分類目錄：《自然語言處理從入門到應用》總目錄

---

LLMChain

LLMChain是查詢LLM對象最流行的方式之一。它使用提供的輸入鍵值（如果有的話，還包括內(nèi)存鍵值）格式化提示模板，將格式化的字符串傳遞給LLM，并返回LLM的輸出。下面我們展示了LLMChain類的附加功能：

from langchain import PromptTemplate, OpenAI, LLMChainprompt_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")

輸出：

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

LLM鏈條的額外運行方式

除了所有Chain對象共享的__call__和run方法之外，LLMChain還提供了幾種調(diào)用鏈條邏輯的方式：

• apply：允許我們對一組輸入運行鏈：

input_list = [{"product": "socks"},{"product": "computer"},{"product": "shoes"}
]llm_chain.apply(input_list)
[{'text': '\n\nSocktastic!'},{'text': '\n\nTechCore Solutions.'},{'text': '\n\nFootwear Factory.'}]

• generate：與apply類似，但返回一個LLMResult而不是字符串。LLMResult通常包含有用的生成信息，例如令牌使用情況和完成原因。

llm_chain.generate(input_list)

輸出：

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：與run方法類似，只是輸入鍵被指定為關鍵字參數(shù)，而不是Python字典。

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

輸出：

'\n\nSocktastic!'

輸入：

# Multiple inputs exampletemplate = """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")

輸出：

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

解析輸出結(jié)果

默認情況下，即使底層的prompt對象具有輸出解析器，LLMChain也不會解析輸出結(jié)果。如果你想在LLM輸出上應用輸出解析器，可以使用predict_and_parse代替predict，以及apply_and_parse代替apply。

僅使用predict方法：

from langchain.output_parsers import CommaSeparatedListOutputParseroutput_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()

輸出：

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

使用predict_and_parser方法：

llm_chain.predict_and_parse()

輸出：

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

從字符串模板初始化

我們還可以直接使用字符串模板構建一個LLMChain。

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

輸出：

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

RouterChain

本節(jié)演示了如何使用RouterChain創(chuàng)建一個根據(jù)給定輸入動態(tài)選擇下一個鏈條的鏈條。RouterChain通常由兩個組件組成：

• 路由鏈本身（負責選擇下一個要調(diào)用的鏈條）
• 目標鏈條，即路由鏈可以路由到的鏈條

本節(jié)中，我們將重點介紹不同類型的路由鏈。我們將展示這些路由鏈在MultiPromptChain中的應用，創(chuàng)建一個問題回答鏈條，根據(jù)給定的問題選擇最相關的提示，然后使用該提示回答問題。

from langchain.chains.router import MultiPromptChain
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
from langchain.chains.llm import LLMChain
from langchain.prompts import PromptTemplate
physics_template = """You are a very smart physics professor. \
You are great at answering questions about physics in a concise and easy to understand manner. \
When you don't know the answer to a question you admit that you don't know.Here is a question:
{input}"""math_template = """You are a very good mathematician. You are great at answering math questions. \
You are so good because you are able to break down hard problems into their component parts, \
answer the component parts, and then put them together to answer the broader question.Here is a question:
{input}"""
prompt_infos = [{"name": "physics", "description": "Good for answering questions about physics", "prompt_template": physics_template},{"name": "math", "description": "Good for answering math questions", "prompt_template": math_template}
]
llm = OpenAI()
destination_chains = {}
for p_info in prompt_infos:name = p_info["name"]prompt_template = p_info["prompt_template"]prompt = PromptTemplate(template=prompt_template, input_variables=["input"])chain = LLMChain(llm=llm, prompt=prompt)destination_chains[name] = chain
default_chain = ConversationChain(llm=llm, output_key="text")

