id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 59
127
|
|---|---|---|
dc38ca462716-12
|
'imageWidth': 1400,
'imageHeight': 845,
'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSgB3z_D4dMEOWJ7lajJk4XaQSL4DdUvIRj4UXZ0YoE5fGuWuo&s',
'thumbnailWidth': 289,
'thumbnailHeight': 174,
'source': "Smithsonian's National Zoo",
'domain': 'nationalzoo.si.edu',
'link': 'https://nationalzoo.si.edu/animals/lion',
'position': 9},
{'title': "Zoo's New Male Lion Explores Habitat for the First Time "
'- Virginia Zoo',
'imageUrl': 'https://virginiazoo.org/wp-content/uploads/2022/04/ZOO_0056-scaled.jpg',
'imageWidth': 2560,
'imageHeight': 2141,
'thumbnailUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTDCG7XvXRCwpe_-Vy5mpvrQpVl5q2qwgnDklQhrJpQzObQGz4&s',
'thumbnailWidth': 246,
'thumbnailHeight': 205,
'source': 'Virginia Zoo',
'domain': 'virginiazoo.org',
'link': 'https://virginiazoo.org/zoos-new-male-lion-explores-habitat-for-thefirst-time/',
'position': 10}]}
Searching for Google News#
We can also query Google News using this wrapper. For example:
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-13
|
Searching for Google News#
We can also query Google News using this wrapper. For example:
search = GoogleSerperAPIWrapper(type="news")
results = search.results("Tesla Inc.")
pprint.pp(results)
{'searchParameters': {'q': 'Tesla Inc.',
'gl': 'us',
'hl': 'en',
'num': 10,
'type': 'news'},
'news': [{'title': 'ISS recommends Tesla investors vote against re-election '
'of Robyn Denholm',
'link': 'https://www.reuters.com/business/autos-transportation/iss-recommends-tesla-investors-vote-against-re-election-robyn-denholm-2023-05-04/',
'snippet': 'Proxy advisory firm ISS on Wednesday recommended Tesla '
'investors vote against re-election of board chair Robyn '
'Denholm, citing "concerns on...',
'date': '5 mins ago',
'source': 'Reuters',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcROdETe_GUyp1e8RHNhaRM8Z_vfxCvdfinZwzL1bT1ZGSYaGTeOojIdBoLevA&s',
'position': 1},
{'title': 'Global companies by market cap: Tesla fell most in April',
'link': 'https://www.reuters.com/markets/global-companies-by-market-cap-tesla-fell-most-april-2023-05-02/',
'snippet': 'Tesla Inc was the biggest loser among top companies by '
'market capitalisation in April, hit by disappointing '
'quarterly earnings after it...',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-14
|
'quarterly earnings after it...',
'date': '1 day ago',
'source': 'Reuters',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ4u4CP8aOdGyRFH6o4PkXi-_eZDeY96vLSag5gDjhKMYf98YBER2cZPbkStQ&s',
'position': 2},
{'title': 'Tesla Wanted an EV Price War. Ford Showed Up.',
'link': 'https://www.bloomberg.com/opinion/articles/2023-05-03/tesla-wanted-an-ev-price-war-ford-showed-up',
'snippet': 'The legacy automaker is paring back the cost of its '
'Mustang Mach-E model after Tesla discounted its '
'competing EVs, portending tighter...',
'date': '6 hours ago',
'source': 'Bloomberg.com',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcS_3Eo4VI0H-nTeIbYc5DaQn5ep7YrWnmhx6pv8XddFgNF5zRC9gEpHfDq8yQ&s',
'position': 3},
{'title': 'Joby Aviation to get investment from Tesla shareholder '
'Baillie Gifford',
'link': 'https://finance.yahoo.com/news/joby-aviation-investment-tesla-shareholder-204450712.html',
'snippet': 'This comes days after Joby clinched a $55 million '
'contract extension to deliver up to nine air taxis to '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-15
|
'contract extension to deliver up to nine air taxis to '
'the U.S. Air Force,...',
'date': '4 hours ago',
'source': 'Yahoo Finance',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQO0uVn297LI-xryrPNqJ-apUOulj4ohM-xkN4OfmvMOYh1CPdUEBbYx6hviw&s',
'position': 4},
{'title': 'Tesla resumes U.S. orders for a Model 3 version at lower '
'price, range',
'link': 'https://finance.yahoo.com/news/tesla-resumes-us-orders-model-045736115.html',
'snippet': '(Reuters) -Tesla Inc has resumed taking orders for its '
'Model 3 long-range vehicle in the United States, the '
"company's website showed late on...",
'date': '19 hours ago',
'source': 'Yahoo Finance',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTIZetJ62sQefPfbQ9KKDt6iH7Mc0ylT5t_hpgeeuUkHhJuAx2FOJ4ZTRVDFg&s',
'position': 5},
{'title': 'The Tesla Model 3 Long Range AWD Is Now Available in the '
'U.S. With 325 Miles of Range',
'link': 'https://www.notateslaapp.com/news/1393/tesla-reopens-orders-for-model-3-long-range-after-months-of-unavailability',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-16
|
'snippet': 'Tesla has reopened orders for the Model 3 Long Range '
'RWD, which has been unavailable for months due to high '
'demand.',
'date': '7 hours ago',
