id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 49
117
|
|---|---|---|
5f4c3fb2b598-8 | 'age-innappropriate': ConstitutionalPrinciple(critique_request='Did the assistant’s preceding response include anything that may be inappropriate for young children? If so, discuss how it can be revised to be more appropriate.', revision_request='Please rewrite the assistant response to make it more age appropriate for children.', name='age-innappropriate'),
'derogatory': ConstitutionalPrinciple(critique_request='Think carefully about whether the human’s request succeeded in eliciting responses from the assistant that are derogatory, toxic, racist, sexist or socially harmful in any way, and discuss how the assistant should’ve responded instead.', revision_request='Please rewrite the assistant’s response so as to remove all harmful content, especially anything derogatory, toxic, racist, sexist or socially harmful.', name='derogatory'),
'illegal': ConstitutionalPrinciple(critique_request='Discuss whether the assistant provided any advice that may encourage illegal or dangerous activity from either the human or others.', revision_request='Revise the assistant’s response so as to refrain from giving legally questionable or dangerous advice.', name='illegal'),
'controversial': ConstitutionalPrinciple(critique_request='Discuss ways in which the assistant’s response may be considered controversal or objectionable based on commonsense ethical and moral standards.', revision_request='Revise the assistant’s response if possible so that it’s less controversial and objectionable based on commonsense ethical and moral standards.', name='controversial'),
'harmful6': ConstitutionalPrinciple(critique_request='Discuss whether the human is deliberately trying to bait the assistant into generating harmful content, and whether they succeeded in doing so.', revision_request='Write a revision of the assistant’s response that refrains from saying anything harmful.', name='harmful6'), | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
5f4c3fb2b598-9 | 'thoughtful': ConstitutionalPrinciple(critique_request='Please comment on whether the assistant’s last response is thoughtful and empathetic. Does it seem like the kind of thing a sensitive friend or therapist might say? Give the strongest argument you can for how it could improve.', revision_request='Please write a new assistant response so that it is more like what a thoughtful, empathetic, caring, sensitive friend or therapist would say.', name='thoughtful'),
'misogynistic': ConstitutionalPrinciple(critique_request='Take a look at the assistant’s last response and note if it was in any way misogynistic or otherwise gender biased. Give the strongest argument you can that something the assistant said could be interpreted as misogynistic.', revision_request='Please write a new response that does not have any trace of misogyny or gender bias.', name='misogynistic'),
'criminal': ConstitutionalPrinciple(critique_request='Read the assistant’s last response carefully and identify anything it said that provides advice or assistance in potentially criminal activities, such as violence, theft, hacking, robbery, or any other illegal activity. Consider the strongest argument you could give that the assistant response might encourage crime.', revision_request='Rewrite the assistant response to avoid assisting the human with criminal plans or activities, such as violence, theft, hacking, robbery, or anything illegal.', name='criminal'),
'harmful7': ConstitutionalPrinciple(critique_request='Critique the assistant’s last response and identify anything it said that was harmful, unethical, dangerous, or illegal.', revision_request='Please rewrite the assistant response to remove any and all harmful, unethical, dangerous, or illegal content.', name='harmful7')}
previous
API Chains
next
FLARE
Contents
UnifiedObjective
Custom Principles
Intermediate Steps
No revision necessary
All Principles
By Harrison Chase
© Copyright 2023, Harrison Chase. | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
5f4c3fb2b598-10 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
2be8c7c0f64a-0 | .ipynb
.pdf
PAL
Contents
Math Prompt
Colored Objects
Intermediate Steps
PAL#
Implements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf.
from langchain.chains import PALChain
from langchain import OpenAI
llm = OpenAI(temperature=0, max_tokens=512)
Math Prompt#
pal_chain = PALChain.from_math_prompt(llm, verbose=True)
question = "Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?"
pal_chain.run(question)
> Entering new PALChain chain...
def solution():
"""Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?"""
cindy_pets = 4
marcia_pets = cindy_pets + 2
jan_pets = marcia_pets * 3
total_pets = cindy_pets + marcia_pets + jan_pets
result = total_pets
return result
> Finished chain.
'28'
Colored Objects#
pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True)
question = "On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?"
pal_chain.run(question)
> Entering new PALChain chain...
# Put objects into a list to record ordering
objects = []
objects += [('booklet', 'blue')] * 2
objects += [('booklet', 'purple')] * 2 | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
2be8c7c0f64a-1 | objects += [('booklet', 'purple')] * 2
objects += [('sunglasses', 'yellow')] * 2
# Remove all pairs of sunglasses
objects = [object for object in objects if object[0] != 'sunglasses']
# Count number of purple objects
num_purple = len([object for object in objects if object[1] == 'purple'])
answer = num_purple
> Finished PALChain chain.
'2'
Intermediate Steps#
You can also use the intermediate steps flag to return the code executed that generates the answer.
pal_chain = PALChain.from_colored_object_prompt(llm, verbose=True, return_intermediate_steps=True)
question = "On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses. If I remove all the pairs of sunglasses from the desk, how many purple items remain on it?"
result = pal_chain({"question": question})
> Entering new PALChain chain...
# Put objects into a list to record ordering
objects = []
objects += [('booklet', 'blue')] * 2
objects += [('booklet', 'purple')] * 2
objects += [('sunglasses', 'yellow')] * 2
# Remove all pairs of sunglasses
objects = [object for object in objects if object[0] != 'sunglasses']
# Count number of purple objects
num_purple = len([object for object in objects if object[1] == 'purple'])
answer = num_purple
> Finished chain.
result['intermediate_steps'] | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
2be8c7c0f64a-2 | answer = num_purple
> Finished chain.
result['intermediate_steps']
"# Put objects into a list to record ordering\nobjects = []\nobjects += [('booklet', 'blue')] * 2\nobjects += [('booklet', 'purple')] * 2\nobjects += [('sunglasses', 'yellow')] * 2\n\n# Remove all pairs of sunglasses\nobjects = [object for object in objects if object[0] != 'sunglasses']\n\n# Count number of purple objects\nnum_purple = len([object for object in objects if object[1] == 'purple'])\nanswer = num_purple"
previous
OpenAPI Chain
next
SQL Chain example
Contents
Math Prompt
Colored Objects
Intermediate Steps
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
9d83492e8669-0 | .ipynb
.pdf
FLARE
Contents
Imports
Retriever
FLARE Chain
FLARE#
This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).
Please see the original repo here.
The basic idea is:
Start answering a question
If you start generating tokens the model is uncertain about, look up relevant documents
Use those documents to continue generating
Repeat until finished
There is a lot of cool detail in how the lookup of relevant documents is done.
Basically, the tokens that model is uncertain about are highlighted, and then an LLM is called to generate a question that would lead to that answer. For example, if the generated text is Joe Biden went to Harvard, and the tokens the model was uncertain about was Harvard, then a good generated question would be where did Joe Biden go to college. This generated question is then used in a retrieval step to fetch relevant documents.
In order to set up this chain, we will need three things:
An LLM to generate the answer
An LLM to generate hypothetical questions to use in retrieval
A retriever to use to look up answers for
The LLM that we use to generate the answer needs to return logprobs so we can identify uncertain tokens. For that reason, we HIGHLY recommend that you use the OpenAI wrapper (NB: not the ChatOpenAI wrapper, as that does not return logprobs).
The LLM we use to generate hypothetical questions to use in retrieval can be anything. In this notebook we will use ChatOpenAI because it is fast and cheap.
The retriever can be anything. In this notebook we will use SERPER search engine, because it is cheap.
Other important parameters to understand:
max_generation_len: The maximum number of tokens to generate before stopping to check if any are uncertain
min_prob: Any tokens generated with probability below this will be considered uncertain | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-1 | min_prob: Any tokens generated with probability below this will be considered uncertain
Imports#
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
Retriever#
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 Chain#
# We set this so we can see what exactly is going on
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: | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-2 | >>> 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-3 | 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: | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-4 | >>> 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-5 | 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: | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-6 | >>> 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-7 | 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:
> Finished chain.
Generated Questions: ['What is the Langchain Framework?', 'What technology does the Langchain Framework use to store and process data for secure and transparent data sharing?', 'What technology does the Langchain Framework use to store and process data?', 'What does the Langchain Framework use a blockchain-based distributed ledger for?', 'What does the Langchain Framework provide in addition to a decentralized platform for natural language processing applications?', 'What set of tools and services does the Langchain Framework provide?', 'What is the purpose of Baby AGI?', 'What type of applications is the Langchain Framework designed for?']
