当前位置：首页 > news >正文

langchain结合searXNG实现基于搜索RAG

news 来源：原创 2024/9/21 8:35:36

一、背景

二、环境说明和安装

1.1 环境说明

2.2 环境安装

2.2.1 searXNG安装

三、代码实现

代码

结果输出

直接请求模型输出

四、参考

一、背景

大语言模型的出现带来了新的技术革新，但是大模型由于训练语料的原因，它的知识和当前实时热点存在时间差距，存在很严重的幻觉。而RAG检索增强生成能够解决这个问题，知识以prompt的形式进行补足，再让LLM进行润色进而呈现给用户。

二、环境说明和安装

1.1 环境说明

整个环境都是基于我本地进行搭建，机器环境采用的是wsl2部署的Ubuntu-20.04，大模型选取的是Qwen/Qwen2-7B-Instruct，采用vllm进行部署推理以openai api的形式提供服务，langchain使用的是最新的0.2版本，由于searXNG是需要docker部署的，所以请确保已安装docker .desktop。

2.2 环境安装

2.2.1 searXNG安装

下载

cd /opt/softwares
git clone https://github.com/searxng/searxng-docker.git
cd searxng-docker

docker-compose配置

searXNG的组件有三个，caddy实现反向代理，这里不需要反向代理，采用直接调用的形式，关于caddy的部分注释掉；redis用来保存session，searXNG提供搜索服务。设置端口映射，0.0.0.0:8080:8080左边的端口为宿主机端口，右边的端口为docker端口

version: "3.7"services:#caddy:#container_name: caddy#image: docker.io/library/caddy:2-alpine#network_mode: host#restart: unless-stopped#volumes:#- ./Caddyfile:/etc/caddy/Caddyfile:ro#- caddy-data:/data:rw#- caddy-config:/config:rw#environment:#- SEARXNG_HOSTNAME=${SEARXNG_HOSTNAME:-http://localhost:80}#- SEARXNG_TLS=${LETSENCRYPT_EMAIL:-internal}#cap_drop:#- ALL#cap_add:#- NET_BIND_SERVICE#logging:#driver: "json-file"#options:#max-size: "1m"#max-file: "1"redis:container_name: redisimage: docker.io/valkey/valkey:7-alpinecommand: valkey-server --save 30 1 --loglevel warningrestart: unless-stoppednetworks:- searxngvolumes:- valkey-data2:/datacap_drop:- ALLcap_add:- SETGID- SETUID- DAC_OVERRIDElogging:driver: "json-file"options:max-size: "1m"max-file: "1"searxng:container_name: searxngimage: docker.io/searxng/searxng:latestrestart: unless-stoppednetworks:- searxngports:- "0.0.0.0:8080:8080"volumes:- ./searxng:/etc/searxng:rwenvironment:- SEARXNG_BASE_URL=https://${SEARXNG_HOSTNAME:-localhost}/cap_drop:- ALLcap_add:- CHOWN- SETGID- SETUIDlogging:driver: "json-file"options:max-size: "1m"max-file: "1"networks:searxng:volumes:caddy-data:caddy-config:valkey-data2:

searxng配置

# 设置秘钥
sed -i "s|ultrasecretkey|$(openssl rand -hex 32)|g" searxng/settings.yml
# limiter设置为false，设置formats
vim searxng/settings.yml

settings.yml内容如下：

use_default_settings: true
server:# base_url is defined in the SEARXNG_BASE_URL environment variable, see .env and docker-compose.ymlsecret_key: "fc6a61736b885ace5f990f840006d057c01604501a36636b4a378f4b2cb89fdf"  # change this!limiter: false  # can be disabled for a private instanceimage_proxy: true
ui:static_use_hash: true
redis:url: redis://redis:6379/0
search:formats:- html- json

