Memory-augmented retrieval in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the memory class from LangChain.

LangChain

from langchain.memory import [1]

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

ARetrievalQA

BOpenAI

CConversationBufferMemory

DVectorStore

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated classes like RetrievalQA or OpenAI.

Forgetting to import any memory class.

The ConversationBufferMemory class is used to store conversation history in LangChain memory-augmented retrieval.

2fill in blank

medium

Complete the code to create a memory object that stores chat history.

LangChain

memory = [1]()

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

AConversationBufferMemory

BRetrievalQA

COpenAI

DVectorStoreRetriever

Attempts:

3 left

💡 Hint

Common Mistakes

Using classes meant for retrieval or language models instead of memory.

Calling a class that requires parameters when none are given.

ConversationBufferMemory() creates a memory object that keeps track of chat history for retrieval.

3fill in blank

hard

Fix the error in the code to create a retrieval-augmented chain with memory.

LangChain

from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory

retriever = VectorStoreRetriever()
qa_chain = ConversationalRetrievalChain.from_llm(llm=OpenAI(), retriever=retriever, memory=[1])

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

ARetrievalQA()

BConversationBufferMemory

Cmemory

DConversationBufferMemory()

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the class name without parentheses.

Passing an undefined variable.

The memory parameter expects an instance, so you must call ConversationBufferMemory() to create it.

4fill in blank

hard

Fill both blanks to create a memory-augmented retrieval chain that uses chat history and a retriever.

LangChain

from langchain.memory import [1]
from langchain.chains import ConversationalRetrievalChain

memory = [2]()
retriever = VectorStoreRetriever()
qa = ConversationalRetrievalChain.from_llm(llm=OpenAI(), retriever=retriever, memory=memory)

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

AConversationBufferMemory

BRetrievalQA

DOpenAI

Attempts:

3 left

💡 Hint

Common Mistakes

Importing the wrong class.

Not creating an instance before passing to the chain.

Import ConversationBufferMemory and create an instance to use as memory in the retrieval chain.

5fill in blank

hard

Fill all three blanks to build a retrieval-augmented chain with memory and run a query.

LangChain

from langchain.memory import [1]
from langchain.chains import ConversationalRetrievalChain

memory = [2]()
retriever = VectorStoreRetriever()
qa = ConversationalRetrievalChain.from_llm(llm=[3](), retriever=retriever, memory=memory)
result = qa.run("What is LangChain?")

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

AConversationBufferMemory

COpenAI

DRetrievalQA

Attempts:

3 left

💡 Hint

Common Mistakes

Not instantiating memory or the language model.

Using wrong classes for memory or LLM.

Import and instantiate ConversationBufferMemory for memory, and use OpenAI() as the language model in the retrieval chain.