wehub/ai-meet--knowledge_qa_rag
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 12:37:02 +08:00
commit fd87f9797d
22 changed files with 1233 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env
+12
View File
@@ -0,0 +1,12 @@
fastapi_host=localhost
fastapi_port=8000
milvus_host=localhost
milvus_port=19530
milvus_collection_name=knowledge_collection
openai_base_url=[YOUR_BASE_URL]
openai_api_key=[YOUR_API_KEY]
openai_llm_model_name=gpt-4o-mini
text_embeddings_model_path=jinaai/jina-embeddings-v3
LICENSE
+201
View File
@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
README.md
+102
View File
@@ -0,0 +1,102 @@
# Knowledge_QA_RAG
## Overview
本系统是一种基于 RAG 的知识库问答系统简单示例，采用前后端分离的架构设计，融合了多种技术和方法。具体详情可参考：[https://blog.csdn.net/weixin_47936614/article/details/143932997](https://blog.csdn.net/weixin_47936614/article/details/143932997)
## Milvus Installation
本系统是在 Windows 11 上进行部署和运行的，关于milvus向量数据库的安装和启动可以参考以下步骤：
1.勾选 `适用于Linux的Windows子系统` 和 `虚拟机平台`
![09afdd4c8869124fd606715f57cae4cb](https://github.com/user-attachments/assets/67c0e85d-cdbc-4a9e-b724-df3f4ea1799a)
2.点击 `确定` 并重新启动计算机
3.以管理员身份打开命令提示符，输入以下命令安装WSL：
- 在 PowerShell 中设置 WSL 2 为默认版本：
```
wsl --set-default-version 2
```
- 更新 WSL 内核，使用国内网络建议添加`--web-download`：
```
wsl --update --web-download
```
安装成功后的结果如下：
![abe944eb639649fae89175ed09af9fdd](https://github.com/user-attachments/assets/74fc0c97-cf3c-47c6-b3a2-240ba97a44ff)
4.下载安装docker-desktop
进入官网下载对应的版本安装即可，官网链接：[https://www.docker.com/products/docker-desktop/](https://www.docker.com/products/docker-desktop/)
5.验证是否安装成功：
```
docker --version
docker-compose --version
```
![a263610663c19d4046f28773a1126369](https://github.com/user-attachments/assets/1f8e801b-b2db-4644-83d7-5da10f4e5764)
6.milvus向量数据库安装
- 创建milvus文件夹，并在该文件夹下创建多个子文件夹，如下：
![image](https://github.com/user-attachments/assets/27599318-2a9a-4358-a1ec-226ca8363921)
- 下载milvus
进入下载页面：[https://github.com/milvus-io/milvus/releases](https://github.com/milvus-io/milvus/releases)
选择milvus版本及其对应的yml文件，点击下载即可，如下：
![image](https://github.com/user-attachments/assets/5b8804ca-5c6b-4102-82ac-d47eee31c77b)
- 将下载好的 `milvus-standalone-docker-compose.yml` 重命名为 `docker-compose.yml` ，并放入milvus文件中，如下：
![bf7215948670e96f9b50f90a67463950](https://github.com/user-attachments/assets/177d4889-49ff-4af4-8515-7722dc65a504)
- 在milvus文件夹中启动cmd命令，输入以下命令：
```
docker compose up -d
docker compose ps
docker port milvus-standalone 19530/tcp
```
运行结果如下：
![694be819cd99abc328136139f2e8e8d2](https://github.com/user-attachments/assets/2506153f-9625-42dd-b09c-db01e5ded5d6)
![1a3086ad4519524717991dffa47cce29](https://github.com/user-attachments/assets/a8e9a22c-2b1c-4c95-9e15-fe8d6cb0c3ee)
至此，milvus数据库部署成功！
7.Attu图形化界面安装
下载地址：[https://github.com/zilliztech/attu/releases](https://github.com/zilliztech/attu/releases)
选择对应的版本直接下载安装即可：
![image](https://github.com/user-attachments/assets/b4e96c46-e5e8-42e0-aae9-670008d3ff53)
