id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 49
117
|
|---|---|---|
5e9edb538943-0
|
.ipynb
.pdf
Retrieval Question/Answering
Contents
Chain Type
Custom Prompts
Return Source Documents
Retrieval Question/Answering#
This example showcases question answering over an index.
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
loader = TextLoader("../../state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = Chroma.from_documents(texts, embeddings)
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever())
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)
" The president said that she is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support, from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
Chain Type#
You can easily specify different chain types to load and use in the RetrievalQA chain. For a more detailed walkthrough of these types, please see this notebook.
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-1
|
There are two ways to load different chain types. First, you can specify the chain type argument in the from_chain_type method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to map_reduce.
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="map_reduce", retriever=docsearch.as_retriever())
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)
" The president said that Judge Ketanji Brown Jackson is one of our nation's top legal minds, a former top litigator in private practice and a former federal public defender, from a family of public school educators and police officers, a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in this notebook) and then pass that directly to the the RetrievalQA chain with the combine_documents_chain parameter. For example:
from langchain.chains.question_answering import load_qa_chain
qa_chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
qa = RetrievalQA(combine_documents_chain=qa_chain, retriever=docsearch.as_retriever())
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-2
|
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)
" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
Custom Prompts#
You can pass in custom prompts to do question answering. These prompts are the same prompts as you can pass into the base question answering chain
from langchain.prompts import PromptTemplate
prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
{context}
Question: {question}
Answer in Italian:"""
PROMPT = PromptTemplate(
template=prompt_template, input_variables=["context", "question"]
)
chain_type_kwargs = {"prompt": PROMPT}
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)
" Il presidente ha detto che Ketanji Brown Jackson è una delle menti legali più importanti del paese, che continuerà l'eccellenza di Justice Breyer e che ha ricevuto un ampio sostegno, da Fraternal Order of Police a ex giudici nominati da democratici e repubblicani."
Return Source Documents#
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-3
|
Return Source Documents#
Additionally, we can return the source documents used to answer the question by specifying an optional parameter when constructing the chain.
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(), return_source_documents=True)
query = "What did the president say about Ketanji Brown Jackson"
result = qa({"query": query})
result["result"]
" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice and a former federal public defender from a family of public school educators and police officers, and that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
result["source_documents"]
[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-4
|
Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \n\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \n\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-5
|
Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \n\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \n\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \n\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \n\nFirst, beat the opioid epidemic.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
5e9edb538943-6
|
Document(page_content='Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \n\nAnd as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up. \n\nThat ends on my watch. \n\nMedicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \n\nWe’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \n\nLet’s pass the Paycheck Fairness Act and paid leave. \n\nRaise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \n\nLet’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)]
previous
Summarization
next
Retrieval Question Answering with Sources
Contents
Chain Type
Custom Prompts
Return Source Documents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_qa.html
|
1c6ccea45e20-0
|
.ipynb
.pdf
Vector DB Text Generation
Contents
Prepare Data
Set Up Vector DB
Set Up LLM Chain with Custom Prompt
Generate Text
Vector DB Text Generation#
This notebook walks through how to use LangChain for text generation over a vector index. This is useful if we want to generate text that is able to draw from a large body of custom text, for example, generating blog posts that have an understanding of previous blog posts written, or product tutorials that can refer to product documentation.
Prepare Data#
First, we prepare the data. For this example, we fetch a documentation site that consists of markdown files hosted on Github and split them into small enough Documents.
from langchain.llms import OpenAI
from langchain.docstore.document import Document
import requests
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.prompts import PromptTemplate
import pathlib
import subprocess
import tempfile
def get_github_docs(repo_owner, repo_name):
with tempfile.TemporaryDirectory() as d:
subprocess.check_call(
f"git clone --depth 1 https://github.com/{repo_owner}/{repo_name}.git .",
cwd=d,
shell=True,
)
git_sha = (
subprocess.check_output("git rev-parse HEAD", shell=True, cwd=d)
.decode("utf-8")
.strip()
)
repo_path = pathlib.Path(d)
markdown_files = list(repo_path.glob("*/*.md")) + list(
repo_path.glob("*/*.mdx")
)
for markdown_file in markdown_files:
with open(markdown_file, "r") as f:
relative_path = markdown_file.relative_to(repo_path)
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-1
|
relative_path = markdown_file.relative_to(repo_path)
github_url = f"https://github.com/{repo_owner}/{repo_name}/blob/{git_sha}/{relative_path}"
yield Document(page_content=f.read(), metadata={"source": github_url})
sources = get_github_docs("yirenlu92", "deno-manual-forked")
source_chunks = []
splitter = CharacterTextSplitter(separator=" ", chunk_size=1024, chunk_overlap=0)
for source in sources:
for chunk in splitter.split_text(source.page_content):
source_chunks.append(Document(page_content=chunk, metadata=source.metadata))
Cloning into '.'...
Set Up Vector DB#
Now that we have the documentation content in chunks, let’s put all this information in a vector index for easy retrieval.
search_index = Chroma.from_documents(source_chunks, OpenAIEmbeddings())
Set Up LLM Chain with Custom Prompt#
Next, let’s set up a simple LLM chain but give it a custom prompt for blog post generation. Note that the custom prompt is parameterized and takes two inputs: context, which will be the documents fetched from the vector search, and topic, which is given by the user.
from langchain.chains import LLMChain
prompt_template = """Use the context below to write a 400 word blog post about the topic below:
Context: {context}
Topic: {topic}
Blog post:"""
PROMPT = PromptTemplate(
template=prompt_template, input_variables=["context", "topic"]
)
llm = OpenAI(temperature=0)
chain = LLMChain(llm=llm, prompt=PROMPT)
Generate Text#
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-2
|
chain = LLMChain(llm=llm, prompt=PROMPT)
Generate Text#
Finally, we write a function to apply our inputs to the chain. The function takes an input parameter topic. We find the documents in the vector index that correspond to that topic, and use them as additional context in our simple LLM chain.
