Skip to content

Commit

Permalink
docs: SMMF introduction and usage (#878)
Browse files Browse the repository at this point in the history
Co-authored-by: junewgl <[email protected]>
  • Loading branch information
csunny and junewgl authored Dec 1, 2023
1 parent 5cc24b7 commit a35b612
Show file tree
Hide file tree
Showing 44 changed files with 276 additions and 1,259 deletions.
7 changes: 7 additions & 0 deletions .env.template
Original file line number Diff line number Diff line change
Expand Up @@ -190,6 +190,13 @@ TONGYI_PROXY_API_KEY={your-tongyi-sk}
#BAICHUAN_PROXY_API_KEY={your-baichuan-sk}
#BAICHUAN_PROXY_API_SECRET={your-baichuan-sct}

# Xunfei Spark
#XUNFEI_SPARK_API_VERSION={version}
#XUNFEI_SPARK_APPID={your_app_id}
#XUNFEI_SPARK_API_KEY={your_api_key}
#XUNFEI_SPARK_API_SECRET={your_api_secret}



#*******************************************************************#
#** SUMMARY_CONFIG **#
Expand Down
1 change: 0 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@ __pycache__/
message/

.env
.idea
.vscode
.idea
.chroma
Expand Down
3 changes: 2 additions & 1 deletion CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,8 @@ git clone https://github.com/<YOUR-GITHUB-USERNAME>/DB-GPT
```
3. Install the project requirements
```
pip install -r requirements/dev-requirements.txt
pip install -e ".[default]"
```
4. Install pre-commit hooks
```
Expand Down
2 changes: 1 addition & 1 deletion MANIFEST.in
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
include README.md
include LICENSE
include README.md
include requirements.txt
6 changes: 5 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,11 @@ At present, we have introduced several key features to showcase our current capa

We offer extensive model support, including dozens of large language models (LLMs) from both open-source and API agents, such as LLaMA/LLaMA2, Baichuan, ChatGLM, Wenxin, Tongyi, Zhipu, and many more.

- [Current Supported LLMs](http://docs.dbgpt.site/docs/modules/smmf)
- News
- 🔥🔥🔥 [qwen-72b-chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
- 🔥🔥🔥 [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)
- [More Supported LLMs](http://docs.dbgpt.site/docs/modules/smmf)

- **Privacy and Security**

We ensure the privacy and security of data through the implementation of various technologies, including privatized large models and proxy desensitization.
Expand Down
50 changes: 7 additions & 43 deletions README.zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -114,27 +114,10 @@ DB-GPT是一个开源的数据库领域大模型框架。目的是构建大模

海量模型支持,包括开源、API代理等几十种大语言模型。如LLaMA/LLaMA2、Baichuan、ChatGLM、文心、通义、智谱等。当前已支持如下模型:

- [Vicuna](https://huggingface.co/Tribbiani/vicuna-13b)
- [vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
- [LLama2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
- [baichuan2-13b](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat)
- [baichuan2-7b](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)
- [chatglm-6b](https://huggingface.co/THUDM/chatglm-6b)
- [chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b)
- [chatglm3-6b](https://huggingface.co/THUDM/chatglm3-6b)
- [falcon-40b](https://huggingface.co/tiiuae/falcon-40b)
- [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b)
- [internlm-chat-20b](https://huggingface.co/internlm/internlm-chat-20b)
- [qwen-7b-chat](https://huggingface.co/Qwen/Qwen-7B-Chat)
- [qwen-14b-chat](https://huggingface.co/Qwen/Qwen-14B-Chat)
- [qwen-72b-chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
- [wizardlm-13b](https://huggingface.co/WizardLM/WizardLM-13B-V1.2)
- [orca-2-7b](https://huggingface.co/microsoft/Orca-2-7b)
- [orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
- [openchat_3.5](https://huggingface.co/openchat/openchat_3.5)
- [zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)
- [mistral-7b-instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
- [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)
- 新增支持模型
- 🔥🔥🔥 [qwen-72b-chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
- 🔥🔥🔥 [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)
- [更多开源模型](https://www.yuque.com/eosphoros/dbgpt-docs/iqaaqwriwhp6zslc#qQktR)

- 支持在线代理模型
- [x] [OpenAI·ChatGPT](https://api.openai.com/)
Expand All @@ -148,28 +131,8 @@ DB-GPT是一个开源的数据库领域大模型框架。目的是构建大模

