github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-09-25 11:39:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: readme features

Browse Source
This commit is contained in:
csunny
2023-11-14 21:41:19 +08:00
parent a1d5323f8e
commit d82884f9f3
3 changed files with 30 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
README.md
View File

@@ -57,16 +57,6 @@ DB-GPT is an experimental open-source project that uses localized GPT large mode
Run on an RTX 4090 GPU.
##### Chat Excel
![excel](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/0474d220-2a9f-449f-a940-92c8a25af390)
##### Chat Plugin
![auto_plugin_new](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/7d95c347-f4b7-4fb6-8dd2-c1c02babaa56)
##### LLM Management
![llm_manage](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/501d6b3f-c4ce-4197-9a6f-f016f8150a11)
##### FastChat && vLLM
![vllm](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/0c9475d2-45ee-4573-aa5a-814f7fd40213)
##### Trace
![trace_new](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/69bd14b8-14d0-4ca9-9cb7-6cef44a2bc93)
##### Chat Knowledge
![kbqa_new](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/72266a48-edef-4c6d-88c6-fbb1a24a6c3e)
## Install
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
@@ -97,23 +87,23 @@ Run on an RTX 4090 GPU.
## Features
Currently, we have released multiple key features, which are listed below to demonstrate our current capabilities:
- Private KBQA & data processing
- **Private Domain Q&A & Data Processing**
The DB-GPT project offers a range of features to enhance knowledge base construction and enable efficient storage and retrieval of both structured and unstructured data. These include built-in support for uploading multiple file formats, the ability to integrate plug-ins for custom data extraction, and unified vector storage and retrieval capabilities for managing large volumes of information.
- Multiple data sources & visualization
- **Multi-Data Source & GBI(Generative Business intelligence)**
The DB-GPT project enables seamless natural language interaction with various data sources, including Excel, databases, and data warehouses. It facilitates effortless querying and retrieval of information from these sources, allowing users to engage in intuitive conversations and obtain insights. Additionally, DB-GPT supports the generation of analysis reports, providing users with valuable summaries and interpretations of the data.
- Multi-Agents&Plugins
- **Multi-Agents&Plugins**
It supports custom plug-ins to perform tasks, natively supports the Auto-GPT plug-in model, and the Agents protocol adopts the Agent Protocol standard.
- Fine-tuning text2SQL
- **Automated Fine-tuning text2SQL**
An automated fine-tuning lightweight framework built around large language models, Text2SQL data sets, LoRA/QLoRA/Pturning, and other fine-tuning methods, making TextSQL fine-tuning as convenient as an assembly line. [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub)
- Multi LLMs Support, Supports multiple large language models, currently supporting
- **SMMF(Service-oriented Multi-model Management Framework)**
Massive model support, including dozens of large language models such as open source and API agents. Such as LLaMA/LLaMA2, Baichuan, ChatGLM, Wenxin, Tongyi, Zhipu, etc.
- [Vicuna](https://huggingface.co/Tribbiani/vicuna-13b)
@@ -126,22 +116,6 @@ Currently, we have released multiple key features, which are listed below to dem
- [falcon-40b](https://huggingface.co/tiiuae/falcon-40b)
- [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b)
- [Qwen-7B-Chat/Qwen-14B-Chat](https://huggingface.co/Qwen/)
- [RWKV-4-Raven](https://huggingface.co/BlinkDL/rwkv-4-raven)
- [CAMEL-13B-Combined-Data](https://huggingface.co/camel-ai/CAMEL-13B-Combined-Data)
- [dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b)
- [h2ogpt-gm-oasst1-en-2048-open-llama-7b](https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b)
- [fastchat-t5-3b-v1.0](https://huggingface.co/lmsys/fastchat-t5)
- [mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat)
- [gpt4all-13b-snoozy](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy)
- [Nous-Hermes-13b](https://huggingface.co/NousResearch/Nous-Hermes-13b)
- [codet5p-6b](https://huggingface.co/Salesforce/codet5p-6b)
- [guanaco-33b-merged](https://huggingface.co/timdettmers/guanaco-33b-merged)
- [WizardLM-13B-V1.0](https://huggingface.co/WizardLM/WizardLM-13B-V1.0)
- [WizardLM/WizardCoder-15B-V1.0](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0)
- [Llama2-Chinese-13b-Chat](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat)
- [OpenLLaMa OpenInstruct](https://huggingface.co/VMware/open-llama-7b-open-instruct)
Etc.
- Support API Proxy LLMs
- [x] [ChatGPT](https://api.openai.com/)
@@ -149,7 +123,7 @@ Currently, we have released multiple key features, which are listed below to dem
- [x] [Wenxin](https://cloud.baidu.com/product/wenxinworkshop?track=dingbutonglan)
- [x] [ChatGLM](http://open.bigmodel.cn/)
- Privacy and security
- **Privacy and Security**
The privacy and security of data are ensured through various technologies, such as privatized large models and proxy desensitization.
@@ -313,16 +287,6 @@ The core capabilities mainly consist of the following parts:
As of October 10, 2023, by fine-tuning an open-source model of 13 billion parameters using this project, the execution accuracy on the Spider evaluation dataset has surpassed that of GPT-4!
| name | Execution Accuracy | reference |
| ----------------------------------| ------------------ | ------------------------------------------------------------------------------------------------------------------------------ |
| **GPT-4** | **0.762** | [numbersstation-eval-res](https://www.numbersstation.ai/post/nsql-llama-2-7b) |
| ChatGPT | 0.728 | [numbersstation-eval-res](https://www.numbersstation.ai/post/nsql-llama-2-7b) |
| **CodeLlama-13b-Instruct-hf_lora**| **0.789** | sft train by our this project,only used spider train dataset ,the same eval way in this project with lora SFT |
| CodeLlama-13b-Instruct-hf_qlora | 0.774 | sft train by our this project,only used spider train dataset ,the same eval way in this project with qlora and nf4,bit4 SFT |
| wizardcoder | 0.610 | [text-to-sql-wizardcoder](https://github.com/cuplv/text-to-sql-wizardcoder/tree/main) |
| CodeLlama-13b-Instruct-hf | 0.556 | eval in this project default param |
| llama2_13b_hf_lora_best | 0.744 | sft train by our this project,only used spider train dataset ,the same eval way in this project |
[More Information about Text2SQL finetune](https://github.com/eosphoros-ai/DB-GPT-Hub)
## Licence