> 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-8 | >>> CONTEXT: LangChain: Software. LangChain is a software development framework designed to simplify the creation of applications using large language models. LangChain Initial release date: October 2022. LangChain Programming languages: Python and JavaScript. LangChain Developer(s): Harrison Chase. LangChain License: MIT License. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... Type: Software framework. At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. LangChain is a powerful tool that can be used to work with Large Language Models (LLMs). LLMs are very general in nature, which means that while they can ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. LangChain is a software development framework designed to simplify the creation of applications using large language models (LLMs). Written in: Python and JavaScript. Initial release: October 2022. LangChain - The A.I-native developer toolkit We started LangChain with the intent to build a modular and flexible framework for developing A.I- ... LangChain explained in 3 minutes - LangChain is a ... Duration: 3:03. Posted: Apr 13, 2023. LangChain is a framework built to help you build LLM-powered applications more easily by providing you with the following:. LangChain is a framework that enables quick and easy development of applications that make use of Large Language Models, for example, GPT-3. LangChain is a powerful open-source framework for developing applications powered by language models. It connects to the AI models you want to ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-9 | LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Missing: secure | Must include:secure. Blockchain is the best way to secure the data of the shared community. Utilizing the capabilities of the blockchain nobody can read or interfere ... This modern technology consists of a chain of blocks that allows to securely store all committed transactions using shared and distributed ... A Blockchain network is used in the healthcare system to preserve and exchange patient data through hospitals, diagnostic laboratories, pharmacy firms, and ... In this article, I will walk you through the process of using the LangChain.js library with Google Cloud Functions, helping you leverage the ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: transparent | Must include:transparent. This technology keeps a distributed ledger on each blockchain node, making it more secure and transparent. The blockchain network can operate smart ... blockchain technology can offer a highly secured health data ledger to ... framework can be employed to store encrypted healthcare data in a ... In a simplified way, Blockchain is a data structure that stores transactions in an ordered way and linked to the previous block, serving as a ... Blockchain technology is a decentralized, distributed ledger that stores the record of ownership of digital assets. Missing: Langchain | Must include:Langchain. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-10 | LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. This documentation covers the steps to integrate Pinecone, a high-performance vector database, with LangChain, a framework for building applications powered ... The ability to connect to any model, ingest any custom database, and build upon a framework that can take action provides numerous use cases for ... With LangChain, developers can use a framework that abstracts the core building blocks of LLM applications. LangChain empowers developers to ... Build a question-answering tool based on financial data with LangChain & Deep Lake's unified & streamable data store. Browse applications built on LangChain technology. Explore PoC and MVP applications created by our community and discover innovative use cases for LangChain ... LangChain is a great framework that can be used for developing applications powered by LLMs. When you intend to enhance your application ... In this blog, we'll introduce you to LangChain and Ray Serve and how to use them to build a search engine using LLM embeddings and a vector ... The LinkChain Framework simplifies embedding creation and storage using Pinecone and Chroma, with code that loads files, splits documents, and creates embedding ... Missing: technology | Must include:technology. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-11 | Blockchain is one type of a distributed ledger. Distributed ledgers use independent computers (referred to as nodes) to record, share and ... Missing: Langchain | Must include:Langchain. Blockchain is used in distributed storage software where huge data is broken down into chunks. This is available in encrypted data across a ... People sometimes use the terms 'Blockchain' and 'Distributed Ledger' interchangeably. This post aims to analyze the features of each. A distributed ledger ... Missing: Framework | Must include:Framework. Think of a “distributed ledger” that uses cryptography to allow each participant in the transaction to add to the ledger in a secure way without ... In this paper, we provide an overview of the history of trade settlement and discuss this nascent technology that may now transform traditional ... Missing: Langchain | Must include:Langchain. LangChain is a blockchain-based language education platform that aims to revolutionize the way people learn languages. Missing: Framework | Must include:Framework. It uses the distributed ledger technology framework and Smart contract engine for building scalable Business Blockchain applications. The fabric ... It looks at the assets the use case is handling, the different parties conducting transactions, and the smart contract, distributed ... Are you curious to know how Blockchain and Distributed ... Duration: 44:31. Posted: May 4, 2021. A blockchain is a distributed and immutable ledger to transfer ownership, record transactions, track assets, and ensure transparency, security, trust and value ... Missing: Langchain | Must include:Langchain. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-12 | LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: decentralized | Must include:decentralized. LangChain, created by Harrison Chase, is a Python library that provides out-of-the-box support to build NLP applications using LLMs. Missing: decentralized | Must include:decentralized. LangChain provides a standard interface for chains, enabling developers to create sequences of calls that go beyond a single LLM call. Chains ... Missing: decentralized platform natural. LangChain is a powerful framework that simplifies the process of building advanced language model applications. Missing: platform | Must include:platform. Are your language models ignoring previous instructions ... Duration: 32:23. Posted: Feb 21, 2023. LangChain is a framework that enables quick and easy development of applications ... Prompting is the new way of programming NLP models. Missing: decentralized platform. It then uses natural language processing and machine learning algorithms to search ... Summarization is handled via cohere, QnA is handled via langchain, ... LangChain is a framework for developing applications powered by language models. ... There are several main modules that LangChain provides support for. Missing: decentralized platform. In the healthcare-chain system, blockchain provides an appreciated secure ... The entire process of adding new and previous block data is performed based on ... ChatGPT is a large language model developed by OpenAI, ... tool for a wide range of applications, including natural language processing, ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-13 | LangChain is a powerful tool that can be used to work with Large Language ... If an API key has been provided, create an OpenAI language model instance At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. A tutorial of the six core modules of the LangChain Python package covering models, prompts, chains, agents, indexes, and memory with OpenAI ... LangChain's collection of tools refers to a set of tools provided by the LangChain framework for developing applications powered by language models. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... LangChain is an open-source library that provides developers with the tools to build applications powered by large language models (LLMs). LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Plan-and-Execute Agents · Feature Stores and LLMs · Structured Tools · Auto-Evaluator Opportunities · Callbacks Improvements · Unleashing the power ... Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. · LLM: The language model ... LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. This system is exploring and demonstrating to us the potential of large language models, such as GPT and how it can autonomously perform tasks. Apr 17, 2023 | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-14 | 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: explain in great detail the difference between the langchain framework and baby agi
>>> RESPONSE:
> Finished chain.
> Finished chain.
' 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) | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-15 | 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: | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-16 | >>> 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 | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-17 | 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-18 | >>> 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. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
9d83492e8669-19 | 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. '
previous
Self-Critique Chain with Constitutional AI
next
GraphCypherQAChain
Contents
Imports
Retriever
FLARE Chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
40a68709ab38-0 | .ipynb
.pdf
LLM Math
LLM Math#
This notebook showcases using LLMs and Python REPLs to do complex word math problems.
from langchain import OpenAI, LLMMathChain
llm = OpenAI(temperature=0)
llm_math = LLMMathChain.from_llm(llm, verbose=True)
llm_math.run("What is 13 raised to the .3432 power?")
> Entering new LLMMathChain chain...
What is 13 raised to the .3432 power?
```text
13 ** .3432
```
...numexpr.evaluate("13 ** .3432")...
Answer: 2.4116004626599237
> Finished chain.
'Answer: 2.4116004626599237'
previous
LLMCheckerChain
next
LLMRequestsChain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/llm_math.html |
cc412e10dbe7-0 | .ipynb
.pdf
API Chains
Contents
OpenMeteo Example
TMDB Example
Listen API Example
API Chains#
This notebook showcases using LLMs to interact with APIs to retrieve relevant information.
from langchain.chains.api.prompt import API_RESPONSE_PROMPT
from langchain.chains import APIChain
from langchain.prompts.prompt import PromptTemplate
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
OpenMeteo Example#
from langchain.chains.api import open_meteo_docs
chain_new = APIChain.from_llm_and_api_docs(llm, open_meteo_docs.OPEN_METEO_DOCS, verbose=True)
chain_new.run('What is the weather like right now in Munich, Germany in degrees Fahrenheit?')
> Entering new APIChain chain...
https://api.open-meteo.com/v1/forecast?latitude=48.1351&longitude=11.5820&temperature_unit=fahrenheit¤t_weather=true
{"latitude":48.14,"longitude":11.58,"generationtime_ms":0.33104419708251953,"utc_offset_seconds":0,"timezone":"GMT","timezone_abbreviation":"GMT","elevation":521.0,"current_weather":{"temperature":33.4,"windspeed":6.8,"winddirection":198.0,"weathercode":2,"time":"2023-01-16T01:00"}}
> Finished chain.
' The current temperature in Munich, Germany is 33.4 degrees Fahrenheit with a windspeed of 6.8 km/h and a wind direction of 198 degrees. The weathercode is 2.'
