langchain/docs/modules/chains/generic/llm_chain.ipynb

LLM Chain

LLMChain is perhaps one of the most popular ways of querying an LLM object. It formats the prompt template using the input key values provided (and also memory key values, if available), passes the formatted string to LLM and returns the LLM output. Below we show additional functionalities of LLMChain class.

In [1]:

from langchain import PromptTemplate, OpenAI, LLMChain

prompt_template = "What is a good name for a company that makes {product}?"

llm = OpenAI(temperature=0)
llm_chain = LLMChain(
    llm=llm,
    prompt=PromptTemplate.from_template(prompt_template)
)
llm_chain("colorful socks")

Out [1]:

{'product': 'colorful socks', 'text': '\n\nSocktastic!'}

Additional ways of running LLM Chain

Aside from __call__ and run methods shared by all Chain object (see Getting Started to learn more), LLMChain offers a few more ways of calling the chain logic:

• apply allows you run the chain against a list of inputs:

In [2]:

input_list = [
    {"product": "socks"},
    {"product": "computer"},
    {"product": "shoes"}
]

llm_chain.apply(input_list)

Out [2]:

[{'text': '\n\nSocktastic!'},
 {'text': '\n\nTechCore Solutions.'},
 {'text': '\n\nFootwear Factory.'}]

• generate is similar to apply, except it return an LLMResult instead of string. LLMResult often contains useful generation such as token usages and finish reason.

In [3]:

llm_chain.generate(input_list)

Out [3]:

LLMResult(generations=[[Generation(text='\n\nSocktastic!', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nTechCore Solutions.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nFootwear Factory.', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'prompt_tokens': 36, 'total_tokens': 55, 'completion_tokens': 19}, 'model_name': 'text-davinci-003'})

• predict is similar to run method except that the input keys are specified as keyword arguments instead of a Python dict.

In [12]:

# Single input example
llm_chain.predict(product="colorful socks")

Out [12]:

'\n\nSocktastic!'

In [14]:

# Multiple inputs example

template = """Tell me a {adjective} joke about {subject}."""
prompt = PromptTemplate(template=template, input_variables=["adjective", "subject"])
llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0))

llm_chain.predict(adjective="sad", subject="ducks")

Out [14]:

'\n\nQ: What did the duck say when his friend died?\nA: Quack, quack, goodbye.'

Parsing the outputs

By default, LLMChain does not parse the output even if the underlying prompt object has an output parser. If you would like to apply that output parser on the LLM output, use predict_and_parse instead of predict and apply_and_parse instead of apply.

With predict:

In [24]:

from langchain.output_parsers import CommaSeparatedListOutputParser

output_parser = CommaSeparatedListOutputParser()
template = """List all the colors in a rainbow"""
prompt = PromptTemplate(template=template, input_variables=[], output_parser=output_parser)
llm_chain = LLMChain(prompt=prompt, llm=llm)

llm_chain.predict()

Out [24]:

'\n\nRed, orange, yellow, green, blue, indigo, violet'

With predict_and_parser:

In [25]:

llm_chain.predict_and_parse()

Out [25]:

['Red', 'orange', 'yellow', 'green', 'blue', 'indigo', 'violet']

Initialize from string

You can also construct an LLMChain from a string template directly.

In [16]:

template = """Tell me a {adjective} joke about {subject}."""
llm_chain = LLMChain.from_string(llm=llm, template=template)

In [18]:

llm_chain.predict(adjective="sad", subject="ducks")

Out [18]:

'\n\nQ: What did the duck say when his friend died?\nA: Quack, quack, goodbye.'