## Environment Installation
```
conda create --name rag-env python=3.10
cd Knowledge_QA_RAG
conda activate rag-env
pip install -r requirements.txt
```
## Quick Start
1.启动milvus数据库
![image](https://github.com/user-attachments/assets/4d2a37ad-3f74-4b72-969c-685c6b023e96)
2.启动系统服务
```
python main.py
```
或
```
uvicorn server:app --reload --host 127.0.0.1 --port 8000
```
3.访问页面: 在浏览器中输入下面url地址即可访问
```
http://127.0.0.1:8000/
```
## 项目演示示例：
📺 [点击观看项目演示视频](https://www.bilibili.com/video/BV1a49KBqE7n/)
README.wehub.md
+7
View File
@@ -0,0 +1,7 @@
# WeHub 来源说明
- 原始项目：`AI-Meet/Knowledge_QA_RAG`
- 原始仓库：https://github.com/AI-Meet/Knowledge_QA_RAG
- 导入方式：上游默认分支的最新快照
- 原作者、版权和许可证信息以原始仓库及本仓库 LICENSE 为准
- 本文件仅用于记录来源，不代表 WeHub 是原项目作者
config.py
+36
View File
@@ -0,0 +1,36 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/10/31 14:30
# @blog: https://blog.csdn.net/weixin_47936614
import os
import torch
from dotenv import load_dotenv
# 从 .env 文件加载环境变量
load_dotenv()
class RagConfig:
# FastAPI 服务配置
fastapi_host = os.getenv("fastapi_host")
fastapi_port = os.getenv("fastapi_port")
# Milvus 配置
milvus_host = os.getenv("milvus_host")
milvus_port = os.getenv("milvus_port")
milvus_collection_name = os.getenv("milvus_collection_name")
# OpenAI 设置
base_url = os.getenv("openai_base_url")
api_key = os.getenv("openai_api_key")
llm_model_name = os.getenv("openai_llm_model_name")
# 嵌入模型路径
text_embeddings_model_path = os.getenv("text_embeddings_model_path")
# 设备设置
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
file_process.py
+45
View File
@@ -0,0 +1,45 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/10/31 13:59
# @blog: https://blog.csdn.net/weixin_47936614
import os
from langchain_community.document_loaders import TextLoader, UnstructuredWordDocumentLoader, PyPDFLoader
from text_utils.text_split import RagTextSplitter
class RagFileProcessor(object):
def __init__(self, chunk_size: int = 512):
self.text_splitter = RagTextSplitter(chunk_size=chunk_size)
def file_process(self, file_path: str):
if not os.path.exists(file_path):
raise FileNotFoundError(f"文件 {file_path} 不存在！")
if file_path.lower().endswith(".txt"):
txt_loader = TextLoader(file_path, autodetect_encoding=True)
txt_docs = txt_loader.load_and_split(text_splitter=self.text_splitter)
return txt_docs
elif file_path.lower().endswith(".docx"):
docx_loader = UnstructuredWordDocumentLoader(file_path, mode="single")
docx_docs = docx_loader.load_and_split(text_splitter=self.text_splitter)
return docx_docs
elif file_path.lower().endswith(".pdf"):
pdf_loader = PyPDFLoader(file_path)
pdf_docs = pdf_loader.load_and_split(text_splitter=self.text_splitter)
return pdf_docs
else:
raise TypeError("文件类型不支持，目前仅支持：txt/docx/pdf")
def get_data(self, file_path: str):
docs = self.file_process(file_path)
passage_docs = [doc.page_content.strip() for doc in docs]
file_name = {"source": os.path.basename(docs[0].metadata['source'])}
