id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
f2a14555186f-1 | synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)
# This is an LLMChain to write a review of a play given a synopsis.
llm = OpenAI(temperature=.7)
template = """You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.
Play Synopsis:
{synopsis}
R... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-2 | The play follows the couple as they struggle to stay together and battle the forces that threaten to tear them apart. Despite the tragedy that awaits them, they remain devoted to one another and fight to keep their love alive. In the end, the couple must decide whether to take a chance on their future together or succu... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-3 | The play's setting of the beach at sunset adds a touch of poignancy and romanticism to the story, while the mysterious figure serves to keep the audience enthralled. Overall, Tragedy at Sunset on the Beach is an engaging and thought-provoking play that is sure to leave audiences feeling inspired and hopeful.
Sequential... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-4 | Play Synopsis:
{synopsis}
Review from a New York Times play critic of the above play:"""
prompt_template = PromptTemplate(input_variables=["synopsis"], template=template)
review_chain = LLMChain(llm=llm, prompt=prompt_template, output_key="review")
# This is the overall chain where we run these two chains in sequence.
... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-5 | 'era': 'Victorian England',
'synopsis': "\n\nThe play follows the story of John, a young man from a wealthy Victorian family, who dreams of a better life for himself. He soon meets a beautiful young woman named Mary, who shares his dream. The two fall in love and decide to elope and start a new life together.\n\nOn th... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-6 | 'review': "\n\nThe latest production from playwright X is a powerful and heartbreaking story of love and loss set against the backdrop of 19th century England. The play follows John, a young man from a wealthy Victorian family, and Mary, a beautiful young woman with whom he falls in love. The two decide to elope and st... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-7 | from langchain.memory import SimpleMemory
llm = OpenAI(temperature=.7)
template = """You are a social media manager for a theater company. Given the title of play, the era it is set in, the date,time and location, the synopsis of the play, and the review of the play, it is your job to write a social media post for tha... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
f2a14555186f-8 | 'location': 'Theater in the Park',
'social_post_text': "\nSpend your Christmas night with us at Theater in the Park and experience the heartbreaking story of love and loss that is 'A Walk on the Beach'. Set in Victorian England, this romantic tragedy follows the story of Frances and Edward, a young couple whose love i... | https://python.langchain.com/en/latest/modules/chains/generic/sequential_chains.html |
548461147591-0 | .ipynb
.pdf
LLM Chain
Contents
LLM Chain
Additional ways of running LLM Chain
Parsing the outputs
Initialize from string
LLM Chain#
LLMChain is perhaps one of the most popular ways of querying an LLM object. It formats the prompt template using the input key values provided (and also memory key values, if available),... | https://python.langchain.com/en/latest/modules/chains/generic/llm_chain.html |
548461147591-1 | llm_chain.generate(input_list)
LLMResult(generations=[[Generation(text='\n\nSocktastic!', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nTechCore Solutions.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nFootwear Factory.', generation_info={'... | https://python.langchain.com/en/latest/modules/chains/generic/llm_chain.html |
548461147591-2 | template = """List all the colors in a rainbow"""
prompt = PromptTemplate(template=template, input_variables=[], output_parser=output_parser)
llm_chain = LLMChain(prompt=prompt, llm=llm)
llm_chain.predict()
'\n\nRed, orange, yellow, green, blue, indigo, violet'
With predict_and_parser:
llm_chain.predict_and_parse()
['R... | https://python.langchain.com/en/latest/modules/chains/generic/llm_chain.html |
fc1037d7c8b8-0 | .rst
.pdf
Vectorstores
Vectorstores#
Note
Conceptual Guide
Vectorstores are one of the most important components of building indexes.
For an introduction to vectorstores and generic functionality see:
Getting Started
We also have documentation for all the types of vectorstores that are supported.
Please see below for t... | https://python.langchain.com/en/latest/modules/indexes/vectorstores.html |
5ca65b9282a9-0 | .rst
.pdf
Retrievers
Retrievers#
Note
Conceptual Guide
The retriever interface is a generic interface that makes it easy to combine documents with
language models. This interface exposes a get_relevant_documents method which takes in a query
(a string) and returns a list of documents.
