FAISS vector store setup in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the FAISS vector store class from LangChain.

LangChain

from langchain.vectorstores import [1]

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

AChroma

BPinecone

CWeaviate

DFAISS

Attempts:

3 left

💡 Hint

Common Mistakes

Importing a different vector store class like Pinecone or Chroma.

Forgetting to import from langchain.vectorstores.

The FAISS vector store class is imported from langchain.vectorstores as FAISS.

2fill in blank

medium

Complete the code to create a FAISS vector store from a list of documents and an embeddings model.

LangChain

faiss_store = FAISS.from_documents(documents=[1], embedding=embedding_model)

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

Adata

Bdocuments

Cdocs

Dtexts

Attempts:

3 left

💡 Hint

Common Mistakes

Using a variable name not defined in the code.

Passing the embedding model as documents.

The variable holding the list of documents is named docs in this example.

3fill in blank

hard

Fix the error in the code to save the FAISS index to disk.

LangChain

faiss_store.[1]("faiss_index")

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

Asave_local

Bsave_local_index

Cload_local

Dsave_to_disk

Attempts:

3 left

💡 Hint

Common Mistakes

Using load_local instead of saving.

Using a method name that does not exist.

The correct method to save a FAISS vector store locally is save_local.

4fill in blank

hard

Fill both blanks to load a FAISS vector store from a local directory with an embeddings model.

LangChain

faiss_store = FAISS.[1]("faiss_index", embeddings=[2])

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

Aload_local

Bembedding_model

Cembeddings

Dsave_local

Attempts:

3 left

💡 Hint

Common Mistakes

Using save_local instead of load_local.

Passing wrong variable names for embeddings.

Use load_local to load the index and pass the embeddings model variable embedding_model.

5fill in blank

hard

Fill all three blanks to create a FAISS vector store, save it locally, and then load it back with the embeddings model.

LangChain

faiss_store = FAISS.[1](documents=[2], embedding=[3])
faiss_store.save_local("faiss_index")
loaded_store = FAISS.load_local("faiss_index", embeddings=[3])

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

Afrom_documents

Bdocs

Cembedding_model

Dload_local

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up method names for creation and loading.

Using wrong variable names for documents or embeddings.

Use from_documents to create the store from docs and embedding_model. Then save and load with the same embeddings model.