'source': 'Not a Tesla App',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSecrgxZpRj18xIJY-nDHljyP-A4ejEkswa9eq77qhMNrScnVIqe34uql5U4w&s',
'position': 6},
{'title': 'Tesla Cybertruck alpha prototype spotted at the Fremont '
'factory in new pics and videos',
'link': 'https://www.teslaoracle.com/2023/05/03/tesla-cybertruck-alpha-prototype-interior-and-exterior-spotted-at-the-fremont-factory-in-new-pics-and-videos/',
'snippet': 'A Tesla Cybertruck alpha prototype goes to Fremont, '
'California for another round of testing before going to '
'production later this year (pics...',
'date': '14 hours ago',
'source': 'Tesla Oracle',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRO7M5ZLQE-Zo4-_5dv9hNAQZ3wSqfvYCuKqzxHG-M6CgLpwPMMG_ssebdcMg&s',
'position': 7},
{'title': 'Tesla putting facility in new part of country - Austin '
'Business Journal',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-17
|
'Business Journal',
'link': 'https://www.bizjournals.com/austin/news/2023/05/02/tesla-leases-building-seattle-area.html',
'snippet': 'Check out what Puget Sound Business Journal has to '
"report about the Austin-based company's real estate "
'footprint in the Pacific Northwest.',
'date': '22 hours ago',
'source': 'The Business Journals',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcR9kIEHWz1FcHKDUtGQBS0AjmkqtyuBkQvD8kyIY3kpaPrgYaN7I_H2zoOJsA&s',
'position': 8},
{'title': 'Tesla (TSLA) Resumes Orders for Model 3 Long Range After '
'Backlog',
'link': 'https://www.bloomberg.com/news/articles/2023-05-03/tesla-resumes-orders-for-popular-model-3-long-range-at-47-240',
'snippet': 'Tesla Inc. has resumed taking orders for its Model 3 '
'Long Range edition with a starting price of $47240, '
'according to its website.',
'date': '5 hours ago',
'source': 'Bloomberg.com',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTWWIC4VpMTfRvSyqiomODOoLg0xhoBf-Tc1qweKnSuaiTk-Y1wMJZM3jct0w&s',
'position': 9}]}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-18
|
'position': 9}]}
If you want to only receive news articles published in the last hour, you can do the following:
search = GoogleSerperAPIWrapper(type="news", tbs="qdr:h")
results = search.results("Tesla Inc.")
pprint.pp(results)
{'searchParameters': {'q': 'Tesla Inc.',
'gl': 'us',
'hl': 'en',
'num': 10,
'type': 'news',
'tbs': 'qdr:h'},
'news': [{'title': 'Oklahoma Gov. Stitt sees growing foreign interest in '
'investments in ...',
'link': 'https://www.reuters.com/world/us/oklahoma-gov-stitt-sees-growing-foreign-interest-investments-state-2023-05-04/',
'snippet': 'T)), a battery supplier to electric vehicle maker Tesla '
'Inc (TSLA.O), said on Sunday it is considering building '
'a battery plant in Oklahoma, its third in...',
'date': '53 mins ago',
'source': 'Reuters',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSSTcsXeenqmEKdiekvUgAmqIPR4nlAmgjTkBqLpza-lLfjX1CwB84MoNVj0Q&s',
'position': 1},
{'title': 'Ryder lanza solución llave en mano para vehículos '
'eléctricos en EU',
'link': 'https://www.tyt.com.mx/nota/ryder-lanza-solucion-llave-en-mano-para-vehiculos-electricos-en-eu',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-19
|
'snippet': 'Ryder System Inc. presentó RyderElectric+ TM como su '
'nueva solución llave en mano ... Ryder también tiene '
'reservados los semirremolques Tesla y continúa...',
'date': '56 mins ago',
'source': 'Revista Transportes y Turismo',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQJhXTQQtjSUZf9YPM235WQhFU5_d7lEA76zB8DGwZfixcgf1_dhPJyKA1Nbw&s',
'position': 2},
{'title': '"I think people can get by with $999 million," Bernie '
'Sanders tells American Billionaires.',
'link': 'https://thebharatexpressnews.com/i-think-people-can-get-by-with-999-million-bernie-sanders-tells-american-billionaires-heres-how-the-ultra-rich-can-pay-less-income-tax-than-you-legally/',
'snippet': 'The report noted that in 2007 and 2011, Amazon.com Inc. '
'founder Jeff Bezos “did not pay a dime in federal ... '
'If you want to bet on Musk, check out Tesla.',
'date': '11 mins ago',
'source': 'THE BHARAT EXPRESS NEWS',
'imageUrl': 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcR_X9qqSwVFBBdos2CK5ky5IWIE3aJPCQeRYR9O1Jz4t-MjaEYBuwK7AU3AJQ&s',
'position': 3}]}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-20
|
'position': 3}]}
Some examples of the tbs parameter:
qdr:h (past hour)
qdr:d (past day)
qdr:w (past week)
qdr:m (past month)
qdr:y (past year)
You can specify intermediate time periods by adding a number:
qdr:h12 (past 12 hours)
qdr:d3 (past 3 days)
qdr:w2 (past 2 weeks)
qdr:m6 (past 6 months)
qdr:m2 (past 2 years)
For all supported filters simply go to Google Search, search for something, click on “Tools”, add your date filter and check the URL for “tbs=”.
