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_content='Team: Yankees\n"Payroll (millions)": 197.96\n"Wins": 95', lookup_str='', metadata={'source': 'Yankees', 'row': 2}, lookup_index=0), Document(page_content='Team: Giants\n"Payroll (millions)": 117.62\n"Wins": 94', lookup_str='', metadata={'source': 'Giants', 'row': 3}, lookup_index=0), Document(page_content='Team: Braves\n"Payroll (millions)": 83.31\n"Wins": 94', lookup_str='', metadata={'source': 'Braves', 'row': 4}, lookup_index=0), Document(page_content='Team: Athletics\n"Payroll (millions)": 55.37\n"Wins": 94', lookup_str='', metadata={'source': 'Athletics', 'row': 5}, lookup_index=0), Document(page_content='Team: Rangers\n"Payroll (millions)": 120.51\n"Wins": 93', lookup_str='', metadata={'source': 'Rangers', 'row': 6}, lookup_index=0), Document(page_content='Team: Orioles\n"Payroll (millions)": 81.43\n"Wins": 93', lookup_str='', metadata={'source': 'Orioles', 'row': 7}, lookup_index=0), Document(page_content='Team: Rays\n"Payroll
|
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), Document(page_content='Team: Tigers\n"Payroll (millions)": 132.30\n"Wins": 88', lookup_str='', metadata={'source': 'Tigers', 'row': 10}, lookup_index=0), Document(page_content='Team: Cardinals\n"Payroll (millions)": 110.30\n"Wins": 88', lookup_str='', metadata={'source': 'Cardinals', 'row': 11}, lookup_index=0), Document(page_content='Team: Dodgers\n"Payroll (millions)": 95.14\n"Wins": 86', lookup_str='', metadata={'source': 'Dodgers', 'row': 12}, lookup_index=0), Document(page_content='Team: White Sox\n"Payroll (millions)": 96.92\n"Wins": 85', lookup_str='', metadata={'source': 'White Sox', 'row': 13}, lookup_index=0), Document(page_content='Team: Brewers\n"Payroll (millions)": 97.65\n"Wins": 83', lookup_str='', metadata={'source': 'Brewers', 'row': 14}, lookup_index=0), Document(page_content='Team: Phillies\n"Payroll (millions)": 174.54\n"Wins": 81', lookup_str='', metadata={'source': 'Phillies', 'row': 15}, lookup_index=0), Document(page_content='Team:
|
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', 'row': 17}, lookup_index=0), Document(page_content='Team: Padres\n"Payroll (millions)": 55.24\n"Wins": 76', lookup_str='', metadata={'source': 'Padres', 'row': 18}, lookup_index=0), Document(page_content='Team: Mariners\n"Payroll (millions)": 81.97\n"Wins": 75', lookup_str='', metadata={'source': 'Mariners', 'row': 19}, lookup_index=0), Document(page_content='Team: Mets\n"Payroll (millions)": 93.35\n"Wins": 74', lookup_str='', metadata={'source': 'Mets', 'row': 20}, lookup_index=0), Document(page_content='Team: Blue Jays\n"Payroll (millions)": 75.48\n"Wins": 73', lookup_str='', metadata={'source': 'Blue Jays', 'row': 21}, lookup_index=0), Document(page_content='Team: Royals\n"Payroll (millions)": 60.91\n"Wins": 72', lookup_str='', metadata={'source': 'Royals', 'row': 22}, lookup_index=0), Document(page_content='Team: Marlins\n"Payroll (millions)": 118.07\n"Wins": 69', lookup_str='', metadata={'source': 'Marlins', 'row': 23}, lookup_index=0),
|
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={'source': 'Indians', 'row': 25}, lookup_index=0), Document(page_content='Team: Twins\n"Payroll (millions)": 94.08\n"Wins": 66', lookup_str='', metadata={'source': 'Twins', 'row': 26}, lookup_index=0), Document(page_content='Team: Rockies\n"Payroll (millions)": 78.06\n"Wins": 64', lookup_str='', metadata={'source': 'Rockies', 'row': 27}, lookup_index=0), Document(page_content='Team: Cubs\n"Payroll (millions)": 88.19\n"Wins": 61', lookup_str='', metadata={'source': 'Cubs', 'row': 28}, lookup_index=0), Document(page_content='Team: Astros\n"Payroll (millions)": 60.65\n"Wins": 55', lookup_str='', metadata={'source': 'Astros', 'row': 29}, lookup_index=0)]
|
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 = UnstructuredCSVLoader(file_path='example_data/mlb_teams_2012.csv', mode="elements")
docs = loader.load()
print(docs[0].metadata["text_as_html"])
<table border="1" class="dataframe">
<tbody>
<tr>
<td>Nationals</td>
<td>81.34</td>
<td>98</td>
</tr>
<tr>
<td>Reds</td>
<td>82.20</td>
<td>97</td>
</tr>
<tr>
<td>Yankees</td>
<td>197.96</td>
<td>95</td>
</tr>
<tr>
<td>Giants</td>
<td>117.62</td>
<td>94</td>
</tr>
<tr>
<td>Braves</td>
<td>83.31</td>
<td>94</td>
</tr>
<tr>
<td>Athletics</td>
<td>55.37</td>
<td>94</td>
</tr>
<tr>
<td>Rangers</td>
<td>120.51</td>
<td>93</td>
|
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>
<td>132.30</td>
<td>88</td>
</tr>
<tr>
<td>Cardinals</td>
<td>110.30</td>
<td>88</td>
</tr>
<tr>
<td>Dodgers</td>
<td>95.14</td>
<td>86</td>
</tr>
<tr>
<td>White Sox</td>
<td>96.92</td>
<td>85</td>
</tr>
<tr>
<td>Brewers</td>
<td>97.65</td>
<td>83</td>
</tr>
<tr>
<td>Phillies</td>
<td>174.54</td>
<td>81</td>
</tr>
<tr>
<td>Diamondbacks</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</td>
</tr>
<tr>
<td>Mets</td>
<td>93.35</td>
<td>74</td>
</tr>
<tr>
<td>Blue Jays</td>
<td>75.48</td>
<td>73</td>
</tr>
<tr>
<td>Royals</td>
<td>60.91</td>
<td>72</td>
</tr>
<tr>
<td>Marlins</td>
<td>118.07</td>
<td>69</td>
</tr>
<tr>
<td>Red Sox</td>
<td>173.18</td>
<td>69</td>
</tr>
<tr>
<td>Indians</td>
<td>78.43</td>
<td>68</td>
|
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>
<td>60.65</td>
<td>55</td>
</tr>
</tbody>
</table>
previous
Copy Paste
next
Email
Contents
Customizing the csv parsing and loading
Specify a column to identify the document source
UnstructuredCSVLoader
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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/69972/pg69972.txt')
data = loader.load()
data[0].page_content[:300]
'The Project Gutenberg eBook of The changed brides, by Emma Dorothy\r\n\n\nEliza Nevitte Southworth\r\n\n\n\r\n\n\nThis eBook is for the use of anyone anywhere in the United States and\r\n\n\nmost other parts of the world at no cost and with almost no restrictions\r\n\n\nwhatsoever. You may copy it, give it away or re-u'
data[0].metadata
{'source': 'https://www.gutenberg.org/cache/epub/69972/pg69972.txt'}
previous
College Confidential
next
Hacker News
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 forth. By default the characters it tries to split on are ["\n\n", "\n", " ", ""]
In addition to controlling which characters you can split on, you can also control a few other things:
length_function: how the length of chunks is calculated. Defaults to just counting number of characters, but it’s pretty common to pass a token counter here.
chunk_size: the maximum size of your chunks (as measured by the length function).
chunk_overlap: the maximum overlap between chunks. It can be nice to have some overlap to maintain some continuity between chunks (eg do a sliding window).
add_start_index : wether to include the starting position of each chunk within the original document in the metadata.