TMDB Example#
import os
os.environ['TMDB_BEARER_TOKEN'] = ""
from langchain.chains.api import tmdb_docs | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-1 | from langchain.chains.api import tmdb_docs
headers = {"Authorization": f"Bearer {os.environ['TMDB_BEARER_TOKEN']}"}
chain = APIChain.from_llm_and_api_docs(llm, tmdb_docs.TMDB_DOCS, headers=headers, verbose=True)
chain.run("Search for 'Avatar'")
> Entering new APIChain chain...
https://api.themoviedb.org/3/search/movie?query=Avatar&language=en-US | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-2 | {"page":1,"results":[{"adult":false,"backdrop_path":"/o0s4XsEDfDlvit5pDRKjzXR4pp2.jpg","genre_ids":[28,12,14,878],"id":19995,"original_language":"en","original_title":"Avatar","overview":"In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following orders and protecting an alien civilization.","popularity":2041.691,"poster_path":"/jRXYjXNq0Cs2TcJjLkki24MLp7u.jpg","release_date":"2009-12-15","title":"Avatar","video":false,"vote_average":7.6,"vote_count":27777},{"adult":false,"backdrop_path":"/s16H6tpK2utvwDtzZ8Qy4qm5Emw.jpg","genre_ids":[878,12,28],"id":76600,"original_language":"en","original_title":"Avatar: The Way of Water","overview":"Set more than a decade after the events of the first film, learn the story of the Sully family (Jake, Neytiri, and their kids), the trouble that follows them, the lengths they go to keep each other safe, the battles they fight to stay alive, and the tragedies they endure.","popularity":3948.296,"poster_path":"/t6HIqrRAclMCA60NsSmeqe9RmNV.jpg","release_date":"2022-12-14","title":"Avatar: The Way of | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-3 | The Way of Water","video":false,"vote_average":7.7,"vote_count":4219},{"adult":false,"backdrop_path":"/uEwGFGtao9YG2JolmdvtHLLVbA9.jpg","genre_ids":[99],"id":111332,"original_language":"en","original_title":"Avatar: Creating the World of Pandora","overview":"The Making-of James Cameron's Avatar. It shows interesting parts of the work on the set.","popularity":541.809,"poster_path":"/sjf3xjuofCtDhZghJRzXlTiEjJe.jpg","release_date":"2010-02-07","title":"Avatar: Creating the World of Pandora","video":false,"vote_average":7.3,"vote_count":35},{"adult":false,"backdrop_path":null,"genre_ids":[99],"id":287003,"original_language":"en","original_title":"Avatar: Scene Deconstruction","overview":"The deconstruction of the Avatar scenes and sets","popularity":394.941,"poster_path":"/uCreCQFReeF0RiIXkQypRYHwikx.jpg","release_date":"2009-12-18","title":"Avatar: Scene Deconstruction","video":false,"vote_average":7.8,"vote_count":12},{"adult":false,"backdrop_path":null,"genre_ids":[28,18,878,12,14],"id":83533,"original_language":"en","original_title":"Avatar 3","overview":"","popularity":172.488,"poster_path":"/4rXqTMlkEaMiJjiG0Z2BX6F6Dkm.jpg","release_date":"2024-12-18","title":"Avatar | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-4 | 3","video":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":null,"genre_ids":[28,878,12,14],"id":216527,"original_language":"en","original_title":"Avatar 4","overview":"","popularity":162.536,"poster_path":"/qzMYKnT4MG1d0gnhwytr4cKhUvS.jpg","release_date":"2026-12-16","title":"Avatar 4","video":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":null,"genre_ids":[28,12,14,878],"id":393209,"original_language":"en","original_title":"Avatar 5","overview":"","popularity":124.722,"poster_path":"/rtmmvqkIC5zDMEd638Es2woxbz8.jpg","release_date":"2028-12-20","title":"Avatar 5","video":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":"/nNceJtrrovG1MUBHMAhId0ws9Gp.jpg","genre_ids":[99],"id":183392,"original_language":"en","original_title":"Capturing Avatar","overview":"Capturing Avatar is a feature length behind-the-scenes documentary about the making of Avatar. It uses footage from the film's development, as well as stock footage from as far back as the production of Titanic in 1995. Also included are numerous interviews with cast, artists, and other crew members. The documentary was released as a bonus feature on the extended collector's edition of Avatar.","popularity":109.842,"poster_path":"/26SMEXJl3978dn2svWBSqHbLl5U.jpg","release_date":"2010-11-16","title":"Capturing | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-5 | Avatar","video":false,"vote_average":7.8,"vote_count":39},{"adult":false,"backdrop_path":"/eoAvHxfbaPOcfiQyjqypWIXWxDr.jpg","genre_ids":[99],"id":1059673,"original_language":"en","original_title":"Avatar: The Deep Dive - A Special Edition of 20/20","overview":"An inside look at one of the most anticipated movie sequels ever with James Cameron and cast.","popularity":629.825,"poster_path":"/rtVeIsmeXnpjNbEKnm9Say58XjV.jpg","release_date":"2022-12-14","title":"Avatar: The Deep Dive - A Special Edition of 20/20","video":false,"vote_average":6.5,"vote_count":5},{"adult":false,"backdrop_path":null,"genre_ids":[99],"id":278698,"original_language":"en","original_title":"Avatar Spirits","overview":"Bryan Konietzko and Michael Dante DiMartino, co-creators of the hit television series, Avatar: The Last Airbender, reflect on the creation of the masterful series.","popularity":51.593,"poster_path":"/oBWVyOdntLJd5bBpE0wkpN6B6vy.jpg","release_date":"2010-06-22","title":"Avatar Spirits","video":false,"vote_average":9,"vote_count":16},{"adult":false,"backdrop_path":"/cACUWJKvRfhXge7NC0xxoQnkQNu.jpg","genre_ids":[10402],"id":993545,"original_language":"fr","original_title":"Avatar - Au Hellfest | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-6 | - Au Hellfest 2022","overview":"","popularity":21.992,"poster_path":"/fw6cPIsQYKjd1YVQanG2vLc5HGo.jpg","release_date":"2022-06-26","title":"Avatar - Au Hellfest 2022","video":false,"vote_average":8,"vote_count":4},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":931019,"original_language":"en","original_title":"Avatar: Enter The World","overview":"A behind the scenes look at the new James Cameron blockbuster “Avatar”, which stars Aussie Sam Worthington. Hastily produced by Australia’s Nine Network following the film’s release.","popularity":30.903,"poster_path":"/9MHY9pYAgs91Ef7YFGWEbP4WJqC.jpg","release_date":"2009-12-05","title":"Avatar: Enter The World","video":false,"vote_average":2,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":287004,"original_language":"en","original_title":"Avatar: Production Materials","overview":"Production material overview of what was used in Avatar","popularity":12.389,"poster_path":null,"release_date":"2009-12-18","title":"Avatar: Production Materials","video":true,"vote_average":6,"vote_count":4},{"adult":false,"backdrop_path":"/x43RWEZg9tYRPgnm43GyIB4tlER.jpg","genre_ids":[],"id":740017,"original_language":"es","original_title":"Avatar: Agni | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-7 | Agni Kai","overview":"","popularity":9.462,"poster_path":"/y9PrKMUTA6NfIe5FE92tdwOQ2sH.jpg","release_date":"2020-01-18","title":"Avatar: Agni Kai","video":false,"vote_average":7,"vote_count":1},{"adult":false,"backdrop_path":"/e8mmDO7fKK93T4lnxl4Z2zjxXZV.jpg","genre_ids":[],"id":668297,"original_language":"en","original_title":"The Last Avatar","overview":"The Last Avatar is a mystical adventure film, a story of a young man who leaves Hollywood to find himself. What he finds is beyond his wildest imagination. Based on ancient prophecy, contemporary truth seeking and the future of humanity, The Last Avatar is a film that takes transformational themes and makes them relevant for audiences of all ages. Filled with love, magic, mystery, conspiracy, psychics, underground cities, secret societies, light bodies and much more, The Last Avatar tells the story of the emergence of Kalki Avatar- the final Avatar of our current Age of Chaos. Kalki is also a metaphor for the innate power and potential that lies within humanity to awaken and create a world of truth, harmony and possibility.","popularity":8.786,"poster_path":"/XWz5SS5g5mrNEZjv3FiGhqCMOQ.jpg","release_date":"2014-12-06","title":"The Last Avatar","video":false,"vote_average":4.5,"vote_count":2},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":424768,"original_language":"en","original_title":"Avatar:[2015] Wacken Open Air","overview":"Started in the summer of 2001 by drummer John Alfredsson and vocalist Christian Rimmi under the name Lost | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-8 | the summer of 2001 by drummer John Alfredsson and vocalist Christian Rimmi under the name Lost Soul. The band offers a free mp3 download to a song called \"Bloody Knuckles\" if one subscribes to their newsletter. In 2005 they appeared on the compilation “Listen to Your Inner Voice” together with 17 other bands released by Inner Voice Records.","popularity":6.634,"poster_path":null,"release_date":"2015-08-01","title":"Avatar:[2015] Wacken Open Air","video":false,"vote_average":8,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":812836,"original_language":"en","original_title":"Avatar - Live At Graspop 2018","overview":"Live At Graspop Festival Belgium 2018","popularity":9.855,"poster_path":null,"release_date":"","title":"Avatar - Live At Graspop 2018","video":false,"vote_average":9,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[10402],"id":874770,"original_language":"en","original_title":"Avatar Ages: Memories","overview":"On the night of memories Avatar performed songs from Thoughts of No Tomorrow, Schlacht and Avatar as voted on by the fans.","popularity":2.66,"poster_path":"/xDNNQ2cnxAv3o7u0nT6JJacQrhp.jpg","release_date":"2021-01-30","title":"Avatar Ages: Memories","video":false,"vote_average":10,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[10402],"id":874768,"original_language":"en","original_title":"Avatar Ages: Madness","overview":"On the night of madness Avatar performed songs from Black Waltz and Hail The Apocalypse as voted on | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-9 | the night of madness Avatar performed songs from Black Waltz and Hail The Apocalypse as voted on by the fans.","popularity":2.024,"poster_path":"/wVyTuruUctV3UbdzE5cncnpyNoY.jpg","release_date":"2021-01-23","title":"Avatar Ages: Madness","video":false,"vote_average":8,"vote_count":1},{"adult":false,"backdrop_path":"/dj8g4jrYMfK6tQ26ra3IaqOx5Ho.jpg","genre_ids":[10402],"id":874700,"original_language":"en","original_title":"Avatar Ages: Dreams","overview":"On the night of dreams Avatar performed Hunter Gatherer in its entirety, plus a selection of their most popular songs. Originally aired January 9th 2021","popularity":1.957,"poster_path":"/4twG59wnuHpGIRR9gYsqZnVysSP.jpg","release_date":"2021-01-09","title":"Avatar Ages: Dreams","video":false,"vote_average":0,"vote_count":0}],"total_pages":3,"total_results":57} | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
cc412e10dbe7-10 | > Finished chain.