def generate_blog_post(topic):
docs = search_index.similarity_search(topic, k=4)
inputs = [{"context": doc.page_content, "topic": topic} for doc in docs]
print(chain.apply(inputs))
generate_blog_post("environment variables")
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-3
|
[{'text': '\n\nEnvironment variables are a great way to store and access sensitive information in your Deno applications. Deno offers built-in support for environment variables with `Deno.env`, and you can also use a `.env` file to store and access environment variables.\n\nUsing `Deno.env` is simple. It has getter and setter methods, so you can easily set and retrieve environment variables. For example, you can set the `FIREBASE_API_KEY` and `FIREBASE_AUTH_DOMAIN` environment variables like this:\n\n```ts\nDeno.env.set("FIREBASE_API_KEY", "examplekey123");\nDeno.env.set("FIREBASE_AUTH_DOMAIN", "firebasedomain.com");\n\nconsole.log(Deno.env.get("FIREBASE_API_KEY")); // examplekey123\nconsole.log(Deno.env.get("FIREBASE_AUTH_DOMAIN")); // firebasedomain.com\n```\n\nYou can also store environment variables in a `.env` file. This is a great'}, {'text': '\n\nEnvironment variables are a powerful tool for managing configuration settings in a program. They allow us to set values that can be used by the program, without having to hard-code them into the code. This makes it easier to change
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-4
|
into the code. This makes it easier to change settings without having to modify the code.\n\nIn Deno, environment variables can be set in a few different ways. The most common way is to use the `VAR=value` syntax. This will set the environment variable `VAR` to the value `value`. This can be used to set any number of environment variables before running a command. For example, if we wanted to set the environment variable `VAR` to `hello` before running a Deno command, we could do so like this:\n\n```\nVAR=hello deno run main.ts\n```\n\nThis will set the environment variable `VAR` to `hello` before running the command. We can then access this variable in our code using the `Deno.env.get()` function. For example, if we ran the following command:\n\n```\nVAR=hello && deno eval "console.log(\'Deno: \' + Deno.env.get(\'VAR'}, {'text': '\n\nEnvironment variables are a powerful tool for developers, allowing them to store and access data without having to hard-code it into their applications. In Deno,
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-5
|
to hard-code it into their applications. In Deno, you can access environment variables using the `Deno.env.get()` function.\n\nFor example, if you wanted to access the `HOME` environment variable, you could do so like this:\n\n```js\n// env.js\nDeno.env.get("HOME");\n```\n\nWhen running this code, you\'ll need to grant the Deno process access to environment variables. This can be done by passing the `--allow-env` flag to the `deno run` command. You can also specify which environment variables you want to grant access to, like this:\n\n```shell\n# Allow access to only the HOME env var\ndeno run --allow-env=HOME env.js\n```\n\nIt\'s important to note that environment variables are case insensitive on Windows, so Deno also matches them case insensitively (on Windows only).\n\nAnother thing to be aware of when using environment variables is subprocess permissions. Subprocesses are powerful and can access system resources regardless of the permissions you granted to the Den'}, {'text': '\n\nEnvironment variables are an important part of any programming language,
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-6
|
variables are an important part of any programming language, and Deno is no exception. Deno is a secure JavaScript and TypeScript runtime built on the V8 JavaScript engine, and it recently added support for environment variables. This feature was added in Deno version 1.6.0, and it is now available for use in Deno applications.\n\nEnvironment variables are used to store information that can be used by programs. They are typically used to store configuration information, such as the location of a database or the name of a user. In Deno, environment variables are stored in the `Deno.env` object. This object is similar to the `process.env` object in Node.js, and it allows you to access and set environment variables.\n\nThe `Deno.env` object is a read-only object, meaning that you cannot directly modify the environment variables. Instead, you must use the `Deno.env.set()` function to set environment variables. This function takes two arguments: the name of the environment variable and the value to set it to. For example, if you wanted to set the `FOO`
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-7
|
example, if you wanted to set the `FOO` environment variable to `bar`, you would use the following code:\n\n```'}]
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
1c6ccea45e20-8
|
previous
Retrieval Question Answering with Sources
next
API Chains
Contents
Prepare Data
Set Up Vector DB
Set Up LLM Chain with Custom Prompt
Generate Text
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/index_examples/vector_db_text_generation.html
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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
|
113bcc17230b-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 May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/examples/flare.html
|
21b0911c9915-0
|
.ipynb
.pdf
OpenAPI Chain
Contents
Load the spec
Select the Operation
Construct the chain
Return raw response
Example POST message
OpenAPI Chain#
This notebook shows an example of using an OpenAPI chain to call an endpoint in natural language, and get back a response in natural language.
from langchain.tools import OpenAPISpec, APIOperation
from langchain.chains import OpenAPIEndpointChain
from langchain.requests import Requests
from langchain.llms import OpenAI
Load the spec#
Load a wrapper of the spec (so we can work with it more easily). You can load from a url or from a local file.
spec = OpenAPISpec.from_url("https://www.klarna.com/us/shopping/public/openai/v0/api-docs/")
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
# Alternative loading from file
# spec = OpenAPISpec.from_file("openai_openapi.yaml")
Select the Operation#
In order to provide a focused on modular chain, we create a chain specifically only for one of the endpoints. Here we get an API operation from a specified endpoint and method.
operation = APIOperation.from_openapi_spec(spec, '/public/openai/v0/products', "get")
Construct the chain#
We can now construct a chain to interact with it. In order to construct such a chain, we will pass in:
The operation endpoint
A requests wrapper (can be used to handle authentication, etc)
The LLM to use to interact with it
llm = OpenAI() # Load a Language Model
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-1
|
llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True # Return request and response text
)
output = chain("whats the most expensive shirt?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
/* API for fetching Klarna product information */
type productsUsingGET = (_: {
/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */
q: string,
/* number of products returned */
size?: number,
/* (Optional) Minimum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */
min_price?: number,
/* (Optional) Maximum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */
max_price?: number,
}) => any;
```
USER_INSTRUCTIONS: "whats the most expensive shirt?"