ids = [str(i) for i in range(len(passage_docs))] # 确保每个文档有唯一的 ID
meta_datas = [file_name for _ in range(len(passage_docs))] # 定义元数据信息，包括文件名等
dict_data = {"texts": passage_docs, "ids": ids, "meta_datas": meta_datas}
return dict_data
main.py
+18
View File
@@ -0,0 +1,18 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/11/26 10:14
# @blog: https://blog.csdn.net/weixin_47936614
import uvicorn
from milvus_vector import config
if __name__ == '__main__':
# 主函数启动方式
uvicorn.run(
"server:app", # 指定模块名和应用实例
host=config.fastapi_host, # 本地地址
port=int(config.fastapi_port), # 端口
reload=True # 开启热重载
)
milvus_vector.py
+37
View File
@@ -0,0 +1,37 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/11/22 18:53
# @blog: https://blog.csdn.net/weixin_47936614
from langchain_milvus import Milvus
from config import RagConfig
from text_utils.text_embeddings import RagTextEmbeddings
# 加载配置
config = RagConfig()
# 配置索引参数和搜索参数
index_params = {
"index_type": "IVF_FLAT",
"metric_type": "L2",
"params": {"nlist": 100}
}
search_params = {
"metric_type": "L2",
"params": {"nprobe": 10}
}
# 初始化 Milvus 向量存储
vector_store = Milvus(
embedding_function=RagTextEmbeddings(embed_model_path=config.text_embeddings_model_path,
batch_size=32,
device=config.device),
collection_name=config.milvus_collection_name,
consistency_level="Bounded",
connection_args={"host": config.milvus_host, "port": config.milvus_port},
index_params=index_params,
search_params=search_params
)
protocol/__init__.py
View File
protocol/mode.py
+12
View File
@@ -0,0 +1,12 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/11/20 16:33
# @blog: https://blog.csdn.net/weixin_47936614
from pydantic import BaseModel
class ChatRequest(BaseModel):
question: str
protocol/prompts.py
+13
View File
@@ -0,0 +1,13 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/11/20 16:17
# @blog: https://blog.csdn.net/weixin_47936614
prompt_template = """
Use the following pieces of context to answer the question at the end.
If you don't know the answer, just say "sorry, I can't answer this question.", don't try to make up an answer.
{context}
Question: {question}
Answer in Chinese:
"""
requirements.txt
+153
View File
@@ -0,0 +1,153 @@
accelerate==1.1.1
aiohappyeyeballs==2.4.3
aiohttp==3.10.10
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.6.2.post1
async-timeout==4.0.3
attrs==24.2.0
backoff==2.2.1
beautifulsoup4==4.12.3
cbor==1.0.0
certifi==2024.8.30
cffi==1.17.1
chardet==5.2.0
charset-normalizer==3.4.0
click==8.1.7
colorama==0.4.6
cryptography==43.0.3
dataclasses-json==0.6.7
datasets==2.19.0
dill==0.3.8
distro==1.9.0
dnspython==2.7.0
einops==0.8.0
email_validator==2.2.0
emoji==2.14.0
environs==9.5.0
eval_type_backport==0.2.0
exceptiongroup==1.2.2
fastapi==0.115.5
fastapi-cli==0.0.5
filelock==3.16.1
filetype==1.2.0
FlagEmbedding==1.3.2
frozenlist==1.5.0
fsspec==2024.3.1
greenlet==3.1.1
grpcio==1.67.1
h11==0.14.0
html5lib==1.1
httpcore==1.0.6