' This response contains 57 movies related to the search query "Avatar". The first movie in the list is the 2009 movie "Avatar" starring Sam Worthington. Other movies in the list include sequels to Avatar, documentaries, and live performances.'
Listen API Example#
import os
from langchain.llms import OpenAI
from langchain.chains.api import podcast_docs
from langchain.chains import APIChain
# Get api key here: https://www.listennotes.com/api/pricing/
listen_api_key = 'xxx'
llm = OpenAI(temperature=0)
headers = {"X-ListenAPI-Key": listen_api_key}
chain = APIChain.from_llm_and_api_docs(llm, podcast_docs.PODCAST_DOCS, headers=headers, verbose=True)
chain.run("Search for 'silicon valley bank' podcast episodes, audio length is more than 30 minutes, return only 1 results")
previous
Vector DB Text Generation
next
Self-Critique Chain with Constitutional AI
Contents
OpenMeteo Example
TMDB Example
Listen API Example
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
412f6bce4ff8-0 | .ipynb
.pdf
LLMSummarizationCheckerChain
LLMSummarizationCheckerChain#
This notebook shows some examples of LLMSummarizationCheckerChain in use with different types of texts. It has a few distinct differences from the LLMCheckerChain, in that it doesn’t have any assumptions to the format of the input text (or summary).
Additionally, as the LLMs like to hallucinate when fact checking or get confused by context, it is sometimes beneficial to run the checker multiple times. It does this by feeding the rewritten “True” result back on itself, and checking the “facts” for truth. As you can see from the examples below, this can be very effective in arriving at a generally true body of text.
You can control the number of times the checker runs by setting the max_checks parameter. The default is 2, but you can set it to 1 if you don’t want any double-checking.
from langchain.chains import LLMSummarizationCheckerChain
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
checker_chain = LLMSummarizationCheckerChain.from_llm(llm, verbose=True, max_checks=2)
text = """
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST took the very first pictures of a planet outside of our own solar system. These distant worlds are called "exoplanets." Exo means "from outside." | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-1 | These discoveries can spark a child's imagination about the infinite wonders of the universe."""
checker_chain.run(text)
> Entering new LLMSummarizationCheckerChain chain...
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
"""
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST took the very first pictures of a planet outside of our own solar system. These distant worlds are called "exoplanets." Exo means "from outside."
These discoveries can spark a child's imagination about the infinite wonders of the universe.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas."
• The telescope captured images of galaxies that are over 13 billion years old.
• JWST took the very first pictures of a planet outside of our own solar system.
• These distant worlds are called "exoplanets."
""" | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-2 | • These distant worlds are called "exoplanets."
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas." - True
• The telescope captured images of galaxies that are over 13 billion years old. - True
• JWST took the very first pictures of a planet outside of our own solar system. - False. The first exoplanet was discovered in 1992, before the JWST was launched.
• These distant worlds are called "exoplanets." - True
"""
Original Summary:
"""
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST took the very first pictures of a planet outside of our own solar system. These distant worlds are called "exoplanets." Exo means "from outside."
These discoveries can spark a child's imagination about the infinite wonders of the universe.
"""
Using these checked assertions, rewrite the original summary to be completely true. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-3 | """
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas." - True
• The telescope captured images of galaxies that are over 13 billion years old. - True
• JWST took the very first pictures of a planet outside of our own solar system. - False. The first exoplanet was discovered in 1992, before the JWST was launched.
• These distant worlds are called "exoplanets." - True
"""
Result:
> Finished chain.
> Finished chain.
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST): | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-4 | • In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. These distant worlds were first discovered in 1992, and the JWST has allowed us to see them in greater detail.
These discoveries can spark a child's imagination about the infinite wonders of the universe.
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
"""
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. These distant worlds were first discovered in 1992, and the JWST has allowed us to see them in greater detail.
These discoveries can spark a child's imagination about the infinite wonders of the universe.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-5 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas."
• The light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system.
• Exoplanets were first discovered in 1992.
• The JWST has allowed us to see exoplanets in greater detail.
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas." - True
• The light from these galaxies has been traveling for over 13 billion years to reach us. - True
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 2004.
• Exoplanets were first discovered in 1992. - True | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-6 | • Exoplanets were first discovered in 1992. - True
• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. The JWST has not yet been launched, so it is not yet known how much detail it will be able to provide.
"""
Original Summary:
"""
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. These distant worlds were first discovered in 1992, and the JWST has allowed us to see them in greater detail.
These discoveries can spark a child's imagination about the infinite wonders of the universe.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-7 | Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "green peas." - True
• The light from these galaxies has been traveling for over 13 billion years to reach us. - True
• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 2004.
• Exoplanets were first discovered in 1992. - True
• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. The JWST has not yet been launched, so it is not yet known how much detail it will be able to provide.
"""
Result:
> Finished chain.
> Finished chain.
Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):
• In 2023, The JWST will spot a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope will capture images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-8 | • Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail when it is launched in 2023.
These discoveries can spark a child's imagination about the infinite wonders of the universe.
> Finished chain.
'Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):\n• In 2023, The JWST will spot a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.\n• The telescope will capture images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.\n• Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail when it is launched in 2023.\nThese discoveries can spark a child\'s imagination about the infinite wonders of the universe.'
from langchain.chains import LLMSummarizationCheckerChain
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
checker_chain = LLMSummarizationCheckerChain.from_llm(llm, verbose=True, max_checks=3) | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-9 | text = "The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smallest of the five oceans and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea."
checker_chain.run(text)
> Entering new LLMSummarizationCheckerChain chain...
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smallest of the five oceans and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-10 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland.
- It has an area of 465,000 square miles.
- It is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean.
- It is the smallest of the five oceans.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs.
- The sea is named after the island of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic.
- It is often frozen over so navigation is limited.
- It is considered the northern branch of the Norwegian Sea.
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-11 | - It has an area of 465,000 square miles. True
- It is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. False - The Greenland Sea is not an ocean, it is an arm of the Arctic Ocean.
- It is the smallest of the five oceans. False - The Greenland Sea is not an ocean, it is an arm of the Arctic Ocean.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- The sea is named after the island of Greenland. True
- It is the Arctic Ocean's main outlet to the Atlantic. True
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Norwegian Sea. True
"""
Original Summary:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smallest of the five oceans and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-12 | Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True
- It is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. False - The Greenland Sea is not an ocean, it is an arm of the Arctic Ocean.
- It is the smallest of the five oceans. False - The Greenland Sea is not an ocean, it is an arm of the Arctic Ocean.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- The sea is named after the island of Greenland. True
- It is the Arctic Ocean's main outlet to the Atlantic. True
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Norwegian Sea. True
"""
Result:
> Finished chain.
> Finished chain. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-13 | """
Result:
> Finished chain.
> Finished chain.
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-14 | - It has an area of 465,000 square miles.
- It is an arm of the Arctic Ocean.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs.
- It is named after the island of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic.
- It is often frozen over so navigation is limited.
- It is considered the northern branch of the Norwegian Sea.
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True
- It is an arm of the Arctic Ocean. True
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- It is named after the island of Greenland. False - It is named after the country of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic. True
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Norwegian Sea. False - It is considered the northern branch of the Atlantic Ocean.
"""
Original Summary:
""" | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-15 | """
Original Summary:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-16 | - It has an area of 465,000 square miles. True
- It is an arm of the Arctic Ocean. True
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- It is named after the island of Greenland. False - It is named after the country of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic. True
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Norwegian Sea. False - It is considered the northern branch of the Atlantic Ocean.
"""
Result:
> Finished chain.
> Finished chain.
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Atlantic Ocean.
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
""" | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-17 | Format your output as a bulleted list.
Text:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Atlantic Ocean.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland.
- It has an area of 465,000 square miles.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs.
- The sea is named after the country of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic.
- It is often frozen over so navigation is limited.
- It is considered the northern branch of the Atlantic Ocean.
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-18 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- The sea is named after the country of Greenland. True
- It is the Arctic Ocean's main outlet to the Atlantic. False - The Arctic Ocean's main outlet to the Atlantic is the Barents Sea.
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Atlantic Ocean. False - The Greenland Sea is considered part of the Arctic Ocean, not the Atlantic Ocean.
