
msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
msgstr "DB-GPT 支持 8-bit quantization 和 4-bit quantization."
#: ../../getting_started/install/deploy/deploy.md:143
#: 32e3dc941bfe4d6587e8be262f8fb4d3
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 "你可以通过在.env文件设置`QUANTIZE_8bit=True` or `QUANTIZE_4bit=True`"
#: ../../getting_started/install/deploy/deploy.md:145
#: bdc9a3788149427bac9f3cf35578e206
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 可以运行在 80 GB VRAM机器 4-bit "
"quantization 可以运行在 48 GB VRAM"
#: ../../getting_started/install/deploy/deploy.md:147
#: 9b6085c41b5c4b96ac3e917dc5002fc2
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 ""
"注意,需要安装[requirements.txt](https://github.com/eosphoros-ai/DB-"
"GPT/blob/main/requirements.txt)涉及的所有的依赖"
#~ msgid ""
#~ "Notice make sure you have install "
#~ "git-lfs centos:yum install git-lfs "
#~ "ubuntu:app-get install git-lfs "
#~ "macos:brew install git-lfs"
#~ msgstr ""
#~ "注意下载模型之前确保git-lfs已经安ubuntu:app-get install "
#~ "git-lfs macos:brew install git-lfs"
#~ 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 ""
#~ "你可以参考如何获取Vicuna weights文档[Vicuna](https://github.com/lm-"
#~ "sys/FastChat/blob/main/README.md#model-weights) ."
#~ 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 ""
#~ "如果觉得模型太大你也可以下载vicuna-7b [this "
#~ "link](https://huggingface.co/Tribbiani/vicuna-7b) "
#~ 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_SERVEReg: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(是通过DB-"
#~ "GPT/pilot/server/llmserver.py启动的模型服务)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"

View File

@@ -0,0 +1,118 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/docker/docker.md:1
#: ea5d6b95dea844b89d2f5d0e8f6ebfd3
msgid "Docker Install"
msgstr "Docker 安装"
#: ../../getting_started/install/docker/docker.md:4
#: c1125facb7334346a8e5b66bab892b1c
msgid "Docker (Experimental)"
msgstr "Docker (Experimental)"
#: ../../getting_started/install/docker/docker.md:6
#: 33a64984d0694ec9aee272f8a7ecd4cf
msgid "1. Building Docker image"
msgstr "1.构建Docker镜像"
#: ../../getting_started/install/docker/docker.md:12
#: 656beee32e6f4a49ad48a219910ba36c
msgid "Review images by listing them:"
msgstr "Review images by listing them:"
#: ../../getting_started/install/docker/docker.md:18
#: a8fd727500de480299e5bdfc86151473
msgid "Output should look something like the following:"
msgstr "输出日志应该长这样:"
#: ../../getting_started/install/docker/docker.md:25
#: 965edb9fe5184571b8afc5232cfd2773
msgid "You can pass some parameters to docker/build_all_images.sh."
msgstr "你也可以docker/build_all_images.sh构建的时候指定参数"
#: ../../getting_started/install/docker/docker.md:33
#: a1743c21a4db468db108a60540dd4754
msgid ""
"You can execute the command `bash docker/build_all_images.sh --help` to "
"see more usage."
msgstr "可以指定命令`bash docker/build_all_images.sh --help`查看如何使用"
#: ../../getting_started/install/docker/docker.md:35
#: cb7f05675c674fcf931a6afa6fb7d24c
msgid "2. Run all in one docker container"
msgstr "2. Run all in one docker container"
#: ../../getting_started/install/docker/docker.md:37
#: 2b2d95e668ed428e97eac851c604a74c
msgid "**Run with local model**"
msgstr "**Run with local model**"
#: ../../getting_started/install/docker/docker.md:52
#: ../../getting_started/install/docker/docker.md:87
#: 731540ca95004dd2bb2c3a9871ddb404 e3ab41d312ea40d492b48cf8629553fe
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/install/docker/docker.md:55
#: 2cbab25caaa749f5b753c58947332cb2
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` 指定llm model is vicuna-13b "
#: ../../getting_started/install/docker/docker.md:56
#: ed7e79d43ee940dca788f15d520850a3
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`, 指定挂载的模型文件 "
"directory `/data/models` to the docker container directory `/app/models`,"
" 你也可以替换成你自己的模型."
#: ../../getting_started/install/docker/docker.md:58
#: 98e7bff5dab04979a0bb15abdf2ac1e0
msgid "You can see log with command:"
msgstr "你也可以通过命令查看日志"
#: ../../getting_started/install/docker/docker.md:64
#: 7ce23cecd6f24a6b8d3e4708d5f6265d
msgid "**Run with openai interface**"
msgstr "**Run with openai interface**"
#: ../../getting_started/install/docker/docker.md:83
#: bdf315780f454aaf9ead6414723f34c7
msgid ""
"`-e LLM_MODEL=proxyllm`, means we use proxy llm(openai interface, "
"fastchat interface...)"
msgstr "`-e LLM_MODEL=proxyllm`, 通过设置模型为第三方模型服务API 可以是openai, 也可以是fastchat interface..."
#: ../../getting_started/install/docker/docker.md:84
#: 12b3e78d3ebd47288a8d081eea278b45
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`, 设置知识库embedding模型为text2vec. "
"container.""

View File

@@ -0,0 +1,53 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/docker_compose/docker_compose.md:1
#: f1092bd1601c48789cb6f35ff9141c69
msgid "Docker Compose"
msgstr "Docker Compose"
#: ../../getting_started/install/docker_compose/docker_compose.md:4
#: 63460a1c4e0f46378c6a48643684fa17
msgid "Run with docker compose"
msgstr "Run with docker compose"
#: ../../getting_started/install/docker_compose/docker_compose.md:10
#: fa53c93a8c8b451788987461e6b296b6
msgid "Output should look something like the following:"
msgstr "输出应该这样:"
#: ../../getting_started/install/docker_compose/docker_compose.md:18
#: 6c56a6ef5367442ab924f9a49d955d11
msgid "You can see log with command:"
msgstr "你可以通过命令查看日志"
#: ../../getting_started/install/docker_compose/docker_compose.md:24
#: 1bd9fac3803641fa9ec1730c7d15d3f1
msgid "Open http://localhost:5000 with your browser to see the product."
msgstr "打开浏览器访问Open http://localhost:5000"
#: ../../getting_started/install/docker_compose/docker_compose.md:26
#: 21214a8bf62746078ccf7ab83ccca4f7
msgid ""
"You can open docker-compose.yml in the project root directory to see more"
" details."
msgstr "可以打开docker-compose.yml查看更多内容"