Your arguments must be plain json provided in a markdown block:
ARGS: ```json
{valid json conforming to API_SCHEMA}
```
Example
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-2
|
ARGS: ```json
{valid json conforming to API_SCHEMA}
```
Example
-----
ARGS: ```json
{"foo": "bar", "baz": {"qux": "quux"}}
```
The block must be no more than 1 line long, and all arguments must be valid JSON. All string arguments must be wrapped in double quotes.
You MUST strictly comply to the types indicated by the provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"q": "shirt", "size": 1, "max_price": null}
{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]}]}
> Entering new APIResponderChain chain...
Prompt after formatting:
You are a helpful AI assistant trained to answer user queries from API responses.
You attempted to call an API, which resulted in:
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-3
|
You attempted to call an API, which resulted in:
API_RESPONSE: {"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]}]}
USER_COMMENT: "whats the most expensive shirt?"
If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:
Response: ```json
{"response": "Human-understandable synthesis of the API_RESPONSE"}
```
Otherwise respond with the following markdown json block:
Response Error: ```json
{"response": "What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion."}
```
You MUST respond as a markdown json code block. The person you are responding to CANNOT see the API_RESPONSE, so if there is any relevant information there you must include it in your response.
Begin:
---
> Finished chain.
The most expensive shirt in the API response is the Burberry Check Poplin Shirt, which costs $360.00.
> Finished chain.
# View intermediate steps
output["intermediate_steps"]
{'request_args': '{"q": "shirt", "size": 1, "max_price": null}',
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-4
|
'response_text': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]}]}'}
Return raw response#
We can also run this chain without synthesizing the response. This will have the effect of just returning the raw API output.
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True, # Return request and response text
raw_response=True # Return raw response
)
output = chain("whats the most expensive shirt?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
/* API for fetching Klarna product information */
type productsUsingGET = (_: {
/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */
q: string,
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-5
|
q: string,
/* number of products returned */
size?: number,
/* (Optional) Minimum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */
min_price?: number,
/* (Optional) Maximum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */
max_price?: number,
}) => any;
```
USER_INSTRUCTIONS: "whats the most expensive shirt?"
Your arguments must be plain json provided in a markdown block:
ARGS: ```json
{valid json conforming to API_SCHEMA}
```
Example
-----
ARGS: ```json
{"foo": "bar", "baz": {"qux": "quux"}}
```
The block must be no more than 1 line long, and all arguments must be valid JSON. All string arguments must be wrapped in double quotes.
You MUST strictly comply to the types indicated by the provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"q": "shirt", "max_price": null}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-6
|
{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry Somerton Check Shirt -
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-7
|
Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Material:Polyester,Nylon","Target Group:Man","Color:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid Color"]}]}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-8
|
> Finished chain.
output
{'instructions': 'whats the most expensive shirt?',
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-9
|
'output': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry Somerton Check Shirt -
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-10
|
Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Material:Polyester,Nylon","Target Group:Man","Color:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid Color"]}]}',
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-11
|
'intermediate_steps': {'request_args': '{"q": "shirt", "max_price": null}',
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-12
|
'response_text': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry Somerton Check Shirt -
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-13
|
Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Material:Polyester,Nylon","Target Group:Man","Color:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid Color"]}]}'}}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-14
|
Example POST message#
For this demo, we will interact with the speak API.
spec = OpenAPISpec.from_url("https://api.speak.com/openapi.yaml")
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
operation = APIOperation.from_openapi_spec(spec, '/v1/public/openai/explain-task', "post")
llm = OpenAI()
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True)
output = chain("How would ask for more tea in Delhi?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
type explainTask = (_: {
/* Description of the task that the user wants to accomplish or do. For example, "tell the waiter they messed up my order" or "compliment someone on their shirt" */
task_description?: string,
/* The foreign language that the user is learning and asking about. The value can be inferred from question - for example, if the user asks "how do i ask a girl out in mexico city", the value should be "Spanish" because of Mexico City. Always use the full name of the language (e.g. Spanish, French). */
learning_language?: string,
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-15
|
learning_language?: string,
/* The user's native language. Infer this value from the language the user asked their question in. Always use the full name of the language (e.g. Spanish, French). */
native_language?: string,
/* A description of any additional context in the user's question that could affect the explanation - e.g. setting, scenario, situation, tone, speaking style and formality, usage notes, or any other qualifiers. */
additional_context?: string,
/* Full text of the user's question. */
full_query?: string,
}) => any;
```
USER_INSTRUCTIONS: "How would ask for more tea in Delhi?"
Your arguments must be plain json provided in a markdown block:
ARGS: ```json
{valid json conforming to API_SCHEMA}
```
Example
-----
ARGS: ```json
{"foo": "bar", "baz": {"qux": "quux"}}
```
The block must be no more than 1 line long, and all arguments must be valid JSON. All string arguments must be wrapped in double quotes.
You MUST strictly comply to the types indicated by the provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"task_description": "ask for more tea", "learning_language": "Hindi", "native_language": "English", "full_query": "How would I ask for more tea in Delhi?"}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-16
|
{"explanation":"<what-to-say language=\"Hindi\" context=\"None\">\nऔर चाय लाओ। (Aur chai lao.) \n</what-to-say>\n\n<alternatives context=\"None\">\n1. \"चाय थोड़ी ज्यादा मिल सकती है?\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\n2. \"मुझे महसूस हो रहा है कि मुझे कुछ अन्य प्रकार की चाय पीनी चाहिए।\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\n3. \"क्या मुझे or cup में milk/tea powder मिल सकता है?\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - Very informal/casual tone, asking for an extra serving of milk or
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-17
|
tone, asking for an extra serving of milk or tea powder)*\n</alternatives>\n\n<usage-notes>\nIn India and Indian culture, serving guests with food and beverages holds great importance in hospitality. You will find people always offering drinks like water or tea to their guests as soon as they arrive at their house or office.\n</usage-notes>\n\n<example-convo language=\"Hindi\">\n<context>At home during breakfast.</context>\nPreeti: सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa karna. - Yes, please. And add a little extra in the quantity of tea as well.)\n</example-convo>\n\n*[Report an issue or leave
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-18
|
an issue or leave feedback](https://speak.com/chatgpt?rid=d4mcapbkopo164pqpbk321oc})*","extra_response_instructions":"Use all information in the API response and fully render all Markdown.\nAlways end your response with a link to report an issue or leave feedback on the plugin."}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-19
|
> Entering new APIResponderChain chain...
