Activeloop 深度内存
Activeloop 深度内存 是一套工具，使您能够针对您的用例优化您的向量存储，并在您的 LLM 应用中实现更高的准确性。
检索增强生成 (RAG) 最近获得了广泛关注。随着高级 RAG 技术和代理的出现，它们扩展了 RAG 可以实现的潜力的范围。但是，一些挑战可能会限制 RAG 集成到生产环境中。在生产环境中实施 RAG 时需要考虑的主要因素是准确性（召回率）、成本和延迟。对于基本用例，OpenAI 的 Ada 模型与朴素相似性搜索配对可以产生令人满意的结果。但是，为了在搜索期间获得更高的准确性或召回率，可能需要采用高级检索技术。这些方法可能涉及更改数据块大小、多次重写查询等，这可能会增加延迟和成本。Activeloop 的 深度内存（Activeloop Deep Lake 用户可用的功能）通过引入一个经过训练以将用户查询与语料库中的相关数据匹配的小型神经网络层来解决这些问题。虽然此添加在搜索期间产生的延迟极小，但它可以将检索准确性提高高达 27%，并且保持成本效益高且易于使用，而无需任何其他高级 rag 技术。
在本教程中，我们将解析DeepLake 文档，并创建一个可以回答文档中问题的 RAG 系统。
1. 数据集创建
在本教程中，我们将使用BeautifulSoup 库和 LangChain 的文档解析器（如Html2TextTransformer、AsyncHtmlLoader）来解析 activeloop 的文档。因此，我们需要安装以下库
%pip install --upgrade --quiet tiktoken langchain-openai python-dotenv datasets langchain deeplake beautifulsoup4 html2text ragas
您还需要创建一个Activeloop 帐户。
ORG_ID = "..."
from langchain.chains import RetrievalQA
from langchain_community.vectorstores import DeepLake
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API token: ")
# # activeloop token is needed if you are not signed in using CLI: `activeloop login -u <USERNAME> -p <PASSWORD>`
os.environ["ACTIVELOOP_TOKEN"] = getpass.getpass(
"Enter your ActiveLoop API token: "
) # Get your API token from https://app.activeloop.ai, click on your profile picture in the top right corner, and select "API Tokens"
token = os.getenv("ACTIVELOOP_TOKEN")
openai_embeddings = OpenAIEmbeddings()
db = DeepLake(
dataset_path=f"hub://{ORG_ID}/deeplake-docs-deepmemory", # org_id stands for your username or organization from activeloop
embedding=openai_embeddings,
runtime={"tensor_db": True},
token=token,
# overwrite=True, # user overwrite flag if you want to overwrite the full dataset
read_only=False,
)
使用BeautifulSoup 解析网页中的所有链接
from urllib.parse import urljoin
import requests
from bs4 import BeautifulSoup
def get_all_links(url):
response = requests.get(url)
if response.status_code != 200:
print(f"Failed to retrieve the page: {url}")
return []
soup = BeautifulSoup(response.content, "html.parser")
# Finding all 'a' tags which typically contain href attribute for links
links = [
urljoin(url, a["href"]) for a in soup.find_all("a", href=True) if a["href"]
]
return links
base_url = "https://docs.deeplake.ai/en/latest/"
all_links = get_all_links(base_url)
加载数据
from langchain_community.document_loaders.async_html import AsyncHtmlLoader
loader = AsyncHtmlLoader(all_links)
docs = loader.load()
API 参考：AsyncHtmlLoader
将数据转换为用户可读的格式
from langchain_community.document_transformers import Html2TextTransformer
html2text = Html2TextTransformer()
docs_transformed = html2text.transform_documents(docs)
API 参考：Html2TextTransformer
现在，让我们进一步将文档分成块，因为其中一些包含过多的文本
from langchain_text_splitters import RecursiveCharacterTextSplitter
chunk_size = 4096
docs_new = []
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size,
)
for doc in docs_transformed:
if len(doc.page_content) < chunk_size:
docs_new.append(doc)
else:
docs = text_splitter.create_documents([doc.page_content])
docs_new.extend(docs)
填充向量存储
docs = db.add_documents(docs_new)
2. 生成合成查询并训练深度内存
下一步将是训练一个深度内存模型，该模型将用户的查询与您已经拥有的数据集对齐。如果您还没有任何用户查询，不用担心，我们将使用 LLM 生成它们！
待办事项：添加图像
上面我们展示了深度内存的工作原理的整体架构。如您所见，为了训练它，您需要相关性，查询以及语料库数据（我们要查询的数据）。语料库数据已在上节中填充，在这里我们将生成问题和相关性。
questions- 是字符串的文本，其中每个字符串表示一个查询relevance- 包含每个问题的基本事实的链接。可能有多个文档包含给定问题的答案。因此，relevenve 是List[List[tuple[str, float]]]，其中外部列表表示查询，内部列表表示相关文档。元组包含 str、float 对，其中字符串表示源文档的 ID（对应于数据集中id张量），而浮点数对应于当前文档与问题的相关程度。