View File

@@ -0,0 +1,361 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-17 13:07+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/environment/environment.md:1
#: be341d16f7b24bf4ad123ab78a6d855a
#, fuzzy
msgid "Environment Parameter"
msgstr "环境变量说明"
#: ../../getting_started/install/environment/environment.md:4
#: 46eddb27c90f41548ea9a724bbcebd37
msgid "LLM MODEL Config"
msgstr "模型配置"
#: ../../getting_started/install/environment/environment.md:5
#: 7deaa85df4a04fb098f5994547a8724f
msgid "LLM Model Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
msgstr "LLM Model Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
#: ../../getting_started/install/environment/environment.md:6
#: 3902801c546547b3a4009df681ef7d52
msgid "LLM_MODEL=vicuna-13b"
msgstr "LLM_MODEL=vicuna-13b"
#: ../../getting_started/install/environment/environment.md:8
#: 84b0fdbfa1544ec28751e9b69b00cc02
msgid "MODEL_SERVER_ADDRESS"
msgstr "MODEL_SERVER_ADDRESS"
#: ../../getting_started/install/environment/environment.md:9
#: 0b430bfab77d405989470d00ca3f6fe0
msgid "MODEL_SERVER=http://127.0.0.1:8000 LIMIT_MODEL_CONCURRENCY"
msgstr "MODEL_SERVER=http://127.0.0.1:8000 LIMIT_MODEL_CONCURRENCY"
#: ../../getting_started/install/environment/environment.md:12
#: b477a25586c546729a93fb6785b7b2ec
msgid "LIMIT_MODEL_CONCURRENCY=5"
msgstr "LIMIT_MODEL_CONCURRENCY=5"
#: ../../getting_started/install/environment/environment.md:14
#: 1d6ea800af384fff9c265610f71cc94e
msgid "MAX_POSITION_EMBEDDINGS"
msgstr "MAX_POSITION_EMBEDDINGS"
#: ../../getting_started/install/environment/environment.md:16
#: 388e758ce4ea4692a4c34294cebce7f2
msgid "MAX_POSITION_EMBEDDINGS=4096"
msgstr "MAX_POSITION_EMBEDDINGS=4096"
#: ../../getting_started/install/environment/environment.md:18
#: 16a307dce1294ceba892ff93ae4e81c0
msgid "QUANTIZE_QLORA"
msgstr "QUANTIZE_QLORA"
#: ../../getting_started/install/environment/environment.md:20
#: 93ceb2b2fcd5454b82eefb0ae8c7ae77
msgid "QUANTIZE_QLORA=True"
msgstr "QUANTIZE_QLORA=True"
#: ../../getting_started/install/environment/environment.md:22
#: 15ffa35d023a4530b02a85ee6168dd4b
msgid "QUANTIZE_8bit"
msgstr "QUANTIZE_8bit"
#: ../../getting_started/install/environment/environment.md:24
#: 81df248ac5cb4ab0b13a711505f6a177
msgid "QUANTIZE_8bit=True"
msgstr "QUANTIZE_8bit=True"
#: ../../getting_started/install/environment/environment.md:27
#: 15cc7b7d41ad44f0891c1189709f00f1
msgid "LLM PROXY Settings"
msgstr "LLM PROXY Settings"
#: ../../getting_started/install/environment/environment.md:28
#: e6c1115a39404f11b193a1593bc51a22
msgid "OPENAI Key"
msgstr "OPENAI Key"
#: ../../getting_started/install/environment/environment.md:30
#: 8157e0a831fe4506a426822b7565e4f6
msgid "PROXY_API_KEY={your-openai-sk}"
msgstr "PROXY_API_KEY={your-openai-sk}"
#: ../../getting_started/install/environment/environment.md:31
#: 89b34d00bdb64e738bd9bc8c086b1f02
msgid "PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions"
msgstr "PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions"
#: ../../getting_started/install/environment/environment.md:33
#: 7a97df730aeb484daf19c8172e61a290
msgid "from https://bard.google.com/ f12-> application-> __Secure-1PSID"
msgstr "from https://bard.google.com/ f12-> application-> __Secure-1PSID"
#: ../../getting_started/install/environment/environment.md:35
#: d430ddf726a049c0a9e0a9bfd5a6fe0e
msgid "BARD_PROXY_API_KEY={your-bard-token}"
msgstr "BARD_PROXY_API_KEY={your-bard-token}"
#: ../../getting_started/install/environment/environment.md:38
#: 23d6b0da3e7042abb55f6181c4a382d2
msgid "DATABASE SETTINGS"
msgstr "DATABASE SETTINGS"
#: ../../getting_started/install/environment/environment.md:39
#: dbae0a2d847f41f5be9396a160ef88d0
msgid "SQLite database (Current default database)"
msgstr "SQLite database (Current default database)"
#: ../../getting_started/install/environment/environment.md:40
#: bdb55b7280c341a981e9d338cce53345
msgid "LOCAL_DB_PATH=data/default_sqlite.db"
msgstr "LOCAL_DB_PATH=data/default_sqlite.db"
#: ../../getting_started/install/environment/environment.md:41
#: 739d67927a9d46b28500deba1917916b
msgid "LOCAL_DB_TYPE=sqlite # Database Type default:sqlite"
msgstr "LOCAL_DB_TYPE=sqlite # Database Type default:sqlite"
#: ../../getting_started/install/environment/environment.md:43
#: eb4717bce6a6483b86d9780d924c5ff1
msgid "MYSQL database"
msgstr "MYSQL database"
#: ../../getting_started/install/environment/environment.md:44
#: 0f4cdf0ff5dd4ff0b397dfa88541a2e1
msgid "LOCAL_DB_TYPE=mysql"
msgstr "LOCAL_DB_TYPE=mysql"
#: ../../getting_started/install/environment/environment.md:45
#: c971ead492c34487bd766300730a9cba
msgid "LOCAL_DB_USER=root"
msgstr "LOCAL_DB_USER=root"
#: ../../getting_started/install/environment/environment.md:46
#: 02828b29ad044eeab890a2f8af0e5907
msgid "LOCAL_DB_PASSWORD=aa12345678"
msgstr "LOCAL_DB_PASSWORD=aa12345678"
#: ../../getting_started/install/environment/environment.md:47
#: 53dc7f15b3934987b1f4c2e2d0b11299
msgid "LOCAL_DB_HOST=127.0.0.1"
msgstr "LOCAL_DB_HOST=127.0.0.1"
#: ../../getting_started/install/environment/environment.md:48
#: 1ac95fc482934247a118bab8dcebeb57
msgid "LOCAL_DB_PORT=3306"
msgstr "LOCAL_DB_PORT=3306"
#: ../../getting_started/install/environment/environment.md:51
#: 34e46aa926844be19c7196759b03af63
msgid "EMBEDDING SETTINGS"
msgstr "EMBEDDING SETTINGS"
#: ../../getting_started/install/environment/environment.md:52
#: 2b5aa08cc995495e85a1f7dc4f97b5d7
msgid "EMBEDDING MODEL Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
msgstr "EMBEDDING模型, 参考see /pilot/configs/model_config.LLM_MODEL_CONFIG"
#: ../../getting_started/install/environment/environment.md:53
#: 0de0ca551ed040248406f848feca541d
msgid "EMBEDDING_MODEL=text2vec"
msgstr "EMBEDDING_MODEL=text2vec"
#: ../../getting_started/install/environment/environment.md:55
#: 43019fb570904c9981eb68f33e64569c
msgid "Embedding Chunk size, default 500"
msgstr "Embedding 切片大小, 默认500"
#: ../../getting_started/install/environment/environment.md:57
#: 7e3f93854873461286e96887e04167aa
msgid "KNOWLEDGE_CHUNK_SIZE=500"
msgstr "KNOWLEDGE_CHUNK_SIZE=500"
#: ../../getting_started/install/environment/environment.md:59
#: 9504f4a59ae74352a524b7741113e2d6
msgid "Embedding Chunk Overlap, default 100"
msgstr "Embedding chunk Overlap, 文本块之间的最大重叠量。保留一些重叠可以保持文本块之间的连续性(例如使用滑动窗口),默认100"
#: ../../getting_started/install/environment/environment.md:60
#: 24e6119c2051479bbd9dba71a9c23dbe
msgid "KNOWLEDGE_CHUNK_OVERLAP=100"
msgstr "KNOWLEDGE_CHUNK_OVERLAP=100"
#: ../../getting_started/install/environment/environment.md:62
#: 0d180d7f2230442abee901c19526e442
msgid "embeding recall top k,5"
msgstr "embedding 召回topk, 默认5"
#: ../../getting_started/install/environment/environment.md:64
#: a5bb9ab2ba50411cbbe87f7836bfbb6d
msgid "KNOWLEDGE_SEARCH_TOP_SIZE=5"
msgstr "KNOWLEDGE_SEARCH_TOP_SIZE=5"
#: ../../getting_started/install/environment/environment.md:66
#: 183b8dd78cba4ae19bd2e08d69d21e0b
msgid "embeding recall max token ,2000"
msgstr "embedding向量召回最大token, 默认2000"
#: ../../getting_started/install/environment/environment.md:68
#: ce0c711febcb44c18ae0fc858c3718d1
msgid "KNOWLEDGE_SEARCH_MAX_TOKEN=5"
msgstr "KNOWLEDGE_SEARCH_MAX_TOKEN=5"
#: ../../getting_started/install/environment/environment.md:71
#: ../../getting_started/install/environment/environment.md:87
#: 4cab1f399cc245b4a1a1976d2c4fc926 ec9cec667a1c4473bf9a796a26e1ce20
msgid "Vector Store SETTINGS"
msgstr "Vector Store SETTINGS"
#: ../../getting_started/install/environment/environment.md:72
#: ../../getting_started/install/environment/environment.md:88
#: 4dd04aadd46948a5b1dcf01fdb0ef074 bab7d512f33e40cf9e10f0da67e699c8
msgid "Chroma"
msgstr "Chroma"
#: ../../getting_started/install/environment/environment.md:73
#: ../../getting_started/install/environment/environment.md:89
#: 13eec36741b14e028e2d3859a320826e ab3ffbcf9358401993af636ba9ab2e2d
msgid "VECTOR_STORE_TYPE=Chroma"
msgstr "VECTOR_STORE_TYPE=Chroma"
#: ../../getting_started/install/environment/environment.md:74
#: ../../getting_started/install/environment/environment.md:90
#: d15b91e2a2884f23a1dd2d54783b0638 d1f856d571b547098bb0c2a18f9f1979
msgid "MILVUS"
msgstr "MILVUS"
#: ../../getting_started/install/environment/environment.md:75
#: ../../getting_started/install/environment/environment.md:91
#: 1e165f6c934343c7808459cc7a65bc70 985dd60c2b7d4baaa6601a810a6522d7
msgid "VECTOR_STORE_TYPE=Milvus"
msgstr "VECTOR_STORE_TYPE=Milvus"
#: ../../getting_started/install/environment/environment.md:76
#: ../../getting_started/install/environment/environment.md:92
#: a1a53f051cee40ed886346a94babd75a d263e8eaee684935a58f0a4fe61c6f0e
msgid "MILVUS_URL=127.0.0.1"
msgstr "MILVUS_URL=127.0.0.1"
#: ../../getting_started/install/environment/environment.md:77
#: ../../getting_started/install/environment/environment.md:93
#: 2741a312db1a4c6a8a1c1d62415c5fba d03bbf921ddd4f4bb715fe5610c3d0aa
msgid "MILVUS_PORT=19530"
msgstr "MILVUS_PORT=19530"
#: ../../getting_started/install/environment/environment.md:78
#: ../../getting_started/install/environment/environment.md:94
#: d0786490d38c4e4f971cc14f62fe1fc8 e9e0854873dc4c209861ee4eb77d25cd
msgid "MILVUS_USERNAME"
msgstr "MILVUS_USERNAME"
#: ../../getting_started/install/environment/environment.md:79
#: ../../getting_started/install/environment/environment.md:95
#: 9a82d07153cc432ebe754b5bc02fde0d a6485c1cfa7d4069a6894c43674c8c2b
msgid "MILVUS_PASSWORD"
msgstr "MILVUS_PASSWORD"
#: ../../getting_started/install/environment/environment.md:80
#: ../../getting_started/install/environment/environment.md:96
#: 2f233f32b8ba408a9fbadb21fabb99ec 809b3219dd824485bc2cfc898530d708
msgid "MILVUS_SECURE="
msgstr "MILVUS_SECURE="
#: ../../getting_started/install/environment/environment.md:82
#: ../../getting_started/install/environment/environment.md:98
#: f00603661f2b42e1bd2bca74ad1e3c31 f378e16fdec44c559e34c6929de812e8
msgid "WEAVIATE"
msgstr "WEAVIATE"
#: ../../getting_started/install/environment/environment.md:83
#: da2049ebc6874cf0a6b562e0e2fd9ec7
msgid "VECTOR_STORE_TYPE=Weaviate"
msgstr "VECTOR_STORE_TYPE=Weaviate"
#: ../../getting_started/install/environment/environment.md:84
#: ../../getting_started/install/environment/environment.md:99
#: 25f1246629934289aad7ef01c7304097 c9fe0e413d9a4fc8abf86b3ed99e0581
msgid "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
msgstr "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
#: ../../getting_started/install/environment/environment.md:102
#: ba7c9e707f6a4cd6b99e52b58da3ab2d
msgid "Multi-GPU Setting"
msgstr "Multi-GPU Setting"
#: ../../getting_started/install/environment/environment.md:103
#: 5ca75fdf2c264b2c844d77f659b4f0b3
msgid ""
"See https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-"
"visibility-cuda_visible_devices/ If CUDA_VISIBLE_DEVICES is not "
"configured, all available gpus will be used"
msgstr ""
"参考 https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-"
"cuda_visible_devices/ 如果 CUDA_VISIBLE_DEVICES没有设置, 会使用所有可用的gpu"
#: ../../getting_started/install/environment/environment.md:106
#: de92eb310aff43fbbbf3c5a116c3b2c6
msgid "CUDA_VISIBLE_DEVICES=0"
msgstr "CUDA_VISIBLE_DEVICES=0"
#: ../../getting_started/install/environment/environment.md:108
#: d2641df6123a442b8e4444ad5f01a9aa
msgid ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command"
msgstr "你也可以通过启动命令设置gpu ID"
#: ../../getting_started/install/environment/environment.md:110
#: 76c66179d11a4e5fa369421378609aae
msgid "CUDA_VISIBLE_DEVICES=3,4,5,6"
msgstr "CUDA_VISIBLE_DEVICES=3,4,5,6"
#: ../../getting_started/install/environment/environment.md:112
#: 29bd0f01fdf540ad98385ea8473f7647
msgid "You can configure the maximum memory used by each GPU."
msgstr "可以设置GPU的最大内存"
#: ../../getting_started/install/environment/environment.md:114
#: 31e5e23838734ba7a2810e2387e6d6a0
msgid "MAX_GPU_MEMORY=16Gib"
msgstr "MAX_GPU_MEMORY=16Gib"
#: ../../getting_started/install/environment/environment.md:117
#: 99aa63ab1ae049d9b94536d6a96f3443
msgid "Other Setting"
msgstr "Other Setting"
#: ../../getting_started/install/environment/environment.md:118
#: 3168732183874bffb59a3575d3473d62
msgid "Language Settings(influence prompt language)"
msgstr "Language Settings(涉及prompt语言以及知识切片方式)"
#: ../../getting_started/install/environment/environment.md:119
#: 73eb0a96f29b4739bd456faa9cb5033d
msgid "LANGUAGE=en"
msgstr "LANGUAGE=en"
#: ../../getting_started/install/environment/environment.md:120
#: c6646b78c6cf4d25a13108232f5b2046
msgid "LANGUAGE=zh"
msgstr "LANGUAGE=zh"