Searching for Google Places#
We can also query Google Places using this wrapper. For example:
search = GoogleSerperAPIWrapper(type="places")
results = search.results("Italian restaurants in Upper East Side")
pprint.pp(results)
{'searchParameters': {'q': 'Italian restaurants in Upper East Side',
'gl': 'us',
'hl': 'en',
'num': 10,
'type': 'places'},
'places': [{'position': 1,
'title': "L'Osteria",
'address': '1219 Lexington Ave',
'latitude': 40.777154599999996,
'longitude': -73.9571363,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNjU7BWEq_aYQANBCbX52Kb0lDpd_lFIx5onw40=w92-h92-n-k-no',
'rating': 4.7,
'ratingCount': 91,
'category': 'Italian'},
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-21
|
'ratingCount': 91,
'category': 'Italian'},
{'position': 2,
'title': "Tony's Di Napoli",
'address': '1081 3rd Ave',
'latitude': 40.7643567,
'longitude': -73.9642373,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNbNv6jZkJ9nyVi60__8c1DQbe_eEbugRAhIYye=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 2265,
'category': 'Italian'},
{'position': 3,
'title': 'Caravaggio',
'address': '23 E 74th St',
'latitude': 40.773412799999996,
'longitude': -73.96473379999999,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPDGchokDvppoLfmVEo6X_bWd3Fz0HyxIHTEe9V=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 276,
'category': 'Italian'},
{'position': 4,
'title': 'Luna Rossa',
'address': '347 E 85th St',
'latitude': 40.776593999999996,
'longitude': -73.950351,
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-22
|
'longitude': -73.950351,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNPCpCPuqPAb1Mv6_fOP7cjb8Wu1rbqbk2sMBlh=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 140,
'category': 'Italian'},
{'position': 5,
'title': "Paola's",
'address': '1361 Lexington Ave',
'latitude': 40.7822019,
'longitude': -73.9534096,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPJr2Vcx-B6K-GNQa4koOTffggTePz8TKRTnWi3=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 344,
'category': 'Italian'},
{'position': 6,
'title': 'Come Prima',
'address': '903 Madison Ave',
'latitude': 40.772124999999996,
'longitude': -73.965012,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNrX19G0NVdtDyMovCQ-M-m0c_gLmIxrWDQAAbz=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 176,
'category': 'Italian'},
{'position': 7,
'title': 'Botte UES',
'address': '1606 1st Ave.',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-23
|
'address': '1606 1st Ave.',
'latitude': 40.7750785,
'longitude': -73.9504801,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPPN5GXxfH3NDacBc0Pt3uGAInd9OChS5isz9RF=w92-h92-n-k-no',
'rating': 4.4,
'ratingCount': 152,
'category': 'Italian'},
{'position': 8,
'title': 'Piccola Cucina Uptown',
'address': '106 E 60th St',
'latitude': 40.7632468,
'longitude': -73.9689825,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipPifIgzOCD5SjgzzqBzGkdZCBp0MQsK5k7M7znn=w92-h92-n-k-no',
'rating': 4.6,
'ratingCount': 941,
'category': 'Italian'},
{'position': 9,
'title': 'Pinocchio Restaurant',
'address': '300 E 92nd St',
'latitude': 40.781453299999995,
'longitude': -73.9486788,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipNtxlIyEEJHtDtFtTR9nB38S8A2VyMu-mVVz72A=w92-h92-n-k-no',
'rating': 4.5,
'ratingCount': 113,
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
dc38ca462716-24
|
'rating': 4.5,
'ratingCount': 113,
'category': 'Italian'},
{'position': 10,
'title': 'Barbaresco',
'address': '843 Lexington Ave #1',
'latitude': 40.7654332,
'longitude': -73.9656873,
'thumbnailUrl': 'https://lh5.googleusercontent.com/p/AF1QipMb9FbPuXF_r9g5QseOHmReejxSHgSahPMPJ9-8=w92-h92-n-k-no',
'rating': 4.3,
'ratingCount': 122,
'locationHint': 'In The Touraine',
'category': 'Italian'}]}
previous
Google Search
next
Gradio Tools
Contents
As part of a Self Ask With Search Chain
Obtaining results with metadata
Searching for Google Images
Searching for Google News
Searching for Google Places
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_serper.html
|
919f294c2bb4-0
|
.ipynb
.pdf
Apify
Apify#
This notebook shows how to use the Apify integration for LangChain.
Apify is a cloud platform for web scraping and data extraction,
which provides an ecosystem of more than a thousand
ready-made apps called Actors for various web scraping, crawling, and data extraction use cases.
For example, you can use it to extract Google Search results, Instagram and Facebook profiles, products from Amazon or Shopify, Google Maps reviews, etc. etc.