httptools==0.6.4
httpx==0.27.2
httpx-sse==0.4.0
huggingface-hub==0.26.2
idna==3.10
ijson==3.3.0
inscriptis==2.5.0
ir_datasets==0.5.9
itsdangerous==2.2.0
Jinja2==3.1.4
jiter==0.7.0
joblib==1.4.2
jsonpatch==1.33
jsonpath-python==1.0.6
jsonpointer==3.0.0
langchain==0.3.7
langchain-community==0.3.7
langchain-core==0.3.18
langchain-milvus==0.1.7
langchain-openai==0.2.6
langchain-text-splitters==0.3.0
langdetect==1.0.9
langsmith==0.1.137
lxml==5.3.0
lz4==4.3.3
markdown-it-py==3.0.0
MarkupSafe==3.0.2
marshmallow==3.23.0
mdurl==0.1.2
mpmath==1.3.0
multidict==6.1.0
multiprocess==0.70.16
mypy-extensions==1.0.0
nest-asyncio==1.6.0
networkx==3.4.2
nltk==3.9.1
numpy==1.26.4
olefile==0.47
openai==1.54.3
orjson==3.10.10
packaging==24.1
pandas==2.2.3
peft==0.13.2
pillow==11.0.0
propcache==0.2.0
protobuf==5.28.3
psutil==6.1.0
pyarrow==18.0.0
pyarrow-hotfix==0.6
pycparser==2.22
pydantic==2.9.2
pydantic-extra-types==2.10.0
pydantic-settings==2.6.0
pydantic_core==2.23.4
Pygments==2.18.0
pymilvus==2.4.8
pypdf==5.1.0
python-dateutil==2.8.2
python-docx==1.1.2
python-dotenv==1.0.1
python-iso639==2024.10.22
python-magic==0.4.27
python-multipart==0.0.17
python-oxmsg==0.0.1
pytz==2024.2
PyYAML==6.0.2
RapidFuzz==3.10.1
regex==2024.9.11
requests==2.32.3
requests-toolbelt==1.0.0
rich==13.9.4
safetensors==0.4.5
scikit-learn==1.5.2
scipy==1.14.1
sentence-transformers==3.1.0
sentencepiece==0.2.0
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
soupsieve==2.6
SQLAlchemy==2.0.35
starlette==0.41.3
sympy==1.13.1
tenacity==8.5.0
threadpoolctl==3.5.0
tiktoken==0.8.0
tokenizers==0.19.1
torch==2.5.1
torchaudio==2.5.1
torchvision==0.20.1
tqdm==4.66.6
transformers==4.44.2
trec-car-tools==2.6
typer==0.13.1
typing-inspect==0.9.0
typing_extensions==4.12.2
tzdata==2024.2
ujson==5.10.0
unlzw3==0.2.2
unstructured==0.16.3
unstructured-client==0.26.2
urllib3==2.2.3
uvicorn==0.32.0
warc3-wet==0.2.5
warc3-wet-clueweb09==0.2.5
watchfiles==0.24.0
webencodings==0.5.1
websockets==14.1
wrapt==1.16.0
xxhash==3.5.0
yarl==1.17.0
zlib-state==0.1.9
server.py
+141
View File
@@ -0,0 +1,141 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/11/20 16:32
# @blog: https://blog.csdn.net/weixin_47936614
import os
import shutil
from fastapi import FastAPI, Request, File, UploadFile
from fastapi.staticfiles import StaticFiles
from fastapi.responses import HTMLResponse
from fastapi.templating import Jinja2Templates
from langchain.chains.retrieval_qa.base import RetrievalQA
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI
from pymilvus import Collection, connections
from pymilvus.orm import utility
from milvus_vector import vector_store, config
from file_process import RagFileProcessor
from protocol.prompts import prompt_template
from protocol.mode import ChatRequest
# 初始化 FastAPI 应用
app = FastAPI(title="Knowledge_QA_RAG API", description="API for data process and retrieval using Milvus and LangChain.")