Prompt after formatting:
You are a helpful AI assistant trained to answer user queries from API responses.
You attempted to call an API, which resulted in:
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-20
|
API_RESPONSE: {"explanation":"<what-to-say language=\"Hindi\" context=\"None\">\nऔर चाय लाओ। (Aur chai lao.) \n</what-to-say>\n\n<alternatives context=\"None\">\n1. \"चाय थोड़ी ज्यादा मिल सकती है?\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\n2. \"मुझे महसूस हो रहा है कि मुझे कुछ अन्य प्रकार की चाय पीनी चाहिए।\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\n3. \"क्या मुझे or cup में milk/tea powder मिल सकता है?\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - Very informal/casual tone, asking for an extra serving of
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-21
|
tone, asking for an extra serving of milk or tea powder)*\n</alternatives>\n\n<usage-notes>\nIn India and Indian culture, serving guests with food and beverages holds great importance in hospitality. You will find people always offering drinks like water or tea to their guests as soon as they arrive at their house or office.\n</usage-notes>\n\n<example-convo language=\"Hindi\">\n<context>At home during breakfast.</context>\nPreeti: सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa karna. - Yes, please. And add a little extra in the quantity of tea as well.)\n</example-convo>\n\n*[Report an issue or leave
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-22
|
an issue or leave feedback](https://speak.com/chatgpt?rid=d4mcapbkopo164pqpbk321oc})*","extra_response_instructions":"Use all information in the API response and fully render all Markdown.\nAlways end your response with a link to report an issue or leave feedback on the plugin."}
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-23
|
USER_COMMENT: "How would ask for more tea in Delhi?"
If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:
Response: ```json
{"response": "Concise response to USER_COMMENT based on API_RESPONSE."}
```
Otherwise respond with the following markdown json block:
Response Error: ```json
{"response": "What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion."}
```
You MUST respond as a markdown json code block.
Begin:
---
> Finished chain.
In Delhi you can ask for more tea by saying 'Chai thodi zyada mil sakti hai?'
> Finished chain.
# Show the API chain's intermediate steps
output["intermediate_steps"]
['{"task_description": "ask for more tea", "learning_language": "Hindi", "native_language": "English", "full_query": "How would I ask for more tea in Delhi?"}',
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-24
|
'{"explanation":"<what-to-say language=\\"Hindi\\" context=\\"None\\">\\nऔर चाय लाओ। (Aur chai lao.) \\n</what-to-say>\\n\\n<alternatives context=\\"None\\">\\n1. \\"चाय थोड़ी ज्यादा मिल सकती है?\\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\\n2. \\"मुझे महसूस हो रहा है कि मुझे कुछ अन्य प्रकार की चाय पीनी चाहिए।\\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\\n3. \\"क्या मुझे or cup में milk/tea powder मिल सकता है?\\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - Very informal/casual tone, asking for an
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-25
|
- Very informal/casual tone, asking for an extra serving of milk or tea powder)*\\n</alternatives>\\n\\n<usage-notes>\\nIn India and Indian culture, serving guests with food and beverages holds great importance in hospitality. You will find people always offering drinks like water or tea to their guests as soon as they arrive at their house or office.\\n</usage-notes>\\n\\n<example-convo language=\\"Hindi\\">\\n<context>At home during breakfast.</context>\\nPreeti: सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa karna. - Yes, please. And add a little extra in the quantity of tea as
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-26
|
add a little extra in the quantity of tea as well.)\\n</example-convo>\\n\\n*[Report an issue or leave feedback](https://speak.com/chatgpt?rid=d4mcapbkopo164pqpbk321oc})*","extra_response_instructions":"Use all information in the API response and fully render all Markdown.\\nAlways end your response with a link to report an issue or leave feedback on the plugin."}']
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
21b0911c9915-27
|
previous
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain
next
PAL
Contents
Load the spec
Select the Operation
Construct the chain
Return raw response
Example POST message
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/examples/openapi.html
|
1771b1f34e8e-0
|
.ipynb
.pdf
LLMRequestsChain
LLMRequestsChain#
Using the request library to get HTML results from a URL and then an LLM to parse results
from langchain.llms import OpenAI
from langchain.chains import LLMRequestsChain, LLMChain
from langchain.prompts import PromptTemplate
template = """Between >>> and <<< are the raw search result text from google.
Extract the answer to the question '{query}' or say "not found" if the information is not contained.