Please see below for a list of all... | https://python.langchain.com/en/latest/modules/indexes/retrievers.html |
ae2c0472d555-0 | .ipynb
.pdf
Getting Started
Contents
One Line Index Creation
Walkthrough
Getting Started#
LangChain primarily focuses on constructing indexes with the goal of using them as a Retriever. In order to best understand what this means, it’s worth highlighting what the base Retriever interface is. The BaseRetriever class i... | https://python.langchain.com/en/latest/modules/indexes/getting_started.html |
ae2c0472d555-1 | Create a Retriever from that index
Create a question answering chain
Ask questions!
Each of the steps has multiple sub steps and potential configurations. In this notebook we will primarily focus on (1). We will start by showing the one-liner for doing so, but then break down what is actually going on.
First, let’s imp... | https://python.langchain.com/en/latest/modules/indexes/getting_started.html |
ae2c0472d555-2 | index.query_with_sources(query)
{'question': 'What did the president say about Ketanji Brown Jackson',
'answer': " The president said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson, one of the nation's top legal minds, to continue Justice Breyer's legacy of excellence, and that she has received... | https://python.langchain.com/en/latest/modules/indexes/getting_started.html |
ae2c0472d555-3 | We will then select which embeddings we want to use.
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
We now create the vectorstore to use as the index.
from langchain.vectorstores import Chroma
db = Chroma.from_documents(texts, embeddings)
Running Chroma using direct local API.
Using D... | https://python.langchain.com/en/latest/modules/indexes/getting_started.html |
ae2c0472d555-4 | )
Hopefully this highlights what is going on under the hood of VectorstoreIndexCreator. While we think it’s important to have a simple way to create indexes, we also think it’s important to understand what’s going on under the hood.
previous
Indexes
next
Document Loaders
Contents
One Line Index Creation
Walkthrough... | https://python.langchain.com/en/latest/modules/indexes/getting_started.html |
6ed7c776f6a6-0 | .rst
.pdf
Text Splitters
Text Splitters#
Note
Conceptual Guide
When you want to deal with long pieces of text, it is necessary to split up that text into chunks.
As simple as this sounds, there is a lot of potential complexity here. Ideally, you want to keep the semantically related pieces of text together. What “seman... | https://python.langchain.com/en/latest/modules/indexes/text_splitters.html |
6ed7c776f6a6-1 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/indexes/text_splitters.html |
d87d02b2a109-0 | .rst
.pdf
Document Loaders
Contents
Transform loaders
Public dataset or service loaders
Proprietary dataset or service loaders
Document Loaders#
Note
Conceptual Guide
Combining language models with your own text data is a powerful way to differentiate them.
The first step in doing this is to load the data into “Docum... | https://python.langchain.com/en/latest/modules/indexes/document_loaders.html |
d87d02b2a109-1 | iFixit
IMSDb
MediaWikiDump
Wikipedia
YouTube transcripts
Proprietary dataset or service loaders#
These datasets and services are not from the public domain.
These loaders mostly transform data from specific formats of applications or cloud services,
for example Google Drive.
We need access tokens and sometime other par... | https://python.langchain.com/en/latest/modules/indexes/document_loaders.html |
43ab4d46f786-0 | .ipynb
.pdf
Self-querying
Contents
Creating a Pinecone index
Creating our self-querying retriever
Testing it out
Filter k
Self-querying#
In the notebook we’ll demo the SelfQueryRetriever, which, as the name suggests, has the ability to query itself. Specifically, given any natural language query, the retriever uses a... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
43ab4d46f786-1 | from langchain.schema import Document
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Pinecone
embeddings = OpenAIEmbeddings()
# create new index
pinecone.create_index("langchain-self-retriever-demo", dimension=1536)
docs = [
Document(page_content="A bunch of scientists b... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
43ab4d46f786-2 | )
Creating our self-querying retriever#
Now we can instantiate our retriever. To do this we’ll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents.
from langchain.llms import OpenAI
from langchain.retrievers.self_query.base impor... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
43ab4d46f786-3 | Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'year': 1995.0}),
Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'director': 'Satoshi Kon', 'rating': 8.6, 'year': 2... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
43ab4d46f786-4 | [Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'director': 'Greta Gerwig', 'rating': 8.3, 'year': 2019.0})]
# This example specifies a composite filter
retriever.get_relevant_documents("What's a highly rated (above 8.5) science fiction film?")
quer... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
43ab4d46f786-5 | We can also use the self query retriever to specify k: the number of documents to fetch.