# 挂载静态文件目录
app.mount("/static", StaticFiles(directory="static"), name="static")
# 配置模板目录
templates = Jinja2Templates(directory="templates")
# 渲染主页
@app.get("/", response_class=HTMLResponse)
async def read_home(request: Request):
return templates.TemplateResponse("qa.html", {"request": request})
@app.post("/rag/chat/")
async def chat(request: ChatRequest):
"""
根据用户问题，从向量库检索并返回回答。
"""
print(f"Q: {request.question}")
try:
# 初始化 OpenAI Chat 模型
llm = ChatOpenAI(model=config.llm_model_name, api_key=config.api_key, base_url=config.base_url)
# 定义 Prompt 模板
qa_prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
# 定义搜索参数
search_kwargs = {"score_threshold": 0.3, "k": 5}
retriever = vector_store.as_retriever(search_type="similarity_score_threshold", search_kwargs=search_kwargs)
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=retriever,
chain_type_kwargs={"prompt": qa_prompt},
return_source_documents=True
)
result = qa_chain.invoke({"query": request.question})
answer_result = result.get("result", "")
print(f"A: {answer_result}")
source = {"source_documents": [{"content": doc.page_content, "metadata": doc.metadata} for doc in
result.get("source_documents", [])]}
print(f"source: {source}")
return {"answer": answer_result}
except Exception as e:
return {"status": "error", "message": str(e)}
@app.post("/rag/clear/")
async def clear_knowledge(collection_name: str = config.milvus_collection_name,
host: str = config.milvus_host,
port: int = config.milvus_port):
"""
清空 Milvus 知识库集合，并删除指定目录中的文件
"""
folder = "./upload_files"
try:
connections.connect("default", host=host, port=port)
if utility.has_collection(collection_name):
collection = Collection(name=collection_name)
collection.drop()
print(f"Collection '{collection_name}' 成功删除.")
else:
print(f"Collection '{collection_name}' 不存在.")
connections.disconnect("default")
for filename in os.listdir(folder):
file_path = os.path.join(folder, filename)
if os.path.isfile(file_path) or os.path.islink(file_path):
os.unlink(file_path)
elif os.path.isdir(file_path):
shutil.rmtree(file_path)
return {"message": f"知识库清空: Collection '{collection_name}' 删除, 文件夹 '{folder}' 清空."}
except Exception as e:
return {"error": f"知识库清空失败. 原因: {str(e)}"}
@app.post("/rag/create/")
async def create_knowledge(file: UploadFile = File(...)):
"""
上传文件到指定目录后，处理文件内容并添加到向量库。
"""
folder = './upload_files' # 文件存储目录
os.makedirs(folder, exist_ok=True) # 确保目录存在
file_path = os.path.join(folder, file.filename)
try:
# 保存文件
with open(file_path, "wb") as f:
content = await file.read()
f.write(content)
folder: str = './upload_files'
file_path = os.path.join(folder, file.filename)
# 初始化文件处理器
file_processor = RagFileProcessor(chunk_size=64)
# 处理文件内容并插入到向量库
text_datas = file_processor.get_data(file_path=file_path)
# 连接到 Milvus
vector_store.add_texts(**text_datas)
return {
"status": "success",
"message": f"文件 '{file.filename}' 上传成功并添加至向量数据库.",
}
except Exception as e:
return {
"status": "error",
"message": f"文件 '{file.filename}'处理失败. 原因: {str(e)}",
}
static/css/qa_style.css
+151
View File
@@ -0,0 +1,151 @@
/*qa_css*/
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
margin: 0;
padding: 0;
display: flex;
justify-content: center;
align-items: center;
height: 100vh;
background: linear-gradient(135deg, #696971FF 0%, #788090FF 100%); /* 渐变背景 */
background-size: cover;
color: #fff;
}
#chat-container {
width: 50%; /* 宽度为页面的一半 */
height: 80%; /* 高度为页面的 80% */
display: flex;
flex-direction: column;
border-radius: 15px; /* 边角圆滑 */
