Similarity search vs MMR retrieval in LangChain - Hands-On Comparison

Similarity Search vs MMR Retrieval with LangChain

📖 Scenario: You are building a simple document search tool using LangChain. You want to compare two ways to find relevant documents: similarity search and Maximal Marginal Relevance (MMR) retrieval. Similarity search finds documents closest to your query. MMR retrieval finds documents that are both relevant and diverse.

🎯 Goal: Build a LangChain script that loads a small set of documents, sets up a vector store, and performs both similarity search and MMR retrieval. See how the results differ.

📋 What You'll Learn

Create a list of 3 documents with exact texts

Create a LangChain vector store from the documents

Perform a similarity search for the query 'apple fruit'

Perform an MMR retrieval for the query 'apple fruit' with k=2 and fetch_k=3

💡 Why This Matters

🌍 Real World

This project shows how to build a simple document search tool that can find relevant information quickly and also provide diverse results to avoid repetition.

💼 Career

Understanding similarity search and MMR retrieval is important for building smart search engines, recommendation systems, and chatbots that use document retrieval.

1

Create the documents list

Create a list called documents containing these exact strings: 'Apple is a fruit.', 'Banana is yellow.', and 'Carrots are vegetables.'

LangChain

# Create the documents list
# Your code here

Hint

Use a Python list with the exact strings given.

2

Set up the vector store

Import FAISS and OpenAIEmbeddings from LangChain. Create a variable called embeddings as OpenAIEmbeddings(). Then create a vector_store by calling FAISS.from_texts(documents, embeddings).

LangChain

documents = ['Apple is a fruit.', 'Banana is yellow.', 'Carrots are vegetables.']
# Import FAISS and OpenAIEmbeddings
# Create embeddings and vector_store
# Your code here

Hint

Use the exact class names and method calls as shown.

3

Perform similarity search

Use vector_store.similarity_search with the query 'apple fruit' and k=2. Store the result in a variable called similar_docs.

LangChain

from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings

documents = ['Apple is a fruit.', 'Banana is yellow.', 'Carrots are vegetables.']

embeddings = OpenAIEmbeddings()
vector_store = FAISS.from_texts(documents, embeddings)
# Perform similarity search for 'apple fruit' with k=2
# Your code here

Hint

Call similarity_search on vector_store with the exact query and k value.

4

Perform MMR retrieval

Use vector_store.max_marginal_relevance_search with the query 'apple fruit', k=2, and fetch_k=3. Store the result in a variable called mmr_docs.

LangChain

from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings

documents = ['Apple is a fruit.', 'Banana is yellow.', 'Carrots are vegetables.']

embeddings = OpenAIEmbeddings()
vector_store = FAISS.from_texts(documents, embeddings)

similar_docs = vector_store.similarity_search('apple fruit', k=2)
# Perform MMR retrieval for 'apple fruit' with k=2 and fetch_k=3
# Your code here

Hint

Call max_marginal_relevance_search on vector_store with the exact parameters.

Practice

1. What is the main difference between Similarity search and MMR retrieval in Langchain?

easy

A. Similarity search uses machine learning; MMR retrieval uses rule-based filtering.

B. Similarity search finds closest matches; MMR retrieval balances closeness and diversity.

C. Similarity search always returns random results; MMR retrieval returns exact matches.

D. Similarity search is slower than MMR retrieval in all cases.

Solution

1. Step 1: Understand Similarity Search

   Similarity search finds the closest matches to the query based on similarity scores.

2. Step 2: Understand MMR Retrieval

   MMR retrieval balances between closeness and diversity to avoid repeated or very similar results.

3. Final Answer:

   Similarity search finds closest matches; MMR retrieval balances closeness and diversity. -> Option B

4. Quick Check:

   Difference = Closest vs Balanced [OK]

Hint: Similarity = closeness; MMR = closeness plus diversity [OK]

Common Mistakes:

• Thinking MMR returns only closest matches
• Confusing MMR with random retrieval
• Assuming similarity search ensures diverse results

2. Which of the following is the correct way to initialize an MMR retriever in Langchain?

easy

A. mmr_retriever = MMRRetriever(documents, k=5, lambda_mult=0.7)

B. mmr_retriever = MMRRetriever(documents, top_k=5, lambda=0.7)

C. mmr_retriever = MMRRetriever(documents, k=5, lambda=0.7)

D. mmr_retriever = MMRRetriever(documents, top_k=5, lambda_mult=0.7)

Solution

1. Step 1: Check parameter names for MMRRetriever

   The correct parameters include k for number of results and lambda_mult for diversity weight.