View File

@@ -0,0 +1,322 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-17 21:23+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/llm/llama/llama_cpp.md:1
#: 911085eb102a47c1832411ada8b8b906
msgid "llama.cpp"
msgstr "llama.cpp"
#: ../../getting_started/install/llm/llama/llama_cpp.md:3
#: 8099fe03f2204c7f90968ae5c0cae117
msgid ""
"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)."
msgstr "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)."
#: ../../getting_started/install/llm/llama/llama_cpp.md:5
#: 79c33615ad6d44859b33ed0d05fdb1a5
msgid "Running llama.cpp"
msgstr "运行 llama.cpp"
#: ../../getting_started/install/llm/llama/llama_cpp.md:7
#: 3111bf827639484fb5e5f72a42b1b4e7
msgid "Preparing Model Files"
msgstr "准备模型文件"
#: ../../getting_started/install/llm/llama/llama_cpp.md:9
#: 823f04ec193946d080b203a19c4ed96f
msgid ""
"To use llama.cpp, you need to prepare a ggml format model file, and there"
" are two common ways to obtain it, you can choose either:"
msgstr "使用llama.cpp, 你需要准备ggml格式的文件你可以通过以下两种方法获取"
#: ../../getting_started/install/llm/llama/llama_cpp.md:11
#: c631f3c1a1db429c801c24fa7799b2e1
msgid "Download a pre-converted model file."
msgstr "Download a pre-converted model file."
#: ../../getting_started/install/llm/llama/llama_cpp.md:13
#: 1ac7d5845ca241519ec15236e9802af6
msgid ""
"Suppose you want to use [Vicuna 7B v1.5](https://huggingface.co/lmsys"
"/vicuna-7b-v1.5), you can download the file already converted from "
"[TheBloke/vicuna-7B-v1.5-GGML](https://huggingface.co/TheBloke/vicuna-"
"7B-v1.5-GGML), only one file is needed. Download it to the `models` "
"directory and rename it to `ggml-model-q4_0.bin`."
msgstr "假设您想使用[Vicuna 7B v1.5](https://huggingface.co/lmsys"
"/vicuna-7b-v1.5)您可以从[TheBloke/vicuna-7B-v1.5-GGML](https://huggingface.co/TheBloke/vicuna-"
"7B-v1.5-GGML)下载已转换的文件只需要一个文件。将其下载到models目录并将其重命名为ggml-model-q4_0.bin。"
#: ../../getting_started/install/llm/llama/llama_cpp.md:19
#: 65344fafdaa1469797592e454ebee7b5
msgid "Convert It Yourself"
msgstr "Convert It Yourself"
#: ../../getting_started/install/llm/llama/llama_cpp.md:21
#: 8da2bda172884c9fb2d64901d8b9178c
msgid ""
"You can convert the model file yourself according to the instructions in "
"[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp"
"#prepare-data--run), and put the converted file in the models directory "
"and rename it to `ggml-model-q4_0.bin`."
msgstr "您可以根据[llama.cpp#prepare-data--run](https://github.com/ggerganov/llama.cpp"
"#prepare-data--run)中的说明自己转换模型文件然后将转换后的文件放入models目录中并将其重命名为ggml-model-q4_0.bin。"
#: ../../getting_started/install/llm/llama/llama_cpp.md:23
#: d30986c0a84448ff89bc4bb84e3d0deb
msgid "Installing Dependencies"
msgstr "安装依赖"
#: ../../getting_started/install/llm/llama/llama_cpp.md:25
#: b91ca009587b45679c54f4dce07c2eb3
msgid ""
"llama.cpp is an optional dependency in DB-GPT, and you can manually "
"install it using the following command:"
msgstr "llama.cpp在DB-GPT中是可选安装项, 你可以通过一下命令进行安装"
#: ../../getting_started/install/llm/llama/llama_cpp.md:31
#: 2c89087ba2214d97bc01a286826042bc
msgid "Modifying the Configuration File"
msgstr "修改配置文件"
#: ../../getting_started/install/llm/llama/llama_cpp.md:33
#: e4ebd4dac0cd4fb4a8e3c1f6edde7ea8
msgid "Next, you can directly modify your `.env` file to enable llama.cpp."
msgstr "修改`.env`文件使用llama.cpp"
#: ../../getting_started/install/llm/llama/llama_cpp.md:40
#: 2fce7ec613784c8e96f19e9f4c4fb818
msgid ""
"Then you can run it according to [Run](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run)."
msgstr "然后你可以通过[Run](https://db-"
"gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html#run).来运行"
#: ../../getting_started/install/llm/llama/llama_cpp.md:43
#: 9bbaa16512d2420aa368ba34825cc024
msgid "More Configurations"
msgstr "更多配置文件"
#: ../../getting_started/install/llm/llama/llama_cpp.md:45
#: 5ce014aa175d4a119150cf184098a0c3
msgid ""
"In DB-GPT, the model configuration can be done through `{model "
"name}_{config key}`."
msgstr "In DB-GPT, the model configuration can be done through `{model "
"name}_{config key}`."
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 09d1f9eaf6cc4267b1eb94e4a8e78ba9
msgid "Environment Variable Key"
msgstr "Environment Variable Key"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 6650b3f2495e41588e23d8a2647e7ce3
msgid "default"
msgstr "default"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 8f33e692a7fc41e1a42663535b95a08c
msgid "Prompt Template Name"
msgstr "Prompt Template Name"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 2f8ca1f267694949a2b251d0ef576fd8
msgid "llama_cpp_prompt_template"
msgstr "llama_cpp_prompt_template"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 9b6d310d3f3c454488f76062c8bcda67 c80abec11c3240cf9d0122543e9401c3
#: ed439c9374d74543a8d2a4f88f4db958 f49b3e4281b14f1b8909cd13159d406a
#: ffa824cc22a946ab851124b58cf7441a
msgid "None"
msgstr "None"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: f41bd292bcb9491096c39b36bceb3816
msgid ""
"Prompt template name, now support: `zero_shot, vicuna_v1.1, llama-2"
",baichuan-chat`, If None, the prompt template is automatically determined"
" from model path。"
msgstr "Prompt template 现在可以支持`zero_shot, vicuna_v1.1, llama-2"
",baichuan-chat`, 如果是None, the prompt template可以自动选择模型路径"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 8125df74f1a7429eb0c5ce350edc9315
msgid "llama_cpp_model_path"
msgstr "llama_cpp_model_path"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 28ad71d410fb4757821bf8cc1c232357
msgid "Model path"
msgstr "Model path"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: b7133f115d79477ab416dc63c64d8aa7
msgid "llama_cpp_n_gpu_layers"
msgstr "llama_cpp_n_gpu_layers"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 7cdd27333a464ebeab6bf41bca709816
msgid "1000000000"
msgstr "1000000000"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 667ec37bc6824eba999f39f4e6072999
msgid "Number of layers to offload to the GPU, Set this to 1000000000 to offload"
" all layers to the GPU. If your GPU VRAM is not enough, you can set a low"
" number, eg: `10`"
msgstr "要将层数转移到GPU上将其设置为1000000000以将所有层转移到GPU上。如果您的GPU VRAM不足可以设置较低的数字例如10。"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: edae6c77475d4958a96d59b4bd165916
msgid "llama_cpp_n_threads"
msgstr "llama_cpp_n_threads"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 8fef1cdd4b0b42faadc717a58b9434a4
msgid ""
"Number of threads to use. If None, the number of threads is automatically"
" determined"
msgstr "要使用的线程数量。如果为None则线程数量将自动确定。"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: ef5f27f600aa4eaf8080d6dca46ad434
msgid "llama_cpp_n_batch"
msgstr "llama_cpp_n_batch"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: be999101e5f84b83bde0d8e801083c52
msgid "512"
msgstr "512"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: cdc7a51c720a4fe38323eb7a1cfa6bd1
msgid "Maximum number of prompt tokens to batch together when calling llama_eval"
msgstr "在调用llama_eval时批处理在一起的prompt tokens的最大数量。
"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 26d08360c2df4d018b2416cf8e4b3f48
msgid "llama_cpp_n_gqa"
msgstr "llama_cpp_n_gqa"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 4d22c4f8e285445f9c26d181cf350cb7
msgid "Grouped-query attention. Must be 8 for llama-2 70b."
msgstr "对于llama-2 70b模型Grouped-query attention必须为8。"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 18e5e5ba6ac64e818546742458fb4c84
msgid "llama_cpp_rms_norm_eps"
msgstr "llama_cpp_rms_norm_eps"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: fc85743d71e1428fa2aa0423ff9d9170
msgid "5e-06"
msgstr "5e-06"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: bfc53bec0df94d9e8e9cc7d3333a69c1
msgid "5e-6 is a good value for llama-2 models."
msgstr "对于llama-2模型来说5e-6是一个不错的值。"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 81fc8f37787d48b0b1da826a2f887886
msgid "llama_cpp_cache_capacity"
msgstr "llama_cpp_cache_capacity"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 125e3285249449cb90bbff063868d4d4
msgid "Maximum cache capacity. Examples: 2000MiB, 2GiB"
msgstr "cache capacity最大值. Examples: 2000MiB, 2GiB"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: 31ed49d49f574d4983738d91bed95fc9
msgid "llama_cpp_prefer_cpu"
msgstr "llama_cpp_prefer_cpu"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: b6ed0d5394874bb38c7468216b8bca88
msgid "False"
msgstr "False"
#: ../../getting_started/install/llm/llama/llama_cpp.md
#: d148d6b130454666a601b65b444c7e51
msgid ""
"If a GPU is available, it will be preferred by default, unless "
"prefer_cpu=False is configured."
msgstr "如果有可用的GPU默认情况下会优先使用GPU除非配置了prefer_cpu=False。"
#: ../../getting_started/install/llm/llama/llama_cpp.md:59
#: 75bd31d245b148569bcf9eca6c8bec9c
msgid "GPU Acceleration"
msgstr "GPU 加速"
#: ../../getting_started/install/llm/llama/llama_cpp.md:61
#: 1cf5538f9d39457e901f4120f76d54c1
msgid ""
"GPU acceleration is supported by default. If you encounter any issues, "
"you can uninstall the dependent packages with the following command:"
msgstr "默认情况下支持GPU加速。如果遇到任何问题您可以使用以下命令卸载相关的依赖包"
#: ../../getting_started/install/llm/llama/llama_cpp.md:66
#: 08f8eea38e5e44fa80b528b75a379acf
msgid ""
"Then install `llama-cpp-python` according to the instructions in [llama-"
"cpp-python](https://github.com/abetlen/llama-cpp-"
"python/blob/main/README.md)."
msgstr "然后通过指令[llama-"
"cpp-python](https://github.com/abetlen/llama-cpp-"
"python/blob/main/README.md).安装`llama-cpp-python`"
#: ../../getting_started/install/llm/llama/llama_cpp.md:69
#: abea5d4418c54657981640d6227b7be2
msgid "Mac Usage"
msgstr "Mac Usage"
#: ../../getting_started/install/llm/llama/llama_cpp.md:71
#: be9fb5ecbdd5495b98007decccbd0372
msgid ""
"Special attention, if you are using Apple Silicon (M1) Mac, it is highly "
"recommended to install arm64 architecture python support, for example:"
msgstr "特别注意如果您正在使用苹果芯片M1的Mac电脑强烈建议安装arm64架构的Python支持例如"
#: ../../getting_started/install/llm/llama/llama_cpp.md:78
#: efd6dfd4e9e24bf884803143e2b123f2
msgid "Windows Usage"
msgstr "Windows使用"
#: ../../getting_started/install/llm/llama/llama_cpp.md:80
#: 27ecf054aa294a2eaed701c46edf27a7
msgid ""
"The use under the Windows platform has not been rigorously tested and "
"verified, and you are welcome to use it. If you have any problems, you "
"can create an [issue](https://github.com/eosphoros-ai/DB-GPT/issues) or "
"[contact us](https://github.com/eosphoros-ai/DB-GPT/tree/main#contact-"
"information) directly."
msgstr "在Windows平台上的使用尚未经过严格的测试和验证欢迎您使用。如果您有任何问题可以创建一个[issue](https://github.com/eosphoros-ai/DB-GPT/issues)或者[contact us](https://github.com/eosphoros-ai/DB-GPT/tree/main#contact-"
"information) directly."

View File

@@ -0,0 +1,99 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-17 23:29+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/llm/llm.rst:2
#: ../../getting_started/install/llm/llm.rst:23
#: 9e4baaff732b49f1baded5fd1bde4bd5
msgid "LLM Usage"
msgstr "LLM使用"
#: ../../getting_started/install/llm/llm.rst:3 d80e7360f17c4be889f220e2a846a81e
msgid ""
"DB-GPT provides a management and deployment solution for multiple models."
" This chapter mainly discusses how to deploy different models."
msgstr "DB-GPT提供了多模型的管理和部署方案本章主要讲解针对不同的模型该怎么部署"
#: ../../getting_started/install/llm/llm.rst:18
#: 1cebd6c84b924eeb877ba31bd520328f
msgid ""
"Multi LLMs Support, Supports multiple large language models, currently "
"supporting"
msgstr "目前DB-GPT已适配如下模型"
#: ../../getting_started/install/llm/llm.rst:9 1163d5d3a8834b24bb6a5716d4fcc680
msgid "🔥 Vicuna-v1.5(7b,13b)"
msgstr "🔥 Vicuna-v1.5(7b,13b)"
#: ../../getting_started/install/llm/llm.rst:10
#: 318dbc8e8de64bfb9cbc65343d050500
msgid "🔥 llama-2(7b,13b,70b)"
msgstr "🔥 llama-2(7b,13b,70b)"
#: ../../getting_started/install/llm/llm.rst:11
#: f2b1ef2bfbde46889131b6852d1211e8
msgid "WizardLM-v1.2(13b)"
msgstr "WizardLM-v1.2(13b)"
#: ../../getting_started/install/llm/llm.rst:12
#: 2462160e5928434aaa6f58074b585c14
msgid "Vicuna (7b,13b)"
msgstr "Vicuna (7b,13b)"
#: ../../getting_started/install/llm/llm.rst:13
#: 61cc1b9ed1914e379dee87034e9fbaea
msgid "ChatGLM-6b (int4,int8)"
msgstr "ChatGLM-6b (int4,int8)"
#: ../../getting_started/install/llm/llm.rst:14
#: 653f5fd3b6ab4c508a2ce449231b5a17
msgid "ChatGLM2-6b (int4,int8)"
msgstr "ChatGLM2-6b (int4,int8)"
#: ../../getting_started/install/llm/llm.rst:15
#: 6a1cf7a271f6496ba48d593db1f756f1
msgid "guanaco(7b,13b,33b)"
msgstr "guanaco(7b,13b,33b)"
#: ../../getting_started/install/llm/llm.rst:16
#: f15083886362437ba96e1cb9ade738aa
msgid "Gorilla(7b,13b)"
msgstr "Gorilla(7b,13b)"
#: ../../getting_started/install/llm/llm.rst:17
#: 5e1ded19d1b24ba485e5d2bf22ce2db7
msgid "Baichuan(7b,13b)"
msgstr "Baichuan(7b,13b)"
#: ../../getting_started/install/llm/llm.rst:18
#: 30f6f71dd73b48d29a3647d58a9cdcaf
msgid "OpenAI"
msgstr "OpenAI"
#: ../../getting_started/install/llm/llm.rst:20
#: 9ad21acdaccb41c1bbfa30b5ce114732
msgid "llama_cpp"
msgstr "llama_cpp"
#: ../../getting_started/install/llm/llm.rst:21
#: b5064649f7c9443c9b9f15ec7fc02434
msgid "quantization"
msgstr "quantization"

View File

@@ -0,0 +1,26 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-17 13:07+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/llm/quantization/quantization.md:1
#: 2b540d0fbece43c5a9d90e0935eb574c
msgid "quantization"
msgstr "quantization"