background-color: rgba(255, 255, 255, 0.9); /* 半透明背景 */
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2); /* 阴影效果 */
overflow: hidden;
}
#chat-box {
flex: 1;
padding: 20px;
overflow-y: auto;
display: flex;
flex-direction: column;
align-items: flex-start;
background: #f8f8f8; /* 聊天框背景 */
border-radius: 10px;
margin: 10px;
}
.message {
display: flex;
margin: 10px 0;
padding: 10px 15px;
border-radius: 10px;
max-width: 75%;
align-items: center;
font-size: 16px;
}
.user-message {
align-self: flex-end;
background-color: #0084ff;
color: white;
flex-direction: row-reverse;
}
.bot-message {
align-self: flex-start;
background-color: #e5e5e5;
color: black;
flex-direction: row;
}
.avatar {
width: 45px;
height: 45px;
border-radius: 50%;
margin: 0 10px;
}
#input-container {
display: flex;
padding: 15px;
border-top: 1px solid #ddd;
background-color: #fff;
justify-content: space-between;
align-items: center;
}
#user-input {
flex: 1;
padding: 10px;
font-size: 16px;
border: 1px solid #ccc;
border-radius: 20px;
margin-right: 15px;
outline: none;
transition: all 0.3s ease;
}
#user-input:focus {
border-color: #0084ff; /* 聚焦时边框颜色变化 */
box-shadow: 0 0 5px rgba(0, 132, 255, 0.5); /* 聚焦时增加阴影效果 */
}
#send-button {
padding: 10px 20px;
font-size: 16px;
background-color: #0084ff;
color: white;
border: none;
border-radius: 30px;
cursor: pointer;
transition: all 0.3s ease;
}
#send-button:hover {
background-color: #005bb5; /* 按钮悬停时的颜色 */
transform: scale(1.05); /* 悬停时轻微放大 */
}
.message-container {
display: flex;
justify-content: flex-start;
align-items: center;
}
.message-container-right {
justify-content: flex-end;
}
/*新添加的知识库按钮*/
#kb-actions {
display: flex;
justify-content: center;
margin-top: 10px;
margin-bottom: 5px;
}
#kb-actions button {
padding: 10px 20px;
font-size: 16px;
background-color: #56a750; /* 默认绿色 */
color: white;
border: none;
border-radius: 30px;
cursor: pointer;
margin: 0 10px;
transition: all 0.3s ease;
}
#kb-actions button:hover {
transform: scale(1.05); /* 悬停时轻微放大 */
}
#clear-knowledge {
background-color: #dc3545; /* 红色清空按钮 */
}
#clear-knowledge:hover {
background-color: #b22b37; /* 悬停时红色更深 */
}
static/images/bot.jpg
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.4 KiB

static/images/user.jpg
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 42 KiB

static/js/kb_manager.js
+73
View File
@@ -0,0 +1,73 @@
// 获取添加知识库按钮
const addKbButton = document.getElementById("create-knowledge");
// 监听添加知识库按钮的点击事件
addKbButton.addEventListener("click", () => {
// 创建一个隐藏的文件输入框
const fileInput = document.createElement("input");
fileInput.type = "file";
fileInput.accept = ".txt,.pdf,.docx"; // 根据需求限制文件类型
fileInput.style.display = "none";
// 将文件输入框添加到页面
document.body.appendChild(fileInput);
// 监听文件选择事件
fileInput.addEventListener("change", async () => {
const file = fileInput.files[0]; // 获取用户选择的文件
if (!file) {
alert("请选择一个文件！");
return;
}
const formData = new FormData();
formData.append("file", file); // 将文件添加到 FormData 对象
try {
// 发起 POST 请求到 /rag/add/ 接口
const response = await fetch("/rag/create/", {
method: "POST",
body: formData,
});
const result = await response.json(); // 解析响应数据
if (response.ok) {
alert(result.message || "文件上传并添加到知识库成功！");
} else {
alert(result.message || "上传失败，请重试！");
}
} catch (error) {
console.error("Error uploading file:", error);
alert("上传操作失败，请检查后端服务！");
} finally {
// 从 DOM 中移除文件输入框
document.body.removeChild(fileInput);
}
});
// 模拟点击文件输入框，触发文件选择对话框
fileInput.click();
});
// 监听清空知识库按钮