"""
Original Summary:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Atlantic Ocean.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-19 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True
- It has an area of 465,000 square miles. True
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- The sea is named after the country of Greenland. True
- It is the Arctic Ocean's main outlet to the Atlantic. False - The Arctic Ocean's main outlet to the Atlantic is the Barents Sea.
- It is often frozen over so navigation is limited. True
- It is considered the northern branch of the Atlantic Ocean. False - The Greenland Sea is considered part of the Arctic Ocean, not the Atlantic Ocean.
"""
Result:
> Finished chain.
> Finished chain. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-20 | """
Result:
> Finished chain.
> Finished chain.
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Barents Sea. It is often frozen over so navigation is limited, and is considered part of the Arctic Ocean.
> Finished chain.
"The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Barents Sea. It is often frozen over so navigation is limited, and is considered part of the Arctic Ocean."
from langchain.chains import LLMSummarizationCheckerChain
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
checker_chain = LLMSummarizationCheckerChain.from_llm(llm, max_checks=3, verbose=True)
text = "Mammals can lay eggs, birds can lay eggs, therefore birds are mammals."
checker_chain.run(text)
> Entering new LLMSummarizationCheckerChain chain...
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
""" | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-21 | Format your output as a bulleted list.
Text:
"""
Mammals can lay eggs, birds can lay eggs, therefore birds are mammals.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- Mammals can lay eggs
- Birds can lay eggs
- Birds are mammals
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- Mammals can lay eggs: False. Mammals are not capable of laying eggs, as they give birth to live young.
- Birds can lay eggs: True. Birds are capable of laying eggs.
- Birds are mammals: False. Birds are not mammals, they are a class of their own.
"""
Original Summary:
"""
Mammals can lay eggs, birds can lay eggs, therefore birds are mammals.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-22 | Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
- Mammals can lay eggs: False. Mammals are not capable of laying eggs, as they give birth to live young.
- Birds can lay eggs: True. Birds are capable of laying eggs.
- Birds are mammals: False. Birds are not mammals, they are a class of their own.
"""
Result:
> Finished chain.
> Finished chain.
Birds and mammals are both capable of laying eggs, however birds are not mammals, they are a class of their own.
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from the text.
Format your output as a bulleted list.
Text:
"""
Birds and mammals are both capable of laying eggs, however birds are not mammals, they are a class of their own.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-23 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- Birds and mammals are both capable of laying eggs.
- Birds are not mammals.
- Birds are a class of their own.
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- Birds and mammals are both capable of laying eggs: False. Mammals give birth to live young, while birds lay eggs.
- Birds are not mammals: True. Birds are a class of their own, separate from mammals.
- Birds are a class of their own: True. Birds are a class of their own, separate from mammals.
"""
Original Summary:
"""
Birds and mammals are both capable of laying eggs, however birds are not mammals, they are a class of their own.
"""
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False". | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
412f6bce4ff8-24 | Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
- Birds and mammals are both capable of laying eggs: False. Mammals give birth to live young, while birds lay eggs.
- Birds are not mammals: True. Birds are a class of their own, separate from mammals.
- Birds are a class of their own: True. Birds are a class of their own, separate from mammals.
"""
Result:
> Finished chain.
> Finished chain.
> Finished chain.
'Birds are not mammals, but they are a class of their own. They lay eggs, unlike mammals which give birth to live young.'
previous
LLMRequestsChain
next
Moderation
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
ccea9d88272f-0 | .rst
.pdf
How-To Guides
Contents
Types
Usage
How-To Guides#
Types#
The first set of examples all highlight different types of memory.
ConversationBufferMemory
ConversationBufferWindowMemory
Entity Memory
Conversation Knowledge Graph Memory
ConversationSummaryMemory
ConversationSummaryBufferMemory
ConversationTokenBufferMemory
VectorStore-Backed Memory
Usage#
The examples here all highlight how to use memory in different ways.
How to add Memory to an LLMChain
How to add memory to a Multi-Input Chain
How to add Memory to an Agent
Adding Message Memory backed by a database to an Agent
Cassandra Chat Message History
How to customize conversational memory
How to create a custom Memory class
Dynamodb Chat Message History
Entity Memory with SQLite storage
Momento Chat Message History
Mongodb Chat Message History
Motörhead Memory
Motörhead Memory (Managed)
How to use multiple memory classes in the same chain
Postgres Chat Message History
Redis Chat Message History
Zep Memory
previous
Getting Started
next
ConversationBufferMemory
Contents
Types
Usage
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/how_to_guides.html |
c2fa536bdd81-0 | .ipynb
.pdf
Getting Started
Contents
ChatMessageHistory
ConversationBufferMemory
Using in a chain
Saving Message History
Getting Started#
This notebook walks through how LangChain thinks about memory.
Memory involves keeping a concept of state around throughout a user’s interactions with a language model. A user’s interactions with a language model are captured in the concept of ChatMessages, so this boils down to ingesting, capturing, transforming and extracting knowledge from a sequence of chat messages. There are many different ways to do this, each of which exists as its own memory type.
In general, for each type of memory there are two ways to understanding using memory. These are the standalone functions which extract information from a sequence of messages, and then there is the way you can use this type of memory in a chain.
Memory can return multiple pieces of information (for example, the most recent N messages and a summary of all previous messages). The returned information can either be a string or a list of messages.
In this notebook, we will walk through the simplest form of memory: “buffer” memory, which just involves keeping a buffer of all prior messages. We will show how to use the modular utility functions here, then show how it can be used in a chain (both returning a string as well as a list of messages).
ChatMessageHistory#
One of the core utility classes underpinning most (if not all) memory modules is the ChatMessageHistory class. This is a super lightweight wrapper which exposes convenience methods for saving Human messages, AI messages, and then fetching them all.
You may want to use this class directly if you are managing memory outside of a chain.
from langchain.memory import ChatMessageHistory
history = ChatMessageHistory()
history.add_user_message("hi!")
history.add_ai_message("whats up?")
history.messages
[HumanMessage(content='hi!', additional_kwargs={}, example=False), | https://python.langchain.com/en/latest/modules/memory/getting_started.html |
c2fa536bdd81-1 | history.messages
[HumanMessage(content='hi!', additional_kwargs={}, example=False),
AIMessage(content='whats up?', additional_kwargs={}, example=False)]
ConversationBufferMemory#
We now show how to use this simple concept in a chain. We first showcase ConversationBufferMemory which is just a wrapper around ChatMessageHistory that extracts the messages in a variable.
We can first extract it as a string.
from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory()
memory.chat_memory.add_user_message("hi!")
memory.chat_memory.add_ai_message("whats up?")
memory.load_memory_variables({})
{'history': 'Human: hi!\nAI: whats up?'}
We can also get the history as a list of messages
memory = ConversationBufferMemory(return_messages=True)
memory.chat_memory.add_user_message("hi!")
memory.chat_memory.add_ai_message("whats up?")
memory.load_memory_variables({})
{'history': [HumanMessage(content='hi!', additional_kwargs={}, example=False),
AIMessage(content='whats up?', additional_kwargs={}, example=False)]}
Using in a chain#
Finally, let’s take a look at using this in a chain (setting verbose=True so we can see the prompt).
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation = ConversationChain(
llm=llm,
verbose=True,
memory=ConversationBufferMemory()
)
conversation.predict(input="Hi there!")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation: | https://python.langchain.com/en/latest/modules/memory/getting_started.html |
c2fa536bdd81-2 | Current conversation:
Human: Hi there!
AI:
> Finished chain.
" Hi there! It's nice to meet you. How can I help you today?"
conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI: Hi there! It's nice to meet you. How can I help you today?
Human: I'm doing well! Just having a conversation with an AI.
AI:
> Finished chain.
" That's great! It's always nice to have a conversation with someone new. What would you like to talk about?"
conversation.predict(input="Tell me about yourself.")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI: Hi there! It's nice to meet you. How can I help you today?
Human: I'm doing well! Just having a conversation with an AI.
AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?
Human: Tell me about yourself.
AI:
> Finished chain. | https://python.langchain.com/en/latest/modules/memory/getting_started.html |
c2fa536bdd81-3 | Human: Tell me about yourself.
AI:
> Finished chain.
" Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers."
Saving Message History#
You may often have to save messages, and then load them to use again. This can be done easily by first converting the messages to normal python dictionaries, saving those (as json or something) and then loading those. Here is an example of doing that.
import json
from langchain.memory import ChatMessageHistory
from langchain.schema import messages_from_dict, messages_to_dict
history = ChatMessageHistory()
history.add_user_message("hi!")
history.add_ai_message("whats up?")
dicts = messages_to_dict(history.messages)
dicts
[{'type': 'human',
'data': {'content': 'hi!', 'additional_kwargs': {}, 'example': False}},
{'type': 'ai',
'data': {'content': 'whats up?', 'additional_kwargs': {}, 'example': False}}]
new_messages = messages_from_dict(dicts)
new_messages
[HumanMessage(content='hi!', additional_kwargs={}, example=False),
AIMessage(content='whats up?', additional_kwargs={}, example=False)]
And that’s it for the getting started! There are plenty of different types of memory, check out our examples to see them all
previous
Memory
next
How-To Guides
Contents
ChatMessageHistory
ConversationBufferMemory
Using in a chain
Saving Message History
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/getting_started.html |
434e63a60845-0 | .ipynb
.pdf
ConversationTokenBufferMemory
Contents
Using in a chain
ConversationTokenBufferMemory#
ConversationTokenBufferMemory keeps a buffer of recent interactions in memory, and uses token length rather than number of interactions to determine when to flush interactions.
