Strategie di recupero multi-query
Migliori il recall del recupero generando più prospettive della query dell'utente e combinando i risultati di ricerche diverse.
Strategie di recupero multi-query è una lezione LangChain / RAG / Vector DBs gratuita su CoddyKit. Questa è la lezione 1 di 4. Puoi leggere la lezione completa qui gratuitamente — poi esercitati direttamente nel browser con un editor di codice integrato e un tutor IA disponibile 24/7. Fa parte del percorso di apprendimento LangChain / RAG / Vector DBs, e i tuoi progressi si sincronizzano tra il web e l'app CoddyKit. Il corso LangChain / RAG / Vector DBs include 4 lezioni in totale.
Parti di questa lezione non sono ancora state tradotte e vengono mostrate in inglese.
Boosting RAG with Multi-Query
Sometimes, a single search query isn't enough to find all the relevant information. Multi-query retrieval is a technique that helps your RAG system cast a wider net.
It generates several different versions of your original question. This helps ensure you don't miss important context, leading to more comprehensive answers.
Why One Query Isn't Enough
Imagine asking "What are the benefits of RAG?". A single search might only pick up documents directly matching those exact words. This can limit the context available to your LLM.
- It might miss documents using terms like "advantages of RAG" or "why use RAG".
- It could also miss related concepts that provide crucial background.
This limitation can lead to incomplete or less accurate answers from the LLM.
Expanding Your Search Horizon
Before advanced tools, people would manually brainstorm related queries to ensure a broader search. For example:
- Original: "How does RAG improve LLM accuracy?"
- Expanded: "What are RAG benefits for LLMs?", "RAG's impact on factual correctness", "How RAG reduces hallucinations".
While effective, this manual process is tedious and hard to scale for complex systems. We need an automated solution!
LLMs as Query Generators
Large Language Models (LLMs) are excellent at understanding context and generating variations of text. We can leverage an LLM to automatically create several alternative questions from an initial user query.
- This uses the LLM's natural language understanding abilities.
- It automates the query expansion process efficiently.
These diverse queries then provide multiple 'angles' for searching your knowledge base.
LangChain's MultiQueryRetriever
LangChain provides a powerful component called MultiQueryRetriever. This tool automates the entire multi-query process for you, making it easy to integrate into your RAG pipeline.
- It uses an LLM to generate diverse queries from your initial input.
- It then runs these multiple queries against your vector store.
- Finally, it combines the results into a single, comprehensive set of documents for the LLM.
MultiQueryRetriever in Action
Let's see how to set up MultiQueryRetriever in Python. You'll need an LLM and an existing retriever (e.g., from a vector store).
This example mocks a vector store for demonstration. In a real application, your vector store would be pre-populated with your documents.
from langchain_community.chat_models import ChatOpenAI
from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_core.documents import Document
# This is a mock setup for demonstration
# In a real app, your vector store would be populated
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(
[
Document(page_content="RAG improves LLM factual accuracy."),
Document(page_content="Retrieval Augmented Generation reduces hallucinations."),
Document(page_content="The advantages of RAG include up-to-date information."),
Document(page_content="RAG systems combine retrieval with generation."),
], embeddings
)
retriever = vectorstore.as_retriever()
# Initialize a chat model (replace with your actual LLM)
# For local testing, consider using a local LLM or mock
llm = ChatOpenAI(temperature=0) # Placeholder
# Create the MultiQueryRetriever
multi_query_retriever = MultiQueryRetriever.from_llm(
retriever=retriever, llm=llm
)
print("MultiQueryRetriever initialized successfully!")
# Example usage would follow: multi_query_retriever.get_relevant_documents(query)The Multi-Query Workflow
Here's a simplified breakdown of what MultiQueryRetriever does behind the scenes:
- Initial Query: You provide one query, e.g., "What are RAG's advantages?"
- Query Generation: The LLM takes your query and generates 2-4 alternative queries (e.g., "Benefits of RAG", "Why use RAG?", "How RAG improves LLMs").
- Parallel Retrieval: Each generated query is sent to your underlying retriever (e.g., vector store) simultaneously.
- Result Combination: All retrieved documents from these multiple searches are collected and often de-duplicated.
- Final Context: This combined set of documents is then passed to your main LLM for generating the final answer.
Merging Retrieved Documents
After multiple queries fetch documents, how do we best combine them to form the final context?
- Unique Documents: The simplest approach is to gather all documents and remove duplicates. This ensures variety without redundancy.
- Re-ranking: For more advanced control, you can apply a re-ranking model to the combined set. This model scores documents based on their relevance to the original query, ensuring the most important ones are prioritized (a topic for a future lesson!).
Why Use Multi-Query Retrieval?
Implementing multi-query strategies offers significant benefits for your RAG system:
- Improved Recall: You're more likely to find all relevant pieces of information, even if they use different phrasing.
- Richer Context: The LLM receives a broader and more diverse set of documents, leading to more comprehensive and accurate answers.
- Reduced Hallucinations: With better context, the LLM is less likely to "make things up" due to lack of information.
- Handles Ambiguity: Helps when the user's initial query is slightly ambiguous or could have multiple interpretations.
Multi-Query Check
Multi-query retrieval aims to improve retrieval by generating multiple perspectives of a user's query. Which of the following best describes the core problem it solves?
Multi-Query Recap
In this lesson, we explored Multi-Query Retrieval. We learned that a single query can often miss valuable context, and how Large Language Models (LLMs) can generate multiple, diverse queries to overcome this.
LangChain's MultiQueryRetriever automates this entire process, significantly improving the recall and richness of the context provided to your RAG system. This ultimately leads to more comprehensive and accurate answers.
Domande Frequenti
La lezione «Strategie di recupero multi-query» è gratuita?
Sì — il testo completo di «Strategie di recupero multi-query» è gratuito qui sul web. Per esercitarvi in modo interattivo (un editor di codice integrato e un tutor IA 24/7) e sbloccare il resto del corso LangChain / RAG / Vector DBs, passa a CoddyKit PRO. Il corso LangChain / RAG / Vector DBs include 4 lezioni in totale.
Cosa imparerò in «Strategie di recupero multi-query»?
Migliori il recall del recupero generando più prospettive della query dell'utente e combinando i risultati di ricerche diverse. Eserciti LangChain / RAG / Vector DBs con codice pratico che esegui direttamente nel browser, e un tutor IA 24/7 risponde alle tue domande mentre lavori sulla lezione.
Ho bisogno di esperienza per iniziare LangChain / RAG / Vector DBs?
Non è richiesta alcuna esperienza precedente. LangChain / RAG / Vector DBs su CoddyKit è strutturato per principianti e studenti avanzati, quindi puoi iniziare da qui o dall'inizio e procedere al tuo ritmo. Questa è la lezione 1 di 4.
Quanto tempo richiede la lezione «Strategie di recupero multi-query»?
La maggior parte delle lezioni CoddyKit richiede circa 5–10 minuti. Ogni lezione è breve e interattiva, quindi fai progressi costanti e riprendi esattamente da dove hai lasciato su web e app.
Posso scrivere ed eseguire codice in questa lezione LangChain / RAG / Vector DBs?
Sì. Ogni lezione LangChain / RAG / Vector DBs include un editor di codice integrato, quindi scrivi ed esegui codice reale direttamente nel tuo browser e ricevi feedback istantaneo dall'IA — nessuna configurazione locale necessaria.
Tutte le lezioni di questo corso
- Strategie di recupero multi-query
- Compressione contestuale con gli LLM
- Ricerca ibrida e riordinamento
- Retrieval di documenti principali e finestre di frasi