const clearKnowledge = async () => {
try {
const response = await fetch("/rag/clear/", {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({
collection_name: "knowledge_collection",
host: "localhost",
port: 19530,
}),
});
const result = await response.json();
alert(result.message || result.error);
} catch (error) {
console.error("Error clearing knowledge:", error);
alert("Failed to clear knowledge.");
}
};
document.getElementById("clear-knowledge").addEventListener("click", clearKnowledge);
static/js/qa_script.js
+97
View File
@@ -0,0 +1,97 @@
// qa_script.js
const chatBox = document.getElementById("chat-box");
const userInput = document.getElementById("user-input");
const sendButton = document.getElementById("send-button");
// 用户头像与机器人头像的路径，从静态资源目录加载
const userAvatar = "./static/images/user.jpg";
const botAvatar = "./static/images/bot.jpg";
async function sendMessage() {
const message = userInput.value.trim();
if (!message) return;
// 显示用户消息
const userMessage = document.createElement("div");
userMessage.textContent = message;
userMessage.className = "message user-message";
// 创建用户头像
const userImage = document.createElement("img");
userImage.src = userAvatar;
userImage.className = "avatar";
// 将用户头像和消息一起放到 message-container 中
const userMessageContainer = document.createElement("div");
userMessageContainer.className = "message-container message-container-right";
userMessageContainer.appendChild(userImage);
userMessageContainer.appendChild(userMessage);
chatBox.appendChild(userMessageContainer);
chatBox.scrollTop = chatBox.scrollHeight; // 滚动到最底部
userInput.value = ""; // 清空输入框
// 发送问题到后端
try {
const response = await fetch("/rag/chat/", {
method: "POST",
headers: {
"Content-Type": "application/json",
},
body: JSON.stringify({ question: message }),
});
if (!response.ok) {
throw new Error(`HTTP error! status: ${response.status}`);
}
const data = await response.json();
// 显示机器人回复
const botMessage = document.createElement("div");
botMessage.textContent = data.answer || "No answer available.";
botMessage.className = "message bot-message";
// 创建机器人头像
const botImage = document.createElement("img");
botImage.src = botAvatar;
botImage.className = "avatar";
// 将机器人头像和消息一起放到 message-container 中
const botMessageContainer = document.createElement("div");
botMessageContainer.className = "message-container";
botMessageContainer.appendChild(botImage);
botMessageContainer.appendChild(botMessage);
chatBox.appendChild(botMessageContainer);
chatBox.scrollTop = chatBox.scrollHeight; // 滚动到最底部
} catch (error) {
console.error("Error:", error);
const botMessage = document.createElement("div");
botMessage.textContent = "An error occurred. Please try again.";
botMessage.className = "message bot-message";
// 创建机器人头像
const botImage = document.createElement("img");
botImage.src = botAvatar;
botImage.className = "avatar";
// 将头像和消息内容添加到消息容器
const botMessageContainer = document.createElement("div");
botMessageContainer.className = "message-container";
botMessageContainer.appendChild(botImage);
botMessageContainer.appendChild(botMessage);
chatBox.appendChild(botMessageContainer);
chatBox.scrollTop = chatBox.scrollHeight; // 滚动到最底部
}
}
// 点击发送按钮时发送消息
sendButton.addEventListener("click", sendMessage);
// 按下 Enter 键发送消息
userInput.addEventListener("keypress", (event) => {
if (event.key === "Enter") {
sendMessage();
}
});
templates/qa.html
+29
View File
@@ -0,0 +1,29 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>基于知识库的文档问答系统</title>