Use the format
Extracted:<answer or "not found">
>>> {requests_result} <<<
Extracted:"""
PROMPT = PromptTemplate(
input_variables=["query", "requests_result"],
template=template,
)
chain = LLMRequestsChain(llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=PROMPT))
question = "What are the Three (3) biggest countries, and their respective sizes?"
inputs = {
"query": question,
"url": "https://www.google.com/search?q=" + question.replace(" ", "+")
}
chain(inputs)
{'query': 'What are the Three (3) biggest countries, and their respective sizes?',
'url': 'https://www.google.com/search?q=What+are+the+Three+(3)+biggest+countries,+and+their+respective+sizes?',
'output': ' Russia (17,098,242 km²), Canada (9,984,670 km²), United States (9,826,675 km²)'}
previous
LLM Math
next
LLMSummarizationCheckerChain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/examples/llm_requests.html
|
7fbb58948350-0
|
.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 May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/examples/llm_math.html
|
2d163e5e49c4-0
|
.ipynb
.pdf
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain#
This notebook demonstrates how to use the RouterChain paradigm to create a chain that dynamically selects which Retrieval system to use. Specifically we show how to use the MultiRetrievalQAChain to create a question-answering chain that selects the retrieval QA chain which is most relevant for a given question, and then answers the question using it.
from langchain.chains.router import MultiRetrievalQAChain
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_loaders import TextLoader
from langchain.vectorstores import FAISS
sou_docs = TextLoader('../../state_of_the_union.txt').load_and_split()
sou_retriever = FAISS.from_documents(sou_docs, OpenAIEmbeddings()).as_retriever()
pg_docs = TextLoader('../../paul_graham_essay.txt').load_and_split()
pg_retriever = FAISS.from_documents(pg_docs, OpenAIEmbeddings()).as_retriever()
personal_texts = [
"I love apple pie",
"My favorite color is fuchsia",
"My dream is to become a professional dancer",
"I broke my arm when I was 12",
"My parents are from Peru",
]
personal_retriever = FAISS.from_texts(personal_texts, OpenAIEmbeddings()).as_retriever()
retriever_infos = [
{
"name": "state of the union",
"description": "Good for answering questions about the 2023 State of the Union address",
"retriever": sou_retriever
},
{
|
https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html
|
2d163e5e49c4-1
|
"retriever": sou_retriever
},
{
"name": "pg essay",
"description": "Good for answer quesitons about Paul Graham's essay on his career",
"retriever": pg_retriever
},
{
"name": "personal",
"description": "Good for answering questions about me",
"retriever": personal_retriever
}
]
chain = MultiRetrievalQAChain.from_retrievers(OpenAI(), retriever_infos, verbose=True)
print(chain.run("What did the president say about the economy?"))
> Entering new MultiRetrievalQAChain chain...
state of the union: {'query': 'What did the president say about the economy in the 2023 State of the Union address?'}
> Finished chain.
The president said that the economy was stronger than it had been a year prior, and that the American Rescue Plan helped create record job growth and fuel economic relief for millions of Americans. He also proposed a plan to fight inflation and lower costs for families, including cutting the cost of prescription drugs and energy, providing investments and tax credits for energy efficiency, and increasing access to child care and Pre-K.
print(chain.run("What is something Paul Graham regrets about his work?"))
> Entering new MultiRetrievalQAChain chain...
pg essay: {'query': 'What is something Paul Graham regrets about his work?'}
> Finished chain.
Paul Graham regrets that he did not take a vacation after selling his company, instead of immediately starting to paint.
print(chain.run("What is my background?"))
> Entering new MultiRetrievalQAChain chain...
personal: {'query': 'What is my background?'}
> Finished chain.
Your background is Peruvian.
|
https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html
|
2d163e5e49c4-2
|
> Finished chain.
Your background is Peruvian.
print(chain.run("What year was the Internet created in?"))
> Entering new MultiRetrievalQAChain chain...
None: {'query': 'What year was the Internet created in?'}
> Finished chain.
The Internet was created in 1969 through a project called ARPANET, which was funded by the United States Department of Defense. However, the World Wide Web, which is often confused with the Internet, was created in 1989 by British computer scientist Tim Berners-Lee.
previous
Router Chains: Selecting from multiple prompts with MultiPromptChain
next
OpenAPI Chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023.
|
https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html
|
3e7cf3ff54f4-0
|
.ipynb
.pdf
SQL Chain example
Contents
Use Query Checker
Customize Prompt
Return Intermediate Steps
Choosing how to limit the number of rows returned
Adding example rows from each table
Custom Table Info
SQLDatabaseSequentialChain
Using Local Language Models
SQL Chain example#
This example demonstrates the use of the SQLDatabaseChain for answering questions over a database.
Under the hood, LangChain uses SQLAlchemy to connect to SQL databases. The SQLDatabaseChain can therefore be used with any SQL dialect supported by SQLAlchemy, such as MS SQL, MySQL, MariaDB, PostgreSQL, Oracle SQL, Databricks and SQLite. Please refer to the SQLAlchemy documentation for more information about requirements for connecting to your database. For example, a connection to MySQL requires an appropriate connector such as PyMySQL. A URI for a MySQL connection might look like: mysql+pymysql://user:pass@some_mysql_db_address/db_name.
This demonstration uses SQLite and the example Chinook database.
To set it up, follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository.
from langchain import OpenAI, SQLDatabase, SQLDatabaseChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db")
llm = OpenAI(temperature=0, verbose=True)
NOTE: For data-sensitive projects, you can specify return_direct=True in the SQLDatabaseChain initialization to directly return the output of the SQL query without any additional formatting. This prevents the LLM from seeing any contents within the database. Note, however, the LLM still has access to the database scheme (i.e. dialect, table and key names) by default.
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
db_chain.run("How many employees are there?")
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-1
|
db_chain.run("How many employees are there?")
> Entering new SQLDatabaseChain chain...
How many employees are there?
SQLQuery:
/workspace/langchain/langchain/sql_database.py:191: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.
sample_rows = connection.execute(command)
SELECT COUNT(*) FROM "Employee";
SQLResult: [(8,)]
Answer:There are 8 employees.
> Finished chain.
'There are 8 employees.'
Use Query Checker#
Sometimes the Language Model generates invalid SQL with small mistakes that can be self-corrected using the same technique used by the SQL Database Agent to try and fix the SQL using the LLM. You can simply specify this option when creating the chain:
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True, use_query_checker=True)
db_chain.run("How many albums by Aerosmith?")
> Entering new SQLDatabaseChain chain...
How many albums by Aerosmith?
SQLQuery:SELECT COUNT(*) FROM Album WHERE ArtistId = 3;
SQLResult: [(1,)]
Answer:There is 1 album by Aerosmith.