# This is a long document we can split up.
with open('../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(
# Set a really small chunk size, just to show.
chunk_size = 100,
chunk_overlap = 20,
length_function = len,
add_start_index = True,
)
texts = text_splitter.create_documents([state_of_the_union])
print(texts[0])
print(texts[1])
page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and' metadata={'start_index': 0}
|
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 list of support languages
[e.value for e in Language]
['cpp',
'go',
'java',
'js',
'php',
'proto',
'python',
'rst',
'ruby',
'rust',
'scala',
'swift',
'markdown',
'latex',
'html',
'sol']
# You can also see the separators used for a given language
RecursiveCharacterTextSplitter.get_separators_for_language(Language.PYTHON)
['\nclass ', '\ndef ', '\n\tdef ', '\n\n', '\n', ' ', '']
Python#
Here’s an example using the PythonTextSplitter
PYTHON_CODE = """
def hello_world():
print("Hello, World!")
# Call the function
hello_world()
"""
python_splitter = RecursiveCharacterTextSplitter.from_language(
language=Language.PYTHON, chunk_size=50, chunk_overlap=0
)
python_docs = python_splitter.create_documents([PYTHON_CODE])
python_docs
[Document(page_content='def hello_world():\n print("Hello, World!")', metadata={}),
Document(page_content='# Call the function\nhello_world()', metadata={})]
JS#
Here’s an example using the JS text splitter
JS_CODE = """
function helloWorld() {
console.log("Hello, World!");
}
// Call the function
helloWorld();
"""
|
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={}),
Document(page_content='// Call the function\nhelloWorld();', metadata={})]
Solidity#
Here’s an example using the Solidity text splitter
SOL_CODE = """
pragma solidity ^0.8.20;
contract HelloWorld {
function add(uint a, uint b) pure public returns(uint) {
return a + b;
}
}
"""
sol_splitter = RecursiveCharacterTextSplitter.from_language(
language=Language.SOL, chunk_size=128, chunk_overlap=0
)
sol_docs = sol_splitter.create_documents([SOL_CODE])
sol_docs
[Document(page_content='pragma solidity ^0.8.20;', metadata={}),
Document(page_content='contract HelloWorld {\n function add(uint a, uint b) pure public returns(uint) {\n return a + b;\n }\n}', metadata={})]
Markdown#
Here’s an example using the Markdown text splitter.
markdown_text = """
# 🦜️🔗 LangChain
⚡ Building applications with LLMs through composability ⚡
## Quick Install
```bash
# Hopefully this code block isn't split
pip install langchain
```
As an open source project in a rapidly developing field, we are extremely open to contributions.
"""
md_splitter = RecursiveCharacterTextSplitter.from_language(
language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
|
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 Install', metadata={}),
Document(page_content="```bash\n# Hopefully this code block isn't split", metadata={}),
Document(page_content='pip install langchain', metadata={}),
Document(page_content='```', metadata={}),
Document(page_content='As an open source project in a rapidly developing field, we', metadata={}),
Document(page_content='are extremely open to contributions.', metadata={})]
Latex#
Here’s an example on Latex text
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 language processing tasks, including language translation, text generation, and sentiment analysis.
\subsection{History of LLMs}
The earliest LLMs were developed in the 1980s and 1990s, but they were limited by the amount of data that could be processed and the computational power available at the time. In the past decade, however, advances in hardware and software have made it possible to train LLMs on massive datasets, leading to significant improvements in performance.
\subsection{Applications of LLMs}
|
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_language(
language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
latex_docs = latex_splitter.create_documents([latex_text])
latex_docs
[Document(page_content='\\documentclass{article}\n\n\x08egin{document}\n\n\\maketitle', metadata={}),
Document(page_content='\\section{Introduction}', metadata={}),
Document(page_content='Large language models (LLMs) are a type of machine learning', metadata={}),
Document(page_content='model that can be trained on vast amounts of text data to', metadata={}),
Document(page_content='generate human-like language. In recent years, LLMs have', metadata={}),
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 LLMs}', metadata={}),
Document(page_content='The earliest LLMs were developed in the 1980s and 1990s,', metadata={}),
Document(page_content='but they were limited by the amount of data that could be', metadata={}),
Document(page_content='processed and the computational power available at the', metadata={}),
Document(page_content='time. In the past decade, however, advances in hardware and', metadata={}),
Document(page_content='software have made it possible to train LLMs on massive', metadata={}),
|
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(page_content='chatbots, content creation, and virtual assistants. They', metadata={}),
Document(page_content='can also be used in academia for research in linguistics,', metadata={}),
Document(page_content='psychology, and computational linguistics.', metadata={}),
Document(page_content='\\end{document}', metadata={})]
HTML#
Here’s an example using an HTML text splitter
html_text = """
<!DOCTYPE html>
<html>
<head>
<title>🦜️🔗 LangChain</title>
<style>
body {
font-family: Arial, sans-serif;
}
h1 {
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 to contributions.
</div>
</body>
</html>
"""
html_splitter = RecursiveCharacterTextSplitter.from_language(
language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
html_docs = html_splitter.create_documents([html_text])
html_docs
[Document(page_content='<!DOCTYPE html>\n<html>\n <head>', metadata={}),
|
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 }', metadata={}),
Document(page_content='</style>\n </head>\n <body>\n <div>', metadata={}),
Document(page_content='<h1>🦜️🔗 LangChain</h1>', metadata={}),
Document(page_content='<p>⚡ Building applications with LLMs through', metadata={}),
Document(page_content='composability ⚡</p>', metadata={}),
Document(page_content='</div>\n <div>', metadata={}),
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
Solidity
Markdown
Latex
HTML
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/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
#!pip install spacy
# This is a long document we can split up.
with open('../../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import SpacyTextSplitter
text_splitter = SpacyTextSplitter(chunk_size=1000)
texts = text_splitter.split_text(state_of_the_union)
print(texts[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.
Last year COVID-19 kept us apart.
This year we are finally together again.
Tonight, we meet as Democrats Republicans and Independents.
But most importantly as Americans.
With a duty to one another to the American people to the Constitution.
And with an unwavering resolve that freedom will always triumph over tyranny.
Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.
But he badly miscalculated.
He thought he could roll into Ukraine and the world would roll over.
Instead he met a wall of strength he never imagined.
He met the Ukrainian people.
From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.
previous
Recursive Character
next
Tiktoken
By Harrison Chase
|
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.read()
from langchain.text_splitter import TokenTextSplitter
text_splitter = TokenTextSplitter(chunk_size=10, chunk_overlap=0)
texts = text_splitter.split_text(state_of_the_union)
print(texts[0])
Madam Speaker, Madam Vice President, our
previous
spaCy
next
Hugging Face tokenizer
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/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
from transformers import GPT2TokenizerFast
tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
# This is a long document we can split up.
with open('../../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import CharacterTextSplitter
text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=100, chunk_overlap=0)
texts = text_splitter.split_text(state_of_the_union)
print(texts[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.
