Open-source embedding models in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the OpenAIEmbeddings class from langchain.embeddings.

LangChain

from langchain.embeddings import [1]

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

AOpenAIEmbedder

BOpenAIEmbedding

COpenAIEmbed

DOpenAIEmbeddings

Attempts:

3 left

💡 Hint

Common Mistakes

Using singular form like OpenAIEmbedding

Using incomplete or incorrect class names

The correct class name to import is OpenAIEmbeddings.

2fill in blank

medium

Complete the code to create an instance of OpenAIEmbeddings with default settings.

LangChain

embedding_model = [1]()

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

AOpenAIEmbeddings

BOpenAIEmbed

COpenAIEmbedder

DOpenAIEmbedding

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong class names

Forgetting parentheses when creating an instance

The correct class to instantiate is OpenAIEmbeddings. It creates the embedding model object.

3fill in blank

hard

Fix the error in the code to generate embeddings for a list of texts.

LangChain

texts = ["hello", "world"]
embeddings = embedding_model.[1](texts)

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

Agenerate_embeddings

Bembed_text

Cembed_documents

Dcreate_embedding

Attempts:

3 left

💡 Hint

Common Mistakes

Using singular method names that expect one text

Using non-existent method names

The method to generate embeddings for multiple texts is embed_documents.

4fill in blank

hard

Fill both blanks to create embeddings for a list and print the shape of the first embedding.

LangChain

texts = ["apple", "banana", "cherry"]
embeddings = embedding_model.[1](texts)
print(len(embeddings[[2]]))

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

Aembed_documents

Bembed_texts

C0

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using embed_texts which may not exist

Using index 1 instead of 0 for the first element

Use embed_documents to embed the list of texts. The first embedding is at index 0.

5fill in blank

hard

Fill the blanks to create embeddings for texts, filter embeddings longer than 100, and print count.

LangChain

texts = ["dog", "cat", "mouse"]
embeddings = embedding_model.[1](texts)
filtered = [e for e in embeddings if len(e) [2] 100]
print(len(filtered))  # Number of embeddings longer than 100

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

Aembed_documents

B>

C<

Dembed_texts

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong method names

Using wrong comparison operators

Use embed_documents to embed texts. Filter embeddings with length greater than 100 using >. The print statement shows how many embeddings are longer than 100.