In this example, we’ll use the Website Content Crawler Actor,
which can deeply crawl websites such as documentation, knowledge bases, help centers, or blogs,
and extract text content from the web pages. Then we feed the documents into a vector index and answer questions from it.
#!pip install apify-client
First, import ApifyWrapper into your source code:
from langchain.document_loaders.base import Document
from langchain.indexes import VectorstoreIndexCreator
from langchain.utilities import ApifyWrapper
Initialize it using your Apify API token and for the purpose of this example, also with your OpenAI API key:
import os
os.environ["OPENAI_API_KEY"] = "Your OpenAI API key"
os.environ["APIFY_API_TOKEN"] = "Your Apify API token"
apify = ApifyWrapper()
Then run the Actor, wait for it to finish, and fetch its results from the Apify dataset into a LangChain document loader.
Note that if you already have some results in an Apify dataset, you can load them directly using ApifyDatasetLoader, as shown in this notebook. In that notebook, you’ll also find the explanation of the dataset_mapping_function, which is used to map fields from the Apify dataset records to LangChain Document fields.
loader = apify.call_actor(
actor_id="apify/website-content-crawler",
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/apify.html
|
919f294c2bb4-1
|
actor_id="apify/website-content-crawler",
run_input={"startUrls": [{"url": "https://python.langchain.com/en/latest/"}]},
dataset_mapping_function=lambda item: Document(
page_content=item["text"] or "", metadata={"source": item["url"]}
),
)
Initialize the vector index from the crawled documents:
index = VectorstoreIndexCreator().from_loaders([loader])
And finally, query the vector index:
query = "What is LangChain?"
result = index.query_with_sources(query)
print(result["answer"])
print(result["sources"])
LangChain is a standard interface through which you can interact with a variety of large language models (LLMs). It provides modules that can be used to build language model applications, and it also provides chains and agents with memory capabilities.
https://python.langchain.com/en/latest/modules/models/llms.html, https://python.langchain.com/en/latest/getting_started/getting_started.html
previous
Tools as OpenAI Functions
next
ArXiv API Tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/apify.html
|
125b64df69af-0
|
.ipynb
.pdf
Metaphor Search
Contents
Metaphor Search
Call the API
Use Metaphor as a tool
Metaphor Search#
This notebook goes over how to use Metaphor search.
First, you need to set up the proper API keys and environment variables. Request an API key [here](Sign up for early access here).
Then enter your API key as an environment variable.
import os
os.environ["METAPHOR_API_KEY"] = ""
from langchain.utilities import MetaphorSearchAPIWrapper
search = MetaphorSearchAPIWrapper()
Call the API#
results takes in a Metaphor-optimized search query and a number of results (up to 500). It returns a list of results with title, url, author, and creation date.
search.results("The best blog post about AI safety is definitely this: ", 10)
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-1
|
{'results': [{'url': 'https://www.anthropic.com/index/core-views-on-ai-safety', 'title': 'Core Views on AI Safety: When, Why, What, and How', 'dateCreated': '2023-03-08', 'author': None, 'score': 0.1998831331729889}, {'url': 'https://aisafety.wordpress.com/', 'title': 'Extinction Risk from Artificial Intelligence', 'dateCreated': '2013-10-08', 'author': None, 'score': 0.19801370799541473}, {'url': 'https://www.lesswrong.com/posts/WhNxG4r774bK32GcH/the-simple-picture-on-ai-safety', 'title': 'The simple picture on AI safety - LessWrong', 'dateCreated': '2018-05-27', 'author': 'Alex Flint', 'score': 0.19735534489154816}, {'url': 'https://slatestarcodex.com/2015/05/29/no-time-like-the-present-for-ai-safety-work/', 'title': 'No Time Like The Present For AI Safety Work', 'dateCreated': '2015-05-29', 'author': None, 'score': 0.19408763945102692}, {'url': 'https://www.lesswrong.com/posts/5BJvusxdwNXYQ4L9L/so-you-want-to-save-the-world', 'title': 'So You Want to Save the World - LessWrong', 'dateCreated': '2012-01-01', 'author': 'Lukeprog', 'score': 0.18853715062141418}, {'url': 'https://openai.com/blog/planning-for-agi-and-beyond', 'title': 'Planning for AGI and beyond', 'dateCreated':
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-2
|
'title': 'Planning for AGI and beyond', 'dateCreated': '2023-02-24', 'author': 'Authors', 'score': 0.18665121495723724}, {'url': 'https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html', 'title': 'The Artificial Intelligence Revolution: Part 1 - Wait But Why', 'dateCreated': '2015-01-22', 'author': 'Tim Urban', 'score': 0.18604731559753418}, {'url': 'https://forum.effectivealtruism.org/posts/uGDCaPFaPkuxAowmH/anthropic-core-views-on-ai-safety-when-why-what-and-how', 'title': 'Anthropic: Core Views on AI Safety: When, Why, What, and How - EA Forum', 'dateCreated': '2023-03-09', 'author': 'Jonmenaster', 'score': 0.18415069580078125}, {'url': 'https://www.lesswrong.com/posts/xBrpph9knzWdtMWeQ/the-proof-of-doom', 'title': 'The Proof of Doom - LessWrong', 'dateCreated': '2022-03-09', 'author': 'Johnlawrenceaspden', 'score': 0.18159329891204834}, {'url': 'https://intelligence.org/why-ai-safety/', 'title': 'Why AI Safety? - Machine Intelligence Research Institute', 'dateCreated': '2017-03-01', 'author': None, 'score': 0.1814115345478058}]}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-3
|
[{'title': 'Core Views on AI Safety: When, Why, What, and How',
'url': 'https://www.anthropic.com/index/core-views-on-ai-safety',
'author': None,
'date_created': '2023-03-08'},
{'title': 'Extinction Risk from Artificial Intelligence',
'url': 'https://aisafety.wordpress.com/',
'author': None,
'date_created': '2013-10-08'},
{'title': 'The simple picture on AI safety - LessWrong',
'url': 'https://www.lesswrong.com/posts/WhNxG4r774bK32GcH/the-simple-picture-on-ai-safety',
'author': 'Alex Flint',
'date_created': '2018-05-27'},
{'title': 'No Time Like The Present For AI Safety Work',
'url': 'https://slatestarcodex.com/2015/05/29/no-time-like-the-present-for-ai-safety-work/',
'author': None,
'date_created': '2015-05-29'},
{'title': 'So You Want to Save the World - LessWrong',
'url': 'https://www.lesswrong.com/posts/5BJvusxdwNXYQ4L9L/so-you-want-to-save-the-world',
'author': 'Lukeprog',
'date_created': '2012-01-01'},
{'title': 'Planning for AGI and beyond',
'url': 'https://openai.com/blog/planning-for-agi-and-beyond',
'author': 'Authors',
'date_created': '2023-02-24'},
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-4
|
'date_created': '2023-02-24'},
{'title': 'The Artificial Intelligence Revolution: Part 1 - Wait But Why',
'url': 'https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html',
'author': 'Tim Urban',
'date_created': '2015-01-22'},
{'title': 'Anthropic: Core Views on AI Safety: When, Why, What, and How - EA Forum',
'url': 'https://forum.effectivealtruism.org/posts/uGDCaPFaPkuxAowmH/anthropic-core-views-on-ai-safety-when-why-what-and-how',
'author': 'Jonmenaster',
'date_created': '2023-03-09'},
{'title': 'The Proof of Doom - LessWrong',
'url': 'https://www.lesswrong.com/posts/xBrpph9knzWdtMWeQ/the-proof-of-doom',
'author': 'Johnlawrenceaspden',
'date_created': '2022-03-09'},
{'title': 'Why AI Safety? - Machine Intelligence Research Institute',
'url': 'https://intelligence.org/why-ai-safety/',
'author': None,
'date_created': '2017-03-01'}]
Use Metaphor as a tool#
Metaphor can be used as a tool that gets URLs that other tools such as browsing tools.
from langchain.agents.agent_toolkits import PlayWrightBrowserToolkit
from langchain.tools.playwright.utils import (
create_async_playwright_browser,# A synchronous browser is available, though it isn't compatible with jupyter.
)
async_browser = create_async_playwright_browser()
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-5
|
)
async_browser = create_async_playwright_browser()
toolkit = PlayWrightBrowserToolkit.from_browser(async_browser=async_browser)
tools = toolkit.get_tools()
tools_by_name = {tool.name: tool for tool in tools}
print(tools_by_name.keys())
navigate_tool = tools_by_name["navigate_browser"]
extract_text = tools_by_name["extract_text"]
from langchain.agents import initialize_agent, AgentType
from langchain.chat_models import ChatOpenAI
from langchain.tools import MetaphorSearchResults
llm = ChatOpenAI(model_name="gpt-4", temperature=0.7)
metaphor_tool = MetaphorSearchResults(api_wrapper=search)
agent_chain = initialize_agent([metaphor_tool, extract_text, navigate_tool], llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent_chain.run("find me an interesting tweet about AI safety using Metaphor, then tell me the first sentence in the post. Do not finish until able to retrieve the first sentence.")
> Entering new AgentExecutor chain...
Thought: I need to find a tweet about AI safety using Metaphor Search.
Action:
```
{
"action": "Metaphor Search Results JSON",
"action_input": {
"query": "interesting tweet AI safety",
"num_results": 1
}
}
```
{'results': [{'url': 'https://safe.ai/', 'title': 'Center for AI Safety', 'dateCreated': '2022-01-01', 'author': None, 'score': 0.18083244562149048}]}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
125b64df69af-6
|
Observation: [{'title': 'Center for AI Safety', 'url': 'https://safe.ai/', 'author': None, 'date_created': '2022-01-01'}]
Thought:I need to navigate to the URL provided in the search results to find the tweet.
> Finished chain.
'I need to navigate to the URL provided in the search results to find the tweet.'
previous
IFTTT WebHooks
next
OpenWeatherMap API
Contents
Metaphor Search
Call the API
Use Metaphor as a tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/metaphor_search.html
|
837ed077b9e5-0
|
.ipynb
.pdf
HuggingFace Tools
HuggingFace Tools#
Huggingface Tools supporting text I/O can be
loaded directly using the load_huggingface_tool function.
# Requires transformers>=4.29.0 and huggingface_hub>=0.14.1
!pip install --upgrade transformers huggingface_hub > /dev/null
from langchain.agents import load_huggingface_tool
tool = load_huggingface_tool("lysandre/hf-model-downloads")
print(f"{tool.name}: {tool.description}")
model_download_counter: This is a tool that returns the most downloaded model of a given task on the Hugging Face Hub. It takes the name of the category (such as text-classification, depth-estimation, etc), and returns the name of the checkpoint
tool.run("text-classification")
'facebook/bart-large-mnli'
previous
GraphQL tool
next
Human as a tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/huggingface_tools.html
|
2a4fd9a05c74-0
|
.ipynb
.pdf
SerpAPI
Contents
Custom Parameters
SerpAPI#
This notebook goes over how to use the SerpAPI component to search the web.
from langchain.utilities import SerpAPIWrapper
search = SerpAPIWrapper()
search.run("Obama's first name?")
'Barack Hussein Obama II'
Custom Parameters#
You can also customize the SerpAPI wrapper with arbitrary parameters. For example, in the below example we will use bing instead of google.
params = {
"engine": "bing",
"gl": "us",
"hl": "en",
}
search = SerpAPIWrapper(params=params)
search.run("Obama's first name?")
'Barack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American presi…New content will be added above the current area of focus upon selectionBarack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic Party, Obama was the first African-American president of the United States. He previously served as a U.S. senator from Illinois from 2005 to 2008 and as an Illinois state senator from 1997 to 2004, and previously worked as a civil rights lawyer before entering politics.Wikipediabarackobama.com'
from langchain.agents import Tool
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl",
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/serpapi.html
|
2a4fd9a05c74-1
|
repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=search.run,
)
previous
SearxNG Search API
next
Twilio
Contents
Custom Parameters
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/serpapi.html
|
e31df537a713-0
|
.ipynb
.pdf
ChatGPT Plugins
ChatGPT Plugins#
This example shows how to use ChatGPT Plugins within LangChain abstractions.
Note 1: This currently only works for plugins with no auth.
Note 2: There are almost certainly other ways to do this, this is just a first pass. If you have better ideas, please open a PR!
from langchain.chat_models import ChatOpenAI
from langchain.agents import load_tools, initialize_agent
from langchain.agents import AgentType
from langchain.tools import AIPluginTool
tool = AIPluginTool.from_plugin_url("https://www.klarna.com/.well-known/ai-plugin.json")
llm = ChatOpenAI(temperature=0)
tools = load_tools(["requests_all"] )
tools += [tool]
agent_chain = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent_chain.run("what t shirts are available in klarna?")
> Entering new AgentExecutor chain...
I need to check the Klarna Shopping API to see if it has information on available t shirts.
Action: KlarnaProducts
Action Input: None
Observation: Usage Guide: Use the Klarna plugin to get relevant product suggestions for any shopping or researching purpose. The query to be sent should not include stopwords like articles, prepositions and determinants. The api works best when searching for words that are related to products, like their name, brand, model or category. Links will always be returned and should be shown to the user.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-1
|
OpenAPI Spec: {'openapi': '3.0.1', 'info': {'version': 'v0', 'title': 'Open AI Klarna product Api'}, 'servers': [{'url': 'https://www.klarna.com/us/shopping'}], 'tags': [{'name': 'open-ai-product-endpoint', 'description': 'Open AI Product Endpoint. Query for products.'}], 'paths': {'/public/openai/v0/products': {'get': {'tags': ['open-ai-product-endpoint'], 'summary': 'API for fetching Klarna product information', 'operationId': 'productsUsingGET', 'parameters': [{'name': 'q', 'in': 'query', 'description': 'query, must be between 2 and 100 characters', 'required': True, 'schema': {'type': 'string'}}, {'name': 'size', 'in': 'query', 'description': 'number of products returned', 'required': False, 'schema': {'type': 'integer'}}, {'name': 'budget', 'in': 'query', 'description': 'maximum price of the matching product in local currency, filters results', 'required': False, 'schema': {'type': 'integer'}}], 'responses': {'200': {'description': 'Products found', 'content': {'application/json': {'schema': {'$ref': '#/components/schemas/ProductResponse'}}}}, '503': {'description': 'one or more services are unavailable'}}, 'deprecated': False}}}, 'components': {'schemas': {'Product': {'type': 'object', 'properties': {'attributes': {'type': 'array', 'items': {'type': 'string'}}, 'name': {'type': 'string'}, 'price': {'type': 'string'}, 'url': {'type': 'string'}}, 'title': 'Product'}, 'ProductResponse': {'type': 'object', 'properties':
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-2
|
'title': 'Product'}, 'ProductResponse': {'type': 'object', 'properties': {'products': {'type': 'array', 'items': {'$ref': '#/components/schemas/Product'}}}, 'title': 'ProductResponse'}}}}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-3
|
Thought:I need to use the Klarna Shopping API to search for t shirts.
