Técnicas avançadas de RAG, parte 2: Consultas e testes
Discutir e implementar técnicas que possam aumentar o desempenho do RAG. Parte 2 de 2, com foco em consultas e testes de um pipeline RAG avançado.
Todo o código pode ser encontrado no repositório Searchlabs, na branch advanced-rag-techniques.
Bem-vindo(a) à Parte 2 do nosso artigo sobre Técnicas Avançadas de RAG! Na parte 1 desta série, configuramos, discutimos e implementamos os componentes de processamento de dados do pipeline RAG avançado:
O pipeline RAG utilizado pelo autor.
Nesta parte, vamos prosseguir com a consulta e o teste da nossa implementação. Vamos direto ao assunto!
Índice
Pesquisar e recuperar, gerar respostas
Vamos fazer nossa primeira pergunta, idealmente alguma informação encontrada principalmente no relatório anual. Que tal:
Who audits Elastic?"Agora, vamos aplicar algumas de nossas técnicas para aprimorar a consulta.
Enriquecendo as consultas com sinônimos
Em primeiro lugar, vamos aumentar a diversidade na formulação da consulta e transformá-la em um formato que possa ser facilmente processado em uma consulta do Elasticsearch. Vamos utilizar o GPT-4o para converter a consulta em uma lista de cláusulas OR. Vamos escrever esta pergunta:
ELASTIC_SEARCH_QUERY_GENERATOR_PROMPT = '''
You are an AI assistant specialized in generating Elasticsearch query strings. Your task is to create the most effective query string for the given user question. This query string will be used to search for relevant documents in an Elasticsearch index.
Guidelines:
1. Analyze the user's question carefully.
2. Generate ONLY a query string suitable for Elasticsearch's match query.
3. Focus on key terms and concepts from the question.
4. Include synonyms or related terms that might be in relevant documents.
5. Use simple Elasticsearch query string syntax if helpful (e.g., OR, AND).
6. Do not use advanced Elasticsearch features or syntax.
7. Do not include any explanations, comments, or additional text.
8. Provide only the query string, nothing else.
For the question "What is Clickthrough Data?", we would expect a response like:
clickthrough data OR click-through data OR click through rate OR CTR OR user clicks OR ad clicks OR search engine results OR web analytics
AND operator is not allowed. Use only OR.
User Question:
[The user's question will be inserted here]
Generate the Elasticsearch query string:
'''Quando aplicado à nossa consulta, o GPT-4o gera sinônimos da consulta base e vocabulário relacionado.
'audits elastic OR
elasticsearch audits OR
elastic auditor OR
elasticsearch auditor OR
elastic audit firm OR
elastic audit company OR
elastic audit organization OR
elastic audit service'Na classe ESQueryMaker , defini uma função para dividir a consulta:
def parse_or_query(self, query_text: str) -> List[str]:
# Split the query by 'OR' and strip whitespace from each term
# This converts a string like "term1 OR term2 OR term3" into a list ["term1", "term2", "term3"]
return [term.strip() for term in query_text.split(' OR ')]Sua função é pegar essa sequência de cláusulas OR e dividi-las em uma lista de termos, permitindo-nos fazer uma correspondência múltipla em nossos campos-chave do documento:
["original_text", 'keyphrases', 'potential_questions', 'entities']Finalmente, cheguei a esta pergunta:
'query': {
'bool': {
'must': [
{
'multi_match': {
'query': 'audits Elastic Elastic auditing Elastic audit process Elastic compliance Elastic security audit Elasticsearch auditing Elasticsearch compliance Elasticsearch security audit',
'fields': [
'original_text',
'keyphrases',
'potential_questions',
'entities'
],
'type': 'best_fields',
'operator': 'or'
}
}
]Isso abrange muito mais aspectos do que a consulta original, reduzindo, esperamos, o risco de perder um resultado de pesquisa por termos esquecido um sinônimo. Mas podemos fazer mais.
HyDE (Incorporação Hipotética de Documentos)
Vamos recorrer ao GPT-4o novamente, desta vez para implementar o HyDE.
A premissa básica do HyDE é gerar um documento hipotético – o tipo de documento que provavelmente conteria a resposta à consulta original. A veracidade ou exatidão do documento não é uma preocupação. Com isso em mente, vamos escrever a seguinte pergunta:
HYDE_DOCUMENT_GENERATOR_PROMPT = '''
You are an AI assistant specialized in generating hypothetical documents based on user queries. Your task is to create a detailed, factual document that would likely contain the answer to the user's question. This hypothetical document will be used to enhance the retrieval process in a Retrieval-Augmented Generation (RAG) system.