LLMRouterChain

LLMRouterChain鏈條使用一個LLM來確定如何進行路由。

from langchain.chains.router.llm_router import LLMRouterChain, RouterOutputParser
from langchain.chains.router.multi_prompt_prompt import MULTI_PROMPT_ROUTER_TEMPLATE
destinations = [f"{p['name']}: {p['description']}" for p in prompt_infos]
destinations_str = "\n".join(destinations)
router_template = MULTI_PROMPT_ROUTER_TEMPLATE.format(destinations=destinations_str
)
router_prompt = PromptTemplate(template=router_template,input_variables=["input"],output_parser=RouterOutputParser(),
)
router_chain = LLMRouterChain.from_llm(llm, router_prompt)
chain = MultiPromptChain(router_chain=router_chain, destination_chains=destination_chains, default_chain=default_chain, verbose=True)
print(chain.run("What is black body radiation?"))

日志輸出：

> Entering new MultiPromptChain chain...
physics: {'input': 'What is black body radiation?'}
> Finished chain.

輸出：

Black body radiation is the term used to describe the electromagnetic radiation emitted by a “black body”—an object that absorbs all radiation incident upon it. A black body is an idealized physical body that absorbs all incident electromagnetic radiation, regardless of frequency or angle of incidence. It does not reflect, emit or transmit energy. This type of radiation is the result of the thermal motion of the body's atoms and molecules, and it is emitted at all wavelengths. The spectrum of radiation emitted is described by Planck's law and is known as the black body spectrum.

輸入：

print(chain.run("What is the first prime number greater than 40 such that one plus the prime number is divisible by 3"))

輸出：

> Entering new MultiPromptChain chain...
math: {'input': 'What is the first prime number greater than 40 such that one plus the prime number is divisible by 3'}
> Finished chain.

輸出：

The answer is 43. One plus 43 is 44 which is divisible by 3.

輸入：

print(chain.run("What is the name of the type of cloud that rins"))

日志輸出：

> Entering new MultiPromptChain chain...
None: {'input': 'What is the name of the type of cloud that rains?'}
> Finished chain.

輸出：

The type of cloud that rains is called a cumulonimbus cloud. It is a tall and dense cloud that is often accompanied by thunder and lightning.

EmbeddingRouterChain

EmbeddingRouterChain使用嵌入和相似性來在目標鏈條之間進行路由。

from langchain.chains.router.embedding_router import EmbeddingRouterChain
from langchain.embeddings import CohereEmbeddings
from langchain.vectorstores import Chroma
names_and_descriptions = [("physics", ["for questions about physics"]),("math", ["for questions about math"]),
]
router_chain = EmbeddingRouterChain.from_names_and_descriptions(names_and_descriptions, Chroma, CohereEmbeddings(), routing_keys=["input"]
)
chain = MultiPromptChain(router_chain=router_chain, destination_chains=destination_chains, default_chain=default_chain, verbose=True)
print(chain.run("What is black body radiation?"))

日志輸出：

> Entering new MultiPromptChain chain...
physics: {'input': 'What is black body radiation?'}
> Finished chain.

輸出：

Black body radiation is the emission of energy from an idealized physical body (known as a black body) that is in thermal equilibrium with its environment. It is emitted in a characteristic pattern of frequencies known as a black-body spectrum, which depends only on the temperature of the body. The study of black body radiation is an important part of astrophysics and atmospheric physics, as the thermal radiation emitted by stars and planets can often be approximated as black body radiation.

輸入：

print(chain.run("What is the first prime number greater than 40 such that one plus the prime number is divisible by 3"))

日志輸出：

> Entering new MultiPromptChain chain...
math: {'input': 'What is the first prime number greater than 40 such that one plus the prime number is divisible by 3'}
> Finished chain.

輸出：

Answer: The first prime number greater than 40 such that one plus the prime number is divisible by 3 is 43.

參考文獻：
[1] LangChain官方網(wǎng)站：https://www.langchain.com/
[2] LangChain 🦜?🔗 中文網(wǎng)，跟著LangChain一起學LLM/GPT開發(fā)：https://www.langchain.com.cn/
[3] LangChain中文網(wǎng) - LangChain 是一個用于開發(fā)由語言模型驅(qū)動的應用程序的框架：http://www.cnlangchain.com/