From 45fbcafbf68c31da751a606b6ec4799ee69551e0 Mon Sep 17 00:00:00 2001 From: aries_ckt <916701291@qq.com> Date: Mon, 24 Jul 2023 17:37:21 +0800 Subject: [PATCH 01/14] fix:word embedding update 1.use Docx2txtLoader replace UnstructuredWordDocumentLoader --- pilot/embedding_engine/word_embedding.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pilot/embedding_engine/word_embedding.py b/pilot/embedding_engine/word_embedding.py index 24f1d0386..55a2b5079 100644 --- a/pilot/embedding_engine/word_embedding.py +++ b/pilot/embedding_engine/word_embedding.py @@ -2,8 +2,8 @@ # -*- coding: utf-8 -*- from typing import List, Optional -from langchain.document_loaders import UnstructuredWordDocumentLoader from langchain.schema import Document +from langchain.document_loaders import Docx2txtLoader from langchain.text_splitter import ( SpacyTextSplitter, RecursiveCharacterTextSplitter, @@ -36,7 +36,7 @@ class WordEmbedding(SourceEmbedding): def read(self): """Load from word path.""" if self.source_reader is None: - self.source_reader = UnstructuredWordDocumentLoader(self.file_path) + self.source_reader = Docx2txtLoader(self.file_path) if self.text_splitter is None: try: self.text_splitter = SpacyTextSplitter( From 48fc8c47ac2f2b7d17c8813c77be9c1598279b43 Mon Sep 17 00:00:00 2001 From: aries_ckt <916701291@qq.com> Date: Tue, 25 Jul 2023 11:26:20 +0800 Subject: [PATCH 02/14] fix:web-ui bug 1.webuibug 2.requirememt update --- pilot/server/static/404.html | 2 +- pilot/server/static/404/index.html | 2 +- .../_next/static/chunks/775-224c8c8f5ee3fd65.js | 16 ++++++++++++++++ .../static/chunks/925f3d25-1af7259455ef26bd.js | 2 ++ .../chunks/app/chat/page-4266d316599e0141.js | 1 + .../documents/chunklist/page-042df8c81ee99ad6.js | 1 + .../documents/page-d01efb573de36698.js | 1 + .../app/datastores/page-d4200bb6a31d3cd4.js | 1 + .../static/chunks/app/layout-6d9f7ec39c148c6a.js | 1 + .../static/chunks/app/page-254872a7b51c14e0.js | 1 + .../static/chunks/main-app-75c197595e152149.js | 1 + .../kvEPRdcHK79LEj3_AaRj1/_buildManifest.js | 1 + .../static/kvEPRdcHK79LEj3_AaRj1/_ssgManifest.js | 1 + pilot/server/static/chat/index.html | 2 +- pilot/server/static/chat/index.txt | 6 +++--- .../datastores/documents/chunklist/index.html | 2 +- .../datastores/documents/chunklist/index.txt | 6 +++--- .../static/datastores/documents/index.html | 2 +- .../server/static/datastores/documents/index.txt | 6 +++--- pilot/server/static/datastores/index.html | 2 +- pilot/server/static/datastores/index.txt | 6 +++--- pilot/server/static/index.html | 2 +- pilot/server/static/index.txt | 6 +++--- pilot/vector_store/connector.py | 3 ++- requirements.txt | 5 +++-- 25 files changed, 54 insertions(+), 25 deletions(-) create mode 100644 pilot/server/static/_next/static/chunks/775-224c8c8f5ee3fd65.js create mode 100644 pilot/server/static/_next/static/chunks/925f3d25-1af7259455ef26bd.js create mode 100644 pilot/server/static/_next/static/chunks/app/chat/page-4266d316599e0141.js create mode 100644 pilot/server/static/_next/static/chunks/app/datastores/documents/chunklist/page-042df8c81ee99ad6.js create mode 100644 pilot/server/static/_next/static/chunks/app/datastores/documents/page-d01efb573de36698.js create mode 100644 pilot/server/static/_next/static/chunks/app/datastores/page-d4200bb6a31d3cd4.js create mode 100644 pilot/server/static/_next/static/chunks/app/layout-6d9f7ec39c148c6a.js create mode 100644 pilot/server/static/_next/static/chunks/app/page-254872a7b51c14e0.js create mode 100644 pilot/server/static/_next/static/chunks/main-app-75c197595e152149.js create mode 100644 pilot/server/static/_next/static/kvEPRdcHK79LEj3_AaRj1/_buildManifest.js create mode 100644 pilot/server/static/_next/static/kvEPRdcHK79LEj3_AaRj1/_ssgManifest.js diff --git a/pilot/server/static/404.html b/pilot/server/static/404.html index c30018f50..3300feb6e 100644 --- a/pilot/server/static/404.html +++ b/pilot/server/static/404.html @@ -1 +1 @@ -
+
+
@@ -99,6 +104,9 @@ Currently, we have released multiple key features, which are listed below to dem
- Knowledge Management(We currently support many document formats: txt, pdf, md, html, doc, ppt, and url.)