Last year COVID-19 kept us apart. This year we are finally together again.
Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.
With a duty to one another to the American people to the Constitution.
previous
Tiktoken
next
tiktoken (OpenAI) tokenizer
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/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 paragraphs (and then sentences, and then words) together as long as possible, as those would generically seem to be the strongest semantically related pieces of text.
How the text is split: by list of characters
How the chunk size is measured: by number of characters
# This is a long document we can split up.
with open('../../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(
# Set a really small chunk size, just to show.
chunk_size = 100,
chunk_overlap = 20,
length_function = len,
)
texts = text_splitter.create_documents([state_of_the_union])
print(texts[0])
print(texts[1])
page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and' lookup_str='' metadata={} lookup_index=0
page_content='of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.' lookup_str='' metadata={} lookup_index=0
text_splitter.split_text(state_of_the_union)[:2]
['Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and',
'of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.']
previous
NLTK
next
spaCy
By Harrison Chase
|
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
#!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.read()
from langchain.text_splitter import CharacterTextSplitter
text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=100, chunk_overlap=0)
texts = text_splitter.split_text(state_of_the_union)
print(texts[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.
Last year COVID-19 kept us apart. This year we are finally together again.
Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.
With a duty to one another to the American people to the Constitution.
previous
Hugging Face tokenizer
next
Vectorstores
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/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.
How the text is split: by NLTK tokenizer.
How the chunk size is measured:by number of characters
#pip install nltk
# This is a long document we can split up.
with open('../../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import NLTKTextSplitter
text_splitter = NLTKTextSplitter(chunk_size=1000)
texts = text_splitter.split_text(state_of_the_union)
print(texts[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.
Last year COVID-19 kept us apart.
This year we are finally together again.
Tonight, we meet as Democrats Republicans and Independents.
But most importantly as Americans.
With a duty to one another to the American people to the Constitution.
And with an unwavering resolve that freedom will always triumph over tyranny.
Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.
But he badly miscalculated.
He thought he could roll into Ukraine and the world would roll over.
Instead he met a wall of strength he never imagined.
He met the Ukrainian people.
From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.
|
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('../../../state_of_the_union.txt') as f:
state_of_the_union = f.read()
from langchain.text_splitter import CharacterTextSplitter
text_splitter = CharacterTextSplitter(
separator = "\n\n",
chunk_size = 1000,
chunk_overlap = 200,
length_function = len,
)
texts = text_splitter.create_documents([state_of_the_union])
print(texts[0])
|
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 and Independents. But most importantly as Americans. \n\nWith a duty to one another to the American people to the Constitution. \n\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \n\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n\nHe met the Ukrainian people. \n\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.' lookup_str='' metadata={} lookup_index=0
Here’s an example of passing metadata along with the documents, notice that it is split along with the documents.
metadatas = [{"document": 1}, {"document": 2}]
documents = text_splitter.create_documents([state_of_the_union, state_of_the_union], metadatas=metadatas)
print(documents[0])
|
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 Republicans and Independents. But most importantly as Americans. \n\nWith a duty to one another to the American people to the Constitution. \n\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \n\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n\nHe met the Ukrainian people. \n\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.' lookup_str='' metadata={'document': 1} lookup_index=0
text_splitter.split_text(state_of_the_union)[0]
|
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 Democrats Republicans and Independents. But most importantly as Americans. \n\nWith a duty to one another to the American people to the Constitution. \n\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \n\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n\nHe met the Ukrainian people. \n\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.'
previous
Getting Started
next
CodeTextSplitter
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/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.
In information retrieval, Okapi BM25 (BM is an abbreviation of best matching) is a ranking function used by search engines to estimate the relevance of documents to a given search query. It is based on the probabilistic retrieval framework developed in the 1970s and 1980s by Stephen E. Robertson, Karen Spärck Jones, and others.
The name of the actual ranking function is BM25. The fuller name, Okapi BM25, includes the name of the first system to use it, which was the Okapi information retrieval system, implemented at London’s City University in the 1980s and 1990s. BM25 and its newer variants, e.g. BM25F (a version of BM25 that can take document structure and anchor text into account), represent TF-IDF-like retrieval functions used in document retrieval.
This notebook shows how to use a retriever that uses ElasticSearch and BM25.
For more information on the details of BM25 see this blog post.
#!pip install elasticsearch
from langchain.retrievers import ElasticSearchBM25Retriever
Create New Retriever#
elasticsearch_url="http://localhost:9200"
retriever = ElasticSearchBM25Retriever.create(elasticsearch_url, "langchain-index-4")
# Alternatively, you can load an existing index
# import elasticsearch
# elasticsearch_url="http://localhost:9200"
|
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", "world", "hello", "foo bar"])
['cbd4cb47-8d9f-4f34-b80e-ea871bc49856',
'f3bd2e24-76d1-4f9b-826b-ec4c0e8c7365',
'8631bfc8-7c12-48ee-ab56-8ad5f373676e',
'8be8374c-3253-4d87-928d-d73550a2ecf0',
'd79f457b-2842-4eab-ae10-77aa420b53d7']
Use Retriever#
We can now use the retriever!
result = retriever.get_relevant_documents("foo")
result
[Document(page_content='foo', metadata={}),
Document(page_content='foo bar', metadata={})]
previous
Databerry
next
kNN
Contents
Create New Retriever
Add texts (if necessary)
Use Retriever
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/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 the hours passed since the object in the retriever was last accessed, not since it was created. This means that frequently accessed objects remain “fresh.”
import faiss
from datetime import datetime, timedelta
from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
from langchain.retrievers import TimeWeightedVectorStoreRetriever
from langchain.schema import Document
from langchain.vectorstores import FAISS
Low Decay Rate#
A low decay rate (in this, to be extreme, we will set close to 0) means memories will be “remembered” for longer. A decay rate of 0 means memories never be forgotten, making this retriever equivalent to the vector lookup.
# Define your embedding model
embeddings_model = OpenAIEmbeddings()
# Initialize the vectorstore as empty
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})
retriever = TimeWeightedVectorStoreRetriever(vectorstore=vectorstore, decay_rate=.0000000000000000000000001, k=1)
yesterday = datetime.now() - timedelta(days=1)
retriever.add_documents([Document(page_content="hello world", metadata={"last_accessed_at": yesterday})])
retriever.add_documents([Document(page_content="hello foo")])
|
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', metadata={'last_accessed_at': datetime.datetime(2023, 5, 13, 21, 0, 27, 678341), 'created_at': datetime.datetime(2023, 5, 13, 21, 0, 27, 279596), 'buffer_idx': 0})]
High Decay Rate#
With a high decay rate (e.g., several 9’s), the recency score quickly goes to 0! If you set this all the way to 1, recency is 0 for all objects, once again making this equivalent to a vector lookup.