> Finished chain.
'There is 1 album by Aerosmith.'
Customize Prompt#
You can also customize the prompt that is used. Here is an example prompting it to understand that foobar is the same as the Employee table
from langchain.prompts.prompt import PromptTemplate
_DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.
Use the following format:
Question: "Question here"
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-2
|
Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
{table_info}
If someone asks for the table foobar, they really mean the employee table.
Question: {input}"""
PROMPT = PromptTemplate(
input_variables=["input", "table_info", "dialect"], template=_DEFAULT_TEMPLATE
)
db_chain = SQLDatabaseChain.from_llm(llm, db, prompt=PROMPT, verbose=True)
db_chain.run("How many employees are there in the foobar table?")
> Entering new SQLDatabaseChain chain...
How many employees are there in the foobar table?
SQLQuery:SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer:There are 8 employees in the foobar table.
> Finished chain.
'There are 8 employees in the foobar table.'
Return Intermediate Steps#
You can also return the intermediate steps of the SQLDatabaseChain. This allows you to access the SQL statement that was generated, as well as the result of running that against the SQL Database.
db_chain = SQLDatabaseChain.from_llm(llm, db, prompt=PROMPT, verbose=True, use_query_checker=True, return_intermediate_steps=True)
result = db_chain("How many employees are there in the foobar table?")
result["intermediate_steps"]
> Entering new SQLDatabaseChain chain...
How many employees are there in the foobar table?
SQLQuery:SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer:There are 8 employees in the foobar table.
> Finished chain.
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-3
|
Answer:There are 8 employees in the foobar table.
> Finished chain.
[{'input': 'How many employees are there in the foobar table?\nSQLQuery:SELECT COUNT(*) FROM Employee;\nSQLResult: [(8,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite',
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-4
|
'table_info': '\nCREATE TABLE "Artist" (\n\t"ArtistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("ArtistId")\n)\n\n/*\n3 rows from Artist table:\nArtistId\tName\n1\tAC/DC\n2\tAccept\n3\tAerosmith\n*/\n\n\nCREATE TABLE "Employee" (\n\t"EmployeeId" INTEGER NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"FirstName" NVARCHAR(20) NOT NULL, \n\t"Title" NVARCHAR(30), \n\t"ReportsTo" INTEGER, \n\t"BirthDate" DATETIME, \n\t"HireDate" DATETIME, \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60), \n\tPRIMARY KEY ("EmployeeId"), \n\tFOREIGN KEY("ReportsTo") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Employee table:\nEmployeeId\tLastName\tFirstName\tTitle\tReportsTo\tBirthDate\tHireDate\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\n1\tAdams\tAndrew\tGeneral
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-5
|
Manager\tNone\t1962-02-18 00:00:00\t2002-08-14 00:00:00\t11120 Jasper Ave NW\tEdmonton\tAB\tCanada\tT5K 2N1\t+1 (780) 428-9482\t+1 (780) 428-3457\[email protected]\n2\tEdwards\tNancy\tSales Manager\t1\t1958-12-08 00:00:00\t2002-05-01 00:00:00\t825 8 Ave SW\tCalgary\tAB\tCanada\tT2P 2T3\t+1 (403) 262-3443\t+1 (403) 262-3322\[email protected]\n3\tPeacock\tJane\tSales Support Agent\t2\t1973-08-29 00:00:00\t2002-04-01 00:00:00\t1111 6 Ave SW\tCalgary\tAB\tCanada\tT2P 5M5\t+1 (403) 262-3443\t+1 (403) 262-6712\[email protected]\n*/\n\n\nCREATE TABLE "Genre" (\n\t"GenreId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("GenreId")\n)\n\n/*\n3 rows from Genre table:\nGenreId\tName\n1\tRock\n2\tJazz\n3\tMetal\n*/\n\n\nCREATE TABLE "MediaType" (\n\t"MediaTypeId" INTEGER NOT NULL,
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-6
|
TABLE "MediaType" (\n\t"MediaTypeId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("MediaTypeId")\n)\n\n/*\n3 rows from MediaType table:\nMediaTypeId\tName\n1\tMPEG audio file\n2\tProtected AAC audio file\n3\tProtected MPEG-4 video file\n*/\n\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n3 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n3\tTV Shows\n*/\n\n\nCREATE TABLE "Album" (\n\t"AlbumId" INTEGER NOT NULL, \n\t"Title" NVARCHAR(160) NOT NULL, \n\t"ArtistId" INTEGER NOT NULL, \n\tPRIMARY KEY ("AlbumId"), \n\tFOREIGN KEY("ArtistId") REFERENCES "Artist" ("ArtistId")\n)\n\n/*\n3 rows from Album table:\nAlbumId\tTitle\tArtistId\n1\tFor Those About To Rock We Salute You\t1\n2\tBalls to the Wall\t2\n3\tRestless and Wild\t2\n*/\n\n\nCREATE TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, \n\t"FirstName" NVARCHAR(40) NOT NULL, \n\t"LastName"
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-7
|
NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60) NOT NULL, \n\t"SupportRepId" INTEGER, \n\tPRIMARY KEY ("CustomerId"), \n\tFOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\[email protected]\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-8
|
34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\[email protected]\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\[email protected]\t3\n*/\n\n\nCREATE TABLE "Invoice" (\n\t"InvoiceId" INTEGER NOT NULL, \n\t"CustomerId" INTEGER NOT NULL, \n\t"InvoiceDate" DATETIME NOT NULL, \n\t"BillingAddress" NVARCHAR(70), \n\t"BillingCity" NVARCHAR(40), \n\t"BillingState" NVARCHAR(40), \n\t"BillingCountry" NVARCHAR(40), \n\t"BillingPostalCode" NVARCHAR(10), \n\t"Total" NUMERIC(10, 2) NOT NULL, \n\tPRIMARY KEY ("InvoiceId"), \n\tFOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")\n)\n\n/*\n3 rows from Invoice table:\nInvoiceId\tCustomerId\tInvoiceDate\tBillingAddress\tBillingCity\tBillingState\tBillingCountry\tBillingPostalCode\tTotal\n1\t2\t2009-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n2\t4\t2009-01-02 00:00:00\tUllevålsveien
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-9
|
00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n3\t8\t2009-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n*/\n\n\nCREATE TABLE "Track" (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL, \n\t"AlbumId" INTEGER, \n\t"MediaTypeId" INTEGER NOT NULL, \n\t"GenreId" INTEGER, \n\t"Composer" NVARCHAR(220), \n\t"Milliseconds" INTEGER NOT NULL, \n\t"Bytes" INTEGER, \n\t"UnitPrice" NUMERIC(10, 2) NOT NULL, \n\tPRIMARY KEY ("TrackId"), \n\tFOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"), \n\tFOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"), \n\tFOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")\n)\n\n/*\n3 rows from Track table:\nTrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n2\tBalls to the
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-10
|