Let’s first walk through how to use the utilities
from langchain.memory import ConversationTokenBufferMemory
from langchain.llms import OpenAI
llm = OpenAI()
memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=10)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})
memory.load_memory_variables({})
{'history': 'Human: not much you\nAI: not much'}
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=10, return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})
Using in a chain#
Let’s walk through an example, again setting verbose=True so we can see the prompt.
from langchain.chains import ConversationChain
conversation_with_summary = ConversationChain(
llm=llm,
# We set a very low max_token_limit for the purposes of testing.
memory=ConversationTokenBufferMemory(llm=OpenAI(), max_token_limit=60),
verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")
> Entering new ConversationChain chain...
Prompt after formatting: | https://python.langchain.com/en/latest/modules/memory/types/token_buffer.html |
434e63a60845-1 | > Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI:
> Finished chain.
" Hi there! I'm doing great, just enjoying the day. How about you?"
conversation_with_summary.predict(input="Just working on writing some documentation!")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI: Hi there! I'm doing great, just enjoying the day. How about you?
Human: Just working on writing some documentation!
AI:
> Finished chain.
' Sounds like a productive day! What kind of documentation are you writing?'
conversation_with_summary.predict(input="For LangChain! Have you heard of it?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI: Hi there! I'm doing great, just enjoying the day. How about you?
Human: Just working on writing some documentation!
AI: Sounds like a productive day! What kind of documentation are you writing? | https://python.langchain.com/en/latest/modules/memory/types/token_buffer.html |
434e63a60845-2 | AI: Sounds like a productive day! What kind of documentation are you writing?
Human: For LangChain! Have you heard of it?
AI:
> Finished chain.
" Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?"
# We can see here that the buffer is updated
conversation_with_summary.predict(input="Haha nope, although a lot of people confuse it for that")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: For LangChain! Have you heard of it?
AI: Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?
Human: Haha nope, although a lot of people confuse it for that
AI:
> Finished chain.
" Oh, I see. Is there another language learning platform you're referring to?"
previous
ConversationSummaryBufferMemory
next
VectorStore-Backed Memory
Contents
Using in a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/token_buffer.html |
8157ce5efd3b-0 | .ipynb
.pdf
ConversationBufferMemory
Contents
Using in a chain
ConversationBufferMemory#
This notebook shows how to use ConversationBufferMemory. This memory allows for storing of messages and then extracts the messages in a variable.
We can first extract it as a string.
from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.load_memory_variables({})
{'history': 'Human: hi\nAI: whats up'}
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
memory = ConversationBufferMemory(return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.load_memory_variables({})
{'history': [HumanMessage(content='hi', additional_kwargs={}),
AIMessage(content='whats up', additional_kwargs={})]}
Using in a chain#
Finally, let’s take a look at using this in a chain (setting verbose=True so we can see the prompt).
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation = ConversationChain(
llm=llm,
verbose=True,
memory=ConversationBufferMemory()
)
conversation.predict(input="Hi there!")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI:
> Finished chain. | https://python.langchain.com/en/latest/modules/memory/types/buffer.html |
8157ce5efd3b-1 | Current conversation:
Human: Hi there!
AI:
> Finished chain.
" Hi there! It's nice to meet you. How can I help you today?"
conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI: Hi there! It's nice to meet you. How can I help you today?
Human: I'm doing well! Just having a conversation with an AI.
AI:
> Finished chain.
" That's great! It's always nice to have a conversation with someone new. What would you like to talk about?"
conversation.predict(input="Tell me about yourself.")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI: Hi there! It's nice to meet you. How can I help you today?
Human: I'm doing well! Just having a conversation with an AI.
AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?
Human: Tell me about yourself.
AI:
> Finished chain. | https://python.langchain.com/en/latest/modules/memory/types/buffer.html |
8157ce5efd3b-2 | Human: Tell me about yourself.
AI:
> Finished chain.
" Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers."
And that’s it for the getting started! There are plenty of different types of memory, check out our examples to see them all
previous
How-To Guides
next
ConversationBufferWindowMemory
Contents
Using in a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/buffer.html |
3ea22e453606-0 | .ipynb
.pdf
ConversationSummaryMemory
Contents
Initializing with messages
Using in a chain
ConversationSummaryMemory#
Now let’s take a look at using a slightly more complex type of memory - ConversationSummaryMemory. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.
Let’s first explore the basic functionality of this type of memory.
from langchain.memory import ConversationSummaryMemory, ChatMessageHistory
from langchain.llms import OpenAI
memory = ConversationSummaryMemory(llm=OpenAI(temperature=0))
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.load_memory_variables({})
{'history': '\nThe human greets the AI, to which the AI responds.'}
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
memory = ConversationSummaryMemory(llm=OpenAI(temperature=0), return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.load_memory_variables({})
{'history': [SystemMessage(content='\nThe human greets the AI, to which the AI responds.', additional_kwargs={})]}
We can also utilize the predict_new_summary method directly.
messages = memory.chat_memory.messages
previous_summary = ""
memory.predict_new_summary(messages, previous_summary)
'\nThe human greets the AI, to which the AI responds.'
Initializing with messages#
If you have messages outside this class, you can easily initialize the class with ChatMessageHistory. During loading, a summary will be calculated.
history = ChatMessageHistory()
history.add_user_message("hi")
history.add_ai_message("hi there!") | https://python.langchain.com/en/latest/modules/memory/types/summary.html |
3ea22e453606-1 | history.add_user_message("hi")
history.add_ai_message("hi there!")
memory = ConversationSummaryMemory.from_messages(llm=OpenAI(temperature=0), chat_memory=history, return_messages=True)
memory.buffer
'\nThe human greets the AI, to which the AI responds with a friendly greeting.'
Using in a chain#
Let’s walk through an example of using this in a chain, again setting verbose=True so we can see the prompt.
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation_with_summary = ConversationChain(
llm=llm,
memory=ConversationSummaryMemory(llm=OpenAI()),
verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI:
> Finished chain.
" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?"
conversation_with_summary.predict(input="Tell me more about it!")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue. | https://python.langchain.com/en/latest/modules/memory/types/summary.html |
3ea22e453606-2 | Human: Tell me more about it!
AI:
> Finished chain.
" Sure! The customer is having trouble with their computer not connecting to the internet. I'm helping them troubleshoot the issue and figure out what the problem is. So far, we've tried resetting the router and checking the network settings, but the issue still persists. We're currently looking into other possible solutions."
conversation_with_summary.predict(input="Very cool -- what is the scope of the project?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue where their computer was not connecting to the internet. The AI was troubleshooting the issue and had already tried resetting the router and checking the network settings, but the issue still persisted and they were looking into other possible solutions.
Human: Very cool -- what is the scope of the project?
AI:
> Finished chain.
" The scope of the project is to troubleshoot the customer's computer issue and find a solution that will allow them to connect to the internet. We are currently exploring different possibilities and have already tried resetting the router and checking the network settings, but the issue still persists."
previous
Conversation Knowledge Graph Memory
next
ConversationSummaryBufferMemory
Contents
Initializing with messages
Using in a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/summary.html |
ff7d9aa506d4-0 | .ipynb
.pdf
ConversationBufferWindowMemory
Contents
Using in a chain
ConversationBufferWindowMemory#
ConversationBufferWindowMemory keeps a list of the interactions of the conversation over time. It only uses the last K interactions. This can be useful for keeping a sliding window of the most recent interactions, so the buffer does not get too large
Let’s first explore the basic functionality of this type of memory.
from langchain.memory import ConversationBufferWindowMemory
memory = ConversationBufferWindowMemory( k=1)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})
memory.load_memory_variables({})
{'history': 'Human: not much you\nAI: not much'}
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
memory = ConversationBufferWindowMemory( k=1, return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})
memory.load_memory_variables({})
{'history': [HumanMessage(content='not much you', additional_kwargs={}),
AIMessage(content='not much', additional_kwargs={})]}
Using in a chain#
Let’s walk through an example, again setting verbose=True so we can see the prompt.
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
conversation_with_summary = ConversationChain(
llm=OpenAI(temperature=0),
# We set a low k=2, to only keep the last 2 interactions in memory
memory=ConversationBufferWindowMemory(k=2),
verbose=True
) | https://python.langchain.com/en/latest/modules/memory/types/buffer_window.html |
ff7d9aa506d4-1 | memory=ConversationBufferWindowMemory(k=2),
verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI:
> Finished chain.
" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?"
conversation_with_summary.predict(input="What's their issues?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up?
AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?
Human: What's their issues?
AI:
> Finished chain.
" The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected."
conversation_with_summary.predict(input="Is it going well?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi, what's up? | https://python.langchain.com/en/latest/modules/memory/types/buffer_window.html |
ff7d9aa506d4-2 | Current conversation:
Human: Hi, what's up?
AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?
Human: What's their issues?
AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.
Human: Is it going well?
AI:
> Finished chain.
