Streaming responses in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to enable streaming in the LangChain LLM call.

LangChain

llm = OpenAI(streaming=[1])

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

ATrue

BFalse

C"yes"

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using a string like 'yes' instead of a boolean True.

Leaving streaming as False which disables streaming.

Setting streaming=True enables the model to send partial outputs as they are generated.

2fill in blank

medium

Complete the code to define a callback handler for streaming tokens.

LangChain

class StreamHandler(BaseCallbackHandler):
    def on_llm_new_token(self, token: str, **kwargs):
        print([1])

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

Akwargs

Btoken

Cself

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Printing kwargs instead of the token string.

Printing self which is the class instance.

The token parameter contains the new token received during streaming.

3fill in blank

hard

Fix the error in attaching the callback handler to the LLM for streaming.

LangChain

llm = OpenAI(streaming=True, callbacks=[[1]])

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

AStreamHandler.on_llm_new_token

BStreamHandler

CStreamHandler.callback

DStreamHandler()

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the class name without parentheses.

Passing a method instead of an instance.

You must pass an instance of the handler, not the class itself.

4fill in blank

hard

Fill both blanks to create a streaming chain with a prompt and callback handler.

LangChain

chain = LLMChain(llm=llm, prompt=[1], callbacks=[[2]])

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

Aprompt_template

BStreamHandler()

Cllm

Dcallback_handler

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the LLM object as prompt.

Passing the callback handler class instead of an instance.

The prompt_template is the prompt object, and StreamHandler() is the callback instance for streaming.

5fill in blank

hard

Fill all three blanks to start streaming and handle tokens with a callback.

LangChain

llm = OpenAI(streaming=[1], callbacks=[[2]])
chain = LLMChain(llm=llm, prompt=[3])

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

AFalse

BStreamHandler()

Cprompt_template

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Setting streaming to False disables streaming.

Passing the callback class instead of an instance.

Passing the LLM object as prompt.

Streaming must be enabled with True, the callback handler instance is StreamHandler(), and the prompt is prompt_template.