# Define your embedding model
embeddings_model = OpenAIEmbeddings()
# Initialize the vectorstore as empty
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})
retriever = TimeWeightedVectorStoreRetriever(vectorstore=vectorstore, decay_rate=.999, k=1)
yesterday = datetime.now() - timedelta(days=1)
retriever.add_documents([Document(page_content="hello world", metadata={"last_accessed_at": yesterday})])
retriever.add_documents([Document(page_content="hello foo")])
['40011466-5bbe-4101-bfd1-e22e7f505de2']
|
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})]
Virtual Time#
Using some utils in LangChain, you can mock out the time component
from langchain.utils import mock_now
import datetime
# Notice the last access time is that date time
with mock_now(datetime.datetime(2011, 2, 3, 10, 11)):
print(retriever.get_relevant_documents("hello world"))
[Document(page_content='hello world', metadata={'last_accessed_at': MockDateTime(2011, 2, 3, 10, 11), 'created_at': datetime.datetime(2023, 5, 13, 21, 0, 27, 279596), 'buffer_idx': 0})]
previous
TF-IDF
next
VectorStore
Contents
Low Decay Rate
High Decay Rate
Virtual Time
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/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 in a retriever. This builds on top of ideas in the ContextualCompressionRetriever.
#!pip install cohere
#!pip install faiss
# OR (depending on Python version)
#!pip install faiss-cpu
# get a new token: https://dashboard.cohere.ai/
import os
import getpass
os.environ['COHERE_API_KEY'] = getpass.getpass('Cohere API Key:')
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')
# Helper function for printing docs
def pretty_print_docs(docs):
print(f"\n{'-' * 100}\n".join([f"Document {i+1}:\n\n" + d.page_content for i, d in enumerate(docs)]))
Set up the base vector store retriever#
Let’s start by initializing a simple vector store retriever and storing the 2023 State of the Union speech (in chunks). We can set up the retriever to retrieve a high number (20) of docs.
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_loaders import TextLoader
from langchain.vectorstores import FAISS
documents = TextLoader('../../../state_of_the_union.txt').load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
texts = text_splitter.split_documents(documents)
|
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 constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
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:
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 we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.
----------------------------------------------------------------------------------------------------
Document 3:
A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.
And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.
----------------------------------------------------------------------------------------------------
Document 4:
He met the Ukrainian people.
From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.
|
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.
----------------------------------------------------------------------------------------------------
Document 5:
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 beat, who’ll know the neighborhood, and who can restore trust and safety.
So let’s not abandon our streets. Or choose between safety and equal justice.
----------------------------------------------------------------------------------------------------
Document 6:
Vice President Harris and I ran for office with a new economic vision for America.
Invest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up
and the middle out, not from the top down.
Because we know that when the middle class grows, the poor have a ladder up and the wealthy do very well.
America used to have the best roads, bridges, and airports on Earth.
Now our infrastructure is ranked 13th in the world.
----------------------------------------------------------------------------------------------------
Document 7:
And tonight, I’m announcing that the Justice Department will name a chief prosecutor for pandemic fraud.
By the end of this year, the deficit will be down to less than half what it was before I took office.
The only president ever to cut the deficit by more than one trillion dollars in a single year.
Lowering your costs also means demanding more competition.
I’m a capitalist, but capitalism without competition isn’t capitalism.
It’s exploitation—and it drives up prices.
|
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 theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century.
Vice President Harris and I ran for office with a new economic vision for America.
----------------------------------------------------------------------------------------------------
Document 9:
All told, we created 369,000 new manufacturing jobs in America just last year.
Powered by people I’ve met like JoJo Burgess, from generations of union steelworkers from Pittsburgh, who’s here with us tonight.
As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.”
It’s time.
But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.
----------------------------------------------------------------------------------------------------
Document 10:
I’m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve.
And fourth, let’s end cancer as we know it.
This is personal to me and Jill, to Kamala, and to so many of you.
Cancer is the #2 cause of death in America–second only to heart disease.
----------------------------------------------------------------------------------------------------
Document 11:
He will never extinguish their love of freedom. He will never weaken the resolve of the free world.
We meet tonight in an America that has lived through two of the hardest years this nation has ever faced.
The pandemic has been punishing.
|
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, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.
Last year COVID-19 kept us apart. This year we are finally together again.
Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.
With a duty to one another to the American people to the Constitution.
And with an unwavering resolve that freedom will always triumph over tyranny.
----------------------------------------------------------------------------------------------------
Document 13:
I know.
One of those soldiers was my son Major Beau Biden.
We don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops.
But I’m committed to finding out everything we can.
Committed to military families like Danielle Robinson from Ohio.
The widow of Sergeant First Class Heath Robinson.
He was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq.
----------------------------------------------------------------------------------------------------
Document 14:
And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things.
So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.
First, beat the opioid epidemic.
There is so much we can do. Increase funding for prevention, treatment, harm reduction, and recovery.
----------------------------------------------------------------------------------------------------
Document 15:
Third, support our veterans.
Veterans are the best of us.
|
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 get VA care debt-free.
Our troops in Iraq and Afghanistan faced many dangers.
----------------------------------------------------------------------------------------------------
Document 16:
When we invest in our workers, when we build the economy from the bottom up and the middle out together, we can do something we haven’t done in a long time: build a better America.
For more than two years, COVID-19 has impacted every decision in our lives and the life of the nation.
And I know you’re tired, frustrated, and exhausted.
But I also know this.
----------------------------------------------------------------------------------------------------
Document 17:
Now is the hour.
Our moment of responsibility.
Our test of resolve and conscience, of history itself.
It is in this moment that our character is formed. Our purpose is found. Our future is forged.
Well I know this nation.
We will meet the test.
To protect freedom and liberty, to expand fairness and opportunity.
We will save democracy.
As hard as these times have been, I am more optimistic about America today than I have been my whole life.
----------------------------------------------------------------------------------------------------
Document 18:
He didn’t know how to stop fighting, and neither did she.
Through her pain she found purpose to demand we do better.
Tonight, Danielle—we are.
The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits.
And tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers.
----------------------------------------------------------------------------------------------------
Document 19:
|
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 I did as President was fight to pass the American Rescue Plan.
Because people were hurting. We needed to act, and we did.
Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis.
----------------------------------------------------------------------------------------------------
Document 20:
So let’s not abandon our streets. Or choose between safety and equal justice.
Let’s come together to protect our communities, restore trust, and hold law enforcement accountable.
That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.
Doing reranking with CohereRerank#
Now let’s wrap our base retriever with a ContextualCompressionRetriever. We’ll add an CohereRerank, uses the Cohere rerank endpoint to rerank the returned results.
from langchain.llms import OpenAI
from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import CohereRerank
llm = OpenAI(temperature=0)
compressor = CohereRerank()
compression_retriever = ContextualCompressionRetriever(base_compressor=compressor, base_retriever=retriever)
compressed_docs = compression_retriever.get_relevant_documents("What did the president say about Ketanji Jackson Brown")
pretty_print_docs(compressed_docs)
Document 1:
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
|
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 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 beat, who’ll know the neighborhood, and who can restore trust and safety.
So let’s not abandon our streets. Or choose between safety and equal justice.
----------------------------------------------------------------------------------------------------
Document 3:
A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.
And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.
You can of course use this retriever within a QA pipeline
from langchain.chains import RetrievalQA
chain = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), retriever=compression_retriever)
chain({"query": query})
{'query': 'What did the president say about Ketanji Brown Jackson',
'result': " The president said that Ketanji Brown Jackson is one of the nation's top legal minds and that she is a consensus builder who has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."}
previous
Self-querying with Chroma
next
Contextual Compression
Contents
|
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 sites.
from langchain.retrievers import PubMedRetriever
retriever = PubMedRetriever()
retriever.get_relevant_documents("chatgpt")
[Document(page_content='', metadata={'uid': '37268021', 'title': 'Dermatology in the wake of an AI revolution: who gets a say?', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>31</Day>'}),
Document(page_content='', metadata={'uid': '37267643', 'title': 'What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>30</Day>'}),
Document(page_content='The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.', metadata={'uid': '37266721', 'title': 'The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.', 'pub_date': '<Year>2023</Year><Month>Jun</Month><Day>02</Day>'})]
|
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 within an organization. Kendra is designed to help users find the information they need quickly and accurately, improving productivity and decision-making.
