Multi-query retrieval for better recall in LangChain - Performance & Optimization

Performance: Multi-query retrieval for better recall

MEDIUM IMPACT

This concept affects the speed and responsiveness of retrieving relevant information from multiple queries in a single user interaction.

Retrieving relevant documents with better recall

LangChain

queries = [query1, query2, query3]
results = []
for q in queries:
    results.extend(retriever.get_relevant_documents(q))

Multiple queries retrieve more relevant documents in one go, reducing repeated user waits and improving recall.

📈 Performance GainReduces total interaction latency by batching queries; single retrieval phase instead of multiple.

Retrieving relevant documents with better recall

LangChain

results = retriever.get_relevant_documents(query)

Single query retrieval may miss relevant documents, causing lower recall and forcing repeated queries.

📉 Performance CostBlocks rendering for longer due to repeated queries; increases latency linearly with query count.

Performance Comparison

Pattern	DOM Operations	Reflows	Paint Cost	Verdict
Single query retrieval	Minimal DOM updates	1 reflow per update	Low paint cost	[!] OK
Multi-query retrieval sequential	More DOM updates	Multiple reflows	Higher paint cost	[X] Bad
Multi-query retrieval batched/parallel	Minimal DOM updates	Single reflow	Moderate paint cost	[!] Good

Rendering Pipeline

Multiple queries increase the retrieval workload before rendering results, affecting the interaction responsiveness stage.

→Data Fetching

→Interaction Responsiveness

→Rendering

⚠️ BottleneckData Fetching due to multiple retrieval calls

Core Web Vital Affected

INP

This concept affects the speed and responsiveness of retrieving relevant information from multiple queries in a single user interaction.

Optimization Tips

1Batch multiple queries to reduce total retrieval latency.

2Parallelize retrieval calls to improve interaction responsiveness.

3Minimize DOM updates during multi-query results rendering to avoid excessive reflows.

Performance Quiz - 3 Questions

What is the main performance drawback of using multiple sequential queries for retrieval?

A Increased total latency due to blocking calls

B Reduced recall of relevant documents

C Lower paint cost on the page

D Fewer DOM updates

DevTools: Performance

How to check: Record a session while triggering multi-query retrieval; look for long tasks and multiple network calls.

What to look for: Check for blocking time during data fetching and multiple reflows indicating inefficient updates.

Practice

1. What is the main purpose of multi-query retrieval in langchain?

easy

A. To store data in multiple vector stores

B. To reduce the number of queries sent to the database

C. To speed up the response time by using a single query

D. To ask several related questions to get better search results

Solution

1. Step 1: Understand the concept of multi-query retrieval

   Multi-query retrieval involves asking multiple related questions instead of just one to improve the quality of search results.

2. Step 2: Identify the main goal of this approach

   The goal is to get better and more complete search results by combining answers from several queries.

3. Final Answer:

   To ask several related questions to get better search results -> Option D

4. Quick Check:

   Multi-query retrieval = multiple related questions for better results [OK]

Hint: Think: multiple questions improve search quality [OK]

Common Mistakes:

• Confusing multi-query with reducing query count
• Thinking it stores data in multiple places
• Assuming it speeds up by using fewer queries

2. Which of the following is the correct way to create a multi-query retriever in langchain?

easy

A. MultiQueryRetriever(vectorstore, llm=llm)

B. MultiQueryRetriever(queries=["query1", "query2"])

C. MultiQueryRetriever.from_llm(vectorstore.as_retriever(), llm)

D. MultiQueryRetriever.from_llm(vectorstore, llm)

Solution

1. Step 1: Check the required parameters for MultiQueryRetriever

   The MultiQueryRetriever is created using from_llm which requires a BaseRetriever (from vectorstore.as_retriever()) and an llm.

2. Step 2: Identify the correct syntax

   MultiQueryRetriever.from_llm(vectorstore.as_retriever(), llm) correctly uses the classmethod with proper arguments.

3. Final Answer:

   MultiQueryRetriever.from_llm(vectorstore.as_retriever(), llm) -> Option C

4. Quick Check:

   Correct syntax includes from_llm, .as_retriever(), and llm [OK]

Hint: Look for from_llm(vectorstore.as_retriever(), llm) syntax [OK]

Common Mistakes:

• Passing queries as a list to constructor
• Using direct constructor without llm_chain
• Forgetting .as_retriever() on vectorstore

3. Given the following code snippet, what will be the output type of results?

retriever = MultiQueryRetriever.from_llm(vectorstore.as_retriever(), llm)
results = retriever.get_relevant_documents("AI")

medium

A. A single document matching the first query only

B. A list of documents combining results from both queries

C. A dictionary with queries as keys and documents as values

D. An error because get_relevant_documents requires no arguments

Solution

1. Step 1: Understand MultiQueryRetriever behavior

   It [uses the LLM to] runs multiple queries and combines their results into a single list of documents.

2. Step 2: Analyze the method call

   Calling get_relevant_documents("AI") triggers retrieval for all [generated] queries, returning combined documents.

3. Final Answer:

   A list of documents combining results from both queries -> Option B

4. Quick Check:

   Multi-query retrieval returns combined document list [OK]

Hint: MultiQueryRetriever returns combined list of documents [OK]

Common Mistakes:

• Expecting a dictionary instead of a list
• Thinking it returns only first query results
• Assuming get_relevant_documents takes no arguments

4. Identify the error in this code snippet using multi-query retrieval:

retriever = MultiQueryRetriever.from_llm(vectorstore, llm)
results = retriever.get_relevant_documents("AI")

medium

A. vectorstore.as_retriever() is missing

B. get_relevant_documents requires a query argument

C. vectorstore is not defined

D. MultiQueryRetriever does not exist in langchain

Solution

1. Step 1: Check the constructor parameters

   from_llm expects a BaseRetriever as the first argument, but vectorstore is a VectorStore; use vectorstore.as_retriever().

2. Step 2: Verify other parts of the code

   get_relevant_documents has argument; llm assumed defined; class exists.

3. Final Answer:

   vectorstore.as_retriever() is missing -> Option A

4. Quick Check:

   from_llm requires BaseRetriever [OK]

Hint: from_llm needs vectorstore.as_retriever() [OK]

Common Mistakes:

• Passing vectorstore directly instead of retriever
• Thinking get_relevant_documents needs no arg when it does
• Assuming vectorstore undefined without context

5. You want to improve recall for a complex topic by using multi-query retrieval with three related queries. Which approach best ensures you get the most relevant documents without duplicates?

hard

A. Use MultiQueryRetriever.from_llm(retriever, llm) to generate multiple queries and deduplicate results

B. Run each query separately and pick the first result from each

C. Combine all queries into one long string and run a single query

D. Use only the query with the highest expected relevance

Solution

1. Step 1: Understand multi-query retrieval goal

   It aims to combine results from multiple related queries to improve recall.

2. Step 2: Identify best practice to avoid duplicates

   Using MultiQueryRetriever.from_llm(retriever, llm) generates multiple queries via LLM and deduplicates results for completeness without repeats.

3. Final Answer:

   Use MultiQueryRetriever.from_llm(retriever, llm) to generate multiple queries and deduplicate results -> Option A

4. Quick Check:

   MultiQueryRetriever generates + deduplicates = best recall [OK]

Hint: MultiQueryRetriever generates queries then deduplicates for best recall [OK]

Common Mistakes:

• Running queries separately without combining results
• Merging queries into one string loses query specificity
• Using only one query misses relevant documents