通过私有化大模型、代理脱敏等多种技术保障数据的隐私安全。

- 支持数据源
- [支持数据源](https://www.yuque.com/eosphoros/dbgpt-docs/rc4r27ybmdwg9472)

| DataSource | support | Notes |
| ------------------------------------------------------------------------------ | ----------- | ------------------------------------------- |
| [MySQL](https://www.mysql.com/) | Yes | |
| [PostgresSQL](https://www.postgresql.org/) | Yes | |
| [Spark](https://github.com/apache/spark) | Yes | |
| [DuckDB](https://github.com/duckdb/duckdb) | Yes | |
| [Sqlite](https://github.com/sqlite/sqlite) | Yes | |
| [MSSQL](https://github.com/microsoft/mssql-jdbc) | Yes | |
| [ClickHouse](https://github.com/ClickHouse/ClickHouse) | Yes | |
| [Oracle](https://github.com/oracle) | No | TODO |
| [Redis](https://github.com/redis/redis) | No | TODO |
| [MongoDB](https://github.com/mongodb/mongo) | No | TODO |
| [HBase](https://github.com/apache/hbase) | No | TODO |
| [Doris](https://github.com/apache/doris) | No | TODO |
| [DB2](https://github.com/IBM/Db2) | No | TODO |
| [Couchbase](https://github.com/couchbase) | No | TODO |
| [Elasticsearch](https://github.com/elastic/elasticsearch) | No | TODO |
| [OceanBase](https://github.com/OceanBase) | No | TODO |
| [TiDB](https://github.com/pingcap/tidb) | No | TODO |
| [StarRocks](https://github.com/StarRocks/starrocks) | No | TODO |

## 架构方案
整个DB-GPT的架构,如下图所示
Expand Down Expand Up @@ -266,6 +229,7 @@ The MIT License (MIT)
- [x] Sqlite
- [x] MSSQL
- [x] ClickHouse
- [x] StarRocks
- [ ] Oracle
- [ ] Redis
- [ ] MongoDB
Expand All @@ -276,7 +240,7 @@ The MIT License (MIT)
- [ ] Elasticsearch
- [ ] OceanBase
- [ ] TiDB
- [ ] StarRocks


### 多模型管理与推理优化
- [x] [集群部署](https://db-gpt.readthedocs.io/en/latest/getting_started/install/cluster/vms/index.html)
Expand Down
Binary file modified assets/wechat.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
67 changes: 0 additions & 67 deletions docs/blog/authors.yml

This file was deleted.

8 changes: 0 additions & 8 deletions docs/blog/welcome/index.md

This file was deleted.

64 changes: 64 additions & 0 deletions docs/docs/application/advanced_tutorial/smmf.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
# SMMF

The DB-GPT project provides service-oriented multi-model management capabilities. Developer who are interested in related capabilities can read the [SMMF](/docs/modules/smmf) module part. Here we focus on how to use multi-LLMs.


Here we mainly introduce the usage through the web interface. For developer interested in the command line, you can refer to the [cluster deployment](/docs/installation/model_service/cluster) model. Open the DB-GPT-Web frontend service and click on `Model Management` to enter the multi-model management interface.


## List Models
By opening the model management interface, we can see the list of currently deployed models. The following is the list of models.

<p align="left">
<img src={'/img/module/model_list.png'} width="720px"/>
</p>

## Use Models
Once the models are deployed, you can switch and use the corresponding model on the multi-model interface.

<p align="left">
<img src={'/img/module/model_use.png'} width="720px"/>
</p>

## Stop Models
As shown in the figure below, click Model Management to enter the model list interface. Select a specific model and click the red `Stop Model` button to stop the model.

<p align="left">
<img src={'/img/module/model_stop.png'} width="720px"/>
</p>

After the model is stopped, the display in the upper right corner will change.

<p align="left">
<img src={'/img/module/model_stopped.png'} width="720px"/>
</p>

## Model Deployment

1. Open the web page, click the `model management` button on the left to enter the model list page, click `Create Model` in the upper left corner, and then select the name of the model you want to deploy in the pop-up dialog box. Here we choose `vicuna-7b-v1.5`, as shown in the figure.

<p align="left">
<img src={'/img/module/model_vicuna-7b-1.5.png'} width="720px"/>
</p>


2. Select the appropriate parameters according to the actual deployed model (if you are not sure, the default is enough), then click the `Submit` button at the bottom left of the dialog box, and wait until the model is deployed successfully.

3. After the new model is deployed, you can see the newly deployed model on the model page, as shown in the figure

<p align="left">
<img src={'/img/module/model_vicuna_deployed.png'} width="720px"/>
</p>

# Operations and Observability

Operations and observability are important components of a production system. In terms of operational capabilities, DB-GPT provides a command-line tool called dbgpt for operations and management, in addition to the common management functionalities available on the web interface. The dbgpt command-line tool offers the following functionalities:

- Starting and stopping various services
- Knowledge base management (batch import, custom import, viewing, and deleting knowledge base documents)
- Model management (viewing, starting, stopping models, and conducting dialogues for debugging)
Observability tools (viewing and analyzing observability logs)

We won't go into detail about the usage of the command-line tool here. You can use the `dbgpt --help` command to obtain specific usage documentation. Additionally, you can check the documentation for individual subcommands. For example, you can use `dbgpt start --help` to view the documentation for starting a service. For more information, please refer to the document provided below.