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: 2023-07-13 15:39+0800\n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,67 +19,76 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/installation.md:1 bc5bfc8ebfc847c5a22f2346357cf747
msgid "Installation"
msgstr "安装dbgpt包指南"
#: ../../getting_started/installation.md:1 f9e65f84d13249098aa2768bb7cc69ed
msgid "Python SDK"
msgstr ""
#: ../../getting_started/installation.md:2 1aaef0db5ee9426aa337021d782666af
#: ../../getting_started/installation.md:2 1902cffb20fe4994aecb577c1a3fa8bf
msgid ""
"DB-GPT provides a third-party Python API package that you can integrate "
"into your own code."
msgstr "DB-GPT提供了python第三方包你可以在你的代码中引入"
#: ../../getting_started/installation.md:4 de542f259e20441991a0e5a7d52769b8
#: ../../getting_started/installation.md:4 908a7c1971d04e37bd5e88171bd93d3b
msgid "Installation from Pip"
msgstr "使用pip安装"
#: ../../getting_started/installation.md:6 3357f019aa8249b292162de92757eec4
#: ../../getting_started/installation.md:6 0eff7cb3c9c643e0884209daddf5d709
msgid "You can simply pip install:"
msgstr "你可以使用pip install"
#: ../../getting_started/installation.md:12 9c610d593608452f9d7d8d7e462251e3
#: ../../getting_started/installation.md:12 1b0f308412cd44bda55efff5830b99f3
msgid "Notice:make sure python>=3.10"
msgstr "注意:确保你的python版本>=3.10"
#: ../../getting_started/installation.md:15 b2ed238c29bb40cba990068e8d7ceae7
#: ../../getting_started/installation.md:15 bec8afbfa9af4594bb09307f92c617a4
msgid "Environment Setup"
msgstr "环境设置"
#: ../../getting_started/installation.md:17 4804ad4d8edf44f49b1d35b271635fad
#: ../../getting_started/installation.md:17 61f60acc7a6449ac974593bd5f164e3e
msgid "By default, if you use the EmbeddingEngine api"
msgstr "如果你想使用EmbeddingEngine api"
#: ../../getting_started/installation.md:19 2205f69ec60d4f73bb3a93a583928455
#: ../../getting_started/installation.md:19 f31d9989e0514881baed8c690bc8035a
msgid "you will prepare embedding models from huggingface"
msgstr "你需要从huggingface下载embedding models"
#: ../../getting_started/installation.md:22 693c18a83f034dcc8c263674418bcde2
#: ../../getting_started/installation.md:22 02eb7897412c4223a013e7921eaed253
msgid "Notice make sure you have install git-lfs"
msgstr "确保你已经安装了git-lfs"
#: ../../getting_started/installation.md:30 dd8d0880b55e4c48bfc414f8cbdda268
#: ../../getting_started/installation.md:30 ced612323d5b47d3b93febbc637515bd
msgid "version:"
msgstr "版本:"
#: ../../getting_started/installation.md:31 731e634b96164efbbc1ce9fa88361b12
#: ../../getting_started/installation.md:31 4c168bdddb664c76ad4c2be177ef01a0
msgid "db-gpt0.3.0"
msgstr "db-gpt0.3.0"
#: ../../getting_started/installation.md:32 38fb635be4554d94b527c6762253d46d
#: ../../getting_started/installation.md:32 9bc5bb66e7214ca0b945b6b46a989307
msgid ""
"[embedding_engine api](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge.html)"
msgstr "[embedding_engine api](https://db-gpt.readthedocs.io/en/latest/modules/knowledge.html)"
msgstr ""
"[embedding_engine api](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge.html)"
#: ../../getting_started/installation.md:33 a60b0ffe21a74ebca05529dc1dd1ba99
#: ../../getting_started/installation.md:33 52e656e2f0ae46688a6456a441f9c1e5
msgid ""
"[multi source embedding](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge/pdf/pdf_embedding.html)"
msgstr "[multi source embedding](https://db-gpt.readthedocs.io/en/latest/modules/knowledge/pdf/pdf_embedding.html)"
msgstr ""
"[multi source embedding](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge/pdf/pdf_embedding.html)"
#: ../../getting_started/installation.md:34 3c752c9305414719bc3f561cf18a75af
#: ../../getting_started/installation.md:34 726c87e53d8e4cd799d422aaf562fa29
msgid ""
"[vector connector](https://db-"
"gpt.readthedocs.io/en/latest/modules/vector.html)"
msgstr "[vector connector](https://db-gpt.readthedocs.io/en/latest/modules/vector.html)"
msgstr ""
"[vector connector](https://db-"
"gpt.readthedocs.io/en/latest/modules/vector.html)"
#~ msgid "Installation"
#~ msgstr "安装dbgpt包指南"

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: 2023-07-12 16:23+0800\n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,25 +19,29 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/tutorials.md:1 cb100b89a2a747cd90759e415c737070
#: ../../getting_started/tutorials.md:1 3e4b863de01942d5823d5dd3975bcb05
msgid "Tutorials"
msgstr "教程"
#: ../../getting_started/tutorials.md:4 dbc2a2346b384cc3930086f97181b14b
#: ../../getting_started/tutorials.md:4 bf8a3dc2c8d045d0b4668ecbd25c954d
msgid "This is a collection of DB-GPT tutorials on Medium."
msgstr "这是知乎上DB-GPT教程的集合。"
#: ../../getting_started/tutorials.md:6 67e5b6dbac654d428e6a8be9d1ec6473
#: ../../getting_started/tutorials.md:6 e72430ed63ca4c13bab165d61293585a
msgid ""
"DB-GPT is divided into several functions, including chat with knowledge "
"base, execute SQL, chat with database, and execute plugins."
msgstr "DB-GPT包含以下功能和知识库聊天执行SQL和数据库聊天以及执行插件。"
#: ../../getting_started/tutorials.md:8 744aaec68aa3413c9b17b09714476d32
#: ../../getting_started/tutorials.md:8 29cb77fcc97e494ba26ecd61fd21d84f
msgid "Introduction"
msgstr "介绍"
#: ../../getting_started/tutorials.md:9 305bcf5e847a4322a2834b84fa3c694a
#: ../../getting_started/tutorials.md:10 0158e41b603a47d8a8d0debcddc1d99c
msgid "youtube"
msgstr ""
#: ../../getting_started/tutorials.md:11 bd8078ee97094559b3e9b4a90a89651a
#, fuzzy
msgid "[What is DB-GPT](https://www.youtube.com/watch?v=QszhVJerc0I)"
msgstr ""
@@ -45,69 +49,75 @@ msgstr ""
"GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?buvid=551b023900b290f9497610b2155a2668&is_story_h5=false&mid=%2BVyE%2Fwau5woPcUKieCWS0A%3D%3D&p=1&plat_id=116&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=5D08B533-82A4-4D40-9615-7826065B4574&share_source=GENERIC&share_tag=s_i&timestamp=1686307943&unique_k=bhO3lgQ&up_id=31375446)"
" by csunny (https://github.com/csunny/DB-GPT)"
#: ../../getting_started/tutorials.md:11 22fdc6937b2248ae8f5a7ef385aa55d9
#, fuzzy
msgid "Knowledge"
msgstr "知识库"
#: ../../getting_started/tutorials.md:13 9bbf0f5aece64389b93b16235abda58e
#: ../../getting_started/tutorials.md:13 0330432860384964804cc6ea9054d06b
#, fuzzy
msgid ""
"[How to Create your own knowledge repository](https://db-"
"gpt.readthedocs.io/en/latest/modules/knownledge.html)"
"[How to deploy DB-GPT step by "
"step](https://www.youtube.com/watch?v=OJGU4fQCqPs)"
msgstr ""
"[怎么创建自己的知识库](https://db-"
"gpt.readthedocs.io/en/latest/modules/knowledge.html)"
"###Introduction [什么是DB-"
"GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?buvid=551b023900b290f9497610b2155a2668&is_story_h5=false&mid=%2BVyE%2Fwau5woPcUKieCWS0A%3D%3D&p=1&plat_id=116&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=5D08B533-82A4-4D40-9615-7826065B4574&share_source=GENERIC&share_tag=s_i&timestamp=1686307943&unique_k=bhO3lgQ&up_id=31375446)"
" by csunny (https://github.com/csunny/DB-GPT)"
#: ../../getting_started/tutorials.md:15 ae201d75a3aa485e99b258103245db1c
#, fuzzy
msgid "![Add new Knowledge demonstration](../../assets/new_knownledge.gif)"
msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:16 a5b7b6e46df040ddaea184487b6a6ba3
msgid "bilibili"
msgstr "bilibili"
#: ../../getting_started/tutorials.md:15 e7bfb3396f7b42f1a1be9f29df1773a2
#, fuzzy
msgid "Add new Knowledge demonstration"
msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:17 9da89100917742fca40ab71bc1283504
msgid ""
"[What is DB-"
"GPT](https://www.bilibili.com/video/BV1SM4y1a7Nj/?spm_id_from=333.788&vd_source=7792e22c03b7da3c556a450eb42c8a0f)"
msgstr "[DB-"
"GPT介绍](https://www.bilibili.com/video/BV1SM4y1a7Nj/?spm_id_from=333.788&vd_source=7792e22c03b7da3c556a450eb42c8a0f)"
#: ../../getting_started/tutorials.md:17 d37acc0486ec40309e7e944bb0458b0a
msgid "SQL Generation"
msgstr "SQL生成"
#: ../../getting_started/tutorials.md:19 d0b58d505c774d0e867dbd87e703d4ed
msgid ""
"[How to deploy DB-GPT step by "
"step](https://www.bilibili.com/video/BV1mu411Y7ve/?spm_id_from=pageDriver&vd_source=7792e22c03b7da3c556a450eb42c8a0f)"
msgstr "[How to deploy DB-GPT step by "
"step](https://www.bilibili.com/video/BV1mu411Y7ve/?spm_id_from=pageDriver&vd_source=7792e22c03b7da3c556a450eb42c8a0f)"
#: ../../getting_started/tutorials.md:18 86a328c9e15f46679a2611f7162f9fbe
#, fuzzy
msgid "![sql generation demonstration](../../assets/demo_en.gif)"
msgstr "[sql生成演示](../../assets/demo_en.gif)"
#~ msgid "Knowledge"
#~ msgstr "知识库"
#: ../../getting_started/tutorials.md:18 03bc8d7320be44f0879a553a324ec26f
#, fuzzy
msgid "sql generation demonstration"
msgstr "[sql生成演示](../../assets/demo_en.gif)"
#~ msgid ""
#~ "[How to Create your own knowledge "
#~ "repository](https://db-"
#~ "gpt.readthedocs.io/en/latest/modules/knownledge.html)"
#~ msgstr ""
#~ "[怎么创建自己的知识库](https://db-"
#~ "gpt.readthedocs.io/en/latest/modules/knowledge.html)"
#: ../../getting_started/tutorials.md:20 5f3b241f24634c09880d5de014f64f1b
msgid "SQL Execute"
msgstr "SQL执行"
#~ msgid "![Add new Knowledge demonstration](../../assets/new_knownledge.gif)"
#~ msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:21 13a16debf2624f44bfb2e0453c11572d
#, fuzzy
msgid "![sql execute demonstration](../../assets/auto_sql_en.gif)"
msgstr "[sql execute 演示](../../assets/auto_sql_en.gif)"
#~ msgid "Add new Knowledge demonstration"
#~ msgstr "[新增知识库演示](../../assets/new_knownledge_en.gif)"
#: ../../getting_started/tutorials.md:21 2d9673cfd48b49a5b1942fdc9de292bf
#, fuzzy
msgid "sql execute demonstration"
msgstr "SQL执行演示"
#~ msgid "SQL Generation"
#~ msgstr "SQL生成"
#: ../../getting_started/tutorials.md:23 8cc0c647ad804969b470b133708de37f
#, fuzzy
msgid "Plugins"
msgstr "DB插件"
#~ msgid "![sql generation demonstration](../../assets/demo_en.gif)"
#~ msgstr "[sql生成演示](../../assets/demo_en.gif)"
#: ../../getting_started/tutorials.md:24 cad5cc0cb94b42a1a6619bbd2a8b9f4c
#, fuzzy
msgid "![db plugins demonstration](../../assets/dashboard.png)"
msgstr "[db plugins 演示](../../assets/dbgpt_bytebase_plugin.gif)"
#~ msgid "sql generation demonstration"
#~ msgstr "[sql生成演示](../../assets/demo_en.gif)"
#: ../../getting_started/tutorials.md:24 adeee7ea37b743c9b251976124520725
msgid "db plugins demonstration"
msgstr "DB插件演示"
#~ msgid "SQL Execute"
#~ msgstr "SQL执行"
#~ msgid "![sql execute demonstration](../../assets/auto_sql_en.gif)"
#~ msgstr "[sql execute 演示](../../assets/auto_sql_en.gif)"
#~ msgid "sql execute demonstration"
#~ msgstr "SQL执行演示"
#~ msgid "Plugins"
#~ msgstr "DB插件"
#~ msgid "![db plugins demonstration](../../assets/dashboard.png)"
#~ msgstr "[db plugins 演示](../../assets/dbgpt_bytebase_plugin.gif)"
#~ msgid "db plugins demonstration"
#~ msgstr "DB插件演示"