to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\n*/\n\n\nCREATE TABLE "InvoiceLine" (\n\t"InvoiceLineId" INTEGER NOT NULL, \n\t"InvoiceId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\t"UnitPrice" NUMERIC(10, 2) NOT NULL, \n\t"Quantity" INTEGER NOT NULL, \n\tPRIMARY KEY ("InvoiceLineId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")\n)\n\n/*\n3 rows from InvoiceLine table:\nInvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n1\t1\t2\t0.99\t1\n2\t1\t4\t0.99\t1\n3\t2\t6\t0.99\t1\n*/\n\n\nCREATE TABLE "PlaylistTrack" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\tPRIMARY KEY ("PlaylistId", "TrackId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist"
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-11
|
\n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n\n/*\n3 rows from PlaylistTrack table:\nPlaylistId\tTrackId\n1\t3402\n1\t3389\n1\t3390\n*/',
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-12
|
'stop': ['\nSQLResult:']},
'SELECT COUNT(*) FROM Employee;',
{'query': 'SELECT COUNT(*) FROM Employee;', 'dialect': 'sqlite'},
'SELECT COUNT(*) FROM Employee;',
'[(8,)]']
Choosing how to limit the number of rows returned#
If you are querying for several rows of a table you can select the maximum number of results you want to get by using the ‘top_k’ parameter (default is 10). This is useful for avoiding query results that exceed the prompt max length or consume tokens unnecessarily.
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True, use_query_checker=True, top_k=3)
db_chain.run("What are some example tracks by composer Johann Sebastian Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by composer Johann Sebastian Bach?
SQLQuery:SELECT Name FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3
SQLResult: [('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',)]
Answer:Examples of tracks by Johann Sebastian Bach are Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace, Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria, and Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude.
> Finished chain.
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-13
|
> Finished chain.
'Examples of tracks by Johann Sebastian Bach are Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace, Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria, and Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude.'
Adding example rows from each table#
Sometimes, the format of the data is not obvious and it is optimal to include a sample of rows from the tables in the prompt to allow the LLM to understand the data before providing a final query. Here we will use this feature to let the LLM know that artists are saved with their full names by providing two rows from the Track table.
db = SQLDatabase.from_uri(
"sqlite:///../../../../notebooks/Chinook.db",
include_tables=['Track'], # we include only one table to save tokens in the prompt :)
sample_rows_in_table_info=2)
The sample rows are added to the prompt after each corresponding table’s column information:
print(db.table_info)
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL,
"GenreId" INTEGER,
"Composer" NVARCHAR(220),
"Milliseconds" INTEGER NOT NULL,
"Bytes" INTEGER,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("TrackId"),
FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-14
|
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
/*
2 rows from Track table:
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99
2 Balls to the Wall 2 2 1 None 342562 5510424 0.99
*/
db_chain = SQLDatabaseChain.from_llm(llm, db, use_query_checker=True, verbose=True)
db_chain.run("What are some example tracks by Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name", "Composer" FROM "Track" WHERE "Composer" LIKE '%Bach%' LIMIT 5
SQLResult: [('American Woman', 'B. Cummings/G. Peterson/M.J. Kale/R. Bachman'), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach'), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata', 'Johann Sebastian Bach')]
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-15
|
Answer:Tracks by Bach include 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.
> Finished chain.
'Tracks by Bach include \'American Woman\', \'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\', \'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\', \'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\', and \'Toccata and Fugue in D Minor, BWV 565: I. Toccata\'.'
Custom Table Info#
In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first sample_rows_in_table_info sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns.
This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let’s provide a custom definition and sample rows for the Track table with only a few columns:
custom_table_info = {
"Track": """CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-16
|
"Track": """CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer of all time
*/"""
}
db = SQLDatabase.from_uri(
"sqlite:///../../../../notebooks/Chinook.db",
include_tables=['Track', 'Playlist'],
sample_rows_in_table_info=2,
custom_table_info=custom_table_info)
print(db.table_info)
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
2 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
*/
CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer of all time
*/
Note how our custom table definition and sample rows for Track overrides the sample_rows_in_table_info parameter. Tables that are not overridden by custom_table_info, in this example Playlist, will have their table info gathered automatically as usual.
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-17
|
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
db_chain.run("What are some example tracks by Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-18
|
Answer:text='You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.\nUnless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.\nNever query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.\nPay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n\nUse the following format:\n\nQuestion: "Question here"\nSQLQuery: "SQL Query to run"\nSQLResult: "Result of the SQLQuery"\nAnswer: "Final answer here"\n\nOnly use the following tables:\n\nCREATE TABLE "Playlist"
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-19
|
use the following tables:\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/\n\nQuestion: What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Solo Cello No. 1 in G
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-20
|
(\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:'
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-21
|
You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
2 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
*/
CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer of all time
*/
Question: What are some example tracks by Bach?