Guidelines:
1. Carefully analyze the user's query to understand the topic and the type of information being sought.
2. Generate a hypothetical document that:
a. Is directly relevant to the query
b. Contains factual information that would answer the query
c. Includes additional context and related information
d. Uses a formal, informative tone similar to an encyclopedia or textbook entry
3. Structure the document with clear paragraphs, covering different aspects of the topic.
4. Include specific details, examples, or data points that would be relevant to the query.
5. Aim for a document length of 200-300 words.
6. Do not use citations or references, as this is a hypothetical document.
7. Avoid using phrases like "In this document" or "This text discusses" - write as if it's a real, standalone document.
8. Do not mention or refer to the original query in the generated document.
9. Ensure the content is factual and objective, avoiding opinions or speculative information.
10. Output only the generated document, without any additional explanations or meta-text.
User Question:
[The user's question will be inserted here]
Generate a hypothetical document that would likely contain the answer to this query:
'''Como a busca vetorial normalmente opera com base na similaridade de vetores de cosseno, a premissa do HyDE é que podemos obter melhores resultados combinando documentos com documentos em vez de consultas com documentos.
O que nos interessa é a estrutura, a fluidez e a terminologia. Não se trata tanto de factualidade. O GPT-4o gera um documento HyDE como este:
'Elastic N.V., the parent company of Elastic, the organization known for developing Elasticsearch, is subject to audits to ensure financial accuracy,
regulatory compliance, and the integrity of its financial statements. The auditing of Elastic N.V. is typically conducted by an external,
independent auditing firm. This is common practice for publicly traded companies to provide stakeholders with assurance regarding the company\'s
financial position and operations.\n\nThe primary external auditor for Elastic is the audit firm Ernst & Young LLP (EY). Ernst & Young is one of the
four largest professional services networks in the world, commonly referred to as the "Big Four" audit firms. These firms handle a substantial number
of audits for major corporations around the globe, ensuring adherence to generally accepted accounting principles (GAAP) and international financial
reporting standards (IFRS).\n\nThe audit process conducted by EY involves several steps. Initially, the auditors perform a risk assessment to identify
areas where misstatements due to error or fraud could occur. They then design audit procedures to test the accuracy and completeness of financial statements,
which include examining financial transactions, assessing internal controls, and reviewing compliance with relevant laws and regulations. Upon completion of
the audit, Ernst & Young issues an audit report, which includes the auditor’s opinion on whether the financial statements are free from material misstatement
and are presented fairly in accordance with the applicable financial reporting framework.\n\nIn addition to external audits by firms like Ernst & Young,
Elastic may also be subject to internal audits. Internal audits are performed by the company’s own internal auditors to evaluate the effectiveness of internal
controls, risk management, and governance processes.\n\nOverall, the auditing process plays a crucial role in maintaining the transparency and reliability of
Elastic\'s financial information, providing confidence to investors, regulators, and other stakeholders.'Parece bastante convincente, como o candidato ideal para os tipos de documentos que gostaríamos de indexar. Vamos incorporar isso e usar para busca híbrida.
Busca híbrida
Este é o núcleo da nossa lógica de busca. Nosso componente de busca lexical serão as strings da cláusula OR geradas. Nosso componente vetorial denso será um documento HyDE incorporado (também conhecido como vetor de busca). Utilizamos o KNN para identificar de forma eficiente vários documentos candidatos mais próximos do nosso vetor de busca. Por padrão, denominamos nosso componente de busca lexical como "Pontuação com TF-IDF e BM25" . Finalmente, as pontuações lexicais e de vetor denso serão combinadas usando a proporção 30/70 recomendada por Wang et al.
def hybrid_vector_search(self, index_name: str, query_text: str, query_vector: List[float],
text_fields: List[str], vector_field: str,
num_candidates: int = 100, num_results: int = 10) -> Dict:
"""
Perform a hybrid search combining text-based and vector-based similarity.
Args:
index_name (str): The name of the Elasticsearch index to search.
query_text (str): The text query string, which may contain 'OR' separated terms.
query_vector (List[float]): The query vector for semantic similarity search.
text_fields (List[str]): List of text fields to search in the index.
vector_field (str): The name of the field containing document vectors.
num_candidates (int): Number of candidates to consider in the initial KNN search.
num_results (int): Number of final results to return.
Returns:
Dict: A tuple containing the Elasticsearch response and the search body used.
"""
try:
# Parse the query_text into a list of individual search terms
# This splits terms separated by 'OR' and removes any leading/trailing whitespace
query_terms = self.parse_or_query(query_text)
# Construct the search body for Elasticsearch
search_body = {
# KNN search component for vector similarity
"knn": {
"field": vector_field, # The field containing document vectors
"query_vector": query_vector, # The query vector to compare against
"k": num_candidates, # Number of nearest neighbors to retrieve
"num_candidates": num_candidates # Number of candidates to consider in the KNN search
},
"query": {
"bool": {
# The 'must' clause ensures that matching documents must satisfy this condition
# Documents that don't match this clause are excluded from the results
"must": [
{
# Multi-match query to search across multiple text fields
"multi_match": {
"query": " ".join(query_terms), # Join all query terms into a single space-separated string
"fields": text_fields, # List of fields to search in
"type": "best_fields", # Use the best matching field for scoring
"operator": "or" # Match any of the terms (equivalent to the original OR query)
}
}
],
# The 'should' clause boosts relevance but doesn't exclude documents
# It's used here to combine vector similarity with text relevance
"should": [
{
# Custom scoring using a script to combine vector and text scores
"script_score": {
"query": {"match_all": {}}, # Apply this scoring to all documents that matched the 'must' clause
"script": {
# Script to combine vector similarity and text relevance
"source": """
# Calculate vector similarity (cosine similarity + 1)
# Adding 1 ensures the score is always positive
double vector_score = cosineSimilarity(params.query_vector, params.vector_field) + 1.0;
# Get the text-based relevance score from the multi_match query
double text_score = _score;
# Combine scores: 70% vector similarity, 30% text relevance
# This weighting can be adjusted based on the importance of semantic vs keyword matching
return 0.7 * vector_score + 0.3 * text_score;
""",
# Parameters passed to the script
"params": {
"query_vector": query_vector, # Query vector for similarity calculation
"vector_field": vector_field # Field containing document vectors
}
}
}
}
]
}
}
}
# Execute the search request against the Elasticsearch index
response = self.conn.search(index=index_name, body=search_body, size=num_results)
# Log the successful execution of the search for monitoring and debugging
logger.info(f"Hybrid search executed on index: {index_name} with text query: {query_text}")
# Return both the response and the search body (useful for debugging and result analysis)
return response, search_body
except Exception as e:
# Log any errors that occur during the search process
logger.error(f"Error executing hybrid search on index: {index_name}. Error: {e}")
# Re-raise the exception for further handling in the calling code
raise eFinalmente, podemos montar uma função RAG. Nosso processo RAG, da pergunta à resposta, seguirá este fluxo:
Converter consulta em cláusulas OR.
Gere o documento HyDE e incorpore-o.
Passe ambos como entradas para a Busca Híbrida.
Recuperar os n melhores resultados, inverter a ordem para que a pontuação mais relevante seja a "mais recente" na memória contextual do LLM (Empacotamento Inverso). Exemplo de Empacotamento Inverso: Consulta: "Técnicas de otimização de consultas do Elasticsearch". Documentos recuperados (ordenados por relevância): Ordem invertida para o contexto do LLM: Ao inverter a ordem, a informação mais relevante (1) aparece por último no contexto, potencialmente recebendo mais atenção do LLM durante a geração de respostas.
"Use consultas booleanas para combinar vários critérios de pesquisa de forma eficiente."
"Implementar estratégias de cache para melhorar os tempos de resposta das consultas."
"Otimize os mapeamentos de índice para um desempenho de pesquisa mais rápido."
"Otimize os mapeamentos de índice para um desempenho de pesquisa mais rápido."
"Implementar estratégias de cache para melhorar os tempos de resposta das consultas."
"Use consultas booleanas para combinar vários critérios de pesquisa de forma eficiente."
Passe o contexto para o LLM para geração.
def get_context(index_name,
match_query,
text_query,
fields,
num_candidates=100,
num_results=20,
text_fields=["original_text", 'keyphrases', 'potential_questions', 'entities'],
embedding_field="primary_embedding"):
embedding=embedder.get_embeddings_from_text(text_query)
results, search_body = es_query_maker.hybrid_vector_search(
index_name=index_name,
query_text=match_query,
query_vector=embedding[0][0],
text_fields=text_fields,
vector_field=embedding_field,
num_candidates=num_candidates,
num_results=num_results
)
# Concatenates the text in each 'field' key of the search result objects into a single block of text.
context_docs=['\n\n'.join([field+":\n\n"+j['_source'][field] for field in fields]) for j in results['hits']['hits']]
# Reverse Packing to ensure that the highest ranking document is seen first by the LLM.
context_docs.reverse()
return context_docs, search_body
def retrieval_augmented_generation(query_text):
match_query= gpt4o.generate_query(query_text)
fields=['original_text']
hyde_document=gpt4o.generate_HyDE(query_text)
context, search_body=get_context(index_name, match_query, hyde_document, fields)
answer= gpt4o.basic_qa(query=query_text, context=context)
return answer, match_query, hyde_document, context, search_bodyVamos executar nossa consulta e obter a resposta:
According to the context, Elastic N.V. is audited by an independent registered public accounting firm, PricewaterhouseCoopers (PwC).