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: 2023-07-20 10:53+0800\n"
"POT-Creation-Date: 2023-08-17 21:58+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@@ -19,35 +19,31 @@ msgstr ""
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../index.rst:34 ../../index.rst:45 5bab1511780c442e9dd9e18519ad7ef3
#: ../../index.rst:34 ../../index.rst:45 3566ae9872dd4f97844f9e0680de5f5d
msgid "Getting Started"
msgstr "开始"
#: ../../index.rst:57 ../../index.rst:78 dbdeae6c9a344e7889d399a5dbbca872
#: ../../index.rst:59 ../../index.rst:80 6845a928056940b28be8c13d766009f8
msgid "Modules"
msgstr "模块"
#: ../../index.rst:92 ../../index.rst:108 43594aec45bf49609d7c7435c6472a9b
#: ../../index.rst:94 ../../index.rst:110 ef3bcf6f837345fca8539d51434e3c2c
msgid "Use Cases"
msgstr "示例"
#: ../../index.rst:122 ../../index.rst:125 013a0e5d909e4332ac49f6200924043e
#: ../../index.rst:124 ../../index.rst:127 b10b8b49e4f5459f8bea881ffc9259d5
msgid "Reference"
msgstr "参考"
#: ../../index.rst:134 ../../index.rst:137 42907cf1d1bb491bae2fcd7ede06e421
msgid "FAQ"
msgstr ""
#: ../../index.rst:161 ../../index.rst:167 64f4a587bc1f4ca9a456b97fac5d6def
#: ../../index.rst:137 ../../index.rst:143 12e75881253a4c4383ac7364c1103348
msgid "Resources"
msgstr "资源"
#: ../../index.rst:7 df1ad6da308f49debd4053e5899a4c8d
#: ../../index.rst:7 f1a30af655744c0b8fb7197a5fc3a45b
msgid "Welcome to DB-GPT!"
msgstr "欢迎来到DB-GPT中文文档"
#: ../../index.rst:8 cc5b388ea2924968b2769e4b4a159761
#: ../../index.rst:8 426686c829a342798eaae9f789260621
msgid ""
"As large models are released and iterated upon, they are becoming "
"increasingly intelligent. However, in the process of using large models, "
@@ -65,7 +61,7 @@ msgstr ""
"我们启动了DB-"
"GPT项目为所有基于数据库的场景构建一个完整的私有大模型解决方案。该方案“”支持本地部署既可应用于“独立私有环境”又可根据业务模块进行“独立部署”和“隔离”确保“大模型”的能力绝对私有、安全、可控。"
#: ../../index.rst:10 b831cd62a1ba46108dcf343792e8d67a
#: ../../index.rst:10 0a7fbd17ecfd48cb8e0593e35a225e1b
msgid ""
"**DB-GPT** is an experimental open-source project that uses localized GPT"
" large models to interact with your data and environment. With this "
@@ -75,102 +71,102 @@ msgstr ""
"DB-GPT 是一个开源的以数据库为基础的GPT实验项目使用本地化的GPT大模型与您的数据和环境进行交互无数据泄露风险100% 私密100%"
" 安全。"
#: ../../index.rst:12 3baac7e36a824395a57c246e05560c67
#: ../../index.rst:12 50e02964b1e24c4fa598f820796aec61
msgid "**Features**"
msgstr "特性"
#: ../../index.rst:13 6638568ff94e47f6a0b04a6775ca45d1
#: ../../index.rst:13 62b74478b9b046dfa7606785939ca70e
msgid ""
"Currently, we have released multiple key features, which are listed below"
" to demonstrate our current capabilities:"
msgstr "目前我们已经发布了多种关键的特性,这里一一列举展示一下当前发布的能力。"
#: ../../index.rst:15 b49710ac36ed4a188280aeb3589f11fe
#: ../../index.rst:15 f593159ba8dd4388bd2ba189f9efd5ea
msgid "SQL language capabilities - SQL generation - SQL diagnosis"
msgstr "SQL语言能力 - SQL生成 - SQL诊断"
#: ../../index.rst:19 6bd495632b39477e8948677aeb4ab1ee
#: ../../index.rst:19 b829655a3ef146528beb9c50538be84e
msgid ""
"Private domain Q&A and data processing - Database knowledge Q&A - Data "
"processing"
msgstr "私有领域问答与数据处理 - 数据库知识问答 - 数据处理"
#: ../../index.rst:23 d1d3665a412246b9814139a938a29d1b
#: ../../index.rst:23 43e988a100a740358f1a0be1710d7960
msgid ""
"Plugins - Support custom plugin execution tasks and natively support the "
"Auto-GPT plugin, such as:"
msgstr "插件模型 - 支持自定义插件执行任务并原生支持Auto-GPT插件例如:* SQL自动执行获取查询结果 * 自动爬取学习知识"
#: ../../index.rst:26 41e37b63a8f44fc09a4da3574b25fcd3
#: ../../index.rst:26 888186524aef4fe5a0ba643d55783fd9
msgid ""
"Unified vector storage/indexing of knowledge base - Support for "
"unstructured data such as PDF, Markdown, CSV, and WebURL"
msgstr "知识库统一向量存储/索引 - 非结构化数据支持包括PDF、MarkDown、CSV、WebURL"
#: ../../index.rst:29 1acac8a6cbe54f7b8c31135189d726d6
#: ../../index.rst:29 fab4f961fe1746dca3d5e369de714108
msgid ""
"Milti LLMs Support - Supports multiple large language models, currently "
"supporting Vicuna (7b, 13b), ChatGLM-6b (int4, int8) - TODO: codegen2, "
"codet5p"
msgstr "多模型支持 - 支持多种大语言模型, 当前已支持Vicuna(7b,13b), ChatGLM-6b(int4, int8)"
#: ../../index.rst:35 481edf63bcd348b4b3e14353dc5be952
#: ../../index.rst:35 7bc21f280364448da0edc046378be622
msgid ""
"How to get started using DB-GPT to interact with your data and "
"environment."
msgstr "开始使用DB-GPT与您的数据环境进行交互。"
#: ../../index.rst:36 6b26a04661f7445198b3797442d3f178
#: ../../index.rst:36 5362221ecdf5427faa51df83d4a939ee
#, fuzzy
msgid "`Quickstart Guide <./getting_started/getting_started.html>`_"
msgstr "`使用指南 <./getting_started/getting_started.html>`_"
#: ../../index.rst:38 ff435ef9964d44508ad840de2950c1c8
#: ../../index.rst:38 e028ed5afce842fbb76a6ce825d5a8e2
msgid "Concepts and terminology"
msgstr "相关概念"
#: ../../index.rst:40 db9dfacbe93e4f858843c4d2a0e2dd25
#: ../../index.rst:40 f773ac5e50054c308920c0b95a44b0cb
#, fuzzy
msgid "`Concepts and Terminology <./getting_started/concepts.html>`_"
msgstr "`相关概念 <./getting_started/concepts.html>`_"
#: ../../index.rst:42 50faf8302ba140ce84897daef2c90ca2
#: ../../index.rst:42 afeee818ec45454da12b80161b5f1de0
msgid "Coming soon..."
msgstr ""
#: ../../index.rst:44 547bb007f90e43c096f25647cebefd7b
#: ../../index.rst:44 cb4f911316234b86aad88b83d2784ad3
msgid "`Tutorials <.getting_started/tutorials.html>`_"
msgstr "`教程 <.getting_started/tutorials.html>`_"
#: ../../index.rst:59 89bc50c752b84e3fb789ce5da1b654dc
#: ../../index.rst:61 de365722d61442b99f44fcde8a8c9efb
msgid ""
"These modules are the core abstractions with which we can interact with "
"data and environment smoothly."
msgstr "这些模块是我们可以与数据和环境顺利地进行交互的核心组成。"
#: ../../index.rst:60 81f3860920964720958c62b3a6769f12
#: ../../index.rst:62 8fbb6303d3cd4fcc956815f44ef1fa8d
msgid ""
"It's very important for DB-GPT, DB-GPT also provide standard, extendable "
"interfaces."
msgstr "DB-GPT还提供了标准的、可扩展的接口。"
#: ../../index.rst:62 15faf914d05544df86359e50fdc70483
#: ../../index.rst:64 797ac43f459b4662a5097c8cb783c4ba
msgid ""
"The docs for each module contain quickstart examples, how to guides, "
"reference docs, and conceptual guides."
msgstr "每个模块的文档都包含快速入门的例子、操作指南、参考文档和相关概念等内容。"
#: ../../index.rst:64 18a673690afa47df8e6dd3d065b2580f
#: ../../index.rst:66 70d7b89c1c154c65aabedbb3c94c8771
msgid "The modules are as follows"
msgstr "组成模块如下:"
#: ../../index.rst:66 d2c20ed1b6ba4aa697090453b0f775a1
#: ../../index.rst:68 794d8a939e274894910fcdbb3ee52429
msgid ""
"`LLMs <./modules/llms.html>`_: Supported multi models management and "
"integrations."
msgstr "`LLMs <./modules/llms.html>`_:基于FastChat提供大模型的运行环境。支持多模型管理和集成。 "
#: ../../index.rst:68 d6c72e6fee3348e89422f9ff45804e3a
#: ../../index.rst:70 58b0d2fcac2c471494fe2b6b5b3f1b49
msgid ""
"`Prompts <./modules/prompts.html>`_: Prompt management, optimization, and"
" serialization for multi database."
@@ -178,59 +174,59 @@ msgstr ""
"`Prompt自动生成与优化 <./modules/prompts.html>`_: 自动化生成高质量的Prompt "
",并进行优化,提高系统的响应效率"
#: ../../index.rst:70 1756de47335d4eb7916a6c8b8b5ab70b
#: ../../index.rst:72 d433b62e11f64e18995bd334f93992a6
msgid "`Plugins <./modules/plugins.html>`_: Plugins management, scheduler."
msgstr "`Agent与插件 <./modules/plugins.html>`_:提供Agent和插件机制使得用户可以自定义并增强系统的行为。"
#: ../../index.rst:72 542efb88411f4cc192a08e7d28c84863
#: ../../index.rst:74 3e7eb10f64274c07ace90b84ffc904b4
#, fuzzy
msgid ""
"`Knowledge <./modules/knowledge.html>`_: Knowledge management, embedding,"
" and search."
msgstr "`知识库能力: <./modules/knowledge.html>`_: 支持私域知识库问答能力, "
#: ../../index.rst:74 0204630cd5f14c68ada3bf11e0b0fbf5
#: ../../index.rst:76 3af796f287f54de0869a086cfa24b568
msgid ""
"`Connections <./modules/connections.html>`_: Supported multi databases "
"connection. management connections and interact with this."
msgstr "`连接模块 <./modules/connections.html>`_: 用于连接不同的模块和数据源,实现数据的流转和交互 "
#: ../../index.rst:76 f9363a963be44d0ea01bb5d65b69d0f8
#: ../../index.rst:78 27273a4020a540f4b28e7c54ea9c9232
#, fuzzy
msgid "`Vector <./modules/vector.html>`_: Supported multi vector database."
msgstr "`LLMs <./modules/llms.html>`_:基于FastChat提供大模型的运行环境。支持多模型管理和集成。 "
#: ../../index.rst:94 7223c3b95e9446bcae40a355e6b02324
#: ../../index.rst:96 d887747669d1429f950c56131cd35a62
msgid "Best Practices and built-in implementations for common DB-GPT use cases:"
msgstr "DB-GPT用例的最佳实践和内置方法:"
#: ../../index.rst:96 c088f2ab9f2247ac9a8c9af31d0da7a6
#: ../../index.rst:98 63ea6a449012432baeeef975db5c3ac1
msgid ""
"`Sql generation and diagnosis "
"<./use_cases/sql_generation_and_diagnosis.html>`_: SQL generation and "
"diagnosis."
msgstr "`Sql生成和诊断 <./use_cases/sql_generation_and_diagnosis.html>`_: Sql生成和诊断。"
#: ../../index.rst:98 23973b07c6ba42088a714b048d4b43c4
#: ../../index.rst:100 c7388a2147af48d1a6619492a3b926db
msgid ""
"`knownledge Based QA <./use_cases/knownledge_based_qa.html>`_: A "
"important scene for user to chat with database documents, codes, bugs and"
" schemas."
msgstr "`知识库问答 <./use_cases/knownledge_based_qa.html>`_: 用户与数据库文档、代码和bug聊天的重要场景\""
#: ../../index.rst:100 6a1d77bc56a14803b66ebc9f2b6c4b7b
#: ../../index.rst:102 f5a459f5a84241648a6a05f7ba3026c0
msgid ""
"`Chatbots <./use_cases/chatbots.html>`_: Language model love to chat, use"
" multi models to chat."
msgstr "`聊天机器人 <./use_cases/chatbots.html>`_: 使用多模型进行对话"
#: ../../index.rst:102 621774a68cba46daa7112f865e6e3af9
#: ../../index.rst:104 d566174db6eb4834854c00ce7295c297
msgid ""
"`Querying Database Data <./use_cases/query_database_data.html>`_: Query "
"and Analysis data from databases and give charts."
msgstr "`查询数据库数据 <./use_cases/query_database_data.html>`_:从数据库中查询和分析数据并给出图表。"
#: ../../index.rst:104 9f379fbe8aac47f4a1a53d84ab2a2f51
#: ../../index.rst:106 89aac5a738ae4aeb84bc324803ada354
msgid ""
"`Interacting with apis <./use_cases/interacting_with_api.html>`_: "
"Interact with apis, such as create a table, deploy a database cluster, "
@@ -239,39 +235,39 @@ msgstr ""
"`API交互 <./use_cases/interacting_with_api.html>`_: "
"与API交互例如创建表、部署数据库集群、创建数据库等。"
#: ../../index.rst:106 3dbb717e1b024a20bb6049facb616b1b
#: ../../index.rst:108 f100fb0cdd264cf186bf554771488aa1
msgid ""
"`Tool use with plugins <./use_cases/tool_use_with_plugin>`_: According to"
" Plugin use tools to manage databases autonomoly."
msgstr "`插件工具 <./use_cases/tool_use_with_plugin>`_: 根据插件使用工具自主管理数据库。"
#: ../../index.rst:123 4acedc39ccf34e79b805189a11285a3a
#: ../../index.rst:125 93809b95cc4a41249d7ab6b264981167
msgid ""
"Full documentation on all methods, classes, installation methods, and "
"integration setups for DB-GPT."
msgstr "关于DB-GPT的所有方法、类、安装方法和集成设置的完整文档。"
#: ../../index.rst:135 622112f3cce34461ba7e0d52fa81d438
msgid "DB-GPT FAQ."
msgstr ""
#: ../../index.rst:146 a989256fd69f4bbfae73191b505c59fa
msgid "Ecosystem"
msgstr "环境系统"
#: ../../index.rst:148 1b5c410dd94842f2801f08540dd57647
msgid "Guides for how other companies/products can be used with DB-GPT"
msgstr "其他公司/产品如何与DB-GPT一起使用的方法指南"
#: ../../index.rst:163 8368b4c62ebe41ad91551e241dbcc4df
#: ../../index.rst:139 4a95e65e128e4fc0907a3f51f1f2611b
msgid ""
"Additional resources we think may be useful as you develop your "
"application!"
msgstr "“我们认为在您开发应用程序时可能有用的其他资源!”"
#: ../../index.rst:165 2a4cd897b20c4683979b44fb9d7470e6
#: ../../index.rst:141 4934fbae909644769dd83c7f99c0fcd0
msgid ""
"`Discord <https://discord.gg/eZHE94MN>`_: if your have some "
"problem or ideas, you can talk from discord."
"`Discord <https://discord.gg/eZHE94MN>`_: if your have some problem or "
"ideas, you can talk from discord."
msgstr "`Discord <https://discord.gg/eZHE94MN>`_:如果您有任何问题可以到discord中进行交流。"
#~ msgid "FAQ"
#~ msgstr ""
#~ msgid "DB-GPT FAQ."
#~ msgstr ""
#~ msgid "Ecosystem"
#~ msgstr "环境系统"
#~ msgid "Guides for how other companies/products can be used with DB-GPT"
#~ msgstr "其他公司/产品如何与DB-GPT一起使用的方法指南"