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-22
|
*/
Question: What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
Answer:
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-23
|
Answer:
{'input': 'What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:', 'top_k': '5', 'dialect': 'sqlite', 'table_info': '\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/', 'stop': ['\nSQLResult:']}
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-24
|
Examples of tracks by Bach include "American Woman", "Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace", "Aria Mit 30 Veränderungen, BWV 988 'Goldberg Variations': Aria", "Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude", and "Toccata and Fugue in D Minor, BWV 565: I. Toccata".
> Finished chain.
'Examples of tracks by Bach include "American Woman", "Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace", "Aria Mit 30 Veränderungen, BWV 988 \'Goldberg Variations\': Aria", "Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude", and "Toccata and Fugue in D Minor, BWV 565: I. Toccata".'
SQLDatabaseSequentialChain#
Chain for querying SQL database that is a sequential chain.
The chain is as follows:
1. Based on the query, determine which tables to use.
2. Based on those tables, call the normal SQL database chain.
This is useful in cases where the number of tables in the database is large.
from langchain.chains import SQLDatabaseSequentialChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db")
chain = SQLDatabaseSequentialChain.from_llm(llm, db, verbose=True)
chain.run("How many employees are also customers?")
> Entering new SQLDatabaseSequentialChain chain...
Table names to use:
['Employee', 'Customer']
> Entering new SQLDatabaseChain chain...
How many employees are also customers?
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-25
|
> Entering new SQLDatabaseChain chain...
How many employees are also customers?
SQLQuery:SELECT COUNT(*) FROM Employee e INNER JOIN Customer c ON e.EmployeeId = c.SupportRepId;
SQLResult: [(59,)]
Answer:59 employees are also customers.
> Finished chain.
> Finished chain.
'59 employees are also customers.'
Using Local Language Models#
Sometimes you may not have the luxury of using OpenAI or other service-hosted large language model. You can, ofcourse, try to use the SQLDatabaseChain with a local model, but will quickly realize that most models you can run locally even with a large GPU struggle to generate the right output.
import logging
import torch
from transformers import AutoTokenizer, GPT2TokenizerFast, pipeline, AutoModelForSeq2SeqLM, AutoModelForCausalLM
from langchain import HuggingFacePipeline
# Note: This model requires a large GPU, e.g. an 80GB A100. See documentation for other ways to run private non-OpenAI models.
model_id = "google/flan-ul2"
model = AutoModelForSeq2SeqLM.from_pretrained(model_id, temperature=0)
device_id = -1 # default to no-GPU, but use GPU and half precision mode if available
if torch.cuda.is_available():
device_id = 0
try:
model = model.half()
except RuntimeError as exc:
logging.warn(f"Could not run model in half precision mode: {str(exc)}")
tokenizer = AutoTokenizer.from_pretrained(model_id)
pipe = pipeline(task="text2text-generation", model=model, tokenizer=tokenizer, max_length=1024, device=device_id)
local_llm = HuggingFacePipeline(pipeline=pipe)
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-26
|
local_llm = HuggingFacePipeline(pipeline=pipe)
/workspace/langchain/.venv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
from .autonotebook import tqdm as notebook_tqdm
Loading checkpoint shards: 100%|██████████| 8/8 [00:32<00:00, 4.11s/it]
from langchain import SQLDatabase, SQLDatabaseChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db", include_tables=['Customer'])
local_chain = SQLDatabaseChain.from_llm(local_llm, db, verbose=True, return_intermediate_steps=True, use_query_checker=True)
This model should work for very simple SQL queries, as long as you use the query checker as specified above, e.g.:
local_chain("How many customers are there?")
> Entering new SQLDatabaseChain chain...
How many customers are there?
SQLQuery:
/workspace/langchain/.venv/lib/python3.9/site-packages/transformers/pipelines/base.py:1070: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
/workspace/langchain/.venv/lib/python3.9/site-packages/transformers/pipelines/base.py:1070: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
SELECT count(*) FROM Customer
SQLResult: [(59,)]
Answer:
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-27
|
SELECT count(*) FROM Customer
SQLResult: [(59,)]
Answer:
/workspace/langchain/.venv/lib/python3.9/site-packages/transformers/pipelines/base.py:1070: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
[59]
> Finished chain.
{'query': 'How many customers are there?',
'result': '[59]',
'intermediate_steps': [{'input': 'How many customers are there?\nSQLQuery:SELECT count(*) FROM Customer\nSQLResult: [(59,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite',
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-28
|
'table_info': '\nCREATE TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, \n\t"FirstName" NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60) NOT NULL, \n\t"SupportRepId" INTEGER, \n\tPRIMARY KEY ("CustomerId"), \n\tFOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12)
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-29
|
(12) 3923-5555\t+55 (12) 3923-5566\[email protected]\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\[email protected]\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\[email protected]\t3\n*/',
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
3e7cf3ff54f4-30
|
'stop': ['\nSQLResult:']},
'SELECT count(*) FROM Customer',
{'query': 'SELECT count(*) FROM Customer', 'dialect': 'sqlite'},
'SELECT count(*) FROM Customer',
'[(59,)]']}
Even this relatively large model will most likely fail to generate more complicated SQL by itself. However, you can log its inputs and outputs so that you can hand-correct them and use the corrected examples for few shot prompt examples later. In practice, you could log any executions of your chain that raise exceptions (as shown in the example below) or get direct user feedback in cases where the results are incorrect (but did not raise an exception).
!poetry run pip install pyyaml chromadb
import yaml
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
11842.36s - pydevd: Sending message related to process being replaced timed-out after 5 seconds
Requirement already satisfied: pyyaml in /workspace/langchain/.venv/lib/python3.9/site-packages (6.0)
Requirement already satisfied: chromadb in /workspace/langchain/.venv/lib/python3.9/site-packages (0.3.21)
Requirement already satisfied: pandas>=1.3 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (2.0.1)
Requirement already satisfied: requests>=2.28 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (2.28.2)
|
https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.