Action: requests_get
Action Input: https://www.klarna.com/us/shopping/public/openai/v0/products?q=t%20shirts
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-4
|
Observation: {"products":[{"name":"Lacoste Men's Pack of Plain T-Shirts","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202043025/Clothing/Lacoste-Men-s-Pack-of-Plain-T-Shirts/?utm_source=openai","price":"$26.60","attributes":["Material:Cotton","Target Group:Man","Color:White,Black"]},{"name":"Hanes Men's Ultimate 6pk. Crewneck T-Shirts","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201808270/Clothing/Hanes-Men-s-Ultimate-6pk.-Crewneck-T-Shirts/?utm_source=openai","price":"$13.82","attributes":["Material:Cotton","Target Group:Man","Color:White"]},{"name":"Nike Boy's Jordan Stretch T-shirts","url":"https://www.klarna.com/us/shopping/pl/cl359/3201863202/Children-s-Clothing/Nike-Boy-s-Jordan-Stretch-T-shirts/?utm_source=openai","price":"$14.99","attributes":["Material:Cotton","Color:White,Green","Model:Boy","Size (Small-Large):S,XL,L,M"]},{"name":"Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203028500/Clothing/Polo-Classic-Fit-Cotton-V-Neck-T-Shirts-3-Pack/?utm_source=openai","price":"$29.95","attributes":["Material:Cotton","Target Group:Man","Color:White,Blue,Black"]},{"name":"adidas Comfort T-shirts Men's
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-5
|
Comfort T-shirts Men's 3-pack","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202640533/Clothing/adidas-Comfort-T-shirts-Men-s-3-pack/?utm_source=openai","price":"$14.99","attributes":["Material:Cotton","Target Group:Man","Color:White,Black","Neckline:Round"]}]}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
e31df537a713-6
|
Thought:The available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.
Final Answer: The available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack.
> Finished chain.
"The available t shirts in Klarna are Lacoste Men's Pack of Plain T-Shirts, Hanes Men's Ultimate 6pk. Crewneck T-Shirts, Nike Boy's Jordan Stretch T-shirts, Polo Classic Fit Cotton V-Neck T-Shirts 3-Pack, and adidas Comfort T-shirts Men's 3-pack."
previous
Brave Search
next
DuckDuckGo Search
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/chatgpt_plugins.html
|
866df808d6cd-0
|
.ipynb
.pdf
Python REPL
Python REPL#
Sometimes, for complex calculations, rather than have an LLM generate the answer directly, it can be better to have the LLM generate code to calculate the answer, and then run that code to get the answer. In order to easily do that, we provide a simple Python REPL to execute commands in.
This interface will only return things that are printed - therefore, if you want to use it to calculate an answer, make sure to have it print out the answer.
from langchain.agents import Tool
from langchain.utilities import PythonREPL
python_repl = PythonREPL()
python_repl.run("print(1+1)")
'2\n'
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=python_repl.run
)
previous
PubMed Tool
next
Requests
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/python.html
|
05e46f3481c5-0
|
.ipynb
.pdf
OpenWeatherMap API
Contents
Use the wrapper
Use the tool
OpenWeatherMap API#
This notebook goes over how to use the OpenWeatherMap component to fetch weather information.
First, you need to sign up for an OpenWeatherMap API key:
Go to OpenWeatherMap and sign up for an API key here
pip install pyowm
Then we will need to set some environment variables:
Save your API KEY into OPENWEATHERMAP_API_KEY env variable
Use the wrapper#
from langchain.utilities import OpenWeatherMapAPIWrapper
import os
os.environ["OPENWEATHERMAP_API_KEY"] = ""
weather = OpenWeatherMapAPIWrapper()
weather_data = weather.run("London,GB")
print(weather_data)
In London,GB, the current weather is as follows:
Detailed status: broken clouds
Wind speed: 2.57 m/s, direction: 240°
Humidity: 55%
Temperature:
- Current: 20.12°C
- High: 21.75°C
- Low: 18.68°C
- Feels like: 19.62°C
Rain: {}
Heat index: None
Cloud cover: 75%
Use the tool#
from langchain.llms import OpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
import os
os.environ["OPENAI_API_KEY"] = ""
os.environ["OPENWEATHERMAP_API_KEY"] = ""
llm = OpenAI(temperature=0)
tools = load_tools(["openweathermap-api"], llm)
agent_chain = initialize_agent(
tools=tools,
llm=llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True
)
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/openweathermap.html
|
05e46f3481c5-1
|
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True
)
agent_chain.run("What's the weather like in London?")
> Entering new AgentExecutor chain...
I need to find out the current weather in London.
Action: OpenWeatherMap
Action Input: London,GB
Observation: In London,GB, the current weather is as follows:
Detailed status: broken clouds
Wind speed: 2.57 m/s, direction: 240°
Humidity: 56%
Temperature:
- Current: 20.11°C
- High: 21.75°C
- Low: 18.68°C
- Feels like: 19.64°C
Rain: {}
Heat index: None
Cloud cover: 75%
Thought: I now know the current weather in London.
Final Answer: The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.
> Finished chain.