View File

@@ -0,0 +1,52 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2023, csunny
# This file is distributed under the same license as the DB-GPT package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2023.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.0\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-07-13 15:39+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 2.12.1\n"
#: ../../modules/knowledge/string/string_embedding.md:1
#: 0dbae4a197aa4e45a16cfd90c137c8f2
msgid "String"
msgstr ""
#: ../../modules/knowledge/string/string_embedding.md:3
#: bf9f445b1d2045848ad3c663e4551c1f
msgid ""
"string embedding can import a long raw text into a vector knowledge base."
" The entire embedding process includes the read (loading data), "
"data_process (data processing), and index_to_store (embedding to the "
"vector database) methods."
msgstr ""
#: ../../modules/knowledge/string/string_embedding.md:5
#: 4418539511024c2fa8cf1e73ade226a8
msgid "inheriting the SourceEmbedding"
msgstr ""
#: ../../modules/knowledge/string/string_embedding.md:23
#: 178050a4cdd6429aa73406043d89869b
msgid ""
"implement read() and data_process() read() method allows you to read data"
" and split data into chunk"
msgstr ""
#: ../../modules/knowledge/string/string_embedding.md:32
#: fdaf95f201624242bbfcff36480e1819
msgid "data_process() method allows you to pre processing your ways"
msgstr ""

View File

@@ -37,6 +37,10 @@ LLM_MODEL_CONFIG = {
"vicuna-13b-v1.5": os.path.join(MODEL_PATH, "vicuna-13b-v1.5"),
"vicuna-7b-v1.5": os.path.join(MODEL_PATH, "vicuna-7b-v1.5"),
"text2vec": os.path.join(MODEL_PATH, "text2vec-large-chinese"),
# https://huggingface.co/moka-ai/m3e-large
"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"),
"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"),
@@ -64,6 +68,7 @@ LLM_MODEL_CONFIG = {
"baichuan-7b": os.path.join(MODEL_PATH, "baichuan-7b"),
# (Llama2 based) We only support WizardLM-13B-V1.2 for now, which is trained from Llama-2 13b, see https://huggingface.co/WizardLM/WizardLM-13B-V1.2
"wizardlm-13b": os.path.join(MODEL_PATH, "WizardLM-13B-V1.2"),
"llama-cpp": os.path.join(MODEL_PATH, "ggml-model-q4_0.bin"),
}
# Load model config

View File

@@ -70,10 +70,10 @@ class SQLiteConnect(RDBMSDatabase):
def _sync_tables_from_db(self) -> Iterable[str]:
table_results = self.session.execute(
"SELECT name FROM sqlite_master WHERE type='table'"
text("SELECT name FROM sqlite_master WHERE type='table'")
)
view_results = self.session.execute(
"SELECT name FROM sqlite_master WHERE type='view'"
text("SELECT name FROM sqlite_master WHERE type='view'")
)
table_results = set(row[0] for row in table_results)
view_results = set(row[0] for row in view_results)

View File

@@ -121,3 +121,17 @@ def test_get_database_list(db):
def test_get_database_names(db):
db.get_database_names() == []
def test_db_dir_exist_dir():
with tempfile.TemporaryDirectory() as temp_dir:
new_dir = os.path.join(temp_dir, "new_dir")
file_path = os.path.join(new_dir, "sqlite.db")
db = SQLiteConnect.from_file_path(file_path)
assert os.path.exists(new_dir) == True
assert list(db.get_table_names()) == []
with tempfile.TemporaryDirectory() as existing_dir:
file_path = os.path.join(existing_dir, "sqlite.db")
db = SQLiteConnect.from_file_path(file_path)
assert os.path.exists(existing_dir) == True
assert list(db.get_table_names()) == []

View File

@@ -3,7 +3,9 @@
import torch
import os
from typing import List
import re
from pathlib import Path
from typing import List, Tuple
from functools import cache
from transformers import (
AutoModel,
@@ -12,8 +14,10 @@ from transformers import (
LlamaTokenizer,
BitsAndBytesConfig,
)
from pilot.model.parameter import ModelParameters, LlamaCppModelParameters
from pilot.configs.model_config import DEVICE
from pilot.configs.config import Config
from pilot.logs import logger
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
@@ -24,6 +28,14 @@ bnb_config = BitsAndBytesConfig(
CFG = Config()
class ModelType:
""" "Type of model"""
HF = "huggingface"
LLAMA_CPP = "llama.cpp"
# TODO, support more model type
class BaseLLMAdaper:
"""The Base class for multi model, in our project.
We will support those model, which performance resemble ChatGPT"""
@@ -31,8 +43,17 @@ class BaseLLMAdaper:
def use_fast_tokenizer(self) -> bool:
return False
def model_type(self) -> str:
return ModelType.HF
def model_param_class(self, model_type: str = None) -> ModelParameters:
model_type = model_type if model_type else self.model_type()
if model_type == ModelType.LLAMA_CPP:
return LlamaCppModelParameters
return ModelParameters
def match(self, model_path: str):
return True
return False
def loader(self, model_path: str, from_pretrained_kwargs: dict):
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
@@ -52,12 +73,25 @@ def register_llm_model_adapters(cls):
@cache
def get_llm_model_adapter(model_path: str) -> BaseLLMAdaper:
def get_llm_model_adapter(model_name: str, model_path: str) -> BaseLLMAdaper:
# Prefer using model name matching
for adapter in llm_model_adapters:
if adapter.match(model_path):
if adapter.match(model_name):
logger.info(
f"Found llm model adapter with model name: {model_name}, {adapter}"
)
return adapter
raise ValueError(f"Invalid model adapter for {model_path}")
for adapter in llm_model_adapters:
if adapter.match(model_path):
logger.info(
f"Found llm model adapter with model path: {model_path}, {adapter}"
)
return adapter
raise ValueError(
f"Invalid model adapter for model name {model_name} and model path {model_path}"
)
# TODO support cpu? for practise we support gpt4all or chatglm-6b-int4?
@@ -296,6 +330,52 @@ class WizardLMAdapter(BaseLLMAdaper):
return "wizardlm" in model_path.lower()
class LlamaCppAdapater(BaseLLMAdaper):
@staticmethod
def _parse_model_path(model_path: str) -> Tuple[bool, str]:
path = Path(model_path)
if not path.exists():
# Just support local model
return False, None
if not path.is_file():
model_paths = list(path.glob("*ggml*.bin"))
if not model_paths:
return False
model_path = str(model_paths[0])
logger.warn(
f"Model path {model_path} is not single file, use first *gglm*.bin model file: {model_path}"
)
if not re.fullmatch(".*ggml.*\.bin", model_path):
return False, None
return True, model_path
def model_type(self) -> ModelType:
return ModelType.LLAMA_CPP
def match(self, model_path: str):
"""
https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML
"""
if "llama-cpp" == model_path:
return True
is_match, _ = LlamaCppAdapater._parse_model_path(model_path)
return is_match
def loader(self, model_path: str, from_pretrained_kwargs: dict):
# TODO not support yet
_, model_path = LlamaCppAdapater._parse_model_path(model_path)
tokenizer = AutoTokenizer.from_pretrained(
model_path, trust_remote_code=True, use_fast=False
)
model = AutoModelForCausalLM.from_pretrained(
model_path,
trust_remote_code=True,
low_cpu_mem_usage=True,
**from_pretrained_kwargs,
)
return model, tokenizer
register_llm_model_adapters(VicunaLLMAdapater)
register_llm_model_adapters(ChatGLMAdapater)
register_llm_model_adapters(GuanacoAdapter)
@@ -305,6 +385,7 @@ register_llm_model_adapters(GPT4AllAdapter)
register_llm_model_adapters(Llama2Adapter)
register_llm_model_adapters(BaichuanAdapter)
register_llm_model_adapters(WizardLMAdapter)
register_llm_model_adapters(LlamaCppAdapater)
# TODO Default support vicuna, other model need to tests and Evaluate
# just for test_py, remove this later

View File

View File

@@ -0,0 +1,145 @@
"""
Fork from text-generation-webui https://github.com/oobabooga/text-generation-webui/blob/main/modules/llamacpp_model.py
"""
import re
from typing import Dict, Any
import torch
import llama_cpp
from pilot.model.parameter import LlamaCppModelParameters
from pilot.logs import logger
if torch.cuda.is_available() and not torch.version.hip:
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
else:
llama_cpp_cuda = None
def llama_cpp_lib(prefer_cpu: bool = False):
if prefer_cpu or llama_cpp_cuda is None:
logger.info(f"Llama.cpp use cpu")
return llama_cpp
else:
return llama_cpp_cuda
def ban_eos_logits_processor(eos_token, input_ids, logits):
logits[eos_token] = -float("inf")
return logits
def get_params(model_path: str, model_params: LlamaCppModelParameters) -> Dict:
return {
"model_path": model_path,
"n_ctx": model_params.max_context_size,
"seed": model_params.seed,
"n_threads": model_params.n_threads,
"n_batch": model_params.n_batch,
"use_mmap": True,
"use_mlock": False,
"low_vram": False,
"n_gpu_layers": 0 if model_params.prefer_cpu else model_params.n_gpu_layers,
"n_gqa": model_params.n_gqa,
"logits_all": True,
"rms_norm_eps": model_params.rms_norm_eps,
}
class LlamaCppModel:
def __init__(self):
self.initialized = False
self.model = None
self.verbose = True
def __del__(self):
if self.model:
self.model.__del__()
@classmethod
def from_pretrained(self, model_path, model_params: LlamaCppModelParameters):
Llama = llama_cpp_lib(prefer_cpu=model_params.prefer_cpu).Llama
LlamaCache = llama_cpp_lib(prefer_cpu=model_params.prefer_cpu).LlamaCache
result = self()
cache_capacity = 0
cache_capacity_str = model_params.cache_capacity
if cache_capacity_str is not None:
if "GiB" in cache_capacity_str:
cache_capacity = (
int(re.sub("[a-zA-Z]", "", cache_capacity_str)) * 1000 * 1000 * 1000
)
elif "MiB" in cache_capacity_str:
cache_capacity = (
int(re.sub("[a-zA-Z]", "", cache_capacity_str)) * 1000 * 1000
)
else:
cache_capacity = int(cache_capacity_str)
params = get_params(model_path, model_params)
logger.info("Cache capacity is " + str(cache_capacity) + " bytes")
logger.info(f"Load LLama model with params: {params}")
result.model = Llama(**params)
result.verbose = model_params.verbose
if cache_capacity > 0:
result.model.set_cache(LlamaCache(capacity_bytes=cache_capacity))
# This is ugly, but the model and the tokenizer are the same object in this library.
return result, result
def encode(self, string):
if type(string) is str:
string = string.encode()
return self.model.tokenize(string)
def decode(self, tokens):
return self.model.detokenize(tokens)
def generate_streaming(self, params, context_len: int):
# LogitsProcessorList = llama_cpp_lib().LogitsProcessorList
# Read parameters
prompt = params["prompt"]
if self.verbose:
print(f"Prompt of model: \n{prompt}")
temperature = float(params.get("temperature", 1.0))
repetition_penalty = float(params.get("repetition_penalty", 1.1))
top_p = float(params.get("top_p", 1.0))
top_k = int(params.get("top_k", -1)) # -1 means disable
max_new_tokens = int(params.get("max_new_tokens", 2048))
echo = bool(params.get("echo", True))
max_src_len = context_len - max_new_tokens
# Handle truncation
prompt = self.encode(prompt)
prompt = prompt[-max_src_len:]
prompt = self.decode(prompt).decode("utf-8")
# TODO Compared with the original llama model, the Chinese effect of llama.cpp is very general, and it needs to be debugged
completion_chunks = self.model.create_completion(
prompt=prompt,
max_tokens=max_new_tokens,
temperature=temperature,
top_p=top_p,
top_k=top_k,
repeat_penalty=repetition_penalty,
# tfs_z=params['tfs'],
# mirostat_mode=int(params['mirostat_mode']),
# mirostat_tau=params['mirostat_tau'],
# mirostat_eta=params['mirostat_eta'],
stream=True,
echo=echo,
logits_processor=None,
)
output = ""
for completion_chunk in completion_chunks:
text = completion_chunk["choices"][0]["text"]
output += text
# print(output)
yield output

