Similarity search vs MMR retrieval in LangChain - Performance Comparison

Performance: Similarity search vs MMR retrieval

MEDIUM IMPACT

This concept affects how quickly and efficiently relevant documents are retrieved and displayed to users, impacting interaction responsiveness and perceived speed.

Retrieving relevant documents for a user query

LangChain

results = vectorstore.max_marginal_relevance_search(query, k=10, fetch_k=20)

MMR retrieval balances relevance and diversity by re-ranking results, reducing redundancy and improving user experience.

📈 Performance Gainslightly higher CPU cost but better user interaction speed due to more meaningful results

Retrieving relevant documents for a user query

LangChain

results = vectorstore.similarity_search(query, k=10)

Simple similarity search returns top-k closest vectors but may include redundant or very similar documents, reducing result diversity.

📉 Performance Costfast retrieval with minimal computation but may cause user to spend more time scanning redundant results

Performance Comparison

Pattern	Computation Cost	Response Time	Result Diversity	Verdict
Similarity Search	Low (simple top-k vector similarity)	Faster (direct retrieval)	Low (may have redundant results)	[OK]
MMR Retrieval	Medium (similarity + re-ranking)	Slightly slower (extra CPU work)	High (diverse, less redundancy)	[OK] Good

Rendering Pipeline

The query triggers vector similarity calculations; similarity search directly returns top matches, while MMR retrieval adds a re-ranking step to optimize diversity before results render.

→JavaScript Execution

→Network Request

→Rendering

⚠️ BottleneckJavaScript Execution due to extra re-ranking computations in MMR

Core Web Vital Affected

INP

This concept affects how quickly and efficiently relevant documents are retrieved and displayed to users, impacting interaction responsiveness and perceived speed.

Optimization Tips

1Similarity search is faster but may return redundant results.

2MMR retrieval improves result diversity at a small CPU cost.

3Limit fetch_k and cache embeddings to optimize MMR performance.

Performance Quiz - 3 Questions

Which retrieval method typically uses more CPU time during query processing?

A Simple similarity search

B MMR retrieval with re-ranking

C Both use the same CPU time

D Neither uses CPU time

DevTools: Performance

How to check: Record a performance profile while triggering a query; compare CPU time spent in JavaScript execution for similarity search vs MMR retrieval.

What to look for: Look for longer scripting time and call stacks related to re-ranking logic in MMR retrieval, indicating extra computation.

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