- [Debugging](/docs/application/advanced_tutorial/debugging)
1 change: 0 additions & 1 deletion docs/docs/application_manual/advanced_tutorial/smmf.md

This file was deleted.

4 changes: 3 additions & 1 deletion docs/docs/changelog/doc.md
Original file line number Diff line number Diff line change
@@ -1 +1,3 @@
# Documentation Description
# ChangeLog

Our version release information is maintained on GitHub. For more details, please visit [ReleaseNotes](https://github.com/eosphoros-ai/DB-GPT/releases)
6 changes: 3 additions & 3 deletions docs/docs/installation/sourcecode.md
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ import TabItem from '@theme/TabItem';
{label: 'Open AI', value: 'openai'},
{label: 'Qwen', value: 'qwen'},
{label: 'ChatGLM', value: 'chatglm'},
{label: 'ERNIE Bot', value: 'erniebot'},
{label: 'WenXin', value: 'erniebot'},
]}>
<TabItem value="openai" label="open ai">
Install dependencies
Expand Down Expand Up @@ -180,7 +180,7 @@ LLM_MODEL=wenxin_proxyllm
PROXY_SERVER_URL={your_service_url}
WEN_XIN_MODEL_VERSION={version}
WEN_XIN_API_KEY={your-wenxin-sk}
WEN_XIN_SECRET_KEY={your-wenxin-sct}
WEN_XIN_API_SECRET={your-wenxin-sct}
```
</TabItem>
</Tabs>
Expand Down Expand Up @@ -218,7 +218,7 @@ mkdir models and cd models

# embedding model
git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
或者
or
git clone https://huggingface.co/moka-ai/m3e-large

# llm model, if you use openai or Azure or tongyi llm api service, you don't need to download llm model
Expand Down
25 changes: 24 additions & 1 deletion docs/docs/modules/connections.md
Original file line number Diff line number Diff line change
@@ -1,2 +1,25 @@
# Connections
The connections module supports connecting to various structured, semi-structured, and unstructured data storage engines. Bring multi-dimensional data into the framework and realize the interaction between natural language and multi-dimensional data
The connections module supports connecting to various structured, semi-structured, and unstructured data storage engines. Bring multi-dimensional data into the framework and realize the interaction between natural language and multi-dimensional data

The list of data sources we currently support is as follows.

| DataSource | support | Notes |
| ------------------------------------------------------------------------------ | ----------- | ------------------------------------------- |
| [MySQL](https://www.mysql.com/) | Yes | MySQL is the world's most popular open source database. |
| [PostgresSQL](https://www.postgresql.org/) | Yes | The World's Most Advanced Open Source Relational Database |
| [Spark](https://github.com/apache/spark) | Yes | Unified Engine for large-scale data analytics |
| [DuckDB](https://github.com/duckdb/duckdb) | Yes | DuckDB is an in-process SQL OLAP database management system |
| [Sqlite](https://github.com/sqlite/sqlite) | Yes | |
| [MSSQL](https://github.com/microsoft/mssql-jdbc) | Yes | |
| [ClickHouse](https://github.com/ClickHouse/ClickHouse) | Yes | ClickHouse is the fastest and most resource efficient open-source database for real-time apps and analytics. |
| [Oracle](https://github.com/oracle) | No | TODO |
| [Redis](https://github.com/redis/redis) | No | The Multi-model NoSQL Database |
| [MongoDB](https://github.com/mongodb/mongo) | No | MongoDB is a source-available cross-platform document-oriented database program |
| [HBase](https://github.com/apache/hbase) | No | Open-source, distributed, versioned, column-oriented store modeled |
| [Doris](https://github.com/apache/doris) | No | Apache Doris is an easy-to-use, high performance and unified analytics database. |
| [DB2](https://github.com/IBM/Db2) | No | TODO |
| [Couchbase](https://github.com/couchbase) | No | TODO |
| [Elasticsearch](https://github.com/elastic/elasticsearch) | No | Free and Open, Distributed, RESTful Search Engine |
| [OceanBase](https://github.com/OceanBase) | No | OceanBase is a distributed relational database. |
| [TiDB](https://github.com/pingcap/tidb) | No | TODO |
| [StarRocks](https://github.com/StarRocks/starrocks) | Yes | StarRocks is a next-gen, high-performance analytical data warehouse |
Loading

0 comments on commit a35b612

Please sign in to comment.