With Kendra, users can search across a wide range of content types, including documents, FAQs, knowledge bases, manuals, and websites. It supports multiple languages and can understand complex queries, synonyms, and contextual meanings to provide highly relevant search results.
Using the AWS Kendra Index Retriever#
#!pip install boto3
import boto3
from langchain.retrievers import AwsKendraIndexRetriever
Create New Retriever
kclient = boto3.client('kendra', region_name="us-east-1")
retriever = AwsKendraIndexRetriever(
kclient=kclient,
kendraindex="kendraindex",
)
Now you can use retrieved documents from AWS Kendra Index
retriever.get_relevant_documents("what is langchain")
previous
Arxiv
next
Azure Cognitive Search
Contents
Using the AWS Kendra Index Retriever
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/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.
Largely based on https://github.com/karpathy/randomfun/blob/master/knn_vs_svm.ipynb
#!pip install scikit-learn
#!pip install lark
We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.
import os
import getpass
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')
from langchain.retrievers import SVMRetriever
from langchain.embeddings import OpenAIEmbeddings
Create New Retriever with Texts#
retriever = SVMRetriever.from_texts(["foo", "bar", "world", "hello", "foo bar"], OpenAIEmbeddings())
Use Retriever#
We can now use the retriever!
result = retriever.get_relevant_documents("foo")
result
[Document(page_content='foo', metadata={}),
Document(page_content='foo bar', metadata={}),
Document(page_content='hello', metadata={}),
Document(page_content='world', metadata={})]
previous
Self-querying
next
TF-IDF
Contents
Create New Retriever with Texts
Use Retriever
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/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.
This notebook goes over how to use a retriever that under the hood uses an kNN.
Largely based on https://github.com/karpathy/randomfun/blob/master/knn_vs_svm.ipynb
from langchain.retrievers import KNNRetriever
from langchain.embeddings import OpenAIEmbeddings
Create New Retriever with Texts#
retriever = KNNRetriever.from_texts(["foo", "bar", "world", "hello", "foo bar"], OpenAIEmbeddings())
Use Retriever#
We can now use the retriever!
result = retriever.get_relevant_documents("foo")
result
[Document(page_content='foo', metadata={}),
Document(page_content='foo bar', metadata={}),
Document(page_content='hello', metadata={}),
Document(page_content='bar', metadata={})]
previous
ElasticSearch BM25
next
LOTR (Merger Retriever)
Contents
Create New Retriever with Texts
Use Retriever
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/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 over private, heterogeneous content in web, mobile, and enterprise applications.
Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you’ll work with the following capabilities:
A search engine for full text search over a search index containing user-owned content
Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation
Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more
Programmability through REST APIs and client libraries in Azure SDKs
Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)
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 here.
Please note
the name of your ACS service,
the name of your ACS index,
your API key.
Your API key can be either Admin or Query key, but as we only read data it is recommended to use a Query key.
Using the Azure Cognitive Search Retriever#
import os
from langchain.retrievers import AzureCognitiveSearchRetriever
Set Service Name, Index Name and API key as environment variables (alternatively, you can pass them as arguments to AzureCognitiveSearchRetriever).
os.environ["AZURE_COGNITIVE_SEARCH_SERVICE_NAME"] = "<YOUR_ACS_SERVICE_NAME>"
os.environ["AZURE_COGNITIVE_SEARCH_INDEX_NAME"] ="<YOUR_ACS_INDEX_NAME>"
|
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
Set up Azure Cognitive Search
Using the Azure Cognitive Search Retriever
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/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 details of TF-IDF see this blog post.
# !pip install scikit-learn
from langchain.retrievers import TFIDFRetriever
Create New Retriever with Texts#
retriever = TFIDFRetriever.from_texts(["foo", "bar", "world", "hello", "foo bar"])
Create a New Retriever with Documents#
You can now create a new retriever with the documents you created.
from langchain.schema import Document
retriever = TFIDFRetriever.from_documents([Document(page_content="foo"), Document(page_content="bar"), Document(page_content="world"), Document(page_content="hello"), Document(page_content="foo bar")])
Use Retriever#
We can now use the retriever!
result = retriever.get_relevant_documents("foo")
result
[Document(page_content='foo', metadata={}),
Document(page_content='foo bar', metadata={}),
Document(page_content='hello', metadata={}),
Document(page_content='world', metadata={})]
previous
SVM
next
Time Weighted VectorStore
Contents
Create New Retriever with Texts
Create a New Retriever with Documents
Use Retriever
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/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 connection a Vespa service.
#!pip install pyvespa
from vespa.application import Vespa
vespa_app = Vespa(url="https://doc-search.vespa.oath.cloud")
This creates a connection to a Vespa service, here the Vespa documentation search service.
Using pyvespa package, you can also connect to a
Vespa Cloud instance
or a local
Docker instance.
After connecting to the service, you can set up the retriever:
from langchain.retrievers.vespa_retriever import VespaRetriever
vespa_query_body = {
"yql": "select content from paragraph where userQuery()",
"hits": 5,
"ranking": "documentation",
"locale": "en-us"
}
vespa_content_field = "content"
retriever = VespaRetriever(vespa_app, vespa_query_body, vespa_content_field)
This sets up a LangChain retriever that fetches documents from the Vespa application.
Here, up to 5 results are retrieved from the content field in the paragraph document type,
using doumentation as the ranking method. The userQuery() is replaced with the actual query
passed from LangChain.
Please refer to the pyvespa documentation
for more information.
Now you can return the results and continue using the results in LangChain.
retriever.get_relevant_documents("what is vespa?")
|
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 enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.
Key Features:
Long-term memory persistence, with access to historical messages irrespective of your summarization strategy.
Auto-summarization of memory messages based on a configurable message window. A series of summaries are stored, providing flexibility for future summarization strategies.
Vector search over memories, with messages automatically embedded on creation.
Auto-token counting of memories and summaries, allowing finer-grained control over prompt assembly.
Python and JavaScript SDKs.
Zep’s Go Extractor model is easily extensible, with a simple, clean interface available to build new enrichment functionality, such as summarizers, entity extractors, embedders, and more.
Zep project: getzep/zep
Retriever Example#
This notebook demonstrates how to search historical chat message histories using the Zep Long-term Memory Store.
We’ll demonstrate:
Adding conversation history to the Zep memory store.
Vector search over the conversation history.
from langchain.memory.chat_message_histories import ZepChatMessageHistory
from langchain.schema import HumanMessage, AIMessage
from uuid import uuid4
# Set this to your Zep server URL
ZEP_API_URL = "http://localhost:8000"
Initialize the Zep Chat Message History Class and add a chat message history to the memory store#
|
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 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 window is 12 messages. We want to push beyond this to demonstrate auto-summarization.
test_history = [
{"role": "human", "content": "Who was Octavia Butler?"},
{
"role": "ai",
"content": (
"Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American"
" science fiction author."
),
},
{"role": "human", "content": "Which books of hers were made into movies?"},
{
"role": "ai",
"content": (
"The most well-known adaptation of Octavia Butler's work is the FX series"
" Kindred, based on her novel of the same name."