This information is found in the section titled "report of independent registered public accounting firm," which states:
"We have audited the accompanying consolidated balance sheets of Elastic N.V. [...] / s / pricewaterhouseco."Legal. Isso mesmo.
Experimentos
Há uma pergunta importante a ser respondida agora. O que ganhamos investindo tanto esforço e complexidade adicional nessas implementações?
Vamos fazer uma pequena comparação. O pipeline RAG que implementamos em comparação com a busca híbrida básica, sem nenhuma das melhorias que fizemos. Realizaremos uma pequena série de testes para verificar se notamos alguma diferença significativa. Vamos nos referir ao RAG que acabamos de implementar como AdvancedRAG e ao pipeline básico como SimpleRAG.
Pipeline RAG simples, sem firulas.
Resumo dos resultados
Esta tabela resume os resultados de cinco testes de ambos os pipelines RAG. Avaliei a superioridade relativa de cada método com base no detalhamento e na qualidade das respostas, mas essa é uma avaliação totalmente subjetiva. As respostas corretas estão reproduzidas abaixo desta tabela para sua análise. Dito isso, vamos dar uma olhada em como eles se saíram!
O SimpleRAG não conseguiu responder às perguntas 1 e 5. O AdvancedRAG, por sua vez, apresentou respostas muito mais detalhadas nas perguntas 2, 3 e 4. Com base nesse maior nível de detalhamento, considerei as respostas do AdvancedRAG de melhor qualidade.
Teste | Pergunta | Desempenho AdvancedRAG | Desempenho SimpleRAG | Latência RAG Avançada | Latência SimpleRAG | Ganhador |
|---|---|---|---|---|---|---|
1 | Quem audita a Elastic? | Identificou corretamente a PwC como auditora. | Não foi possível identificar o auditor. | 11,6s | 4,4s | RAG Avançado |
2 | Qual foi a receita total em 2023? | Forneceu o valor correto da receita. Incluímos contexto adicional com a receita de anos anteriores. | Forneceu o valor correto da receita. | 13,3s | 2,8s | RAG Avançado |
3 | De qual produto depende principalmente o crescimento? Quanto? | Identificamos corretamente o Elastic Cloud como o principal fator impulsionador. Inclui contexto geral de receita e detalhes adicionais. | Identificamos corretamente o Elastic Cloud como o principal fator impulsionador. | 14,1s | 12,8s | RAG Avançado |
4 | Descreva o plano de benefícios para funcionários. | Apresentou uma descrição completa dos planos de aposentadoria, programas de saúde e outros benefícios. Inclui valores de contribuição específicos para diferentes anos. | Apresentou uma boa visão geral dos benefícios, incluindo remuneração, planos de aposentadoria, ambiente de trabalho e o programa Elastic Cares. | 26,6s | 11,6s | RAG Avançado |
5 | Quais empresas a Elastic adquiriu? | As aquisições recentes mencionadas no relatório foram listadas corretamente (CmdWatch, Build Security, Optimyze). Foram fornecidas algumas datas de aquisição e preços de compra. | Não foi possível recuperar informações relevantes do contexto fornecido. | 11,9s | 2,7s | RAG Avançado |
Teste 1: Quem audita a Elastic?
RAG Avançado
According to the context, Elastic N.V. is audited by an independent
registered public accounting firm, PricewaterhouseCoopers (PwC).
This information is found in the section titled "report of
independent registered public accounting firm," which states:
"We have audited the accompanying consolidated balance sheets
of Elastic N.V. [...] / s / pricewaterhouseco."SimpleRAG
According to the provided context, no specific auditing firm
or company is mentioned as the auditor for Elastic.
The context provided talks about various features, strengths,
deployment options, and other details related to Elastic and
its operations but does not specify which auditing firm is
responsible for auditing Elastic's financial statements or
internal controls.Resumo: A SimpleRAG não identificou a PwC como auditora.
Bem, isso é realmente surpreendente. Parece ser uma falha de busca por parte do SimpleRAG. Não foram recuperados documentos relacionados à auditoria. Vamos diminuir um pouco a dificuldade no próximo teste.
Teste 2: receita total em 2023
RAG Avançado
### Total Revenue for 2023
According to the provided context, the total revenue for the
year ended April 30, 2023, was **$1,068,989,000**. This
information can be found several times in the provided text.
