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

Need a 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

Need a 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

Need a 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

Need a hint?

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