),
},
{"role": "human", "content": "Who were her contemporaries?"},
{
"role": "ai",
"content": (
"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R."
" Delany, and Joanna Russ."
),
},
|
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",
"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": (
"Write a short synopsis of Butler's book, Parable of the Sower. What is it"
" about?"
),
},
{
"role": "ai",
"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."
),
},
]
for msg in test_history:
zep_chat_history.append(
HumanMessage(content=msg["content"])
if msg["role"] == "human"
else AIMessage(content=msg["content"])
)
Use the Zep Retriever to vector search over the Zep memory#
Zep provides native vector search over historical conversation memory. Embedding happens automatically.
|
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_retriever = ZepRetriever(
session_id=session_id, # Ensure that you provide the session_id when instantiating the Retriever
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': 8}),
Document(page_content="Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.", metadata={'score': 0.7602262941130749, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),
|
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 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 books of hers were made into movies?', metadata={'score': 0.7496714959247069, 'uuid': '18046c3a-9666-4d3e-b4f0-43d1394732b7', 'created_at': '2023-05-25T15:03:30.236837Z', 'role': 'human', 'token_count': 11})]
We can also use the Zep sync API to retrieve results:
zep_retriever.get_relevant_documents("Who wrote Parable of the Sower?")
|
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, 'uuid': '1c09603a-52c1-40d7-9d69-29f26256029c', 'created_at': '2023-05-25T15:03:30.268257Z', 'role': 'ai', 'token_count': 56}),
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 Butler?', metadata={'score': 0.7759670375149477, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),
|
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 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
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
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/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 points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful
In the notebook we’ll demo the SelfQueryRetriever wrapped around a Qdrant vector store.
Creating a Qdrant vectorstore#
First we’ll want to create a Chroma VectorStore and seed it with some data. We’ve created a small demo set of documents that contain summaries of movies.
NOTE: The self-query retriever requires you to have lark installed (pip install lark). We also need the qdrant-client package.
#!pip install lark qdrant-client
We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.
# import os
# import getpass
# os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')
from langchain.schema import Document
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Qdrant
embeddings = OpenAIEmbeddings()
docs = [
Document(page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose", metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"}),
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}),
|
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", 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="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})
]
vectorstore = Qdrant.from_documents(
docs,
embeddings,
location=":memory:", # Local mode with in-memory storage only
collection_name="my_documents",
)
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 import SelfQueryRetriever
from langchain.chains.query_constructor.base import AttributeInfo
metadata_field_info=[
AttributeInfo(
name="genre",
description="The genre of the movie",
type="string or list[string]",
),
AttributeInfo(
name="year",
description="The year the movie was released",
type="integer",
),
|
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 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 specifies a relevant query
retriever.get_relevant_documents("What are some movies about dinosaurs")
query='dinosaur' filter=None limit=None
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
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'}),
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})]
# This example only specifies a filter
retriever.get_relevant_documents("I want to watch a movie rated higher than 8.5")
|
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 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})]
# This example specifies a query and a filter
retriever.get_relevant_documents("Has Greta Gerwig directed any movies about women")
query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None
[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})]
# This example specifies a composite filter
retriever.get_relevant_documents("What's a highly rated (above 8.5) science fiction film?")
query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None
|
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 that's all about toys, and preferably is animated")
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')]) limit=None
[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]
Filter k#
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=True
)
# This example only specifies a relevant query
retriever.get_relevant_documents("what are two movies about dinosaurs")
query='dinosaur' filter=None limit=2
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
|
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 Chase.
Last updated on Jun 16, 2023.
|
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 allow ChatGPT to do things like:
Retrieve real-time information; e.g., sports scores, stock prices, the latest news, etc.
Retrieve knowledge-base information; e.g., company docs, personal notes, etc.
Perform actions on behalf of the user; e.g., booking a flight, ordering food, etc.
This notebook shows how to use the ChatGPT Retriever Plugin within LangChain.
# STEP 1: Load
# Load documents using LangChain's DocumentLoaders
# This is from https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/csv.html
from langchain.document_loaders.csv_loader import CSVLoader
loader = CSVLoader(file_path='../../document_loaders/examples/example_data/mlb_teams_2012.csv')
data = loader.load()
# STEP 2: Convert
# Convert Document to format expected by https://github.com/openai/chatgpt-retrieval-plugin
from typing import List
from langchain.docstore.document import Document
import json
def write_json(path: str, documents: List[Document])-> None:
results = [{"text": doc.page_content} for doc in documents]
with open(path, "w") as f:
json.dump(results, f, indent=2)
write_json("foo.json", data)
# STEP 3: Use
# Ingest this as you would any other json file in https://github.com/openai/chatgpt-retrieval-plugin/tree/main/scripts/process_json
|
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 API Key:')
from langchain.retrievers import ChatGPTPluginRetriever
retriever = ChatGPTPluginRetriever(url="http://0.0.0.0:8000", bearer_token="foo")
retriever.get_relevant_documents("alice's phone number")
[Document(page_content="This is Alice's phone number: 123-456-7890", lookup_str='', metadata={'id': '456_0', 'metadata': {'source': 'email', 'source_id': '567', 'url': None, 'created_at': '1609592400.0', 'author': 'Alice', 'document_id': '456'}, 'embedding': None, 'score': 0.925571561}, lookup_index=0),
Document(page_content='This is a document about something', lookup_str='', metadata={'id': '123_0', 'metadata': {'source': 'file', 'source_id': 'https://example.com/doc1', 'url': 'https://example.com/doc1', 'created_at': '1609502400.0', 'author': 'Alice', 'document_id': '123'}, 'embedding': None, 'score': 0.6987589}, lookup_index=0),
|
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': None, 'score': 0.697888613}, lookup_index=0)]
previous
Azure Cognitive Search
next
Self-querying with Chroma
Contents
Using the ChatGPT Retriever Plugin
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/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 notebook introduces the concept of DocumentCompressors and the ContextualCompressionRetriever. The core idea is simple: given a specific query, we should be able to return only the documents relevant to that query, and only the parts of those documents that are relevant. The ContextualCompressionsRetriever is a wrapper for another retriever that iterates over the initial output of the base retriever and filters and compresses those initial documents, so that only the most relevant information is returned.
# Helper function for printing docs
def pretty_print_docs(docs):
print(f"\n{'-' * 100}\n".join([f"Document {i+1}:\n\n" + d.page_content for i, d in enumerate(docs)]))
Using a vanilla vector store retriever#
Let’s start by initializing a simple vector store retriever and storing the 2023 State of the Union speech (in chunks). We can see that given an example question our retriever returns one or two relevant docs and a few irrelevant docs. And even the relevant docs have a lot of irrelevant information in them.
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_loaders import TextLoader
from langchain.vectorstores import FAISS
documents = TextLoader('../../../state_of_the_union.txt').load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
|
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. 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.
Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
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:
A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.
And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.
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.
|
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 refugees and secure their own borders.
----------------------------------------------------------------------------------------------------
Document 3:
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.
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 we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.
And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things.
So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.
First, beat the opioid epidemic.
----------------------------------------------------------------------------------------------------
Document 4:
Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers.
And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.
That ends on my watch.
Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect.
We’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees.
|
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 best-kept secret: community colleges.