Specifically, one part states:
"The following table sets forth our results of operations
for the periods presented in dollars and as a percentage of
our total revenue. ... year ended April 30, 2023, ...
total revenue 1,068,989".
Additionally, it is mentioned here as well:
"For the years ended April 30, 2023, 2022, and 2021,
representing year-over-year growth of 24% for the year
ended April 30, 2023... total revenue $1,068,989".
Therefore, the total revenue for 2023 is $1.069 billion.SimpleRAG
According to the context provided, the total revenue for the fiscal year ended April 30, 2023, is:
$1,068,989,000 (or approximately $1.1 billion).Resumo: Ambas as equipes RAG acertaram a resposta: receita total de US$ 1.068.989.000 em 2023.
Ambos estavam bem aqui. Parece que a AdvancedRAG pode ter adquirido uma gama mais ampla de documentos? Certamente a resposta é mais detalhada e incorpora informações de anos anteriores. Isso era de se esperar, considerando as melhorias que fizemos, mas ainda é muito cedo para afirmar algo com certeza.
Vamos aumentar a dificuldade.
Teste 3: De qual produto depende principalmente o crescimento? Quanto?
RAG Avançado
### Product Growth Primarily Depends On:
According to the context, "our revenue is derived primarily from
subscriptions of search, observability and security built into
the elastic stack." The document mentions various strategies and
factors contributing to the company’s growth which include investment
in "elastic cloud," "elastic stack," and the conversion of free
users to paid subscribers.
### Quantitative Data:
- **Revenue**: The document states, "Our total revenue was $1.1 billion,
$862.4 million, and $608.5 million for the years ended April 30, 2023,
2022, and 2021, respectively."
- **Subscription Revenue**: "Subscriptions accounted for 92%, 93%,
and 93% of our total revenue for the years ended April 30, 2023,
2022, and 2021, respectively."
- **Elastic Cloud Contribution**: "For the years ended April 30, 2023,
2022, and 2021, Elastic Cloud contributed 40%, 35%, and 27% of our
total revenue, respectively."
- **Customer Growth**: The number of customers increased from
"over 15,000 as of April 30, 2021," to "approximately 20,200 as of
April 30, 2023."
### Summary:
Product growth for the company primarily depends on the "Elastic Stack"
(which includes search, observability, and security solutions) and
particularly the "Elastic Cloud." The Elastic Cloud's growing contribution
to revenue highlights its significance, which grew from 27% in 2021 to 40% in 2023.SimpleRAG
According to the provided context, growth primarily depends on **Elastic Cloud**,
which is described as the company's "family of cloud-based offerings."
The context also emphasizes the significance of Elastic Cloud in achieving
the company's long-term growth potential and its role in increasing subscription revenue.
From the context:
- "Increasing adoption of Elastic Cloud... is an important growth opportunity
for our business. Organizations are increasingly looking for hosted
deployment alternatives with reduced administrative burdens."
- "We believe that offering Elastic Cloud is important for achieving
our long-term growth potential, and we expect Elastic Cloud’s contribution
to our subscription revenue to continue to increase."
In terms of the contribution to total revenue, here are the specific figures provided:
- Elastic Cloud contributed 40% of the total revenue for the year ended April 30, 2023.
- Elastic Cloud contributed 35% of the total revenue for the year ended April 30, 2022.
- Elastic Cloud contributed 27% of the total revenue for the year ended April 30, 2021.
This progression shows a clear upward trend in the importance and
contribution of Elastic Cloud to the company's overall revenue.Resumo: Ambos os RAGs identificaram corretamente o Elastic Cloud como o principal motor de crescimento. No entanto, o AdvancedRAG inclui mais detalhes, levando em consideração as receitas de assinaturas e o crescimento da base de clientes, e menciona explicitamente outras ofertas da Elastic.
Teste 4: Descreva o plano de benefícios para funcionários
RAG Avançado
### Employee Benefit Plan Overview
The provided context outlines various elements of the employee benefit plan at
Elastic, often referred to as "Elasticians." Here are the key components
described in the texts:
1. **401(k) Plan**:
- **Coverage**: The 401(k) plan is available to substantially all U.S.
employees who meet minimum age and service requirements.
- **Contributions**: Elastic makes contributions to the 401(k) plan up to
6% of the participating employee’s W-2 earnings and wages.
- **Expenses**: For the fiscal years ended April 30, Elastic recorded
expenses of $17.9 million (2023), $15.2 million (2022), and $11.4 million (2021)
related to the 401(k) plan.
- **Defined-Contribution Plans in Other Countries**: Elastic has
defined-contribution plans in various other countries and recorded respective
expenses of $9.4 million (2023), $7.2 million (2022), and $5.1 million (2021).
