LangChain中文网

FLARE

这个笔记本是 Forward-Looking Active REtrieval augmented generation (FLARE) 的实现。

请参阅原始的代码仓库 这里open in new window。

基本思想是：

  • 开始回答一个问题
  • 如果生成的标记让模型不确定，查找相关文档
  • 使用这些文档继续生成
  • 重复以上步骤，直到完成

在如何查找相关文档方面有很多有趣的细节。 基本上，模型不确定的标记会被突出显示，然后调用 LLM 生成一个问题，该问题将导致该答案。例如，如果生成的文本是 Joe Biden went to Harvard，而模型不确定的标记是 Harvard，那么一个好的生成的问题可能是 Joe Biden 在哪里上大学。然后，这个生成的问题将在检索步骤中用于获取相关文档。

为了设置这个链条，我们需要三样东西：

  • 用于生成答案的 LLM
  • 用于生成用于检索的假设问题的 LLM
  • 用于查找答案的检索器

我们使用的 LLM 用于生成答案需要返回 logprobs，以便我们可以识别不确定的标记。因此，我们强烈建议您使用 OpenAI 的包装器（注意：不要使用 ChatOpenAI 的包装器，因为它不返回 logprobs）。

我们用于生成用于检索的假设问题的 LLM 可以是任何模型。在这个笔记本中，我们将使用 ChatOpenAI，因为它快速且便宜。

检索器可以是任何检索工具。在这个笔记本中，我们将使用 SERPERopen in new window 搜索引擎，因为它价格便宜。

其他重要的参数：

  • max_generation_len：在停止检查是否存在不确定的标记之前，生成的标记的最大数量
  • min_prob：生成的标记的概率低于此值将被视为不确定的标记

导入库

import os
os.environ["SERPER_API_KEY"] = ""

import re

import numpy as np

from langchain.schema import BaseRetriever
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.embeddings import OpenAIEmbeddings
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI
from langchain.schema import Document

检索器

class SerperSearchRetriever(BaseRetriever):
    def __init__(self, search):
        self.search = search
    
    def get_relevant_documents(self, query: str):
        return [Document(page_content=self.search.run(query))]
    
    async def aget_relevant_documents(self, query: str):
        raise NotImplemented
        
        
retriever = SerperSearchRetriever(GoogleSerperAPIWrapper())

FLARE 链条

# 我们设置这个变量以便查看具体的操作过程
import langchain
langchain.verbose = True

from langchain.chains import FlareChain

flare = FlareChain.from_llm(
    ChatOpenAI(temperature=0), 
    retriever=retriever,
    max_generation_len=164,
    min_prob=.3,
)

query = "explain in great detail the difference between the langchain framework and baby agi"

flare.run(query)

> Entering new FlareChain chain...
Current Response: 
Prompt after formatting:
Respond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.

>>> CONTEXT: 
>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> RESPONSE: 


> Entering new QuestionGeneratorChain chain...
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " decentralized platform for natural language processing" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " uses a blockchain" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " distributed ledger to" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " process data, allowing for secure and transparent data sharing." is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " set of tools" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " help developers create" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " create an AI system" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:  
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.

Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.

In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for

The question to which the answer is the term/entity/phrase " NLP applications" is:


' LangChain is a framework for developing applications powered by language models. It provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications. On the other hand, Baby AGI is an AI system that is exploring and demonstrating the potential of large language models, such as GPT, and how it can autonomously perform tasks. Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. '

llm = OpenAI()
llm(query)

'\n\nThe Langchain framework and Baby AGI are both artificial intelligence (AI) frameworks that are used to create intelligent agents. The Langchain framework is a supervised learning system that is based on the concept of “language chains”. It uses a set of rules to map natural language inputs to specific outputs. It is a general-purpose AI framework and can be used to build applications such as natural language processing (NLP), chatbots, and more.\n\nBaby AGI, on the other hand, is an unsupervised learning system that uses neural networks and reinforcement learning to learn from its environment. It is used to create intelligent agents that can adapt to changing environments. It is a more advanced AI system and can be used to build more complex applications such as game playing, robotic vision, and more.\n\nThe main difference between the two is that the Langchain framework uses supervised learning while Baby AGI uses unsupervised learning. The Langchain framework is a general-purpose AI framework that can be used for various applications, while Baby AGI is a more advanced AI system that can be used to create more complex applications.'

flare.run("how are the origin stories of langchain and bitcoin similar or different?")

> Entering new FlareChain chain...
Current Response: 
Prompt after formatting:
Respond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.

>>> CONTEXT: 
>>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> RESPONSE: 


> Entering new QuestionGeneratorChain chain...
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> EXISTING PARTIAL RESPONSE:  

Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. 

FINISHED

The question to which the answer is the term/entity/phrase " very different origin" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> EXISTING PARTIAL RESPONSE:  

Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. 

FINISHED

The question to which the answer is the term/entity/phrase " 2020 by a" is:
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:

>>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> EXISTING PARTIAL RESPONSE:  

Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. 

FINISHED

The question to which the answer is the term/entity/phrase " developers as a platform for creating and managing decentralized language learning applications." is:

> Finished chain.
Generated Questions: ['How would you describe the origin stories of Langchain and Bitcoin in terms of their similarities or differences?', 'When was Langchain created and by whom?', 'What was the purpose of creating Langchain?']


> Entering new _OpenAIResponseChain chain...
Prompt after formatting:
Respond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.

>>> CONTEXT: Bitcoin and Ethereum have many similarities but different long-term visions and limitations. Ethereum changed from proof of work to proof of ... Bitcoin will be around for many years and examining its white paper origins is a great exercise in understanding why. Satoshi Nakamoto's blueprint describes ... Bitcoin is a new currency that was created in 2009 by an unknown person using the alias Satoshi Nakamoto. Transactions are made with no middle men – meaning, no ... Missing: Langchain | Must include:Langchain. By comparison, Bitcoin transaction speeds are tremendously lower. ... learn about its history and its role in the emergence of the Bitcoin ... LangChain is a powerful framework that simplifies the process of ... tasks like document retrieval, clustering, and similarity comparisons. Key terms: Bitcoin System, Blockchain Technology, ... Furthermore, the research paper will discuss and compare the five payment. Blockchain first appeared in Nakamoto's Bitcoin white paper that describes a new decentralized cryptocurrency [1]. Bitcoin takes the blockchain technology ... Missing: stories | Must include:stories. A score of 0 means there were not enough data for this term. Google trends was accessed on 5 November 2018 with searches for bitcoin, euro, gold ... Contracts, transactions, and records of them provide critical structure in our economic system, but they haven't kept up with the world's digital ... Missing: Langchain | Must include:Langchain. Of course, traders try to make a profit on their portfolio in this way.The difference between investing and trading is the regularity with which ...

After all these giant leaps forward in the LLM space, OpenAI released ChatGPT — thrusting LLMs into the spotlight. LangChain appeared around the same time. Its creator, Harrison Chase, made the first commit in late October 2022. Leaving a short couple of months of development before getting caught in the LLM wave.

At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.
>>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> RESPONSE: 

> Finished chain.

> Finished chain.


' The origin stories of LangChain and Bitcoin are quite different. Bitcoin was created in 2009 by an unknown person using the alias Satoshi Nakamoto. LangChain was created in late October 2022 by Harrison Chase. Bitcoin is a decentralized cryptocurrency, while LangChain is a framework built around LLMs. '
Last Updated:
Contributors: 刘强