Metadata filtering in vector stores in LangChain - Mini Project: Build & Apply

Metadata filtering in vector stores

📖 Scenario: You are building a simple document search system using LangChain and a vector store. Your documents have metadata like category and author. You want to filter search results by metadata to find only documents matching certain criteria.

🎯 Goal: Create a LangChain vector store with documents and metadata. Then add a metadata filter to search only documents with category equal to technology.

📋 What You'll Learn

Create a list of documents with text and metadata

Create a LangChain vector store from the documents

Define a metadata filter dictionary with category set to technology

Use the metadata filter in the vector store search method

💡 Why This Matters

🌍 Real World

Filtering search results by metadata is common in document search, recommendation systems, and knowledge bases to improve relevance.

💼 Career

Understanding metadata filtering in vector stores is useful for building intelligent search applications and working with modern AI frameworks like LangChain.

1

Create documents with metadata

Create a list called documents with two dictionaries. The first dictionary should have text set to 'Learn Python programming' and metadata with {'category': 'technology', 'author': 'Alice'}. The second dictionary should have text set to 'Cooking tips for beginners' and metadata with {'category': 'cooking', 'author': 'Bob'}.

LangChain

# Create the list of documents with text and metadata
# Your code here

Need a hint?

Use a list with two dictionaries. Each dictionary has keys text and metadata. Metadata is another dictionary with category and author.

2

Create a LangChain vector store

Import FAISS from langchain.vectorstores. Create a variable called vector_store by calling FAISS.from_texts with the list of document texts extracted from documents and metadata from documents.

LangChain

documents = [
    {'text': 'Learn Python programming', 'metadata': {'category': 'technology', 'author': 'Alice'}},
    {'text': 'Cooking tips for beginners', 'metadata': {'category': 'cooking', 'author': 'Bob'}}
]

# Import FAISS and create vector_store from document texts and metadata
# Your code here

Need a hint?

Extract texts and metadata from documents using list comprehensions. Then call FAISS.from_texts with these lists.

3

Define metadata filter

Create a dictionary called metadata_filter with a key category and value 'technology'.

LangChain

from langchain.vectorstores import FAISS

texts = [doc['text'] for doc in documents]
metadatas = [doc['metadata'] for doc in documents]
vector_store = FAISS.from_texts(texts, metadatas=metadatas)

# Create metadata_filter dictionary with category 'technology'
# Your code here

Need a hint?

Just create a dictionary with the key category and value 'technology'.

4

Search with metadata filter

Call vector_store.similarity_search with query 'Python' and filter=metadata_filter. Assign the result to a variable called results.

LangChain

from langchain.vectorstores import FAISS

texts = [doc['text'] for doc in documents]
metadatas = [doc['metadata'] for doc in documents]
vector_store = FAISS.from_texts(texts, metadatas=metadatas)

metadata_filter = {'category': 'technology'}

# Search vector_store with query 'Python' and filter=metadata_filter
# Your code here

Need a hint?

Call similarity_search on vector_store with the query string and the filter argument set to metadata_filter.