Multi-query retrieval for better recall in LangChain - Mini Project: Build & Apply

Multi-query retrieval for better recall

📖 Scenario: You are building a smart document search tool using LangChain. You want to improve recall by querying your document store with multiple related queries instead of just one. This helps find more relevant information from your documents.

🎯 Goal: Create a LangChain retrieval system that uses multiple queries to search a vector store and combines the results for better recall.

📋 What You'll Learn

Create a list of multiple query strings

Set a retrieval limit for number of documents per query

Use LangChain's VectorStoreRetriever to run each query

Combine results from all queries into a single list

💡 Why This Matters

🌍 Real World

Multi-query retrieval helps search engines and AI assistants find more complete information by asking related questions instead of just one.

💼 Career

Knowledge of multi-query retrieval is useful for building advanced search tools, chatbots, and AI systems that need to recall diverse information effectively.

1

Create the list of queries

Create a list called queries with these exact strings: "climate change impact", "global warming effects", and "environmental changes".

LangChain

# Create the list of queries
# Your code here

Hint

Use square brackets to create a list and include the exact strings separated by commas.

2

Set the retrieval limit

Create a variable called retrieval_limit and set it to 3 to limit the number of documents retrieved per query.

LangChain

queries = ["climate change impact", "global warming effects", "environmental changes"]
# Set the retrieval limit
# Your code here

Hint

Just assign the number 3 to the variable retrieval_limit.

3

Retrieve documents for each query

Assuming you have a LangChain VectorStoreRetriever instance called retriever, write a loop using for query in queries that retrieves documents with retriever.get_relevant_documents(query) limited by retrieval_limit. Store all retrieved documents in a list called all_docs.

LangChain

queries = ["climate change impact", "global warming effects", "environmental changes"]
retrieval_limit = 3
all_docs = []
# Loop over queries and retrieve documents
# Your code here

Hint

Use a for loop to go through each query, get documents, slice to limit, and add to all_docs.

4

Combine and finalize retrieval

After collecting documents from all queries, create a set called unique_docs from all_docs to remove duplicates. Then convert it back to a list.

LangChain

queries = ["climate change impact", "global warming effects", "environmental changes"]
retrieval_limit = 3
all_docs = []
for query in queries:
    docs = retriever.get_relevant_documents(query)[:retrieval_limit]
    all_docs.extend(docs)

# Remove duplicates by converting to a set and back to a list
# Your code here

Hint

Use set() to remove duplicates and then convert back to list.

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