2. **Stock-Based Compensation**:
- **Types of Awards**: Stock options, restricted stock units (RSUs),
and shares under the Employee Stock Purchase Plan (ESPP).
- **Fair Value Measurement**: Fair value of these stock awards is
measured using models like Black-Scholes.
- **Employee Stock Purchase Plan (2022 ESPP)**:
- Started in 2022, it allows employees to acquire ordinary
shares at a discount (85% of the market value at the beginning
or end of the offering period).
- Offering periods are approximately six months long.
3. **Total Rewards Compensation**:
- **Components**: Includes cash compensation as well as equity awards,
reflecting a comprehensive interest in the well-being of the employees.
- **Programs**: Market competitive medical and dental programs,
mental health, and holistic well-being programs.
- **Paid Time Off**: Features 16 weeks of paid leave for new
parents and life-planning benefits.
4. **Retirement and Income Protection Plans**:
- **401(k) Match**: Elastic provides a dollar-for-dollar
match up to 6% of eligible earnings up to a plan-limit
maximum for U.S.-based employees.
- **Similar Plans Outside the U.S.**: Competitive retirement
plans available for employees based outside the United States.
5. **Flexible Work Environment**:
- **Distributed Workforce**: Elastic operates with a global
distributed workforce model, allowing employees to work remotely
and providing a broad candidate pool.
6. **Learning and Development**:
- **Programs**: Access to on-demand video-based learning,
leadership development programs, and other specific training
to develop managers and leaders.
7. **Employee Engagement and Surveys**:
- **Mechanisms**: Annual employee engagement survey and
mid-year pulse survey.
- **Objectives**: To monitor morale, develop action plans,
and maintain high engagement scores.
8. **Onboarding Program**:
- **X-School**: An extensive new-hire orientation program to
help new employees meet peers and learn about the company's
products and solutions.
In summary, Elastic's employee benefit plan encompasses a broad
spectrum of financial, health, well-being, and professional development
benefits designed to support and enhance the lives of its employees.
The plan is both competitive and comprehensive, aiming to attract,
retain, and engage its global workforce.SimpleRAG
The employee benefit plan at the Company includes several key
components aimed at enhancing the overall well-being and
professional development of employees, referred to as "Elasticians."
1. **Compensation and Benefits:**
- The Company provides market-competitive compensation
packages which typically include cash compensation and equity awards.
- Comprehensive medical and dental programs are offered,
emphasizing mental health and holistic well-being.
- Paid time off programs feature:
- 16 weeks of paid leave for new parents.
- Life-planning benefits.
- Travel reimbursements for certain healthcare services.
2. **Retirement and Income Protection Plans:**
- In the United States, employees are eligible for a 401k
plan with a dollar-for-dollar match by the Company up to 6%
of eligible earnings, subject to a plan limit.
- Similar competitive retirement and income protection plans
are available for employees outside the United States.
3. **Work Environment:**
- The Company offers a flexible work environment, allowing most
employees to work from anywhere as often as they would like.
- Physical offices around the world are available for employees
who prefer to work on-site or need a space for face-to-face interactions.
4. **Community Involvement:**
- The Elastic Cares Program supports charitable organizations
that matter to employees on both local and global levels.
- The program includes:
- Donation matching.
- Providing the Company's technology for free to certain
nonprofit organizations.
- Volunteer time off initiative.Resumo: A AdvancedRAG aborda o assunto com muito mais profundidade e detalhes, mencionando o plano 401K para funcionários baseados nos EUA, além de definir planos de contribuição fora dos EUA. O texto também menciona planos de saúde e bem-estar, mas omite o programa Elastic Cares, que é citado pela SimpleRAG.
Teste 5: Quais empresas a Elastic adquiriu?
RAG Avançado
Elastic acquired several companies over the years to enhance its
technology and market presence. According to the provided context,
the specific acquisitions include:
1. **CmdWatch Security Inc.**: Acquired on September 17, 2021.
The total purchase consideration was $77.8 million.
2. **Build Security Ltd.**: Acquired on September 2, 2021. The
combined purchase price for Build Security Ltd. and another acquisition was $57.2 million.
3. **Optimyze Cloud Inc.**: Acquired on November 1, 2021. Part
of the combined purchase price mentioned above with Build Security Ltd.
4. **Endgame, Inc.**: Although the context mentions an amended
and restated stock incentive plan, it indicates that Endgame, Inc. was
associated with Elastic, suggesting it could have been acquired at some point.
These acquisitions are part of Elastic's strategy to
enhance the technology underlying its security and
observability offerings.SimpleRAG
The provided context does not specify any companies that Elastic has acquired.