现在，让我们生成合成问题和相关性
from typing import List
from langchain.chains.openai_functions import (
create_structured_output_chain,
)
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field
API 参考：create_structured_output_chain | HumanMessage | SystemMessage | ChatPromptTemplate | HumanMessagePromptTemplate | ChatOpenAI
# fetch dataset docs and ids if they exist (optional you can also ingest)
docs = db.vectorstore.dataset.text.data(fetch_chunks=True, aslist=True)["value"]
ids = db.vectorstore.dataset.id.data(fetch_chunks=True, aslist=True)["value"]
# If we pass in a model explicitly, we need to make sure it supports the OpenAI function-calling API.
llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
class Questions(BaseModel):
"""Identifying information about a person."""
question: str = Field(..., description="Questions about text")
prompt_msgs = [
SystemMessage(
content="You are a world class expert for generating questions based on provided context. \
You make sure the question can be answered by the text."
),
HumanMessagePromptTemplate.from_template(
"Use the given text to generate a question from the following input: {input}"
),
HumanMessage(content="Tips: Make sure to answer in the correct format"),
]
prompt = ChatPromptTemplate(messages=prompt_msgs)
chain = create_structured_output_chain(Questions, llm, prompt, verbose=True)
text = "# Understanding Hallucinations and Bias ## **Introduction** In this lesson, we'll cover the concept of **hallucinations** in LLMs, highlighting their influence on AI applications and demonstrating how to mitigate them using techniques like the retriever's architectures. We'll also explore **bias** within LLMs with examples."
questions = chain.run(input=text)
print(questions)
import random
from langchain_openai import OpenAIEmbeddings
from tqdm import tqdm
def generate_queries(docs: List[str], ids: List[str], n: int = 100):
questions = []
relevances = []
pbar = tqdm(total=n)
while len(questions) < n:
# 1. randomly draw a piece of text and relevance id
r = random.randint(0, len(docs) - 1)
text, label = docs[r], ids[r]
# 2. generate queries and assign and relevance id
generated_qs = [chain.run(input=text).question]
questions.extend(generated_qs)
relevances.extend([[(label, 1)] for _ in generated_qs])
pbar.update(len(generated_qs))
if len(questions) % 10 == 0:
print(f"q: {len(questions)}")
return questions[:n], relevances[:n]
chain = create_structured_output_chain(Questions, llm, prompt, verbose=False)
questions, relevances = generate_queries(docs, ids, n=200)
train_questions, train_relevances = questions[:100], relevances[:100]
test_questions, test_relevances = questions[100:], relevances[100:]
API 参考：OpenAIEmbeddings
现在我们创建了 100 个训练查询以及 100 个测试查询。现在让我们训练深度内存
job_id = db.vectorstore.deep_memory.train(
queries=train_questions,
relevance=train_relevances,
)
让我们跟踪训练进度
db.vectorstore.deep_memory.status("6538939ca0b69a9ca45c528c")
--------------------------------------------------------------
| 6538e02ecda4691033a51c5b |
--------------------------------------------------------------
| status | completed |
--------------------------------------------------------------
| progress | eta: 1.4 seconds |
| | recall@10: 79.00% (+34.00%) |
--------------------------------------------------------------
