44 <img src =" ./assets/LOGO.png " width =" 100% " />
55</p >
66
7-
87<div align =" center " >
98 <p >
109 <a href="https://github.com/eosphoros-ai/DB-GPT">
@@ -73,24 +72,11 @@ In the era of Data 3.0, enterprises and developers can take the ability to creat
7372![ macOS] ( https://img.shields.io/badge/mac%20os-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0 )
7473![ Windows] ( https://img.shields.io/badge/Windows-0078D6?style=for-the-badge&logo=windows&logoColor=white )
7574
76- [ ** Usage Tutorial** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy/deploy.html )
77- - [ ** Install** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy.html )
78- - [ ** Install Step by Step** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/deploy.html )
79- - [ ** Docker Install** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/docker/docker.html )
80- - [ ** Docker Compose** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/docker_compose/docker_compose.html )
81- - [ ** How to Use** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/chatdb/chatdb.html )
82- - [ ** ChatData** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/chatdb/chatdb.html )
83- - [ ** ChatKnowledge** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/kbqa/kbqa.html )
84- - [ ** ChatExcel** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/chatexcel/chatexcel.html )
85- - [ ** Dashboard** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/dashboard/dashboard.html )
86- - [ ** LLM Management** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/model/model.html )
87- - [ ** Chat Agent** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/application/chatagent/chatagent.html )
88- - [ ** How to Deploy LLM** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/cluster/cluster.html )
89- - [ ** Standalone** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/cluster/vms/standalone.html )
90- - [ ** Cluster** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/cluster/vms/index.html )
91- - [ ** vLLM** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/install/llm/vllm/vllm.html )
92- - [ ** How to Debug** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/observability.html )
93- - [ ** FAQ** ] ( https://db-gpt.readthedocs.io/en/latest/getting_started/faq/deploy/deploy_faq.html )
75+ [ ** Usage Tutorial** ] ( http://docs.dbgpt.site/docs/overview )
76+ - [ ** Install** ] ( http://docs.dbgpt.site/docs/installation )
77+ - [ ** Quickstart** ] ( http://docs.dbgpt.site/docs/quickstart )
78+ - [ ** Application** ] ( http://docs.dbgpt.site/docs/operation_manual )
79+ - [ ** Debugging** ] ( http://docs.dbgpt.site/docs/operation_manual/advanced_tutorial/debugging )
9480
9581
9682## Features
@@ -114,61 +100,15 @@ At present, we have introduced several key features to showcase our current capa
114100
115101- ** SMMF(Service-oriented Multi-model Management Framework)**
116102
117- 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.
118-
119- - [ Vicuna] ( https://huggingface.co/Tribbiani/vicuna-13b )
120- - [ vicuna-13b-v1.5] ( https://huggingface.co/lmsys/vicuna-13b-v1.5 )
121- - [ LLama2] ( https://huggingface.co/meta-llama/Llama-2-7b-chat-hf )
122- - [ baichuan2-13b] ( https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat )
123- - [ baichuan2-7b] ( https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat )
124- - [ chatglm-6b] ( https://huggingface.co/THUDM/chatglm-6b )
125- - [ chatglm2-6b] ( https://huggingface.co/THUDM/chatglm2-6b )
126- - [ chatglm3-6b] ( https://huggingface.co/THUDM/chatglm3-6b )
127- - [ falcon-40b] ( https://huggingface.co/tiiuae/falcon-40b )
128- - [ internlm-chat-7b] ( https://huggingface.co/internlm/internlm-chat-7b )
129- - [ internlm-chat-20b] ( https://huggingface.co/internlm/internlm-chat-20b )
130- - [ qwen-7b-chat] ( https://huggingface.co/Qwen/Qwen-7B-Chat )
131- - [ qwen-14b-chat] ( https://huggingface.co/Qwen/Qwen-14B-Chat )
132- - [ wizardlm-13b] ( https://huggingface.co/WizardLM/WizardLM-13B-V1.2 )
133- - [ orca-2-7b] ( https://huggingface.co/microsoft/Orca-2-7b )
134- - [ orca-2-13b] ( https://huggingface.co/microsoft/Orca-2-13b )
135- - [ openchat_3.5] ( https://huggingface.co/openchat/openchat_3.5 )
136- - [ zephyr-7b-alpha] ( https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha )
137- - [ mistral-7b-instruct-v0.1] ( https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 )
138- - [ Yi-34B-Chat] ( https://huggingface.co/01-ai/Yi-34B-Chat )
139-
140- - Support API Proxy LLMs
141- - [x] [ ChatGPT] ( https://api.openai.com/ )
142- - [x] [ Tongyi] ( https://www.aliyun.com/product/dashscope )
143- - [x] [ Wenxin] ( https://cloud.baidu.com/product/wenxinworkshop?track=dingbutonglan )
144- - [x] [ ChatGLM] ( http://open.bigmodel.cn/ )
103+ 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.
145104
105+ - [ Current Supported LLMs] ( http://docs.dbgpt.site/docs/modules/smmf )
146106- ** Privacy and Security**
147107
148108 We ensure the privacy and security of data through the implementation of various technologies, including privatized large models and proxy desensitization.
149109
150110- Support Datasources
151-
152- | DataSource | support | Notes |
153- | ------------------------------------------------------------------------------ | ----------- | ------------------------------------------- |
154- | [ MySQL] ( https://www.mysql.com/ ) | Yes | |
155- | [ PostgreSQL] ( https://www.postgresql.org/ ) | Yes | |
156- | [ Spark] ( https://github.com/apache/spark ) | Yes | |
157- | [ DuckDB] ( https://github.com/duckdb/duckdb ) | Yes | |
158- | [ Sqlite] ( https://github.com/sqlite/sqlite ) | Yes | |
159- | [ MSSQL] ( https://github.com/microsoft/mssql-jdbc ) | Yes | |
160- | [ ClickHouse] ( https://github.com/ClickHouse/ClickHouse ) | Yes | |
161- | [ Oracle] ( https://github.com/oracle ) | No | TODO |
162- | [ Redis] ( https://github.com/redis/redis ) | No | TODO |
163- | [ MongoDB] ( https://github.com/mongodb/mongo ) | No | TODO |
164- | [ HBase] ( https://github.com/apache/hbase ) | No | TODO |
165- | [ Doris] ( https://github.com/apache/doris ) | No | TODO |
166- | [ DB2] ( https://github.com/IBM/Db2 ) | No | TODO |
167- | [ Couchbase] ( https://github.com/couchbase ) | No | TODO |
168- | [ Elasticsearch] ( https://github.com/elastic/elasticsearch ) | No | TODO |
169- | [ OceanBase] ( https://github.com/OceanBase ) | No | TODO |
170- | [ TiDB] ( https://github.com/pingcap/tidb ) | No | TODO |
171- | [ StarRocks] ( https://github.com/StarRocks/starrocks ) | No | TODO |
111+ - [ Datasources] ( http://docs.dbgpt.site/docs/modules/connections )
172112
173113## Introduction
174114The architecture of DB-GPT is shown in the following figure:
0 commit comments