Multi-query retrieval for better recall in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the MultiQueryRetriever class from langchain.

LangChain

from langchain.retrievers import [1]

Drag options to blanks, or click blank then click option'

AMultiQueryRetriever

BBaseRetriever

CVectorStoreRetriever

DSimpleRetriever

Attempts:

3 left

💡 Hint

Common Mistakes

Importing a wrong retriever class like BaseRetriever or SimpleRetriever.

Forgetting to import from the retrievers submodule.

The MultiQueryRetriever class is imported from langchain.retrievers to enable multi-query retrieval.

2fill in blank

medium

Complete the code to create a MultiQueryRetriever with two queries.

LangChain

retriever = MultiQueryRetriever(
    retrievers=[
        retriever1,
        retriever2
    ],
    queries=[[1]]
)

Drag options to blanks, or click blank then click option'

A['How to code?']

B['AI', 'ML']

C['What is AI?', 'Explain machine learning']

D['Query1', 'Query2', 'Query3']

Attempts:

3 left

💡 Hint

Common Mistakes

Providing too few or too many queries.

Using short keywords instead of full questions.

The queries parameter expects a list of meaningful questions to improve recall. Here, two clear queries are provided.

3fill in blank

hard

Fix the error in the code to correctly retrieve documents using MultiQueryRetriever.

LangChain

docs = retriever.[1]('Explain AI and ML')

Drag options to blanks, or click blank then click option'

Afetch

Bsearch

Cretrieve_docs

Dget_documents

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-existent methods like 'fetch' or 'search'.

Confusing method names from other libraries.

The correct method to get documents from a retriever is get_documents. Other method names will cause errors.

4fill in blank

hard

Fill both blanks to create a MultiQueryRetriever that combines two retrievers and uses two queries.

LangChain

retriever = MultiQueryRetriever(
    retrievers=[[1], [2]],
    queries=['What is AI?', 'What is NLP?']
)

Drag options to blanks, or click blank then click option'

Aretriever_a

Bretriever_b

Cretriever_c

Dretriever_d

Attempts:

3 left

💡 Hint

Common Mistakes

Using the same retriever twice.

Using undefined retriever variable names.

To combine two retrievers, you list them inside the retrievers parameter. Here, retriever_a and retriever_b are used.

5fill in blank

hard

Fill all three blanks to create a MultiQueryRetriever, run a query, and print the number of documents retrieved.

LangChain

retriever = MultiQueryRetriever(
    retrievers=[[1], [2]],
    queries=['Define AI', 'Define ML']
)
docs = retriever.[3]('Define AI and ML')
print(len(docs))

Drag options to blanks, or click blank then click option'

Aretriever_x

Bretriever_y

Cget_documents

Dretriever_z

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect method names for retrieval.

Using undefined retriever variables.

The retrievers retriever_x and retriever_y are combined. The method get_documents is called to retrieve documents, then their count is printed.

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