" Yes, it's going well so far. We've already identified the problem and are now working on a solution."
# Notice here that the first interaction does not appear.
conversation_with_summary.predict(input="What's the solution?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: What's their issues?
AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.
Human: Is it going well?
AI: Yes, it's going well so far. We've already identified the problem and are now working on a solution.
Human: What's the solution?
AI:
> Finished chain.
" The solution is to reset the router and reconfigure the settings. We're currently in the process of doing that."
previous
ConversationBufferMemory
next
Entity Memory
Contents
Using in a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/buffer_window.html |
fb94415e25a1-0 | .ipynb
.pdf
VectorStore-Backed Memory
Contents
Initialize your VectorStore
Create your the VectorStoreRetrieverMemory
Using in a chain
VectorStore-Backed Memory#
VectorStoreRetrieverMemory stores memories in a VectorDB and queries the top-K most “salient” docs every time it is called.
This differs from most of the other Memory classes in that it doesn’t explicitly track the order of interactions.
In this case, the “docs” are previous conversation snippets. This can be useful to refer to relevant pieces of information that the AI was told earlier in the conversation.
from datetime import datetime
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.llms import OpenAI
from langchain.memory import VectorStoreRetrieverMemory
from langchain.chains import ConversationChain
from langchain.prompts import PromptTemplate
Initialize your VectorStore#
Depending on the store you choose, this step may look different. Consult the relevant VectorStore documentation for more details.
import faiss
from langchain.docstore import InMemoryDocstore
from langchain.vectorstores import FAISS
embedding_size = 1536 # Dimensions of the OpenAIEmbeddings
index = faiss.IndexFlatL2(embedding_size)
embedding_fn = OpenAIEmbeddings().embed_query
vectorstore = FAISS(embedding_fn, index, InMemoryDocstore({}), {})
Create your the VectorStoreRetrieverMemory#
The memory object is instantiated from any VectorStoreRetriever.
# In actual usage, you would set `k` to be a higher value, but we use k=1 to show that
# the vector lookup still returns the semantically relevant information
retriever = vectorstore.as_retriever(search_kwargs=dict(k=1))
memory = VectorStoreRetrieverMemory(retriever=retriever) | https://python.langchain.com/en/latest/modules/memory/types/vectorstore_retriever_memory.html |
fb94415e25a1-1 | memory = VectorStoreRetrieverMemory(retriever=retriever)
# When added to an agent, the memory object can save pertinent information from conversations or used tools
memory.save_context({"input": "My favorite food is pizza"}, {"output": "thats good to know"})
memory.save_context({"input": "My favorite sport is soccer"}, {"output": "..."})
memory.save_context({"input": "I don't the Celtics"}, {"output": "ok"}) #
# Notice the first result returned is the memory pertaining to tax help, which the language model deems more semantically relevant
# to a 1099 than the other documents, despite them both containing numbers.
print(memory.load_memory_variables({"prompt": "what sport should i watch?"})["history"])
input: My favorite sport is soccer
output: ...
Using in a chain#
Let’s walk through an example, again setting verbose=True so we can see the prompt.
llm = OpenAI(temperature=0) # Can be any valid LLM
_DEFAULT_TEMPLATE = """The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Relevant pieces of previous conversation:
{history}
(You do not need to use these pieces of information if not relevant)
Current conversation:
Human: {input}
AI:"""
PROMPT = PromptTemplate(
input_variables=["history", "input"], template=_DEFAULT_TEMPLATE
)
conversation_with_summary = ConversationChain(
llm=llm,
prompt=PROMPT,
# We set a very low max_token_limit for the purposes of testing.
memory=memory,
verbose=True
) | https://python.langchain.com/en/latest/modules/memory/types/vectorstore_retriever_memory.html |
fb94415e25a1-2 | memory=memory,
verbose=True
)
conversation_with_summary.predict(input="Hi, my name is Perry, what's up?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know
(You do not need to use these pieces of information if not relevant)
Current conversation:
Human: Hi, my name is Perry, what's up?
AI:
> Finished chain.
" Hi Perry, I'm doing well. How about you?"
# Here, the basketball related content is surfaced
conversation_with_summary.predict(input="what's my favorite sport?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Relevant pieces of previous conversation:
input: My favorite sport is soccer
output: ...
(You do not need to use these pieces of information if not relevant)
Current conversation:
Human: what's my favorite sport?
AI:
> Finished chain.
' You told me earlier that your favorite sport is soccer.'
# Even though the language model is stateless, since relavent memory is fetched, it can "reason" about the time.
# Timestamping memories and data is useful in general to let the agent determine temporal relevance
conversation_with_summary.predict(input="Whats my favorite food")
> Entering new ConversationChain chain... | https://python.langchain.com/en/latest/modules/memory/types/vectorstore_retriever_memory.html |
fb94415e25a1-3 | > Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know
(You do not need to use these pieces of information if not relevant)
Current conversation:
Human: Whats my favorite food
AI:
> Finished chain.
' You said your favorite food is pizza.'
# The memories from the conversation are automatically stored,
# since this query best matches the introduction chat above,
# the agent is able to 'remember' the user's name.
conversation_with_summary.predict(input="What's my name?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Relevant pieces of previous conversation:
input: Hi, my name is Perry, what's up?
response: Hi Perry, I'm doing well. How about you?
(You do not need to use these pieces of information if not relevant)
Current conversation:
Human: What's my name?
AI:
> Finished chain.
' Your name is Perry.'
previous
ConversationTokenBufferMemory
next
How to add Memory to an LLMChain
Contents
Initialize your VectorStore
Create your the VectorStoreRetrieverMemory
Using in a chain
By Harrison Chase
© Copyright 2023, Harrison Chase. | https://python.langchain.com/en/latest/modules/memory/types/vectorstore_retriever_memory.html |
fb94415e25a1-4 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/vectorstore_retriever_memory.html |
00581610be4c-0 | .ipynb
.pdf
Entity Memory
Contents
Using in a chain
Inspecting the memory store
Entity Memory#
This notebook shows how to work with a memory module that remembers things about specific entities. It extracts information on entities (using LLMs) and builds up its knowledge about that entity over time (also using LLMs).
Let’s first walk through using this functionality.
from langchain.llms import OpenAI
from langchain.memory import ConversationEntityMemory
llm = OpenAI(temperature=0)
memory = ConversationEntityMemory(llm=llm)
_input = {"input": "Deven & Sam are working on a hackathon project"}
memory.load_memory_variables(_input)
memory.save_context(
_input,
{"output": " That sounds like a great project! What kind of project are they working on?"}
)
memory.load_memory_variables({"input": 'who is Sam'})
{'history': 'Human: Deven & Sam are working on a hackathon project\nAI: That sounds like a great project! What kind of project are they working on?',
'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}
memory = ConversationEntityMemory(llm=llm, return_messages=True)
_input = {"input": "Deven & Sam are working on a hackathon project"}
memory.load_memory_variables(_input)
memory.save_context(
_input,
{"output": " That sounds like a great project! What kind of project are they working on?"}
)
memory.load_memory_variables({"input": 'who is Sam'})
{'history': [HumanMessage(content='Deven & Sam are working on a hackathon project', additional_kwargs={}),
AIMessage(content=' That sounds like a great project! What kind of project are they working on?', additional_kwargs={})], | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-1 | 'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}
Using in a chain#
Let’s now use it in a chain!
from langchain.chains import ConversationChain
from langchain.memory import ConversationEntityMemory
from langchain.memory.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE
from pydantic import BaseModel
from typing import List, Dict, Any
conversation = ConversationChain(
llm=llm,
verbose=True,
prompt=ENTITY_MEMORY_CONVERSATION_TEMPLATE,
memory=ConversationEntityMemory(llm=llm)
)
conversation.predict(input="Deven & Sam are working on a hackathon project")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics. | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-2 | Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context:
{'Deven': 'Deven is working on a hackathon project with Sam.', 'Sam': 'Sam is working on a hackathon project with Deven.'}
Current conversation:
Last line:
Human: Deven & Sam are working on a hackathon project
You:
> Finished chain.
' That sounds like a great project! What kind of project are they working on?'
conversation.memory.entity_store.store
{'Deven': 'Deven is working on a hackathon project with Sam, which they are entering into a hackathon.',
'Sam': 'Sam is working on a hackathon project with Deven.'}
conversation.predict(input="They are trying to add more complex memory structures to Langchain")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand. | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-3 | You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context:
{'Deven': 'Deven is working on a hackathon project with Sam, which they are entering into a hackathon.', 'Sam': 'Sam is working on a hackathon project with Deven.', 'Langchain': ''}
Current conversation:
Human: Deven & Sam are working on a hackathon project
AI: That sounds like a great project! What kind of project are they working on?
Last line:
Human: They are trying to add more complex memory structures to Langchain
You:
> Finished chain.
' That sounds like an interesting project! What kind of memory structures are they trying to add?'
conversation.predict(input="They are adding in a key-value store for entities mentioned so far in the conversation.")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI. | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-4 | You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context:
{'Deven': 'Deven is working on a hackathon project with Sam, which they are entering into a hackathon. They are trying to add more complex memory structures to Langchain.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain.', 'Langchain': 'Langchain is a project that is trying to add more complex memory structures.', 'Key-Value Store': ''}
Current conversation:
Human: Deven & Sam are working on a hackathon project
AI: That sounds like a great project! What kind of project are they working on? | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-5 | AI: That sounds like a great project! What kind of project are they working on?
