id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 59 127 |
|---|---|---|
2b0042d6f350-13 | [Document(page_content='Team: Nationals\n"Payroll (millions)": 81.34\n"Wins": 98', lookup_str='', metadata={'source': 'Nationals', 'row': 0}, lookup_index=0), Document(page_content='Team: Reds\n"Payroll (millions)": 82.20\n"Wins": 97', lookup_str='', metadata={'source': 'Reds', 'row': 1}, lookup_index=0), Document(page... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-14 | 7}, lookup_index=0), Document(page_content='Team: Rays\n"Payroll (millions)": 64.17\n"Wins": 90', lookup_str='', metadata={'source': 'Rays', 'row': 8}, lookup_index=0), Document(page_content='Team: Angels\n"Payroll (millions)": 154.49\n"Wins": 89', lookup_str='', metadata={'source': 'Angels', 'row': 9}, lookup_index=0)... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-15 | 'row': 15}, lookup_index=0), Document(page_content='Team: Diamondbacks\n"Payroll (millions)": 74.28\n"Wins": 81', lookup_str='', metadata={'source': 'Diamondbacks', 'row': 16}, lookup_index=0), Document(page_content='Team: Pirates\n"Payroll (millions)": 63.43\n"Wins": 79', lookup_str='', metadata={'source': 'Pirates', ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-16 | metadata={'source': 'Marlins', 'row': 23}, lookup_index=0), Document(page_content='Team: Red Sox\n"Payroll (millions)": 173.18\n"Wins": 69', lookup_str='', metadata={'source': 'Red Sox', 'row': 24}, lookup_index=0), Document(page_content='Team: Indians\n"Payroll (millions)": 78.43\n"Wins": 68', lookup_str='', metadata=... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-17 | UnstructuredCSVLoader#
You can also load the table using the UnstructuredCSVLoader. One advantage of using UnstructuredCSVLoader is that if you use it in "elements" mode, an HTML representation of the table will be available in the metadata.
from langchain.document_loaders.csv_loader import UnstructuredCSVLoader
loader... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-18 | <td>120.51</td>
<td>93</td>
</tr>
<tr>
<td>Orioles</td>
<td>81.43</td>
<td>93</td>
</tr>
<tr>
<td>Rays</td>
<td>64.17</td>
<td>90</td>
</tr>
<tr>
<td>Angels</td>
<td>154.49</td>
<td>89</td>
</tr>
<tr>
<td>Tigers</td>
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-19 | </tr>
<tr>
<td>Diamondbacks</td>
<td>74.28</td>
<td>81</td>
</tr>
<tr>
<td>Pirates</td>
<td>63.43</td>
<td>79</td>
</tr>
<tr>
<td>Padres</td>
<td>55.24</td>
<td>76</td>
</tr>
<tr>
<td>Mariners</td>
<td>81.97</td>
<td>75<... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
2b0042d6f350-20 | <td>78.43</td>
<td>68</td>
</tr>
<tr>
<td>Twins</td>
<td>94.08</td>
<td>66</td>
</tr>
<tr>
<td>Rockies</td>
<td>78.06</td>
<td>64</td>
</tr>
<tr>
<td>Cubs</td>
<td>88.19</td>
<td>61</td>
</tr>
<tr>
<td>Astros</td>
<t... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/csv.html |
0adfb2e97933-0 | .ipynb
.pdf
Gutenberg
Gutenberg#
Project Gutenberg is an online library of free eBooks.
This notebook covers how to load links to Gutenberg e-books into a document format that we can use downstream.
from langchain.document_loaders import GutenbergLoader
loader = GutenbergLoader('https://www.gutenberg.org/cache/epub/699... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/document_loaders/examples/gutenberg.html |
c3caf977f19c-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/getting_started.html |
c3caf977f19c-1 | page_content='of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.' metadata={'start_index': 82}
previous
Text Splitters
next
Character
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/getting_started.html |
44526870d883-0 | .ipynb
.pdf
CodeTextSplitter
Contents
Python
JS
Solidity
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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
44526870d883-1 | }
// Call the function
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={}),
D... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
44526870d883-2 | language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
md_docs = md_splitter.create_documents([markdown_text])
md_docs
[Document(page_content='# 🦜️🔗 LangChain', metadata={}),
Document(page_content='⚡ Building applications with LLMs through composability ⚡', metadata={}),
Document(page_content='## Quick Instal... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
44526870d883-3 | \subsection{Applications of LLMs}
LLMs have many applications in industry, including chatbots, content creation, and virtual assistants. They can also be used in academia for research in linguistics, psychology, and computational linguistics.
\end{document}
"""
latex_splitter = RecursiveCharacterTextSplitter.from_langu... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
44526870d883-4 | Document(page_content='datasets, leading to significant improvements in', metadata={}),
Document(page_content='performance.', metadata={}),
Document(page_content='\\subsection{Applications of LLMs}', metadata={}),
Document(page_content='LLMs have many applications in industry, including', metadata={}),
Document(pag... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
44526870d883-5 | Document(page_content='<title>🦜️🔗 LangChain</title>\n <style>', metadata={}),
Document(page_content='body {', metadata={}),
Document(page_content='font-family: Arial, sans-serif;', metadata={}),
Document(page_content='}\n h1 {', metadata={}),
Document(page_content='color: darkblue;\n ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/code_splitter.html |
de368ca32158-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/spacy.html |
de368ca32158-1 | previous
Recursive Character
next
Tiktoken
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/spacy.html |
663fb253628f-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.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/tiktoken_splitter.html |
785ac476db93-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/huggingface_length_function.html |
17aca0b5d2a3-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/recursive_text_splitter.html |
17aca0b5d2a3-1 | previous
NLTK
next
spaCy
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/recursive_text_splitter.html |
a040b66c6ffb-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/tiktoken.html |
ee7c634c6fbd-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.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/nltk.html |
ee7c634c6fbd-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 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/nltk.html |
d7922252429a-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('../... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/character_text_splitter.html |
d7922252429a-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/character_text_splitter.html |
d7922252429a-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/character_text_splitter.html |
d7922252429a-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/text_splitters/examples/character_text_splitter.html |
a16d2d34b47f-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.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/elastic_search_bm25.html |
a16d2d34b47f-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/elastic_search_bm25.html |
fec7d90c114b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
fec7d90c114b-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
fec7d90c114b-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})]... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/time_weighted_vectorstore.html |
b7a9c4399cc4-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-2 | 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.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-4 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-6 | ----------------------------------------------------------------------------------------------------
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-7 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
b7a9c4399cc4-8 | 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 Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/cohere-reranker.html |
fd71ef51b801-0 | .ipynb
.pdf
PubMed Retriever
PubMed Retriever#
This notebook goes over how to use PubMed as a retriever
PubMed® comprises more than 35 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/pubmed.html |
fd71ef51b801-1 | previous
Pinecone Hybrid Search
next
Self-querying with Qdrant
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/pubmed.html |
58a9730fb62e-0 | .ipynb
.pdf
AWS Kendra
Contents
Using the AWS Kendra Index Retriever
AWS Kendra#
AWS Kendra is an intelligent search service provided by Amazon Web Services (AWS). It utilizes advanced natural language processing (NLP) and machine learning algorithms to enable powerful search capabilities across various data sources ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/aws_kendra_index_retriever.html |
2b8d91c15960-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/svm.html |
6fdfbdafed2d-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.
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/knn.html |
7ebc8806f552-0 | .ipynb
.pdf
Azure Cognitive Search
Contents
Set up Azure Cognitive Search
Using the Azure Cognitive Search Retriever
Azure Cognitive Search#
Azure Cognitive Search (formerly known as Azure Search) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience ove... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/azure_cognitive_search.html |
7ebc8806f552-1 | os.environ["AZURE_COGNITIVE_SEARCH_API_KEY"] = "<YOUR_API_KEY>"
Create the Retriever
retriever = AzureCognitiveSearchRetriever(content_key="content")
Now you can use retrieve documents from Azure Cognitive Search
retriever.get_relevant_documents("what is langchain")
previous
AWS Kendra
next
ChatGPT Plugin
Contents
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/azure_cognitive_search.html |
8910a72533a0-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/tf_idf.html |
9221c2b71a88-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/vespa.html |
9221c2b71a88-1 | retriever.get_relevant_documents("what is vespa?")
previous
VectorStore
next
Weaviate Hybrid Search
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/vespa.html |
440a546753af-0 | .ipynb
.pdf
Zep
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#
Zep - A long-term memory store for LLM applications.
More on Zep:
Zep stores, summarizes, embeds, indexes, and enr... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-1 | Initialize the Zep Chat Message History Class and add a chat message history to the memory store#
NOTE: Unlike other Retrievers, the content returned by the Zep Retriever is session/user specific. A session_id is required when instantiating the Retriever.
session_id = str(uuid4()) # This is a unique identifier for the... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-2 | " Delany, and Joanna Russ."
),
},
{"role": "human", "content": "What awards did she win?"},
{
"role": "ai",
"content": (
"Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur"
" Fellowship."
),
},
{
"role": "human",
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-3 | Zep provides native vector search over historical conversation memory. Embedding happens automatically.
NOTE: Embedding of messages occurs asynchronously, so the first query may not return results. Subsequent queries will return results as the embeddings are generated.
from langchain.retrievers import ZepRetriever
zep_... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-4 | Document(page_content='Who were her contemporaries?', metadata={'score': 0.757553366415519, 'uuid': '41f9c41a-a205-41e1-b48b-a0a4cd943fc8', 'created_at': '2023-05-25T15:03:30.243995Z', 'role': 'human', 'token_count': 8}),
Document(page_content='Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-5 | [Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.8897321402776546, 'uu... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
440a546753af-6 | Document(page_content="Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.", metadata={'score': 0.7602854653476563, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),
Document(page_content='You might... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/zep_memorystore.html |
15c22005e0bd-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
15c22005e0bd-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"... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
15c22005e0bd-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
15c22005e0bd-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
15c22005e0bd-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
15c22005e0bd-5 | Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]
previous
PubMed Retriever
next
Self-querying
Contents
Creating a Qdrant vectorstore
Creating our self-querying retriever
Testing it out
Filter k
By Harrison Chase
© Copyright 2023, Harrison C... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/qdrant_self_query.html |
7751380b00c9-0 | .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 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chatgpt-plugin.html |
7751380b00c9-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chatgpt-plugin.html |
7751380b00c9-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chatgpt-plugin.html |
989b78f99164-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-4 | ----------------------------------------------------------------------------------------------------
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-6 | ----------------------------------------------------------------------------------------------------
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-7 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
989b78f99164-8 | ----------------------------------------------------------------------------------------------------
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/contextual-compression.html |
d7797d46d7af-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
d7797d46d7af-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
d7797d46d7af-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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/pinecone_hybrid_search.html |
214c45ef31c4-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/vectorstore.html |
214c45ef31c4-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/vectorstore.html |
a9607cc3ce89-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
a9607cc3ce89-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
a9607cc3ce89-2 | )
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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
a9607cc3ce89-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
a9607cc3ce89-4 | [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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
a9607cc3ce89-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/self_query.html |
21705101c034-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
21705101c034-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
21705101c034-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
21705101c034-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
21705101c034-4 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
21705101c034-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/chroma_self_query.html |
127fa9812842-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/arxiv.html |
127fa9812842-1 | '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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/arxiv.html |
127fa9812842-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/arxiv.html |
127fa9812842-3 | -> **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... | rtdocs_stable/api.python.langchain.com/en/stable/modules/indexes/retrievers/examples/arxiv.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.