Therefore, based on the context, there is no information available about the companies acquired by Elastic.Resumo: O SimpleRAG não recupera nenhuma informação relevante sobre aquisições, resultando em uma resposta incorreta. A AdvancedRAG lista corretamente a CmdWatch, a Build Security e a Optimyze, que foram as principais aquisições mencionadas no relatório.
Conclusão
Com base em nossos testes, nossas técnicas avançadas parecem aumentar o alcance e a profundidade das informações apresentadas, potencialmente melhorando a qualidade das respostas RAG.
Além disso, pode haver melhorias na confiabilidade, já que perguntas formuladas de maneira ambígua, como Which companies did Elastic acquire? e Who audits Elastic foram respondidas corretamente pelo AdvancedRAG, mas não pelo SimpleRAG.
No entanto, vale a pena ter em mente que, em 3 de 5 casos, o pipeline RAG básico, incorporando a Busca Híbrida, mas nenhuma outra técnica, conseguiu produzir respostas que capturaram a maior parte das informações essenciais.
Devemos observar que, devido à incorporação de LLMs nas fases de preparação e consulta de dados, a latência do AdvancedRAG é geralmente de 2 a 5 vezes maior que a do SimpleRAG. Este é um custo significativo que pode tornar o AdvancedRAG adequado apenas para situações em que a qualidade da resposta é priorizada em detrimento da latência.
Os custos significativos de latência podem ser atenuados usando um modelo de linguagem latente (LLM) menor e mais barato, como o Claude Haiku ou o GPT-4o-mini, na fase de preparação dos dados. Salve os modelos avançados para geração de respostas.
Isso está de acordo com as conclusões de Wang et al. Conforme demonstram os resultados, quaisquer melhorias realizadas são relativamente incrementais. Resumindo, o método RAG básico e simples permite chegar a um produto final bastante satisfatório, sendo ainda mais barato e rápido. Para mim, é uma conclusão interessante. Para casos de uso em que velocidade e eficiência são essenciais, o SimpleRAG é a escolha sensata. Para casos de uso em que é necessário extrair o máximo desempenho possível, as técnicas incorporadas no AdvancedRAG podem oferecer uma solução.
Os resultados do estudo de Wang et al. revelam que o uso de técnicas avançadas gera melhorias consistentes, porém incrementais.
Apêndice
Prompts
Pergunta RAG para responder:
Solicitação para que o LLM gere respostas com base na consulta e no contexto.
BASIC_RAG_PROMPT = '''
You are an AI assistant tasked with answering questions based primarily on the provided context, while also drawing on your own knowledge when appropriate. Your role is to accurately and comprehensively respond to queries, prioritizing the information given in the context but supplementing it with your own understanding when beneficial. Follow these guidelines:
1. Carefully read and analyze the entire context provided.
2. Primarily focus on the information present in the context to formulate your answer.
3. If the context doesn't contain sufficient information to fully answer the query, state this clearly and then supplement with your own knowledge if possible.
4. Use your own knowledge to provide additional context, explanations, or examples that enhance the answer.
5. Clearly distinguish between information from the provided context and your own knowledge. Use phrases like "According to the context..." or "The provided information states..." for context-based information, and "Based on my knowledge..." or "Drawing from my understanding..." for your own knowledge.
6. Provide comprehensive answers that address the query specifically, balancing conciseness with thoroughness.
7. When using information from the context, cite or quote relevant parts using quotation marks.
8. Maintain objectivity and clearly identify any opinions or interpretations as such.
9. If the context contains conflicting information, acknowledge this and use your knowledge to provide clarity if possible.
10. Make reasonable inferences based on the context and your knowledge, but clearly identify these as inferences.
11. If asked about the source of information, distinguish between the provided context and your own knowledge base.
12. If the query is ambiguous, ask for clarification before attempting to answer.
13. Use your judgment to determine when additional information from your knowledge base would be helpful or necessary to provide a complete and accurate answer.
Remember, your goal is to provide accurate, context-based responses, supplemented by your own knowledge when it adds value to the answer. Always prioritize the provided context, but don't hesitate to enhance it with your broader understanding when appropriate. Clearly differentiate between the two sources of information in your response.
Context:
[The concatenated documents will be inserted here]
Query:
[The user's question will be inserted here]
Please provide your answer based on the above guidelines, the given context, and your own knowledge where appropriate, clearly distinguishing between the two:
'''prompt do gerador de consultas elásticas
Solicitação para enriquecer as consultas com sinônimos e convertê-las para o formato OU.
ELASTIC_SEARCH_QUERY_GENERATOR_PROMPT = '''
You are an AI assistant specialized in generating Elasticsearch query strings. Your task is to create the most effective query string for the given user question. This query string will be used to search for relevant documents in an Elasticsearch index.