<link rel="stylesheet" href="../static/css/qa_style.css">
</head>
<body>
<div id="chat-container">
<div id="chat-box"></div>
<div id="input-container">
<input type="text" id="user-input" placeholder="请输入你的问题...">
<button id="send-button">发送</button>
</div>
<div>
<div id="kb-actions">
<button id="create-knowledge">创建知识库</button>
<button id="clear-knowledge">清空知识库</button>
</div>
</div>
</div>
<script src="../static/js/qa_script.js"></script>
<script src="../static/js/kb_manager.js"></script>
</body>
</html>
text_utils/__init__.py
View File
text_utils/text_embeddings.py
+30
View File
@@ -0,0 +1,30 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/10/31 14:33
# @blog: https://blog.csdn.net/weixin_47936614
from langchain_core.embeddings import Embeddings
from sentence_transformers import SentenceTransformer
class RagTextEmbeddings(Embeddings):
def __init__(self, embed_model_path: str, **kwargs):
self.batch_size = kwargs['batch_size']
self.device = kwargs['device']
self.embed_model = SentenceTransformer(embed_model_path, trust_remote_code=True, device=self.device)
def embed_documents(self, texts: list[str]) -> list[list[float]]:
docs_embeddings = self.embed_model.encode(texts,
task="retrieval.passage",
batch_size=self.batch_size,
device=self.device,
show_progress_bar=True)
return docs_embeddings.tolist()
def embed_query(self, text: str) -> list[float]:
query_embeddings = self.embed_model.encode([text],
task="retrieval.query",
device=self.device)
return query_embeddings.tolist()[0]
text_utils/text_split.py
+76
View File
@@ -0,0 +1,76 @@
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
# @author: CS_木成河
# @time: 2024/10/31 11:17
# @blog: https://blog.csdn.net/weixin_47936614
import re
from typing import List
from langchain.text_splitter import CharacterTextSplitter
class RagTextSplitter(CharacterTextSplitter):
def __init__(self, chunk_size: int = 1024):
super().__init__()
self.chunk_size = chunk_size
def split_text(self, text: str) -> List[str]:
text = re.sub(r"\n{3,}", "\n", text) # 移除三个或更多的连续换行符，用一个换行符代替
text = re.sub(r'\s+', ' ', text) # 替换所有的空白字符为单个空格
text = text.replace("\n\n", "") # 移除双换行符
sent_sep_pattern = re.compile(r'([﹒﹔﹖﹗．。！？]["’”」』]{0,2})') # 用于匹配中文句子结束标点符号以及紧随其后的引号
sentences = []
current_chunk = ""
start = 0
for match in sent_sep_pattern.finditer(text):
end = match.end()
sentence = text[start:end]
start = end
# 检查当前块是否能容纳新句子
if len(current_chunk) + len(sentence) > self.chunk_size: # 不能容纳
if current_chunk:
sentences.append(current_chunk)
current_chunk = sentence
else: # 可以容纳
current_chunk += sentence
if len(sentences) == 0:
sentences.append(text.strip())
final_sentences = []
for line in sentences:
if len(line) <= self.chunk_size:
final_sentences.append(line)
else:
final_sentences.extend(self.split_string(line, self.chunk_size))
return final_sentences
@staticmethod
def split_string(text: str, size: int) -> List[str]:
"""
Split the input string into chunks of specified size, splitting at the last space if needed.
Parameters:
text (str): The input string to be split.
size (int): The size of each chunk.
Returns:
list: A list containing the chunks of the input string.
"""
# 定义句子或标记分割符号列表
SENTENCE_BREAK_SYMBOLS = [' ', '.', '!', '?', ',', ';', ':', '。', '？', '！', '，', '；', '：']
chunks = []
start = 0
while start < len(text):
end = start + size
if end < len(text):
# 在最后一个空格处进行切分
while end > start and text[end - 1] not in SENTENCE_BREAK_SYMBOLS:
end -= 1
chunks.append(text[start:end])
start = end
return chunks