Activeloop 深度记忆

%pip install --upgrade --quiet  tiktoken langchain-openai python-dotenv datasets langchain deeplake beautifulsoup4 html2text ragas

ORG_ID = "..."

from langchain.chains import RetrievalQA
from langchain_community.vectorstores import DeepLake
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    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>`
if "ACTIVELOOP_TOKEN" not in os.environ:
    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,
)

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)

from langchain_community.document_loaders.async_html import AsyncHtmlLoader

loader = AsyncHtmlLoader(all_links)
docs = loader.load()

from langchain_community.document_transformers import Html2TextTransformer

html2text = Html2TextTransformer()
docs_transformed = html2text.transform_documents(docs)

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)

docs = db.add_documents(docs_new)

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

# 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:]

job_id = db.vectorstore.deep_memory.train(
    queries=train_questions,
    relevance=train_relevances,
)

db.vectorstore.deep_memory.status("6538939ca0b69a9ca45c528c")

recall = db.vectorstore.deep_memory.evaluate(
    queries=test_questions,
    relevance=test_relevances,
)

from ragas.langchain import RagasEvaluatorChain
from ragas.metrics import (
    context_recall,
)

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("===================================")

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))

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)