2. Step 2: Identify correct parameter usage

   Options B, C, and D use top_k or lambda which are incorrect parameter names.

3. Final Answer:

   mmr_retriever = MMRRetriever(documents, k=5, lambda_mult=0.7) -> Option A

4. Quick Check:

   Correct params = k and lambda_mult [OK]

Hint: MMR uses k and lambda_mult parameters [OK]

Common Mistakes:

• Using 'top_k' instead of 'k'
• Using 'lambda' instead of 'lambda_mult'
• Mixing parameter names from similarity search

3. Given the following code snippet using Langchain's similarity search and MMR retrieval, what will be the main difference in their outputs?

docs = ["apple pie recipe", "apple tart recipe", "banana bread recipe", "cherry pie recipe"]
query = "apple dessert"
sim_results = similarity_search(docs, query, k=2)
mmr_results = mmr_retrieval(docs, query, k=2, lambda_mult=0.5)

medium

A. sim_results will return the two most similar apple recipes; mmr_results will return one apple and one different dessert recipe.

B. sim_results will return random recipes; mmr_results will return the two closest apple recipes.

C. Both sim_results and mmr_results will return the same two apple recipes.

D. sim_results will return only one recipe; mmr_results will return three recipes.

Solution

1. Step 1: Analyze similarity_search output

   Similarity search returns the top 2 closest matches, likely both apple recipes due to query "apple dessert".

2. Step 2: Analyze mmr_retrieval output

   MMR balances similarity and diversity, so it will likely return one apple recipe and one different dessert (like cherry pie) to increase variety.

3. Final Answer:

   sim_results will return the two most similar apple recipes; mmr_results will return one apple and one different dessert recipe. -> Option A

4. Quick Check:

   Similarity = closest; MMR = closest + diverse [OK]

Hint: Similarity = closest matches; MMR adds variety [OK]

Common Mistakes:

• Assuming both return identical results
• Thinking MMR returns random results
• Confusing number of results returned

4. You wrote this code to perform MMR retrieval but get an error:

mmr = MMRRetriever(documents, k=3, lambda_mult=0.6)
results = mmr.get_relevant_documents(query)

What is the likely cause of the error?

medium

A. Calling 'get_relevant_documents' instead of 'retrieve_documents'.

B. Using 'k' instead of 'top_k' when initializing MMRRetriever.

C. Missing import statement for MMRRetriever.

D. Using 'lambda_mult' instead of 'lambda' parameter.

Solution

1. Step 1: Check parameter names in MMRRetriever initialization

   The parameters k and lambda_mult are correct.

2. Step 2: Confirm method name correctness

   get_relevant_documents is a valid method for retrievers.

3. Final Answer:

   Missing import statement for MMRRetriever. -> Option C

4. Quick Check:

   Missing import = NameError [OK]

Hint: Import MMRRetriever before use [OK]

Common Mistakes:

• Forgetting import statement for MMRRetriever
• Confusing method names
• Wrong parameter names like top_k or lambda

5. You want to retrieve 3 documents related to "climate change" using Langchain. You want results that are relevant but also cover different aspects like causes, effects, and solutions. Which retrieval method and parameters should you choose?

hard

A. Use MMR retrieval with k=3 and lambda_mult=0 to get only closest matches.

B. Use similarity search with k=3 for closest matches only.

C. Use similarity search with k=1 repeated 3 times to get variety.

D. Use MMR retrieval with k=3 and lambda_mult=0.8 to balance relevance and diversity.

Solution

1. Step 1: Identify need for relevance and diversity

   You want documents that are relevant but cover different aspects, so diversity is important.

2. Step 2: Choose retrieval method and parameters

   MMR retrieval balances relevance and diversity using lambda_mult. A value like 0.8 prioritizes relevance while introducing some diversity.

3. Final Answer:

   Use MMR retrieval with k=3 and lambda_mult=0.8 to balance relevance and diversity. -> Option D

4. Quick Check:

   Diversity + relevance = MMR with 0 < lambda_mult < 1 [OK]

Hint: Lower lambda_mult increases diversity in MMR [OK]

Common Mistakes:

• Using similarity search only for diverse results
• Setting lambda_mult to 0 disables relevance
• Repeating similarity search calls for variety