如果没有配置search.formats，在使用langchain进行调用的时候会报503错误，相关issue如下：

https://github.com/langchain-ai/langchain/issues/855

启动

# 启动
docker-compose up -d
# 停止
docker-compose stop

访问localhost:8080，如下：

三、代码实现

代码

from typing import List
from langchain_community.utilities import SearxSearchWrapper
import requests
from requests.exceptions import RequestException
from langchain_community.document_loaders import AsyncHtmlLoader
from langchain_community.document_transformers.html2text import Html2TextTransformer
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_openai.chat_models import ChatOpenAI
from langchain.prompts.chat import ChatPromptTemplate
import faiss
from langchain_community.vectorstores import FAISS
from langchain_community.docstore import InMemoryDocstore
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_core.documents import Document
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains.retrieval import create_retrieval_chain
import os
import sys
sys.path.append(os.path.abspath(os.pardir))
from global_config import MODEL_CACHE_DIR
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"def check_url_access(urls: List[str]) -> List[str]:urls_can_access = []for url in urls:try:req_res = requests.get(url)if req_res is not None and req_res.ok:urls_can_access.append(url)except RequestException as e:continuereturn urls_can_accessdef get_chat_llm(streaming=False, temperature=0, max_tokens=2048) -> ChatOpenAI:chat_llm = ChatOpenAI(model_name="Qwen2-7B-Instruct",openai_api_key="empty",openai_api_base="http://localhost:8000/v1",max_tokens=max_tokens,temperature=temperature,streaming=streaming)return chat_llmdef get_retriever(documents: List[Document]):# embeddingembeddings = HuggingFaceEmbeddings(model_name=os.path.join(MODEL_CACHE_DIR, "maidalun/bce-embedding-base_v1"))# faissfaiss_index = faiss.IndexFlatL2(len(embeddings.embed_query("hello world")))  # 指定向量维度vector_store = FAISS(embedding_function=embeddings,index=faiss_index,docstore=InMemoryDocstore(),index_to_docstore_id={})vector_store.add_documents(documents)return vector_store.as_retriever()def get_answer_prompt() -> ChatPromptTemplate:system_prompt = """你是一个问答任务的助手，请依据以下检索出来的信息去回答问题：{context}"""return ChatPromptTemplate([("system", system_prompt),("human", "{input}")])if __name__ == '__main__':llm = get_chat_llm()search = SearxSearchWrapper(searx_host="http://localhost:8080/")query = "《元梦之星》这款游戏是什么时候发行的"results = search.results(query,                                  # 搜索内容language="zh-CN",                       # 语言safesearch=1,                           # 可选0(不过滤任何结果),1(中等级别内容过滤),2(严格级别内容过滤)categories="general",                   # 搜索内容，取值general/images/videos等engines=["bing", "brave", "google"],    # 搜索引擎num_results=3                           # 返回内容数)print(f"search results: {results}")urls_to_look = [ele["link"] for ele in results if ele.get("link", None)]# 检查url是否可达urls = check_url_access(urls_to_look)print(f"urls: {urls}")# loaderloader = AsyncHtmlLoader(urls, ignore_load_errors=True, requests_kwargs={"timeout": 5})docs = loader.load()# transformerhtml2text = Html2TextTransformer()docs = html2text.transform_documents(docs)# text splittext_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)docs = text_splitter.split_documents(docs)# retrieverretriever = get_retriever(docs)# create_stuff_documents_chain的prompt必须含有context变量qa_chain = create_stuff_documents_chain(llm, get_answer_prompt())rag_chain = create_retrieval_chain(retriever, qa_chain)res = rag_chain.invoke({"input": query})print(res["answer"])

结果输出

《元梦之星》这款游戏是在2023年12月15日全平台上线发行的。

直接请求模型输出

curl http://localhost:8000/v1/chat/completions \-H "Content-Type: application/json" \-d '{"model": "Qwen2-7B-Instruct","messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "《元梦之星》这款游戏是什么时候发行的"}]}'