langchain/docs/examples/model_laboratory.ipynb

Model Laboratory

This example goes over basic functionality of how to use the ModelLaboratory to test out and try different models.

In [1]:

from langchain import LLMChain, OpenAI, Cohere, HuggingFaceHub, PromptTemplate
from langchain.model_laboratory import ModelLaboratory

In [2]:

llms = [
    OpenAI(temperature=0), 
    Cohere(model="command-xlarge-20221108", max_tokens=20, temperature=0), 
    HuggingFaceHub(repo_id="google/flan-t5-xl", model_kwargs={"temperature":1})
]

In [3]:

model_lab = ModelLaboratory.from_llms(llms)

In [4]:

model_lab.compare("What color is a flamingo?")

Input:
What color is a flamingo?

OpenAI
Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}


Flamingos are pink.

Cohere
Params: {'model': 'command-xlarge-20221108', 'max_tokens': 20, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}


Pink

HuggingFaceHub
Params: {'repo_id': 'google/flan-t5-xl', 'temperature': 1}
pink

In [5]:

prompt = PromptTemplate(template="What is the capital of {state}?", input_variables=["state"])
model_lab_with_prompt = ModelLaboratory.from_llms(llms, prompt=prompt)

In [6]:

model_lab_with_prompt.compare("New York")

Input:
New York

OpenAI
Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}


The capital of New York is Albany.

Cohere
Params: {'model': 'command-xlarge-20221108', 'max_tokens': 20, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}


The capital of New York is Albany.

HuggingFaceHub
Params: {'repo_id': 'google/flan-t5-xl', 'temperature': 1}
st john s

In [7]:

from langchain import SelfAskWithSearchChain, SerpAPIWrapper

open_ai_llm = OpenAI(temperature=0)
search = SerpAPIWrapper()
self_ask_with_search_openai = SelfAskWithSearchChain(llm=open_ai_llm, search_chain=search, verbose=True)

cohere_llm = Cohere(temperature=0, model="command-xlarge-20221108")
search = SerpAPIWrapper()
self_ask_with_search_cohere = SelfAskWithSearchChain(llm=cohere_llm, search_chain=search, verbose=True)

In [8]:

chains = [self_ask_with_search_openai, self_ask_with_search_cohere]
names = [str(open_ai_llm), str(cohere_llm)]

In [9]:

model_lab = ModelLaboratory(chains, names=names)

In [10]:

model_lab.compare("What is the hometown of the reigning men's U.S. Open champion?")

Input:
What is the hometown of the reigning men's U.S. Open champion?

OpenAI
Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}


> Entering new chain...
What is the hometown of the reigning men's U.S. Open champion?
Are follow up questions needed here: Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Carlos Alcaraz.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain.
So the final answer is: El Palmar, Spain
> Finished chain.

So the final answer is: El Palmar, Spain

Cohere
Params: {'model': 'command-xlarge-20221108', 'max_tokens': 256, 'temperature': 0.0, 'k': 0, 'p': 1, 'frequency_penalty': 0, 'presence_penalty': 0}


> Entering new chain...
What is the hometown of the reigning men's U.S. Open champion?
Are follow up questions needed here: Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Carlos Alcaraz.
So the final answer is:

Carlos Alcaraz
> Finished chain.

So the final answer is:

Carlos Alcaraz

In [ ]: