id stringlengths 14 16 | text stringlengths 29 2.73k | source stringlengths 49 117 |
|---|---|---|
af7149cb26dd-3 | text text (42, 1) str None
Deep Lake, for now, is single writer and multiple reader. Setting read_only=True helps to avoid acquring the writer lock.
Retrieval Question/Answering#
from langchain.chains import RetrievalQA
from langchain.llms import OpenAIChat
qa = RetrievalQA.from_chain_type(llm=Open... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-4 | tensor htype shape dtype compression
------- ------- ------- ------- -------
embedding generic (4, 1536) float32 None
ids text (4, 1) str None
metadata json (4, 1) str None
text text (4, 1) str None
db.similarity_search... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-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... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-6 | [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: Justic... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-7 | 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... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-8 | 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... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-9 | 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 ... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-10 | [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: Justic... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-11 | 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 ... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-12 | 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... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-13 | 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... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-14 | username = "<username>" # your username on app.activeloop.ai
dataset_path = f"hub://{username}/langchain_test" # could be also ./local/path (much faster locally), s3://bucket/path/to/dataset, gcs://path/to/dataset, etc.
embedding = OpenAIEmbeddings()
db = DeepLake(dataset_path=dataset_path, embedding_function=embedd... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-15 | 'd6d6ccb7-e187-11ed-b66d-41c5f7b85421']
query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)
print(docs[0].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 ... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-16 | })
s3://hub-2.0-datasets-n/langchain_test loaded successfully.
Evaluating ingest: 100%|██████████| 1/1 [00:10<00:00
\
Dataset(path='s3://hub-2.0-datasets-n/langchain_test', tensors=['embedding', 'ids', 'metadata', 'text'])
tensor htype shape dtype compression
------- ------- ------- ------- ----... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-17 | username = "davitbun" # your username on app.activeloop.ai
source = f"hub://{username}/langchain_test" # could be local, s3, gcs, etc.
destination = f"hub://{username}/langchain_test_copy" # could be local, s3, gcs, etc.
deeplake.deepcopy(src=source, dest=destination, overwrite=True)
Copying dataset: 100%|██████████... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
af7149cb26dd-18 | metadata json (4, 1) str None
text text (4, 1) str None
Evaluating ingest: 100%|██████████| 1/1 [00:31<00:00
-
Dataset(path='hub://davitbun/langchain_test_copy', tensors=['embedding', 'ids', 'metadata', 'text'])
tensor htype shape dtype compression
------- -... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/deeplake.html |
3d20810c0eb5-0 | .ipynb
.pdf
LanceDB
LanceDB#
LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrevial, filtering and management of embeddings. Fully open source.
This notebook shows how to use functionality related to the LanceDB vector database based on the Lance data form... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html |
3d20810c0eb5-1 | I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves.
I’ve worked on these issues a long time.
I know what works: Investing in crime preventionand community police officers who’ll walk the... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html |
3d20810c0eb5-2 | These laws don’t infringe on the Second Amendment. They save lives.
The most fundamental right in America is the right to vote – and to have it counted. And it’s under assault.
In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections.
We cannot let this happen. ... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html |
3d20810c0eb5-3 | 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 their cases heard faster.
previous
FAISS
next
MatchingEngine
By Harrison Chase
© Copyright 2023, Harrison Chase.
... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html |
d8f072b2b2a3-0 | .ipynb
.pdf
SKLearnVectorStore
Contents
Basic usage
Load a sample document corpus
Create the SKLearnVectorStore, index the document corpus and run a sample query
Saving and loading a vector store
Clean-up
SKLearnVectorStore#
scikit-learn is an open source collection of machine learning algorithms, including some impl... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/sklearn.html |
d8f072b2b2a3-1 | persist_path = os.path.join(tempfile.gettempdir(), 'union.parquet')
vector_store = SKLearnVectorStore.from_documents(
documents=docs,
embedding=embeddings,
persist_path=persist_path, # persist_path and serializer are optional
serializer='parquet'
)
query = "What did the president say about Ketanji Brow... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/sklearn.html |
d8f072b2b2a3-2 | )
print('A new instance of vector store was loaded from', persist_path)
A new instance of vector store was loaded from /var/folders/6r/wc15p6m13nl_nl_n_xfqpc5c0000gp/T/union.parquet
docs = vector_store2.similarity_search(query)
print(docs[0].page_content)
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. ... | https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/sklearn.html |
d37b069f0fbd-0 | .ipynb
.pdf
Getting Started
Getting Started#
The default recommended text splitter is the RecursiveCharacterTextSplitter. This text splitter takes a list of characters. It tries to create chunks based on splitting on the first character, but if any chunks are too large it then moves onto the next character, and so fort... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/getting_started.html |
d37b069f0fbd-1 | previous
Text Splitters
next
Character
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/text_splitters/getting_started.html |
5dd940d4791b-0 | .ipynb
.pdf
tiktoken (OpenAI) tokenizer
tiktoken (OpenAI) tokenizer#
tiktoken is a fast BPE tokenizer created by OpenAI.
We can use it to estimate tokens used. It will probably be more accurate for the OpenAI models.
How the text is split: by character passed in
How the chunk size is measured: by tiktoken tokenizer
#!p... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/tiktoken.html |
68132bbe2d9e-0 | .ipynb
.pdf
Character
Character#
This is the simplest method. This splits based on characters (by default “\n\n”) and measure chunk length by number of characters.
How the text is split: by single character
How the chunk size is measured: by number of characters
# This is a long document we can split up.
with open('../... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html |
68132bbe2d9e-1 | print(texts[0])
page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n\nLast year COVID-19 kept us apart. This year we are finally together again. \n\nTonight, we meet as Democrats Republicans a... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html |
68132bbe2d9e-2 | print(documents[0])
page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n\nLast year COVID-19 kept us apart. This year we are finally together again. \n\nTonight, we meet as Democrats Republica... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html |
68132bbe2d9e-3 | text_splitter.split_text(state_of_the_union)[0]
'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n\nLast year COVID-19 kept us apart. This year we are finally together again. \n\nTonight, we meet as Demo... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html |
7a7e0c794cdf-0 | .ipynb
.pdf
spaCy
spaCy#
spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython.
Another alternative to NLTK is to use Spacy tokenizer.
How the text is split: by spaCy tokenizer
How the chunk size is measured: by number of characters
#!p... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/spacy.html |
7a7e0c794cdf-1 | previous
Recursive Character
next
Tiktoken
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/spacy.html |
f37275476d02-0 | .ipynb
.pdf
CodeTextSplitter
Contents
Python
JS
Markdown
Latex
HTML
CodeTextSplitter#
CodeTextSplitter allows you to split your code with multiple language support. Import enum Language and specify the language.
from langchain.text_splitter import (
RecursiveCharacterTextSplitter,
Language,
)
# Full list of s... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
f37275476d02-1 | helloWorld();
"""
js_splitter = RecursiveCharacterTextSplitter.from_language(
language=Language.JS, chunk_size=60, chunk_overlap=0
)
js_docs = js_splitter.create_documents([JS_CODE])
js_docs
[Document(page_content='function helloWorld() {\n console.log("Hello, World!");\n}', metadata={}),
Document(page_content='/... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
f37275476d02-2 | latex_text = """
\documentclass{article}
\begin{document}
\maketitle
\section{Introduction}
Large language models (LLMs) are a type of machine learning model that can be trained on vast amounts of text data to generate human-like language. In recent years, LLMs have made significant advances in a variety of natural lan... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
f37275476d02-3 | Document(page_content='made significant advances in a variety of natural language', metadata={}),
Document(page_content='processing tasks, including language translation, text', metadata={}),
Document(page_content='generation, and sentiment analysis.', metadata={}),
Document(page_content='\\subsection{History of LLM... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
f37275476d02-4 | color: darkblue;
}
</style>
</head>
<body>
<div>
<h1>🦜️🔗 LangChain</h1>
<p>⚡ Building applications with LLMs through composability ⚡</p>
</div>
<div>
As an open source project in a rapidly developing field, we are extremely open t... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
f37275476d02-5 | Document(page_content='As an open source project in a rapidly', metadata={}),
Document(page_content='developing field, we are extremely open to contributions.', metadata={}),
Document(page_content='</div>\n </body>\n</html>', metadata={})]
previous
Character
next
NLTK
Contents
Python
JS
Markdown
Latex
HTML
By ... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/code_splitter.html |
48462f38fd74-0 | .ipynb
.pdf
Tiktoken
Tiktoken#
tiktoken is a fast BPE tokeniser created by OpenAI.
How the text is split: by tiktoken tokens
How the chunk size is measured: by tiktoken tokens
#!pip install tiktoken
# This is a long document we can split up.
with open('../../../state_of_the_union.txt') as f:
state_of_the_union = f.... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/tiktoken_splitter.html |
5eee34143928-0 | .ipynb
.pdf
NLTK
NLTK#
The Natural Language Toolkit, or more commonly NLTK, is a suite of libraries and programs for symbolic and statistical natural language processing (NLP) for English written in the Python programming language.
Rather than just splitting on “\n\n”, we can use NLTK to split based on NLTK tokenizers.... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/nltk.html |
5eee34143928-1 | Groups of citizens blocking tanks with their bodies.
previous
CodeTextSplitter
next
Recursive Character
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/nltk.html |
3d497d4e2cfa-0 | .ipynb
.pdf
Hugging Face tokenizer
Hugging Face tokenizer#
Hugging Face has many tokenizers.
We use Hugging Face tokenizer, the GPT2TokenizerFast to count the text length in tokens.
How the text is split: by character passed in
How the chunk size is measured: by number of tokens calculated by the Hugging Face tokenizer... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/huggingface_length_function.html |
e50487211f68-0 | .ipynb
.pdf
Recursive Character
Recursive Character#
This text splitter is the recommended one for generic text. It is parameterized by a list of characters. It tries to split on them in order until the chunks are small enough. The default list is ["\n\n", "\n", " ", ""]. This has the effect of trying to keep all parag... | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/recursive_text_splitter.html |
e50487211f68-1 | previous
NLTK
next
spaCy
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/recursive_text_splitter.html |
d45bf0c52292-0 | .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 |
d45bf0c52292-1 | 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 |
d45bf0c52292-2 | 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 |
71efb01e3d2c-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 |
71efb01e3d2c-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 |
71efb01e3d2c-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 |
9d6b31adff14-0 | .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 |
9d6b31adff14-1 | retriever.get_relevant_documents("what is vespa?")
previous
VectorStore
next
Weaviate Hybrid Search
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vespa.html |
8426a36550df-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 |
8426a36550df-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 |
8426a36550df-2 | 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 their cases heard faster.
We’re securing commitments and supporting partners in South and Central America to host more refuge... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-3 | Let’s pass the Paycheck Fairness Act and paid leave.
Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty.
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 b... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-4 | ----------------------------------------------------------------------------------------------------
Document 2:
"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 receive... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-5 | EmbeddingsFilter#
Making an extra LLM call over each retrieved document is expensive and slow. The EmbeddingsFilter provides a cheaper and faster option by embedding the documents and query and only returning those documents which have sufficiently similar embeddings to the query.
from langchain.embeddings import OpenA... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-6 | ----------------------------------------------------------------------------------------------------
Document 2:
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... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-7 | First, beat the opioid epidemic.
Stringing compressors and document transformers together#
Using the DocumentCompressorPipeline we can also easily combine multiple compressors in sequence. Along with compressors we can add BaseDocumentTransformers to our pipeline, which don’t perform any contextual compression but simp... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
8426a36550df-8 | ----------------------------------------------------------------------------------------------------
Document 2:
As 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.
While it often appears that w... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/contextual-compression.html |
e82e0605cbc5-0 | .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 |
c3d8ca1d2cda-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 |
97a9a5836da4-0 | .ipynb
.pdf
Self-querying with Qdrant
Contents
Creating a Qdrant vectorstore
Creating our self-querying retriever
Testing it out
Filter k
Self-querying with Qdrant#
Qdrant (read: quadrant ) is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage ... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
97a9a5836da4-1 | Document(page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea", metadata={"year": 2006, "director": "Satoshi Kon", "rating": 8.6}),
Document(page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them"... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
97a9a5836da4-2 | type="integer",
),
AttributeInfo(
name="director",
description="The name of the movie director",
type="string",
),
AttributeInfo(
name="rating",
description="A 1-10 rating for the movie",
type="float"
),
]
document_content_description = "Brief summa... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
97a9a5836da4-3 | query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None
[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'}),
Document(page_content='A ps... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
97a9a5836da4-4 | [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 composite filter
retriever.get_relevant_documents("What's a movie after 1990 but before 2005 th... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
97a9a5836da4-5 | Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]
previous
Pinecone Hybrid Search
next
Self-querying
Contents
Creating a Qdrant vectorstore
Creating our self-querying retriever
Testing it out
Filter k
By Harrison Chase
© Copyright 2023, Harr... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/qdrant_self_query.html |
a17616639ebd-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 |
a17616639ebd-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 |
497b3d93f1e7-0 | .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 |
497b3d93f1e7-1 | 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 |
497b3d93f1e7-2 | " 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 |
497b3d93f1e7-3 | 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 |
497b3d93f1e7-4 | 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 |
497b3d93f1e7-5 | 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 |
497b3d93f1e7-6 | 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 |
23b99c2ceefa-0 | .ipynb
.pdf
Time Weighted VectorStore
Contents
Low Decay Rate
High Decay Rate
Virtual Time
Time Weighted VectorStore#
This retriever uses a combination of semantic similarity and a time decay.
The algorithm for scoring them is:
semantic_similarity + (1.0 - decay_rate) ** hours_passed
Notably, hours_passed refers to t... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
23b99c2ceefa-1 | retriever.add_documents([Document(page_content="hello foo")])
['d7f85756-2371-4bdf-9140-052780a0f9b3']
# "Hello World" is returned first because it is most salient, and the decay rate is close to 0., meaning it's still recent enough
retriever.get_relevant_documents("hello world")
[Document(page_content='hello world', m... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
23b99c2ceefa-2 | # "Hello Foo" is returned first because "hello world" is mostly forgotten
retriever.get_relevant_documents("hello world")
[Document(page_content='hello foo', metadata={'last_accessed_at': datetime.datetime(2023, 4, 16, 22, 9, 2, 494798), 'created_at': datetime.datetime(2023, 4, 16, 22, 9, 2, 178722), 'buffer_idx': 1})]... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
e6df33fa9f7a-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 |
237e8a3fd5b0-0 | .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 |
237e8a3fd5b0-1 | previous
kNN
next
Pinecone Hybrid Search
Contents
Ingest Documents
Query
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/metal.html |
b918f8934731-0 | .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 |
b918f8934731-1 | )
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 |
b918f8934731-2 | 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 |
b918f8934731-3 | 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 |
e5f8fc12f635-0 | .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 |
e5f8fc12f635-1 | '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 |
e5f8fc12f635-2 | 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 |
e5f8fc12f635-3 | -> **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 |
e5f8fc12f635-4 | **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 |
e9d2830392d1-0 | .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 |
e9d2830392d1-1 | 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 |
e9d2830392d1-2 | 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 |
e9d2830392d1-3 | 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=True
)
# This example only specifies a relevant query
retriever.get_relevant_documents("wha... | https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html |
d70d254758ea-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 |
d70d254758ea-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 |
d70d254758ea-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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.