Adding contextual compression with an LLMChainExtractor#
Now let’s wrap our base retriever with a ContextualCompressionRetriever. We’ll add an LLMChainExtractor, which will iterate over the initially returned documents and extract from each only the content that is relevant to the query.
from langchain.llms import OpenAI
from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import LLMChainExtractor
llm = OpenAI(temperature=0)
compressor = LLMChainExtractor.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(base_compressor=compressor, base_retriever=retriever)
compressed_docs = compression_retriever.get_relevant_documents("What did the president say about Ketanji Jackson Brown")
pretty_print_docs(compressed_docs)
Document 1:
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
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:
|
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 received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
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_compressors import LLMChainFilter
_filter = LLMChainFilter.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(base_compressor=_filter, base_retriever=retriever)
compressed_docs = compression_retriever.get_relevant_documents("What did the president say about Ketanji Jackson Brown")
pretty_print_docs(compressed_docs)
Document 1:
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.
Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
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.
EmbeddingsFilter#
|
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 OpenAIEmbeddings
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_docs = compression_retriever.get_relevant_documents("What did the president say about Ketanji Jackson Brown")
pretty_print_docs(compressed_docs)
Document 1:
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.
Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
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:
|
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 a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.
And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.
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 their cases heard faster.
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 to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong.
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 we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.
And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things.
So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.
First, beat the opioid epidemic.
Stringing compressors and document transformers together#
|
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 simply perform some transformation on a set of documents. For example TextSplitters can be used as document transformers to split documents into smaller pieces, and the EmbeddingsRedundantFilter can be used to filter out redundant documents based on embedding similarity between documents.
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 DocumentCompressorPipeline
from langchain.text_splitter import CharacterTextSplitter
splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=0, separator=". ")
redundant_filter = EmbeddingsRedundantFilter(embeddings=embeddings)
relevant_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.76)
pipeline_compressor = DocumentCompressorPipeline(
transformers=[splitter, redundant_filter, relevant_filter]
)
compression_retriever = ContextualCompressionRetriever(base_compressor=pipeline_compressor, base_retriever=retriever)
compressed_docs = compression_retriever.get_relevant_documents("What did the president say about Ketanji Jackson Brown")
pretty_print_docs(compressed_docs)
Document 1:
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson
----------------------------------------------------------------------------------------------------
Document 2:
|
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 we never agree, that isn’t true. I signed 80 bipartisan bills into law last year
----------------------------------------------------------------------------------------------------
Document 3:
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
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
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 Hybrid Search.
The logic of this retriever is taken from this documentaion
To use Pinecone, you must have an API key and an Environment.
Here are the installation instructions.
#!pip install pinecone-client pinecone-text
import os
import getpass
os.environ['PINECONE_API_KEY'] = getpass.getpass('Pinecone API Key:')
from langchain.retrievers import PineconeHybridSearchRetriever
os.environ['PINECONE_ENVIRONMENT'] = getpass.getpass('Pinecone Environment:')
We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')
Setup Pinecone#
You should only have to do this part once.
Note: it’s important to make sure that the “context” field that holds the document text in the metadata is not indexed. Currently you need to specify explicitly the fields you do want to index. For more information checkout Pinecone’s docs.
import os
import pinecone
api_key = os.getenv("PINECONE_API_KEY") or "PINECONE_API_KEY"
# find environment next to your API key in the Pinecone console
env = os.getenv("PINECONE_ENVIRONMENT") or "PINECONE_ENVIRONMENT"
index_name = "langchain-pinecone-hybrid-search"
pinecone.init(api_key=api_key, enviroment=env)
|
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 for dotproduct
pod_type = "s1",
metadata_config={"indexed": []} # see explaination above
)
Now that its created, we can use it
index = pinecone.Index(index_name)
Get embeddings and sparse encoders#
Embeddings are used for the dense vectors, tokenizer is used for the sparse vector
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
To encode the text to sparse values you can either choose SPLADE or BM25. For out of domain tasks we recommend using BM25.
For more information about the sparse encoders you can checkout pinecone-text library docs.
from pinecone_text.sparse import BM25Encoder
# or from pinecone_text.sparse import SpladeEncoder if you wish to work with SPLADE
# use default tf-idf values
bm25_encoder = BM25Encoder().default()
The above code is using default tfids values. It’s highly recommended to fit the tf-idf values to your own corpus. You can do it as follow:
corpus = ["foo", "bar", "world", "hello"]
# fit tf-idf values on your corpus
bm25_encoder.fit(corpus)
# store the values to a json file
bm25_encoder.dump("bm25_values.json")
# load to your BM25Encoder object
bm25_encoder = BM25Encoder().load("bm25_values.json")
Load Retriever#
|
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"])
100%|██████████| 1/1 [00:02<00:00, 2.27s/it]
Use Retriever#
We can now use the retriever!
result = retriever.get_relevant_documents("foo")
result[0]
Document(page_content='foo', metadata={})
previous
Metal
next
PubMed Retriever
Contents
Setup Pinecone
Get embeddings and sparse encoders
Load Retriever
Add texts (if necessary)
Use Retriever
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/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 VectorStore.
Once you construct a VectorStore, its very easy to construct a retriever. Let’s walk through an example.
from langchain.document_loaders import TextLoader
loader = TextLoader('../../../state_of_the_union.txt')
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
db = FAISS.from_documents(texts, embeddings)
Exiting: Cleaning up .chroma directory
retriever = db.as_retriever()
docs = retriever.get_relevant_documents("what did he say about ketanji brown jackson")
Maximum Marginal Relevance Retrieval#
By default, the vectorstore retriever uses similarity search. If the underlying vectorstore support maximum marginal relevance search, you can specify that as the search type.
retriever = db.as_retriever(search_type="mmr")
docs = retriever.get_relevant_documents("what did he say abotu ketanji brown jackson")
Similarity Score Threshold Retrieval#
You can also use a retrieval method that sets a similarity score threshold and only returns documents with a score above that threshold
retriever = db.as_retriever(search_type="similarity_score_threshold", search_kwargs={"score_threshold": .5})
|
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(docs)
1
previous
Time Weighted VectorStore
next
Vespa
Contents
Maximum Marginal Relevance Retrieval
Similarity Score Threshold Retrieval
Specifying top k
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/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 query-constructing LLM chain to write a structured query and then applies that structured query to it’s underlying VectorStore. This allows the retriever to not only use the user-input query for semantic similarity comparison with the contents of stored documented, but to also extract filters from the user query on the metadata of stored documents and to execute those filters.
Creating a Pinecone index#
First we’ll want to create a Pinecone VectorStore and seed it with some data. We’ve created a small demo set of documents that contain summaries of movies.
To use Pinecone, you to have pinecone package installed and you must have an API key and an Environment. Here are the installation instructions.
NOTE: The self-query retriever requires you to have lark package installed.
