Exercise#1 LLM & Fakes

from langchain_community.llms.fake import FakeListLLM
from langchain_community.llms.fake import FakeStreamingListLLM

# Random responses sent by the LLM
fake_responses = [
    "this is a fake response 1",
    "this is a fake response 2",
]

# Create the faker
fake_list_llm = FakeListLLM(responses=fake_responses)

# Quick test 
fake_list_llm.invoke("give whatever")

# use await to invoke the async function
response =  await fake_list_llm.ainvoke("give whatever")

# print response
print(response)

# Create a fake streaming LLM with an artificial delay of 0.5 seconds between chunks
fake_streaming_llm = FakeStreamingListLLM(responses=fake_responses, sleep=0.5)

# Sysnchronous streaming
for chunk in fake_streaming_llm.stream("does not matter"):
    print(chunk,end="")

# Initiate the LLM streaming as async
streaming_object = fake_streaming_llm.astream("does not matter")

# Do other things, while LLM is processing in parallel
print("\nDo something while, while LLM is generating a response i.e., thread is not blocked ...")

# Gather some of the streamed 
async for chunk in streaming_object:
    print(chunk,end="")

# Fake responses
fake_responses = [
    '{"person": "tom", "org": "apple"}',
    '{"person": "nick", "org": "amazon"}',
    '{"person": "anil", "org": "meta"}',
]

fake_list_llm = FakeListLLM(responses=fake_responses)

# Test requests sent in a batch in parallel
request_inputs = [
    "extract named entitities :  ......",
    "extract named entitities :  ......",
    "extract named entitities :  ......",
    "extract named entitities :  ......",
]

# Invoke LLM in parallel for all 3 
fake_list_llm.batch(request_inputs)