- Database knowledge Q&A
- knowledge Embedding
+
+- ChatDB
+- ChatDashboard
- Plugins
- Support custom plugin execution tasks and natively support the Auto-GPT plugin, such as:
- Automatic execution of SQL and retrieval of query results
@@ -106,9 +114,14 @@ Currently, we have released multiple key features, which are listed below to dem
- Unified vector storage/indexing of knowledge base
- Support for unstructured data such as PDF, TXT, Markdown, CSV, DOC, PPT, and WebURL
-- Multi LLMs Support
- - Supports multiple large language models, currently supporting Vicuna (7b,13b), ChatGLM-6b (int4,int8), guanaco(7b,13b,33b), Gorilla(7b,13b), 🔥 llama-2(7b,13b,70b), baichuan(7b,13b)
-
+- Multi LLMs Support, Supports multiple large language models, currently supporting
+ - 🔥 llama-2(7b,13b,70b)
+ - Vicuna (7b,13b)
+ - ChatGLM-6b (int4,int8)
+ - ChatGLM2-6b (int4,int8)
+ - guanaco(7b,13b,33b)
+ - Gorilla(7b,13b)
+ - baichuan(7b,13b)
[](https://star-history.com/#csunny/DB-GPT)
diff --git a/README.zh.md b/README.zh.md
index 3dffe3040..123236cf4 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -1,4 +1,10 @@
# DB-GPT: 用私有化LLM技术定义数据库下一代交互方式
+
+
+
@@ -96,6 +102,8 @@ https://github.com/csunny/DB-GPT/assets/13723926/55f31781-1d49-4757-b96e-7ef6d3d
- 知识库管理(目前支持 txt, pdf, md, html, doc, ppt, and url)
- 数据库知识问答
- 数据处理
+- 数据库对话
+- Chat2Dashboard
- 插件模型
- 支持自定义插件执行任务,原生支持Auto-GPT插件。如:
- SQL自动执行,获取查询结果
diff --git a/assets/LOGO.png b/assets/LOGO.png
new file mode 100644
index 0000000000000000000000000000000000000000..d08919a7fffc2ba44d0f2319365fa13173d26ac7
GIT binary patch
literal 133365
zcmV)jK%u{hP) 7a6^{Udzu^4Z}`u-{|6n@e(bftUi8HW_5o1}_Suon)E# a`ki~nqiFF$d`iOVmG@y^Q(
z@AMc?m3HP4XX1_jfr)(hX2GDES6b7^gfw2fndxY-A?zc@jd<4<5*I6RQAX?pIbt<2
zG%~nkMzKU}qmIQ5)h3YEYH?C{&Dc(vTB6rRz)>pxh!^5|n6QH?RKW|jmW0LT
+
wZmq0SR)u%n_@
$2YAK8%{9i?+P
zAh$kUF$WjHCX>d>cIrBk84brQdv0~T=;mWUsKqi69g)Ulg*n-a+@Sh`2J#d!