We can do this by passing enable_limit=True to the constructor.
retriever = SelfQueryRetriever.from_llm(
llm,
vectorstore,
document_content_description,
metadata_field_info,
enable_limit=True,
verbose=Tr... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html |
84704f9ddf9b-0 | .ipynb
.pdf
VectorStore
Contents
Maximum Marginal Relevance Retrieval
Similarity Score Threshold Retrieval
Specifying top k
VectorStore#
The index - and therefore the retriever - that LangChain has the most support for is the VectorStoreRetriever. As the name suggests, this retriever is backed heavily by a VectorStor... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vectorstore.html |
84704f9ddf9b-1 | docs = retriever.get_relevant_documents("what did he say abotu ketanji brown jackson")
Specifying top k#
You can also specify search kwargs like k to use when doing retrieval.
retriever = db.as_retriever(search_kwargs={"k": 1})
docs = retriever.get_relevant_documents("what did he say abotu ketanji brown jackson")
len(d... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vectorstore.html |
2663f0dba321-0 | .ipynb
.pdf
Pinecone Hybrid Search
Contents
Setup Pinecone
Get embeddings and sparse encoders
Load Retriever
Add texts (if necessary)
Use Retriever
Pinecone Hybrid Search#
Pinecone is a vector database with broad functionality.
This notebook goes over how to use a retriever that under the hood uses Pinecone and Hybri... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
2663f0dba321-1 | pinecone.init(api_key=api_key, enviroment=env)
pinecone.whoami()
WhoAmIResponse(username='load', user_label='label', projectname='load-test')
# create the index
pinecone.create_index(
name = index_name,
dimension = 1536, # dimensionality of dense model
metric = "dotproduct", # sparse values supported only f... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
2663f0dba321-2 | Load Retriever#
We can now construct the retriever!
retriever = PineconeHybridSearchRetriever(embeddings=embeddings, sparse_encoder=bm25_encoder, index=index)
Add texts (if necessary)#
We can optionally add texts to the retriever (if they aren’t already in there)
retriever.add_texts(["foo", "bar", "world", "hello"])
10... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
c563f1ac893d-0 | .ipynb
.pdf
Vespa
Vespa#
Vespa is a fully featured search engine and vector database. It supports vector search (ANN), lexical search, and search in structured data, all in the same query.
This notebook shows how to use Vespa.ai as a LangChain retriever.
In order to create a retriever, we use pyvespa to
create a connec... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vespa.html |
c563f1ac893d-1 | retriever.get_relevant_documents("what is vespa?")
previous
VectorStore
next
Weaviate Hybrid Search
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vespa.html |
86caca60b759-0 | .ipynb
.pdf
SVM
Contents
Create New Retriever with Texts
Use Retriever
SVM#
Support vector machines (SVMs) are a set of supervised learning methods used for classification, regression and outliers detection.
This notebook goes over how to use a retriever that under the hood uses an SVM using scikit-learn package.
Lar... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/svm.html |
a252b67840a3-0 | .ipynb
.pdf
Zep Memory
Contents
Retriever Example
Initialize the Zep Chat Message History Class and add a chat message history to the memory store
Use the Zep Retriever to vector search over the Zep memory
Zep Memory#
Retriever Example#
This notebook demonstrates how to search historical chat message histories using ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-1 | session_id = str(uuid4()) # This is a unique identifier for the user/session
# Set up Zep Chat History. We'll use this to add chat histories to the memory store
zep_chat_history = ZepChatMessageHistory(
session_id=session_id,
url=ZEP_API_URL,
)
# Preload some messages into the memory. The default message windo... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-2 | " Fellowship."
),
},
{
"role": "human",
"content": "Which other women sci-fi writers might I want to read?",
},
{
"role": "ai",
"content": "You might want to read Ursula K. Le Guin or Joanna Russ.",
},
{
"role": "human",
"content": (
... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-3 | url=ZEP_API_URL,
top_k=5,
)
await zep_retriever.aget_relevant_documents("Who wrote Parable of the Sower?")
[Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759001673780126, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-4 | Document(page_content='Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', metadata={'score': 0.7546211059317948, 'uuid': '34678311-0098-4f1a-8fd4-5615ac692deb', 'created_at': '2023-05-25T15:03:30.231427Z', 'role': 'ai', 'token_count': 31}),
Document(page_content='Which... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-5 | Document(page_content="Write a short synopsis of Butler's book, Parable of the Sower. What is it about?", metadata={'score': 0.8857628682610436, 'uuid': 'f6706e8c-6c91-452f-8c1b-9559fd924657', 'created_at': '2023-05-25T15:03:30.265302Z', 'role': 'human', 'token_count': 23}),
Document(page_content='Who was Octavia Butl... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
a252b67840a3-6 | Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7595293992240313, 'uuid': 'f22f2498-6118-4c74-8718-aa89ccd7e3d6', 'created_at': '2023-05-25T15:03:30.261198Z', 'role': 'ai', 'token_count': 18})]
previous
Wikipedia
next
Chains
Contents
Retriever Example
Initializ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/zep_memorystore.html |
eda9700557d0-0 | .ipynb
.pdf
Wikipedia
Contents
Installation
Examples
Running retriever
Question Answering on facts
Wikipedia#
Wikipedia is a multilingual free online encyclopedia written and maintained by a community of volunteers, known as Wikipedians, through open collaboration and using a wiki-based editing system called MediaWik... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
eda9700557d0-1 | 'summary': 'Hunter × Hunter (stylized as HUNTER×HUNTER and pronounced "hunter hunter") is a Japanese manga series written and illustrated by Yoshihiro Togashi. It has been serialized in Shueisha\'s shōnen manga magazine Weekly Shōnen Jump since March 1998, although the manga has frequently gone on extended hiatuses sin... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
eda9700557d0-2 | Hunter was adapted into a 62-episode anime television series produced by Nippon Animation and directed by Kazuhiro Furuhashi, which ran on Fuji Television from October 1999 to March 2001. Three separate original video animations (OVAs) totaling 30 episodes were subsequently produced by Nippon Animation and released in ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
eda9700557d0-3 | Hunter has been a huge critical and financial success and has become one of the best-selling manga series of all time, having over 84 million copies in circulation by July 2022.\n\n'} | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
eda9700557d0-4 | docs[0].page_content[:400] # a content of the Document
'Hunter × Hunter (stylized as HUNTER×HUNTER and pronounced "hunter hunter") is a Japanese manga series written and illustrated by Yoshihiro Togashi. It has been serialized in Shueisha\'s shōnen manga magazine Weekly Shōnen Jump since March 1998, although the mang... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
eda9700557d0-5 | -> **Question**: What is Apify?
**Answer**: Apify is a platform that allows you to easily automate web scraping, data extraction and web automation. It provides a cloud-based infrastructure for running web crawlers and other automation tasks, as well as a web-based tool for building and managing your crawlers. Additio... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/wikipedia.html |
d6fb658dd57d-0 | .ipynb
.pdf
Self-querying with Chroma
Contents
Creating a Chroma vectorstore
Creating our self-querying retriever
Testing it out
Filter k
Self-querying with Chroma#
Chroma is a database for building AI applications with embeddings.
In the notebook we’ll demo the SelfQueryRetriever wrapped around a Chroma vector store... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
d6fb658dd57d-1 | Document(page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them", metadata={"year": 2019, "director": "Greta Gerwig", "rating": 8.3}),
Document(page_content="Toys come alive and have a blast doing so", metadata={"year": 1995, "genre": "animated"}),
Document(page_content... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
d6fb658dd57d-2 | type="float"
),
]
document_content_description = "Brief summary of a movie"
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(llm, vectorstore, document_content_description, metadata_field_info, verbose=True)
Testing it out#
And now we can try actually using our retriever!
# This example only spec... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
d6fb658dd57d-3 | Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'})]
# This example specifies a query and a filter
retriever.get_relevant_documents("Has Greta Gerwig directed any movies about women")
qu... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
d6fb658dd57d-4 | query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')])
[Document(p... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
d6fb658dd57d-5 | Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.2})]
previous
ChatGPT Plugin
next
Cohere Reranker
Contents
Creating a Chroma vectorstore
Creating our self-querying retriever
Testing it out
Filt... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chroma_self_query.html |
36be6b46348a-0 | .ipynb
.pdf
Azure Cognitive Search Retriever
Contents
Set up Azure Cognitive Search
Using the Azure Cognitive Search Retriever
Azure Cognitive Search Retriever#
This notebook shows how to use Azure Cognitive Search (ACS) within LangChain.
