Long-term memory with vector stores in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a vector store from embeddings.

Agentic AI

vector_store = VectorStore.from_texts(texts, [1])

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

Aembeddings

Btexts

Cdocuments

Dvectors

Attempts:

3 left

💡 Hint

Common Mistakes

Using raw texts instead of embeddings

Passing documents instead of embeddings

The vector store needs embeddings to index the texts properly.

2fill in blank

medium

Complete the code to retrieve similar documents from the vector store.

Agentic AI

results = vector_store.similarity_search([1], k=3)

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

Adocument_list

Bembedding_vector

Cquery_text

Dsearch_index

Attempts:

3 left

💡 Hint

Common Mistakes

Passing embedding vectors directly

Passing the whole document list

The similarity search takes a query text to find related documents.

3fill in blank

hard

Fix the error in the code to add documents to the vector store.

Agentic AI

vector_store.[1](new_documents)

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

Aappend

Bextend

Cinsert

Dadd_texts

Attempts:

3 left

💡 Hint

Common Mistakes

Using append which is not defined

Using extend which is for lists

The method to add new documents as texts to the vector store is add_texts.

4fill in blank

hard

Fill both blanks to create embeddings and initialize the vector store.

Agentic AI

embeddings = [1]()
vector_store = VectorStore.from_texts(texts, [2])

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

AOpenAIEmbeddings

Btexts

Cembeddings

DDocumentLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Passing texts instead of embeddings

Using wrong class names

First, create embeddings using OpenAIEmbeddings(). Then pass these embeddings to from_texts to build the vector store.

5fill in blank

hard

Fill all three blanks to perform a similarity search and print the top result.

Agentic AI

query = [1]
results = vector_store.similarity_search(query, k=[2])
print(results[[3]].page_content)

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

A"What is AI?"

B3

C0

D"Explain machine learning"

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong query strings

Incorrect index for top result

Wrong number of results requested

We set the query to "Explain machine learning", ask for top 3 results, and print the first result's content.