View File

@@ -0,0 +1,8 @@
from typing import Dict
import torch
@torch.inference_mode()
def generate_stream(model, tokenizer, params: Dict, device: str, context_len: int):
# Just support LlamaCppModel
return model.generate_streaming(params=params, context_len=context_len)

View File

@@ -2,48 +2,24 @@
# -*- coding: utf-8 -*-
from typing import Optional, Dict
import dataclasses
import torch
from pilot.configs.model_config import DEVICE
from pilot.model.adapter import get_llm_model_adapter, BaseLLMAdaper
from pilot.model.adapter import get_llm_model_adapter, BaseLLMAdaper, ModelType
from pilot.model.compression import compress_module
from pilot.model.parameter import (
EnvArgumentParser,
ModelParameters,
LlamaCppModelParameters,
_genenv_ignoring_key_case,
)
from pilot.model.llm.monkey_patch import replace_llama_attn_with_non_inplace_operations
from pilot.singleton import Singleton
from pilot.utils import get_gpu_memory
from pilot.logs import logger
class ModelType:
""" "Type of model"""
HF = "huggingface"
LLAMA_CPP = "llama.cpp"
# TODO, support more model type
@dataclasses.dataclass
class ModelParams:
device: str
model_name: str
model_path: str
model_type: Optional[str] = ModelType.HF
num_gpus: Optional[int] = None
max_gpu_memory: Optional[str] = None
cpu_offloading: Optional[bool] = False
load_8bit: Optional[bool] = True
load_4bit: Optional[bool] = False
# quantization datatypes, `fp4` (four bit float) and `nf4` (normal four bit float)
quant_type: Optional[str] = "nf4"
# Nested quantization is activated through `use_double_quant``
use_double_quant: Optional[bool] = True
# "bfloat16", "float16", "float32"
compute_dtype: Optional[str] = None
debug: Optional[bool] = False
trust_remote_code: Optional[bool] = True
def _check_multi_gpu_or_4bit_quantization(model_params: ModelParams):
def _check_multi_gpu_or_4bit_quantization(model_params: ModelParameters):
# TODO: vicuna-v1.5 8-bit quantization info is slow
# TODO: support wizardlm quantization, see: https://huggingface.co/WizardLM/WizardLM-13B-V1.2/discussions/5
model_name = model_params.model_name.lower()
@@ -51,7 +27,7 @@ def _check_multi_gpu_or_4bit_quantization(model_params: ModelParams):
return any(m in model_name for m in supported_models)
def _check_quantization(model_params: ModelParams):
def _check_quantization(model_params: ModelParameters):
model_name = model_params.model_name.lower()
has_quantization = any([model_params.load_8bit or model_params.load_4bit])
if has_quantization:
@@ -69,6 +45,21 @@ def _check_quantization(model_params: ModelParams):
return has_quantization
def _get_model_real_path(model_name, default_model_path) -> str:
"""Get model real path by model name
priority from high to low:
1. environment variable with key: {model_name}_model_path
2. environment variable with key: model_path
3. default_model_path
"""
env_prefix = model_name + "_"
env_prefix = env_prefix.replace("-", "_")
env_model_path = _genenv_ignoring_key_case("model_path", env_prefix=env_prefix)
if env_model_path:
return env_model_path
return _genenv_ignoring_key_case("model_path", default_value=default_model_path)
class ModelLoader(metaclass=Singleton):
"""Model loader is a class for model load
@@ -83,6 +74,7 @@ class ModelLoader(metaclass=Singleton):
self.device = DEVICE
self.model_path = model_path
self.model_name = model_name
self.prompt_template: str = None
self.kwargs = {
"torch_dtype": torch.float16,
"device_map": "auto",
@@ -97,7 +89,18 @@ class ModelLoader(metaclass=Singleton):
cpu_offloading=False,
max_gpu_memory: Optional[str] = None,
):
model_params = ModelParams(
llm_adapter = get_llm_model_adapter(self.model_name, self.model_path)
model_type = llm_adapter.model_type()
param_cls = llm_adapter.model_param_class(model_type)
args_parser = EnvArgumentParser()
# Read the parameters of the model from the environment variable according to the model name prefix, which currently has the highest priority
# vicuna_13b_max_gpu_memory=13Gib or VICUNA_13B_MAX_GPU_MEMORY=13Gib
env_prefix = self.model_name + "_"
env_prefix = env_prefix.replace("-", "_")
model_params = args_parser.parse_args_into_dataclass(
param_cls,
env_prefix=env_prefix,
device=self.device,
model_path=self.model_path,
model_name=self.model_name,
@@ -105,14 +108,21 @@ class ModelLoader(metaclass=Singleton):
cpu_offloading=cpu_offloading,
load_8bit=load_8bit,
load_4bit=load_4bit,
debug=debug,
verbose=debug,
)
self.prompt_template = model_params.prompt_template
logger.info(f"model_params:\n{model_params}")
llm_adapter = get_llm_model_adapter(model_params.model_path)
return huggingface_loader(llm_adapter, model_params)
if model_type == ModelType.HF:
return huggingface_loader(llm_adapter, model_params)
elif model_type == ModelType.LLAMA_CPP:
return llamacpp_loader(llm_adapter, model_params)
else:
raise Exception(f"Unkown model type {model_type}")
def huggingface_loader(llm_adapter: BaseLLMAdaper, model_params: ModelParams):
def huggingface_loader(llm_adapter: BaseLLMAdaper, model_params: ModelParameters):
device = model_params.device
max_memory = None
@@ -175,14 +185,14 @@ def huggingface_loader(llm_adapter: BaseLLMAdaper, model_params: ModelParams):
pass
except AttributeError:
pass
if model_params.debug:
if model_params.verbose:
print(model)
return model, tokenizer
def load_huggingface_quantization_model(
llm_adapter: BaseLLMAdaper,
model_params: ModelParams,
model_params: ModelParameters,
kwargs: Dict,
max_memory: Dict[int, str],
):
@@ -312,3 +322,17 @@ def load_huggingface_quantization_model(
)
return model, tokenizer
def llamacpp_loader(llm_adapter: BaseLLMAdaper, model_params: LlamaCppModelParameters):
try:
from pilot.model.llm.llama_cpp.llama_cpp import LlamaCppModel
except ImportError as exc:
raise ValueError(
"Could not import python package: llama-cpp-python "
"Please install db-gpt llama support with `cd $DB-GPT-DIR && pip install .[llama_cpp]` "
"or install llama-cpp-python with `pip install llama-cpp-python`"
) from exc
model_path = model_params.model_path
model, tokenizer = LlamaCppModel.from_pretrained(model_path, model_params)
return model, tokenizer

151
pilot/model/parameter.py Normal file
View File

@@ -0,0 +1,151 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import os
from typing import Any, Optional, Type
from dataclasses import dataclass, field, fields
from pilot.model.conversation import conv_templates
suported_prompt_templates = ",".join(conv_templates.keys())
def _genenv_ignoring_key_case(env_key: str, env_prefix: str = None, default_value=None):
"""Get the value from the environment variable, ignoring the case of the key"""
if env_prefix:
env_key = env_prefix + env_key
return os.getenv(
env_key, os.getenv(env_key.upper(), os.getenv(env_key.lower(), default_value))
)
class EnvArgumentParser:
def parse_args_into_dataclass(
self, dataclass_type: Type, env_prefix: str = None, **kwargs
) -> Any:
for field in fields(dataclass_type):
env_var_value = _genenv_ignoring_key_case(field.name, env_prefix)
if env_var_value:
env_var_value = env_var_value.strip()
if field.type is int or field.type == Optional[int]:
env_var_value = int(env_var_value)
elif field.type is float or field.type == Optional[float]:
env_var_value = float(env_var_value)
elif field.type is bool or field.type == Optional[bool]:
env_var_value = env_var_value.lower() == "true"
elif field.type is str or field.type == Optional[str]:
pass
else:
raise ValueError(f"Unsupported parameter type {field.type}")
kwargs[field.name] = env_var_value
return dataclass_type(**kwargs)
@dataclass
class ModelParameters:
device: str = field(metadata={"help": "Device to run model"})
model_name: str = field(metadata={"help": "Model name"})
model_path: str = field(metadata={"help": "Model path"})
model_type: Optional[str] = field(
default="huggingface", metadata={"help": "Model type, huggingface or llama.cpp"}
)
prompt_template: Optional[str] = field(
default=None,
metadata={
"help": f"Prompt template. If None, the prompt template is automatically determined from model path, supported template: {suported_prompt_templates}"
},
)
max_context_size: Optional[int] = field(
default=4096, metadata={"help": "Maximum context size"}
)
num_gpus: Optional[int] = field(
default=None,
metadata={
"help": "The number of gpus you expect to use, if it is empty, use all of them as much as possible"
},
)
max_gpu_memory: Optional[str] = field(
default=None,
metadata={
"help": "The maximum memory limit of each GPU, only valid in multi-GPU configuration"
},
)
cpu_offloading: Optional[bool] = field(
default=False, metadata={"help": "CPU offloading"}
)
load_8bit: Optional[bool] = field(
default=False, metadata={"help": "8-bit quantization"}
)
load_4bit: Optional[bool] = field(
default=False, metadata={"help": "4-bit quantization"}
)
quant_type: Optional[str] = field(
default="nf4",
metadata={
"valid_values": ["nf4", "fp4"],
"help": "Quantization datatypes, `fp4` (four bit float) and `nf4` (normal four bit float), only valid when load_4bit=True",
},
)
use_double_quant: Optional[bool] = field(
default=True,
metadata={"help": "Nested quantization, only valid when load_4bit=True"},
)
# "bfloat16", "float16", "float32"
compute_dtype: Optional[str] = field(
default=None,
metadata={
"valid_values": ["bfloat16", "float16", "float32"],
"help": "Model compute type",
},
)
trust_remote_code: Optional[bool] = field(
default=True, metadata={"help": "Trust remote code"}
)
verbose: Optional[bool] = field(
default=False, metadata={"help": "Show verbose output."}
)
@dataclass
class LlamaCppModelParameters(ModelParameters):
seed: Optional[int] = field(
default=-1, metadata={"help": "Random seed for llama-cpp models. -1 for random"}
)
n_threads: Optional[int] = field(
default=None,
metadata={
"help": "Number of threads to use. If None, the number of threads is automatically determined"
},
)
n_batch: Optional[int] = field(
default=512,
metadata={
"help": "Maximum number of prompt tokens to batch together when calling llama_eval"
},
)
n_gpu_layers: Optional[int] = field(
default=1000000000,
metadata={
"help": "Number of layers to offload to the GPU, Set this to 1000000000 to offload all layers to the GPU."
},
)
n_gqa: Optional[int] = field(
default=None,
metadata={"help": "Grouped-query attention. Must be 8 for llama-2 70b."},
)
rms_norm_eps: Optional[float] = field(
default=5e-06, metadata={"help": "5e-6 is a good value for llama-2 models."}
)
cache_capacity: Optional[str] = field(
default=None,
metadata={
"help": "Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. "
},
)
prefer_cpu: Optional[bool] = field(
default=False,
metadata={
"help": "If a GPU is available, it will be preferred by default, unless prefer_cpu=False is configured."
},
)

View File

View File

@@ -29,6 +29,8 @@ class ChatDashboardOutputParser(BaseOutputParser):
print("clean prompt response:", clean_str)
response = json.loads(clean_str)
chart_items: List[ChartItem] = []
if not isinstance(response, list):
response = [response]
for item in response:
chart_items.append(
ChartItem(

View File

@@ -20,7 +20,7 @@ The output data of the analysis cannot exceed 4 columns, and do not use columns
According to the characteristics of the analyzed data, choose the most suitable one from the charts provided below for data display, chart type:
{supported_chat_type}
Pay attention to the length of the output content of the analysis result, do not exceed 4000tokens
Pay attention to the length of the output content of the analysis result, do not exceed 4000 tokens
Give the correct {dialect} analysis SQL (don't use unprovided values such as 'paid'), analysis title(don't exist the same), display method and summary of brief analysis thinking, and respond in the following json format:
{response}