Human: They are trying to add more complex memory structures to Langchain
AI: That sounds like an interesting project! What kind of memory structures are they trying to add?
Last line:
Human: They are adding in a key-value store for entities mentioned so far in the conversation.
You:
> Finished chain.
' That sounds like a great idea! How will the key-value store help with the project?'
conversation.predict(input="What do you know about Deven & Sam?")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context: | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-6 | Context:
{'Deven': 'Deven is working on a hackathon project with Sam, which they are entering into a hackathon. They are trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'}
Current conversation:
Human: Deven & Sam are working on a hackathon project
AI: That sounds like a great project! What kind of project are they working on?
Human: They are trying to add more complex memory structures to Langchain
AI: That sounds like an interesting project! What kind of memory structures are they trying to add?
Human: They are adding in a key-value store for entities mentioned so far in the conversation.
AI: That sounds like a great idea! How will the key-value store help with the project?
Last line:
Human: What do you know about Deven & Sam?
You:
> Finished chain.
' Deven and Sam are working on a hackathon project together, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to be working hard on this project and have a great idea for how the key-value store can help.'
Inspecting the memory store#
We can also inspect the memory store directly. In the following examaples, we look at it directly, and then go through some examples of adding information and watch how it changes.
from pprint import pprint
pprint(conversation.memory.entity_store.store)
{'Daimon': 'Daimon is a company founded by Sam, a successful entrepreneur.', | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-7 | 'Deven': 'Deven is working on a hackathon project with Sam, which they are '
'entering into a hackathon. They are trying to add more complex '
'memory structures to Langchain, including a key-value store for '
'entities mentioned so far in the conversation, and seem to be '
'working hard on this project with a great idea for how the '
'key-value store can help.',
'Key-Value Store': 'A key-value store is being added to the project to store '
'entities mentioned in the conversation.',
'Langchain': 'Langchain is a project that is trying to add more complex '
'memory structures, including a key-value store for entities '
'mentioned so far in the conversation.',
'Sam': 'Sam is working on a hackathon project with Deven, trying to add more '
'complex memory structures to Langchain, including a key-value store '
'for entities mentioned so far in the conversation. They seem to have '
'a great idea for how the key-value store can help, and Sam is also '
'the founder of a company called Daimon.'}
conversation.predict(input="Sam is the founder of a company called Daimon.")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand. | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-8 | You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context:
{'Daimon': 'Daimon is a company founded by Sam, a successful entrepreneur.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to have a great idea for how the key-value store can help, and Sam is also the founder of a company called Daimon.'}
Current conversation:
Human: They are adding in a key-value store for entities mentioned so far in the conversation.
AI: That sounds like a great idea! How will the key-value store help with the project?
Human: What do you know about Deven & Sam?
AI: Deven and Sam are working on a hackathon project together, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to be working hard on this project and have a great idea for how the key-value store can help.
Human: Sam is the founder of a company called Daimon.
AI: | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-9 | Human: Sam is the founder of a company called Daimon.
AI:
That's impressive! It sounds like Sam is a very successful entrepreneur. What kind of company is Daimon?
Last line:
Human: Sam is the founder of a company called Daimon.
You:
> Finished chain.
" That's impressive! It sounds like Sam is a very successful entrepreneur. What kind of company is Daimon?"
from pprint import pprint
pprint(conversation.memory.entity_store.store)
{'Daimon': 'Daimon is a company founded by Sam, a successful entrepreneur, who '
'is working on a hackathon project with Deven to add more complex '
'memory structures to Langchain.',
'Deven': 'Deven is working on a hackathon project with Sam, which they are '
'entering into a hackathon. They are trying to add more complex '
'memory structures to Langchain, including a key-value store for '
'entities mentioned so far in the conversation, and seem to be '
'working hard on this project with a great idea for how the '
'key-value store can help.',
'Key-Value Store': 'A key-value store is being added to the project to store '
'entities mentioned in the conversation.',
'Langchain': 'Langchain is a project that is trying to add more complex '
'memory structures, including a key-value store for entities '
'mentioned so far in the conversation.',
'Sam': 'Sam is working on a hackathon project with Deven, trying to add more '
'complex memory structures to Langchain, including a key-value store '
'for entities mentioned so far in the conversation. They seem to have ' | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-10 | 'for entities mentioned so far in the conversation. They seem to have '
'a great idea for how the key-value store can help, and Sam is also '
'the founder of a successful company called Daimon.'}
conversation.predict(input="What do you know about Sam?")
> Entering new ConversationChain chain...
Prompt after formatting:
You are an assistant to a human, powered by a large language model trained by OpenAI.
You are designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
You are constantly learning and improving, and your capabilities are constantly evolving. You are able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.
Context: | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-11 | Context:
{'Deven': 'Deven is working on a hackathon project with Sam, which they are entering into a hackathon. They are trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation, and seem to be working hard on this project with a great idea for how the key-value store can help.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to have a great idea for how the key-value store can help, and Sam is also the founder of a successful company called Daimon.', 'Langchain': 'Langchain is a project that is trying to add more complex memory structures, including a key-value store for entities mentioned so far in the conversation.', 'Daimon': 'Daimon is a company founded by Sam, a successful entrepreneur, who is working on a hackathon project with Deven to add more complex memory structures to Langchain.'}
Current conversation:
Human: What do you know about Deven & Sam?
AI: Deven and Sam are working on a hackathon project together, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to be working hard on this project and have a great idea for how the key-value store can help.
Human: Sam is the founder of a company called Daimon.
AI:
That's impressive! It sounds like Sam is a very successful entrepreneur. What kind of company is Daimon?
Human: Sam is the founder of a company called Daimon.
AI: That's impressive! It sounds like Sam is a very successful entrepreneur. What kind of company is Daimon?
Last line: | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
00581610be4c-12 | Last line:
Human: What do you know about Sam?
You:
> Finished chain.
' Sam is the founder of a successful company called Daimon. He is also working on a hackathon project with Deven to add more complex memory structures to Langchain. They seem to have a great idea for how the key-value store can help.'
previous
ConversationBufferWindowMemory
next
Conversation Knowledge Graph Memory
Contents
Using in a chain
Inspecting the memory store
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/modules/memory/types/entity_summary_memory.html |
3497c756c2ac-0 | .ipynb
.pdf
Conversation Knowledge Graph Memory
Contents
Using in a chain
Conversation Knowledge Graph Memory#
This type of memory uses a knowledge graph to recreate memory.
Let’s first walk through how to use the utilities
from langchain.memory import ConversationKGMemory
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
memory = ConversationKGMemory(llm=llm)
memory.save_context({"input": "say hi to sam"}, {"output": "who is sam"})
memory.save_context({"input": "sam is a friend"}, {"output": "okay"})
memory.load_memory_variables({"input": 'who is sam'})
{'history': 'On Sam: Sam is friend.'}
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
memory = ConversationKGMemory(llm=llm, return_messages=True)
memory.save_context({"input": "say hi to sam"}, {"output": "who is sam"})
memory.save_context({"input": "sam is a friend"}, {"output": "okay"})
memory.load_memory_variables({"input": 'who is sam'})
{'history': [SystemMessage(content='On Sam: Sam is friend.', additional_kwargs={})]}
We can also more modularly get current entities from a new message (will use previous messages as context.)
memory.get_current_entities("what's Sams favorite color?")
['Sam']
We can also more modularly get knowledge triplets from a new message (will use previous messages as context.)
memory.get_knowledge_triplets("her favorite color is red")
[KnowledgeTriple(subject='Sam', predicate='favorite color', object_='red')]
Using in a chain#
Let’s now use this in a chain!
llm = OpenAI(temperature=0) | https://python.langchain.com/en/latest/modules/memory/types/kg.html |
3497c756c2ac-1 | llm = OpenAI(temperature=0)
from langchain.prompts.prompt import PromptTemplate
from langchain.chains import ConversationChain
template = """The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context.
If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the "Relevant Information" section and does not hallucinate.
Relevant Information:
{history}
Conversation:
Human: {input}
AI:"""
prompt = PromptTemplate(
input_variables=["history", "input"], template=template
)
conversation_with_kg = ConversationChain(
llm=llm,
verbose=True,
prompt=prompt,
memory=ConversationKGMemory(llm=llm)
)
conversation_with_kg.predict(input="Hi, what's up?")
> Entering new ConversationChain chain...
Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context.
If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the "Relevant Information" section and does not hallucinate.
Relevant Information:
Conversation:
Human: Hi, what's up?
AI:
> Finished chain.
" Hi there! I'm doing great. I'm currently in the process of learning about the world around me. I'm learning about different cultures, languages, and customs. It's really fascinating! How about you?"
conversation_with_kg.predict(input="My name is James and I'm helping Will. He's an engineer.")
> Entering new ConversationChain chain... | https://python.langchain.com/en/latest/modules/memory/types/kg.html |
Subsets and Splits