zgFvGc`z?zQ-3*k3Deqw7A*?9cXjxEbOaxzNdrYA@&Dxc@#7k$o1cJS=@@hAHy`@nt
z6&|!G8G*%r8f^~-+zM5$@un_k*eXceOLMJ?Lo57ga>P5`hD@pRi}K2H*)Y)3+Yo
VsLL#CfakpzXCad}dVS7~H0&`ODjN2x>s8ZUjNjeV#H(B`ORA1G5Iamp*fIwTsD
zaz`w+V?>%>DMW6_423Y;j=cQ|CwYq1z+f(JH{KdTvTig3k&%?x8=e__(0J>cT8XY*
z>ZE>uyfqz%%Eg4vLaB|gAeGWw!IIga)*7|QIT&H(na&w~Rs)2YX)a=QgB58lUZuK%
z#;BgS9%b@CnMBmPp?E7%wlavyh??&O*2LSmo)V<@9o1#0bd
zN~GO!m$)`zoOsc)YRc0e6EY|(oX+z#0gs3%7DW#KFRE3+n3Ernx;K2NSJ8Gtu9XAb
zHO_E81{cfn3(w1RCsD^P!UDnw&k>2jker7@(>3%fk60VCtLjkmwc${Yh$_BJTD1ywK0U27oFa$!Rk%8mSx8-c8};^}Zo6Scl_XHB7iwXVlT
zrhJ6!p$3-#+E!!`6%Ti5jEF)P5Huld>CA(~8>tA6R@EnY^=b~aXK8zJa9_L;)A)*=
z1V&d{!(1AbS7EKB>zHStbqO(6oUUULWHoT{OIZe};Aqi6UiCQQ8d}NNrPD(|v4GR1
zO-F>J3vm~yI8f_Y)S&OrgEgzFRCmy7Olbc^rg5MS0r^E%gdCgHl{c=qM3**?pgqi;
z)924~-Rc~x{>Ii0AGPqC!<&b;w|GkI<~g=-`9^R~NI~JN!ACbvU%L19yY73-YffHu
z;@J7)8;`j9_%>fs<#~Z;HtxCi{98`md+(W@qsO-{Il+Z{-&ecm)Cn*3r4b)TW;jO8
zM;%wn=h^TPwUoxHX5+QBUK(o!M|%qLT1slEr3^zW?qC5M$+ddStl{0tbCNe$2p?1j
zC$mI116cJn*mXmJnv%-Yhe<&fib
S_yIB^Gu39uG1|T5{WpBiKlq!k
zf7Q$K6CDq3jfD6?F@HT#MH*1y7);MtyBl|(yyI7X`Imn6mw(~NVNM)tfE|=I!ht4V
z4Y~W|$q(H0el7>nF8AuIui+8aJh_I!3|h?DiXRR;4QEc?o6vM3>?;zK?|gI8AZ;xTB9`^
zc^zIN9C>I9rR{-lL;;MzAV$=%!WD1&0}+{G4Q_FfDZTzodC9>q*EZT!iM(j*rW
`w$z9tgnn<29XzTZHxr0t*3s<
z(_iu(-}%HRelkL$`SeHgL&JCBjB`$$j=N(T!;E=|qOK)8))Yg^;b=35X2qaiR9?Xr
zk{&h1g0oK^QruwBoqiO>CDEl-I(5bB0bDZB{h!J6IAIguMfJs>pzfPF*sc2TC%v{?
z$2ip}>wcD0%*pq)<}PfEu#(Av6J-qz&yqJarL5BxfY>q{N)>@dhz&;v>PDc3_?ke-
z0v5FbLu}0sV(VsWycXMT{b2Fdy=6Yk?ocm%VvTt5gTI+2m|e0u^ov8C7tZ|5cJs-6
zXlW#=eaFOcK|6~reA);)Pa;sGhFSHT{zn`4Vur4=IkJ|d$qIt5CQ&u6Cv8QA_K=$N
z3M