Set up Azure Cognitive Search#
To set up ACS, please follow the instrcutions he... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/azure-cognitive-search-retriever.html |
d9ff4168059c-0 | .ipynb
.pdf
Self-querying with Weaviate
Contents
Creating a Weaviate vectorstore
Creating our self-querying retriever
Testing it out
Filter k
Self-querying with Weaviate#
Creating a Weaviate vectorstore#
First we’ll want to create a Weaviate VectorStore and seed it with some data. We’ve created a small demo set of do... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html |
d9ff4168059c-1 | Document(page_content="Toys come alive and have a blast doing so", metadata={"year": 1995, "genre": "animated"}),
Document(page_content="Three men walk into the Zone, three men walk out of the Zone", metadata={"year": 1979, "rating": 9.9, "director": "Andrei Tarkovsky", "genre": "science fiction", "rating": 9.9})
]... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html |
d9ff4168059c-2 | llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(llm, vectorstore, document_content_description, metadata_field_info, verbose=True)
Testing it out#
And now we can try actually using our retriever!
# This example only specifies a relevant query
retriever.get_relevant_documents("What are some movies ab... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html |
d9ff4168059c-3 | We can also use the self query retriever to specify k: the number of documents to fetch.
We can do this by passing enable_limit=True to the constructor.
retriever = SelfQueryRetriever.from_llm(
llm,
vectorstore,
document_content_description,
metadata_field_info,
enable_limit=True,
verbose=Tr... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html |
f0fa91f792ab-0 | .ipynb
.pdf
ElasticSearch BM25
Contents
Create New Retriever
Add texts (if necessary)
Use Retriever
ElasticSearch BM25#
Elasticsearch is a distributed, RESTful search and analytics engine. It provides a distributed, multitenant-capable full-text search engine with an HTTP web interface and schema-free JSON documents.... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/elastic_search_bm25.html |
f0fa91f792ab-1 | # import elasticsearch
# elasticsearch_url="http://localhost:9200"
# retriever = ElasticSearchBM25Retriever(elasticsearch.Elasticsearch(elasticsearch_url), "langchain-index")
Add texts (if necessary)#
We can optionally add texts to the retriever (if they aren’t already in there)
retriever.add_texts(["foo", "bar", "worl... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/elastic_search_bm25.html |
c9abf70b2026-0 | .ipynb
.pdf
kNN
Contents
Create New Retriever with Texts
Use Retriever
kNN#
In statistics, the k-nearest neighbors algorithm (k-NN) is a non-parametric supervised learning method first developed by Evelyn Fix and Joseph Hodges in 1951, and later expanded by Thomas Cover. It is used for classification and regression.
... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/knn.html |
43dc5a00e5e9-0 | .ipynb
.pdf
TF-IDF
Contents
Create New Retriever with Texts
Create a New Retriever with Documents
Use Retriever
TF-IDF#
TF-IDF means term-frequency times inverse document-frequency.
This notebook goes over how to use a retriever that under the hood uses TF-IDF using scikit-learn package.
For more information on the d... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/tf_idf.html |
9098a34417f0-0 | .ipynb
.pdf
Databerry
Contents
Query
Databerry#
Databerry platform brings data from anywhere (Datsources: Text, PDF, Word, PowerPpoint, Excel, Notion, Airtable, Google Sheets, etc..) into Datastores (container of multiple Datasources).
Then your Datastores can be connected to ChatGPT via Plugins or any other Large La... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/databerry.html |
9098a34417f0-1 | )
retriever.get_relevant_documents("What is Daftpage?")
[Document(page_content='✨ Made with DaftpageOpen main menuPricingTemplatesLoginSearchHelpGetting StartedFeaturesAffiliate ProgramGetting StartedDaftpage is a new type of website builder that works like a doc.It makes website building easy, fun and offers tons of p... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/databerry.html |
9098a34417f0-2 | Document(page_content="✨ Made with DaftpageOpen main menuPricingTemplatesLoginSearchHelpGetting StartedFeaturesAffiliate ProgramHelp CenterWelcome to Daftpage’s help center—the one-stop shop for learning everything about building websites with Daftpage.Daftpage is the simplest way to create websites for all purposes in... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/databerry.html |
9098a34417f0-3 | Document(page_content=" is the simplest way to create websites for all purposes in seconds. Without knowing how to code, and for free!Get StartedDaftpage is a new type of website builder that works like a doc.It makes website building easy, fun and offers tons of powerful features for free. Just type / in your page to ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/databerry.html |
070c6b971e0f-0 | .ipynb
.pdf
ChatGPT Plugin
Contents
Using the ChatGPT Retriever Plugin
ChatGPT Plugin#
OpenAI plugins connect ChatGPT to third-party applications. These plugins enable ChatGPT to interact with APIs defined by developers, enhancing ChatGPT’s capabilities and allowing it to perform a wide range of actions.