# !pip install lark
#!pip install pinecone-client
import os
import pinecone
pinecone.init(api_key=os.environ["PINECONE_API_KEY"], environment=os.environ["PINECONE_ENV"])
/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/pinecone/index.py:4: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)
from tqdm.autonotebook import tqdm
from langchain.schema import Document
from langchain.embeddings.openai import OpenAIEmbeddings
|
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 bring back dinosaurs and mayhem breaks loose", metadata={"year": 1993, "rating": 7.7, "genre": ["action", "science fiction"]}),
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}),
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", 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="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", "thriller"], "rating": 9.9})
]
vectorstore = Pinecone.from_documents(
docs, embeddings, index_name="langchain-self-retriever-demo"
)
Creating our self-querying retriever#
|
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 import SelfQueryRetriever
from langchain.chains.query_constructor.base import AttributeInfo
metadata_field_info=[
AttributeInfo(
name="genre",
description="The genre of the movie",
type="string or list[string]",
),
AttributeInfo(
name="year",
description="The year the movie was released",
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 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 specifies a relevant query
retriever.get_relevant_documents("What are some movies about dinosaurs")
query='dinosaur' filter=None
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'genre': ['action', 'science fiction'], 'rating': 7.7, 'year': 1993.0}),
|
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': 2006.0}),
Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'director': 'Christopher Nolan', 'rating': 8.2, 'year': 2010.0})]
# This example only specifies a filter
retriever.get_relevant_documents("I want to watch a movie rated higher than 8.5")
query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)
[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': 2006.0}),
Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'director': 'Andrei Tarkovsky', 'genre': ['science fiction', 'thriller'], 'rating': 9.9, 'year': 1979.0})]
# This example specifies a query and a filter
retriever.get_relevant_documents("Has Greta Gerwig directed any movies about women")
query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig')
|
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?")
query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction'), Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)])
[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'director': 'Andrei Tarkovsky', 'genre': ['science fiction', 'thriller'], 'rating': 9.9, 'year': 1979.0})]
# This example specifies a query and composite filter
retriever.get_relevant_documents("What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated")
query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990.0), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005.0), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')])
[Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'year': 1995.0})]
Filter k#
We can also use the self query retriever to specify k: the number of documents to fetch.
|
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("What are two movies about dinosaurs")
previous
Self-querying with Qdrant
next
SVM
Contents
Creating a Pinecone index
Creating our self-querying retriever
Testing it out
Filter k
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/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.
Creating a Chroma vectorstore#
First we’ll want to create a Chroma VectorStore and seed it with some data. We’ve created a small demo set of documents that contain summaries of movies.
NOTE: The self-query retriever requires you to have lark installed (pip install lark). We also need the chromadb package.
#!pip install lark
#!pip install chromadb
We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.
import os
import getpass
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')
from langchain.schema import Document
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
embeddings = OpenAIEmbeddings()
docs = [
Document(page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose", metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"}),
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}),
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}),
|
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="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})
]
vectorstore = Chroma.from_documents(
docs, embeddings
)
Using embedded DuckDB without persistence: data will be transient
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 import SelfQueryRetriever
from langchain.chains.query_constructor.base import AttributeInfo
metadata_field_info=[
AttributeInfo(
name="genre",
description="The genre of the movie",
type="string or list[string]",
),
AttributeInfo(
name="year",
description="The year the movie was released",
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"
),
]
|
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 specifies a relevant query
retriever.get_relevant_documents("What are some movies about dinosaurs")
query='dinosaur' filter=None
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),
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='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.2})]
# This example only specifies a filter
retriever.get_relevant_documents("I want to watch a movie rated higher than 8.5")
query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)
[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}),
|
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")
query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig')
[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})]
# This example specifies a composite filter
retriever.get_relevant_documents("What's a highly rated (above 8.5) science fiction film?")
query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction'), Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)])
[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 that's all about toys, and preferably is animated")
|
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(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]
Filter k#
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=True
)
# This example only specifies a relevant query
retriever.get_relevant_documents("what are two movies about dinosaurs")
query='dinosaur' filter=None
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),
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}),
|
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
Filter k
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/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 science, and economics.
This notebook shows how to retrieve scientific articles from Arxiv.org into the Document format that is used downstream.
Installation#
First, you need to install arxiv python package.
#!pip install arxiv
ArxivRetriever has these arguments:
optional load_max_docs: default=100. Use it to limit number of downloaded documents. It takes time to download all 100 documents, so use a small number for experiments. There is a hard limit of 300 for now.
optional load_all_available_meta: default=False. By default only the most important fields downloaded: Published (date when document was published/last updated), Title, Authors, Summary. If True, other fields also downloaded.
get_relevant_documents() has one argument, query: free text which used to find documents in Arxiv.org
Examples#
Running retriever#
from langchain.retrievers import ArxivRetriever
retriever = ArxivRetriever(load_max_docs=2)
docs = retriever.get_relevant_documents(query='1605.08386')
docs[0].metadata # meta-information of the Document
{'Published': '2016-05-26',
'Title': 'Heat-bath random walks with Markov bases',
'Authors': 'Caprice Stanley, Tobias Windisch',
|
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 behaviour of heat-bath random walks on these graphs. We\nalso state explicit conditions on the set of moves so that the heat-bath random\nwalk, a generalization of the Glauber dynamics, is an expander in fixed\ndimension.'}
docs[0].page_content[:400] # a content of the Document
'arXiv:1605.08386v1 [math.CO] 26 May 2016\nHEAT-BATH RANDOM WALKS WITH MARKOV BASES\nCAPRICE STANLEY AND TOBIAS WINDISCH\nAbstract. 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 fibers of a\nfixed integer matrix can be bounded from above by a constant. We then study the mixing\nbehaviour of heat-b'
Question Answering on facts#
# get a token: https://platform.openai.com/account/api-keys
from getpass import getpass
OPENAI_API_KEY = getpass()
import os
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationalRetrievalChain
model = ChatOpenAI(model_name='gpt-3.5-turbo') # switch to 'gpt-4'
qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)
questions = [
|
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.append((question, result['answer']))
print(f"-> **Question**: {question} \n")
print(f"**Answer**: {result['answer']} \n")
-> **Question**: What are Heat-bath random walks with Markov base?
**Answer**: I'm not sure, as I don't have enough context to provide a definitive answer. The term "Heat-bath random walks with Markov base" is not mentioned in the given text. Could you provide more information or context about where you encountered this term?
-> **Question**: What is the ImageBind model?
**Answer**: ImageBind is an approach developed by Facebook AI Research to learn a joint embedding across six different modalities, including images, text, audio, depth, thermal, and IMU data. The approach uses the binding property of images to align each modality's embedding to image embeddings and achieve an emergent alignment across all modalities. This enables novel multimodal capabilities, including cross-modal retrieval, embedding-space arithmetic, and audio-to-image generation, among others. The approach sets a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Additionally, it shows strong few-shot recognition results and serves as a new way to evaluate vision models for visual and non-visual tasks.
-> **Question**: How does Compositional Reasoning with Large Language Models works?
|
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 structured way. This involves understanding the syntax and semantics of language and using that understanding to build up more complex meanings from simpler ones.
In the context of the paper "Does CLIP Bind Concepts? Probing Compositionality in Large Image Models", the authors focus specifically on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way. They examine CLIP's ability to compose concepts in a single-object setting, as well as in situations where concept binding is needed.
The authors situate their work within the tradition of research on compositional distributional semantics models (CDSMs), which seek to bridge the gap between distributional models and formal semantics by building architectures which operate over vectors yet still obey traditional theories of linguistic composition. They compare the performance of CLIP with several architectures from research on CDSMs to evaluate its ability to encode and reason about compositional concepts.
questions = [
"What are Heat-bath random walks with Markov base? Include references to answer.",
]
chat_history = []
for question in questions:
result = qa({"question": question, "chat_history": chat_history})
chat_history.append((question, result['answer']))
print(f"-> **Question**: {question} \n")
print(f"**Answer**: {result['answer']} \n")
-> **Question**: What are Heat-bath random walks with Markov base? Include references to answer.
|
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.