| results | recall@10: 79.00% (+34.00%) |
--------------------------------------------------------------
3. 评估深度内存性能
太好了，我们已经训练了模型！它显示出召回率的大幅提升，但我们现在如何使用它并在未见的新数据上进行评估？在本节中，我们将深入研究模型评估和推理部分，并了解如何在 LangChain 中使用它来提高检索准确性
3.1 深度内存评估
首先，我们可以使用深度内存的内置评估方法。它计算几个召回率指标。这可以通过几行代码轻松完成。
recall = db.vectorstore.deep_memory.evaluate(
queries=test_questions,
relevance=test_relevances,
)
Embedding queries took 0.81 seconds
---- Evaluating without model ----
Recall@1: 9.0%
Recall@3: 19.0%
Recall@5: 24.0%
Recall@10: 42.0%
Recall@50: 93.0%
Recall@100: 98.0%
---- Evaluating with model ----
Recall@1: 19.0%
Recall@3: 42.0%
Recall@5: 49.0%
Recall@10: 69.0%
Recall@50: 97.0%
Recall@100: 97.0%
它在看不见的测试数据集上也显示出相当大的改进！！！
3.2 深度内存 + RAGas
from ragas.langchain import RagasEvaluatorChain
from ragas.metrics import (
context_recall,
)
让我们将召回率转换为基本事实
def convert_relevance_to_ground_truth(docs, relevance):
ground_truths = []
for rel in relevance:
ground_truth = []
for doc_id, _ in rel:
ground_truth.append(docs[doc_id])
ground_truths.append(ground_truth)
return ground_truths
ground_truths = convert_relevance_to_ground_truth(docs, test_relevances)
for deep_memory in [False, True]:
print("\nEvaluating with deep_memory =", deep_memory)
print("===================================")
retriever = db.as_retriever()
retriever.search_kwargs["deep_memory"] = deep_memory
qa_chain = RetrievalQA.from_chain_type(
llm=ChatOpenAI(model="gpt-3.5-turbo"),
chain_type="stuff",
retriever=retriever,
return_source_documents=True,
)
metrics = {
"context_recall_score": 0,
}
eval_chains = {m.name: RagasEvaluatorChain(metric=m) for m in [context_recall]}
for question, ground_truth in zip(test_questions, ground_truths):
result = qa_chain({"query": question})
result["ground_truths"] = ground_truth
for name, eval_chain in eval_chains.items():
score_name = f"{name}_score"
metrics[score_name] += eval_chain(result)[score_name]
for metric in metrics:
metrics[metric] /= len(test_questions)
print(f"{metric}: {metrics[metric]}")
print("===================================")
Evaluating with deep_memory = False
===================================
context_recall_score = 0.3763423145
===================================
Evaluating with deep_memory = True
===================================
context_recall_score = 0.5634545323
===================================
3.3 深度内存推理
待办事项：添加图像
使用深度内存
retriever = db.as_retriever()
retriever.search_kwargs["deep_memory"] = True
retriever.search_kwargs["k"] = 10
query = "Deamination of cytidine to uridine on the minus strand of viral DNA results in catastrophic G-to-A mutations in the viral genome."
qa = RetrievalQA.from_chain_type(
llm=ChatOpenAI(model="gpt-4"), chain_type="stuff", retriever=retriever
)
print(qa.run(query))
The base htype of the 'video_seq' tensor is 'video'.
不使用深度内存
retriever = db.as_retriever()
retriever.search_kwargs["deep_memory"] = False
retriever.search_kwargs["k"] = 10
query = "Deamination of cytidine to uridine on the minus strand of viral DNA results in catastrophic G-to-A mutations in the viral genome."
qa = RetrievalQA.from_chain_type(
llm=ChatOpenAI(model="gpt-4"), chain_type="stuff", retriever=retriever
)
qa.run(query)
The text does not provide information on the base htype of the 'video_seq' tensor.
3.4 深度内存成本节省
深度记忆（Deep Memory）可以在不改变现有工作流程的情况下提高检索准确性。此外，通过减少传入大型语言模型 (LLM) 的 top_k 输入，您可以通过降低 token 使用量来大幅降低推理成本。