Plugins can ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chatgpt-plugin.html |
070c6b971e0f-1 | Using the ChatGPT Retriever Plugin#
Okay, so we’ve created the ChatGPT Retriever Plugin, but how do we actually use it?
The below code walks through how to do that.
We want to use ChatGPTPluginRetriever so we have to get the OpenAI API Key.
import os
import getpass
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chatgpt-plugin.html |
070c6b971e0f-2 | Document(page_content='Team: Angels "Payroll (millions)": 154.49 "Wins": 89', lookup_str='', metadata={'id': '59c2c0c1-ae3f-4272-a1da-f44a723ea631_0', 'metadata': {'source': None, 'source_id': None, 'url': None, 'created_at': None, 'author': None, 'document_id': '59c2c0c1-ae3f-4272-a1da-f44a723ea631'}, 'embedding': Non... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/chatgpt-plugin.html |
de656f6bc752-0 | .ipynb
.pdf
Weaviate Hybrid Search
Weaviate Hybrid Search#
Weaviate is an open source vector database.
Hybrid search is a technique that combines multiple search algorithms to improve the accuracy and relevance of search results. It uses the best features of both keyword-based search algorithms with vector search techn... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate-hybrid.html |
de656f6bc752-1 | )
Add some data:
docs = [
Document(
metadata={
"title": "Embracing The Future: AI Unveiled",
"author": "Dr. Rebecca Simmons",
},
page_content="A comprehensive analysis of the evolution of artificial intelligence, from its inception to its future prospects. Dr. Simmons... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate-hybrid.html |
de656f6bc752-2 | "author": "Prof. Jonathan K. Sterling",
},
page_content="In his follow-up to 'Symbiosis', Prof. Sterling takes a look at the subtle, unnoticed presence and influence of AI in our everyday lives. It reveals how AI has become woven into our routines, often without our explicit realization.",
),
]
retr... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate-hybrid.html |
de656f6bc752-3 | Document(page_content='Prof. Sterling explores the potential for harmonious coexistence between humans and artificial intelligence. The book discusses how AI can be integrated into society in a beneficial and non-disruptive manner.', metadata={})]
Do a hybrid search with where filter:
retriever.get_relevant_documents(
... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate-hybrid.html |
ddf95ffb81c3-0 | .ipynb
.pdf
Arxiv
Contents
Installation
Examples
Running retriever
Question Answering on facts
Arxiv#
arXiv is an open-access archive for 2 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems sci... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/arxiv.html |
ddf95ffb81c3-1 | 'Authors': 'Caprice Stanley, Tobias Windisch',
'Summary': 'Graphs on lattice points are studied whose edges come from a finite set of\nallowed moves of arbitrary length. We show that the diameter of these graphs on\nfibers of a fixed integer matrix can be bounded from above by a constant. We\nthen study the mixing beh... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/arxiv.html |
ddf95ffb81c3-2 | questions = [
"What are Heat-bath random walks with Markov base?",
"What is the ImageBind model?",
"How does Compositional Reasoning with Large Language Models works?",
]
chat_history = []
for question in questions:
result = qa({"question": question, "chat_history": chat_history})
chat_history... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/arxiv.html |
ddf95ffb81c3-3 | -> **Question**: How does Compositional Reasoning with Large Language Models works?
**Answer**: Compositional reasoning with large language models refers to the ability of these models to correctly identify and represent complex concepts by breaking them down into smaller, more basic parts and combining them in a stru... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/arxiv.html |
ddf95ffb81c3-4 | **Answer**: Heat-bath random walks with Markov base (HB-MB) is a class of stochastic processes that have been studied in the field of statistical mechanics and condensed matter physics. In these processes, a particle moves in a lattice by making a transition to a neighboring site, which is chosen according to a probabi... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/arxiv.html |
4b19ed377cb0-0 | .ipynb
.pdf
Contextual Compression
Contents
Contextual Compression
Using a vanilla vector store retriever
Adding contextual compression with an LLMChainExtractor
More built-in compressors: filters
LLMChainFilter
EmbeddingsFilter
Stringing compressors and document transformers together
Contextual Compression#
This not... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-1 | texts = text_splitter.split_documents(documents)
retriever = FAISS.from_documents(texts, OpenAIEmbeddings()).as_retriever()
docs = retriever.get_relevant_documents("What did the president say about Ketanji Brown Jackson")
pretty_print_docs(docs)
Document 1:
Tonight. I call on the Senate to: Pass the Freedom to Vote Act... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-2 | We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.