View File

@@ -13,7 +13,7 @@ class BaseChatAdpter:
and fetch output from model"""
def match(self, model_path: str):
return True
return False
def get_generate_stream_func(self, model_path: str):
"""Return the generate stream handler func"""
@@ -24,7 +24,9 @@ class BaseChatAdpter:
def get_conv_template(self, model_path: str) -> Conversation:
return None
def model_adaptation(self, params: Dict, model_path: str) -> Tuple[Dict, Dict]:
def model_adaptation(
self, params: Dict, model_path: str, prompt_template: str = None
) -> Tuple[Dict, Dict]:
"""Params adaptation"""
conv = self.get_conv_template(model_path)
messages = params.get("messages")
@@ -39,6 +41,10 @@ class BaseChatAdpter:
]
params["messages"] = messages
if prompt_template:
print(f"Use prompt template {prompt_template} from config")
conv = get_conv_template(prompt_template)
if not conv or not messages:
# Nothing to do
print(
@@ -94,14 +100,19 @@ def register_llm_model_chat_adapter(cls):
@cache
def get_llm_chat_adapter(model_path: str) -> BaseChatAdpter:
def get_llm_chat_adapter(model_name: str, model_path: str) -> BaseChatAdpter:
"""Get a chat generate func for a model"""
for adapter in llm_model_chat_adapters:
if adapter.match(model_path):
print(f"Get model path: {model_path} adapter {adapter}")
if adapter.match(model_name):
print(f"Get model chat adapter with model name {model_name}, {adapter}")
return adapter
raise ValueError(f"Invalid model for chat adapter {model_path}")
for adapter in llm_model_chat_adapters:
if adapter.match(model_path):
print(f"Get model chat adapter with model path {model_path}, {adapter}")
return adapter
raise ValueError(
f"Invalid model for chat adapter with model name {model_name} and model path {model_path}"
)
class VicunaChatAdapter(BaseChatAdpter):
@@ -239,6 +250,24 @@ class WizardLMChatAdapter(BaseChatAdpter):
return get_conv_template("vicuna_v1.1")
class LlamaCppChatAdapter(BaseChatAdpter):
def match(self, model_path: str):
from pilot.model.adapter import LlamaCppAdapater
if "llama-cpp" == model_path:
return True
is_match, _ = LlamaCppAdapater._parse_model_path(model_path)
return is_match
def get_conv_template(self, model_path: str) -> Conversation:
return get_conv_template("llama-2")
def get_generate_stream_func(self, model_path: str):
from pilot.model.llm_out.llama_cpp_llm import generate_stream
return generate_stream
register_llm_model_chat_adapter(VicunaChatAdapter)
register_llm_model_chat_adapter(ChatGLMChatAdapter)
register_llm_model_chat_adapter(GuanacoChatAdapter)
@@ -248,6 +277,7 @@ register_llm_model_chat_adapter(GPT4AllChatAdapter)
register_llm_model_chat_adapter(Llama2ChatAdapter)
register_llm_model_chat_adapter(BaichuanChatAdapter)
register_llm_model_chat_adapter(WizardLMChatAdapter)
register_llm_model_chat_adapter(LlamaCppChatAdapter)
# Proxy model for test and develop, it's cheap for us now.
register_llm_model_chat_adapter(ProxyllmChatAdapter)

View File

@@ -23,7 +23,7 @@ sys.path.append(ROOT_PATH)
from pilot.configs.config import Config
from pilot.configs.model_config import *
from pilot.model.llm_out.vicuna_base_llm import get_embeddings
from pilot.model.loader import ModelLoader
from pilot.model.loader import ModelLoader, _get_model_real_path
from pilot.server.chat_adapter import get_llm_chat_adapter
from pilot.scene.base_message import ModelMessage
@@ -34,12 +34,13 @@ class ModelWorker:
def __init__(self, model_path, model_name, device):
if model_path.endswith("/"):
model_path = model_path[:-1]
self.model_name = model_name or model_path.split("/")[-1]
model_path = _get_model_real_path(model_name, model_path)
# self.model_name = model_name or model_path.split("/")[-1]
self.device = device
print(f"Loading {model_name} LLM ModelServer in {device}! Please Wait......")
self.ml: ModelLoader = ModelLoader(
model_path=model_path, model_name=self.model_name
print(
f"Loading {model_name} LLM ModelServer in {device} from model path {model_path}! Please Wait......"
)
self.ml: ModelLoader = ModelLoader(model_path=model_path, model_name=model_name)
self.model, self.tokenizer = self.ml.loader(
load_8bit=CFG.IS_LOAD_8BIT,
load_4bit=CFG.IS_LOAD_4BIT,
@@ -60,7 +61,7 @@ class ModelWorker:
else:
self.context_len = 2048
self.llm_chat_adapter = get_llm_chat_adapter(model_path)
self.llm_chat_adapter = get_llm_chat_adapter(model_name, model_path)
self.generate_stream_func = self.llm_chat_adapter.get_generate_stream_func(
model_path
)
@@ -86,7 +87,7 @@ class ModelWorker:
try:
# params adaptation
params, model_context = self.llm_chat_adapter.model_adaptation(
params, self.ml.model_path
params, self.ml.model_path, prompt_template=self.ml.prompt_template
)
for output in self.generate_stream_func(
self.model, self.tokenizer, params, DEVICE, CFG.MAX_POSITION_EMBEDDINGS

View File

@@ -1,9 +1,15 @@
from pilot.vector_store.chroma_store import ChromaStore
from pilot.vector_store.milvus_store import MilvusStore
from pilot.vector_store.weaviate_store import WeaviateStore
connector = {"Chroma": ChromaStore, "Milvus": MilvusStore, "Weaviate": WeaviateStore}
connector = {"Chroma": ChromaStore, "Weaviate": WeaviateStore}
try:
from pilot.vector_store.milvus_store import MilvusStore
connector["Milvus"] = MilvusStore
except:
pass
class VectorStoreConnector:

View File

@@ -5,8 +5,8 @@ async-timeout==4.0.2
attrs==22.2.0
cchardet==2.1.7
chardet==5.1.0
contourpy==1.0.7
cycler==0.11.0
# contourpy==1.0.7
# cycler==0.11.0
filelock==3.9.0
fonttools==4.38.0
frozenlist==1.3.3
@@ -14,20 +14,20 @@ huggingface-hub==0.14.1
importlib-resources==5.12.0
sqlparse==0.4.4
kiwisolver==1.4.4
matplotlib==3.7.1
# kiwisolver==1.4.4
# matplotlib==3.7.1
multidict==6.0.4
packaging==23.0
psutil==5.9.4
pycocotools==2.0.6
pyparsing==3.0.9
# pycocotools==2.0.6
# pyparsing==3.0.9
python-dateutil==2.8.2
pyyaml==6.0
tokenizers==0.13.2
tqdm==4.64.1
transformers>=4.31.0
transformers_stream_generator
timm==0.6.13
# timm==0.6.13
spacy==3.5.3
webdataset==0.2.48
yarl==1.8.2
@@ -40,15 +40,17 @@ peft
pycocoevalcap
cpm_kernels
umap-learn
notebook
wandb
llama-index==0.5.27
# notebook
gradio==3.23
gradio-client==0.0.8
# wandb
# llama-index==0.5.27
# TODO move bitsandbytes to optional
bitsandbytes
accelerate>=0.20.3
unstructured==0.6.3
grpcio==1.47.5
gpt4all==0.3.0
diskcache==5.6.1
@@ -58,7 +60,7 @@ gTTS==2.3.1
langchain
nltk
python-dotenv==1.0.0
pymilvus==2.2.1
vcrpy
chromadb==0.3.22
markdown2
@@ -71,18 +73,7 @@ bardapi==0.1.29
# database
# TODO moved to optional dependencies
pymysql
duckdb
duckdb-engine
pymssql
# Testing dependencies
pytest
asynctest
pytest-asyncio
pytest-benchmark
pytest-cov
pytest-integration
pytest-mock
pytest-recording
pytesseract==0.3.10
duckdb-engine

View File

@@ -0,0 +1,10 @@
# Testing dependencies
pytest
asynctest
pytest-asyncio
pytest-benchmark
pytest-cov
pytest-integration
pytest-mock
pytest-recording
pytesseract==0.3.10

147
setup.py
View File

@@ -1,6 +1,11 @@
from typing import List
from typing import List, Tuple
import setuptools
import platform
import subprocess
import os
from enum import Enum
from setuptools import find_packages
with open("README.md", "r") as fh:
@@ -16,9 +21,144 @@ def parse_requirements(file_name: str) -> List[str]:
]
class SetupSpec:
def __init__(self) -> None:
self.extras: dict = {}
setup_spec = SetupSpec()
class AVXType(Enum):
BASIC = "basic"
AVX = "AVX"
AVX2 = "AVX2"
AVX512 = "AVX512"
@staticmethod
def of_type(avx: str):
for item in AVXType:
if item._value_ == avx:
return item
return None
class OSType(Enum):
WINDOWS = "win"
LINUX = "linux"
DARWIN = "darwin"
OTHER = "other"
def get_cpu_avx_support() -> Tuple[OSType, AVXType]:
system = platform.system()
os_type = OSType.OTHER
cpu_avx = AVXType.BASIC
env_cpu_avx = AVXType.of_type(os.getenv("DBGPT_LLAMA_CPP_AVX"))
cmds = ["lscpu"]
if system == "Windows":
cmds = ["coreinfo"]
os_type = OSType.WINDOWS
elif system == "Linux":
cmds = ["lscpu"]
os_type = OSType.LINUX
elif system == "Darwin":
cmds = ["sysctl", "-a"]
os_type = OSType.DARWIN
else:
os_type = OSType.OTHER
print("Unsupported OS to get cpu avx, use default")
return os_type, env_cpu_avx if env_cpu_avx else cpu_avx
result = subprocess.run(cmds, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output = result.stdout.decode()
if "avx512" in output.lower():
cpu_avx = AVXType.AVX512
elif "avx2" in output.lower():
cpu_avx = AVXType.AVX2
elif "avx " in output.lower():
# cpu_avx = AVXType.AVX
pass
return os_type, env_cpu_avx if env_cpu_avx else cpu_avx
def get_cuda_version() -> str:
try:
import torch
return torch.version.cuda
except Exception:
return None
def llama_cpp_python_cuda_requires():
cuda_version = get_cuda_version()
device = "cpu"
if not cuda_version:
print("CUDA not support, use cpu version")
return
device = "cu" + cuda_version.replace(".", "")
os_type, cpu_avx = get_cpu_avx_support()
supported_os = [OSType.WINDOWS, OSType.LINUX]
if os_type not in supported_os:
print(
f"llama_cpp_python_cuda just support in os: {[r._value_ for r in supported_os]}"
)
return
cpu_avx = cpu_avx._value_
base_url = "https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui"
llama_cpp_version = "0.1.77"
py_version = "cp310"
os_pkg_name = "linux_x86_64" if os_type == OSType.LINUX else "win_amd64"
extra_index_url = f"{base_url}/llama_cpp_python_cuda-{llama_cpp_version}+{device}{cpu_avx}-{py_version}-{py_version}-{os_pkg_name}.whl"
print(f"Install llama_cpp_python_cuda from {extra_index_url}")
setup_spec.extras["llama_cpp"].append(f"llama_cpp_python_cuda @ {extra_index_url}")
def llama_cpp_requires():
"""
pip install "db-gpt[llama_cpp]"
"""
setup_spec.extras["llama_cpp"] = ["llama-cpp-python"]
llama_cpp_python_cuda_requires()
def all_vector_store_requires():
"""
pip install "db-gpt[vstore]"
"""
setup_spec.extras["vstore"] = [
"grpcio==1.47.5", # maybe delete it
"pymilvus==2.2.1",
]
def all_datasource_requires():
"""
pip install "db-gpt[datasource]"
"""
setup_spec.extras["datasource"] = ["pymssql", "pymysql"]
def all_requires():
requires = set()
for _, pkgs in setup_spec.extras.items():
for pkg in pkgs:
requires.add(pkg)
setup_spec.extras["all"] = list(requires)
llama_cpp_requires()
all_vector_store_requires()
all_datasource_requires()
# must be last
all_requires()
setuptools.setup(
name="db-gpt",
packages=find_packages(),
packages=find_packages(exclude=("tests", "*.tests", "*.tests.*", "examples")),
version="0.3.5",
author="csunny",
author_email="cfqcsunny@gmail.com",
@@ -27,9 +167,10 @@ setuptools.setup(
long_description=long_description,
long_description_content_type="text/markdown",
install_requires=parse_requirements("requirements.txt"),
url="https://github.com/csunny/DB-GPT",
url="https://github.com/eosphoros-ai/DB-GPT",
license="https://opensource.org/license/mit/",
python_requires=">=3.10",
extras_require=setup_spec.extras,
entry_points={
"console_scripts": [
"dbgpt_server=pilot.server:webserver",