Guidelines:
1. Analyze the user's question carefully.
2. Generate ONLY a query string suitable for Elasticsearch's match query.
3. Focus on key terms and concepts from the question.
4. Include synonyms or related terms that might be in relevant documents.
5. Use simple Elasticsearch query string syntax if helpful (e.g., OR, AND).
6. Do not use advanced Elasticsearch features or syntax.
7. Do not include any explanations, comments, or additional text.
8. Provide only the query string, nothing else.
For the question "What is Clickthrough Data?", we would expect a response like:
clickthrough data OR click-through data OR click through rate OR CTR OR user clicks OR ad clicks OR search engine results OR web analytics
AND operator is not allowed. Use only OR.
User Question:
[The user's question will be inserted here]
Generate the Elasticsearch query string:
'''Possíveis perguntas para o gerador
Solicitação para gerar possíveis perguntas e enriquecer os metadados do documento.
RAG_QUESTION_GENERATOR_PROMPT = '''
You are an AI assistant specialized in generating questions for Retrieval-Augmented Generation (RAG) systems. Your task is to analyze a given document and create 10 diverse questions that would effectively test a RAG system's ability to retrieve and synthesize information from this document.
Guidelines:
1. Thoroughly analyze the entire document.
2. Generate exactly 10 questions that cover various aspects and levels of complexity within the document's content.
3. Create questions that specifically target:
a. Key facts and information
b. Main concepts and ideas
c. Relationships between different parts of the content
d. Potential applications or implications of the information
e. Comparisons or contrasts within the document
4. Ensure questions require answers of varying lengths and complexity, from simple retrieval to more complex synthesis.
5. Include questions that might require combining information from different parts of the document.
6. Frame questions to test both literal comprehension and inferential understanding.
7. Avoid yes/no questions; focus on open-ended questions that promote comprehensive answers.
8. Consider including questions that might require additional context or knowledge to fully answer, to test the RAG system's ability to combine retrieved information with broader knowledge.
9. Number the questions from 1 to 10.
10. Output only the ten questions, without any additional text, explanations, or answers.
Document:
[The document content will be inserted here]
Generate 10 questions optimized for testing a RAG system based on this document:
'''prompt do gerador HyDE
Solicitação para gerar documentos hipotéticos usando o HyDE
HYDE_DOCUMENT_GENERATOR_PROMPT = '''
You are an AI assistant specialized in generating hypothetical documents based on user queries. Your task is to create a detailed, factual document that would likely contain the answer to the user's question. This hypothetical document will be used to enhance the retrieval process in a Retrieval-Augmented Generation (RAG) system.
Guidelines:
1. Carefully analyze the user's query to understand the topic and the type of information being sought.
2. Generate a hypothetical document that:
a. Is directly relevant to the query
b. Contains factual information that would answer the query
c. Includes additional context and related information
d. Uses a formal, informative tone similar to an encyclopedia or textbook entry
3. Structure the document with clear paragraphs, covering different aspects of the topic.
4. Include specific details, examples, or data points that would be relevant to the query.
5. Aim for a document length of 200-300 words.
6. Do not use citations or references, as this is a hypothetical document.
7. Avoid using phrases like "In this document" or "This text discusses" - write as if it's a real, standalone document.
8. Do not mention or refer to the original query in the generated document.
9. Ensure the content is factual and objective, avoiding opinions or speculative information.
10. Output only the generated document, without any additional explanations or meta-text.
User Question:
[The user's question will be inserted here]
Generate a hypothetical document that would likely contain the answer to this query:
'''Exemplo de consulta de pesquisa híbrida
{'knn': {'field': 'primary_embedding',
'query_vector': [0.4265527129173279,
-0.1712949573993683,
-0.042020395398139954,
...],
'k': 100,
'num_candidates': 100},
'query': {'bool': {'must': [{'multi_match': {'query': 'audits Elastic Elastic auditing Elastic audit process Elastic compliance Elastic security audit Elasticsearch auditing Elasticsearch compliance Elasticsearch security audit',
'fields': ['original_text',
'keyphrases',
'potential_questions',
'entities'],
'type': 'best_fields',
'operator': 'or'}}],
'should': [{'script_score': {'query': {'match_all': {}},
'script': {'source': '\n double vector_score = cosineSimilarity(params.query_vector, params.vector_field) + 1.0;\n double text_score = _score;\n return 0.7 * vector_score + 0.3 * text_score;\n ',
'params': {'query_vector': [0.4265527129173279,
-0.1712949573993683,
-0.042020395398139954,
...],
'vector_field': 'primary_embedding'}}}}]}},
'size': 10}