----------------------------------------------------------------------------------------------------
Document 3:
And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-3 | Let’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.
Adding contextual compression with an LLMChainExtractor#
Now let’s wrap our base retriever with a ContextualCompressionRetriever. We’l... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-4 | More built-in compressors: filters#
LLMChainFilter#
The LLMChainFilter is slightly simpler but more robust compressor that uses an LLM chain to decide which of the initially retrieved documents to filter out and which ones to return, without manipulating the document contents.
from langchain.retrievers.document_compres... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-5 | from langchain.retrievers.document_compressors import EmbeddingsFilter
embeddings = OpenAIEmbeddings()
embeddings_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.76)
compression_retriever = ContextualCompressionRetriever(base_compressor=embeddings_filter, base_retriever=retriever)
compressed_doc... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-6 | We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.
We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.
We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have th... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-7 | Below we create a compressor pipeline by first splitting our docs into smaller chunks, then removing redundant documents, and then filtering based on relevance to the query.
from langchain.document_transformers import EmbeddingsRedundantFilter
from langchain.retrievers.document_compressors import DocumentCompressorPipe... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
4b19ed377cb0-8 | previous
Cohere Reranker
next
Databerry
Contents
Contextual Compression
Using a vanilla vector store retriever
Adding contextual compression with an LLMChainExtractor
More built-in compressors: filters
LLMChainFilter
EmbeddingsFilter
Stringing compressors and document transformers together
By Harrison Chase
... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
a1ec34e55cb8-0 | .ipynb
.pdf
Cohere Reranker
Contents
Set up the base vector store retriever
Doing reranking with CohereRerank
Cohere Reranker#
Cohere is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions.
This notebook shows how to use Cohere’s rerank endpoint i... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-1 | texts = text_splitter.split_documents(documents)
retriever = FAISS.from_documents(texts, OpenAIEmbeddings()).as_retriever(search_kwargs={"k": 20})
query = "What did the president say about Ketanji Brown Jackson"
docs = retriever.get_relevant_documents(query)
pretty_print_docs(docs)
Document 1:
One of the most serious c... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-2 | Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland.
In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-3 | It’s exploitation—and it drives up prices.
----------------------------------------------------------------------------------------------------
Document 8:
For the past 40 years we were told that if we gave tax breaks to those at the very top, the benefits would trickle down to everyone else.
But that trickle-down the... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-4 | The pandemic has been punishing.
And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more.
I understand.
----------------------------------------------------------------------------------------------------
Document 12:
Madam Speaker, Mada... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-5 | Third, support our veterans.
Veterans are the best of us.
I’ve always believed that we have a sacred obligation to equip all those we send to war and care for them and their families when they come home.
My administration is providing assistance with job training and housing, and now helping lower-income veterans ge... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-6 | ----------------------------------------------------------------------------------------------------
Document 19:
I understand.
I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work. I grew up in a family where if the price of food went up, you felt it.
That’s why one of the first things... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-7 | And 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.
----------------------------------------------------------------------------------------------------
Document 2:
I spoke with th... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
a1ec34e55cb8-8 | previous
Self-querying with Chroma
next
Contextual Compression
Contents
Set up the base vector store retriever
Doing reranking with CohereRerank
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/cohere-reranker.html |
4856a8d3860d-0 | .ipynb
.pdf
Metal
Contents
Ingest Documents
Query
Metal#
Metal is a managed service for ML Embeddings.
This notebook shows how to use Metal’s retriever.
First, you will need to sign up for Metal and get an API key. You can do so here
# !pip install metal_sdk
from metal_sdk.metal import Metal
API_KEY = ""
CLIENT_ID = ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/metal.html |
4856a8d3860d-1 | previous
kNN
next
Pinecone Hybrid Search
Contents
Ingest Documents
Query
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/metal.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.