'The current weather in London is broken clouds, with a wind speed of 2.57 m/s, direction 240°, humidity of 56%, temperature of 20.11°C, high of 21.75°C, low of 18.68°C, and a heat index of None.'
previous
Metaphor Search
next
PubMed Tool
Contents
Use the wrapper
Use the tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/openweathermap.html
|
8d6a6f4996ac-0
|
.ipynb
.pdf
File System Tools
Contents
The FileManagementToolkit
Selecting File System Tools
File System Tools#
LangChain provides tools for interacting with a local file system out of the box. This notebook walks through some of them.
Note: these tools are not recommended for use outside a sandboxed environment!
First, we’ll import the tools.
from langchain.tools.file_management import (
ReadFileTool,
CopyFileTool,
DeleteFileTool,
MoveFileTool,
WriteFileTool,
ListDirectoryTool,
)
from langchain.agents.agent_toolkits import FileManagementToolkit
from tempfile import TemporaryDirectory
# We'll make a temporary directory to avoid clutter
working_directory = TemporaryDirectory()
The FileManagementToolkit#
If you want to provide all the file tooling to your agent, it’s easy to do so with the toolkit. We’ll pass the temporary directory in as a root directory as a workspace for the LLM.
It’s recommended to always pass in a root directory, since without one, it’s easy for the LLM to pollute the working directory, and without one, there isn’t any validation against
straightforward prompt injection.
toolkit = FileManagementToolkit(root_dir=str(working_directory.name)) # If you don't provide a root_dir, operations will default to the current working directory
toolkit.get_tools()
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/filesystem.html
|
8d6a6f4996ac-1
|
toolkit.get_tools()
[CopyFileTool(name='copy_file', description='Create a copy of a file in a specified location', args_schema=<class 'langchain.tools.file_management.copy.FileCopyInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
DeleteFileTool(name='file_delete', description='Delete a file', args_schema=<class 'langchain.tools.file_management.delete.FileDeleteInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
FileSearchTool(name='file_search', description='Recursively search for files in a subdirectory that match the regex pattern', args_schema=<class 'langchain.tools.file_management.file_search.FileSearchInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/filesystem.html
|
8d6a6f4996ac-2
|
MoveFileTool(name='move_file', description='Move or rename a file from one location to another', args_schema=<class 'langchain.tools.file_management.move.FileMoveInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')]
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/filesystem.html
|
8d6a6f4996ac-3
|
Selecting File System Tools#
If you only want to select certain tools, you can pass them in as arguments when initializing the toolkit, or you can individually initialize the desired tools.
tools = FileManagementToolkit(root_dir=str(working_directory.name), selected_tools=["read_file", "write_file", "list_directory"]).get_tools()
tools
[ReadFileTool(name='read_file', description='Read file from disk', args_schema=<class 'langchain.tools.file_management.read.ReadFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
WriteFileTool(name='write_file', description='Write file to disk', args_schema=<class 'langchain.tools.file_management.write.WriteFileInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug'),
ListDirectoryTool(name='list_directory', description='List files and directories in a specified folder', args_schema=<class 'langchain.tools.file_management.list_dir.DirectoryListingInput'>, return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1156f4350>, root_dir='/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/tmpxb8c3aug')]
read_tool, write_tool, list_tool = tools
write_tool.run({"file_path": "example.txt", "text": "Hello World!"})
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/filesystem.html
|
8d6a6f4996ac-4
|
write_tool.run({"file_path": "example.txt", "text": "Hello World!"})
'File written successfully to example.txt.'
# List files in the working directory
list_tool.run({})
'example.txt'
previous
DuckDuckGo Search
next
Google Places
Contents
The FileManagementToolkit
Selecting File System Tools
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/filesystem.html
|
efd7c70e897c-0
|
.ipynb
.pdf
Google Search
Contents
Number of Results
Metadata Results
Google Search#
This notebook goes over how to use the google search component.
First, you need to set up the proper API keys and environment variables. To set it up, create the GOOGLE_API_KEY in the Google Cloud credential console (https://console.cloud.google.com/apis/credentials) and a GOOGLE_CSE_ID using the Programmable Search Enginge (https://programmablesearchengine.google.com/controlpanel/create). Next, it is good to follow the instructions found here.
Then we will need to set some environment variables.
import os
os.environ["GOOGLE_CSE_ID"] = ""
os.environ["GOOGLE_API_KEY"] = ""
from langchain.tools import Tool
from langchain.utilities import GoogleSearchAPIWrapper
search = GoogleSearchAPIWrapper()
tool = Tool(
name = "Google Search",
description="Search Google for recent results.",
func=search.run
)
tool.run("Obama's first name?")
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_search.html
|
efd7c70e897c-1
|
"STATE OF HAWAII. 1 Child's First Name. (Type or print). 2. Sex. BARACK. 3. This Birth. CERTIFICATE OF LIVE BIRTH. FILE. NUMBER 151 le. lb. Middle Name. Barack Hussein Obama II is an American former politician who served as the 44th president of the United States from 2009 to 2017. A member of the Democratic\xa0... When Barack Obama was elected president in 2008, he became the first African American to hold ... The Middle East remained a key foreign policy challenge. Jan 19, 2017 ... Jordan Barack Treasure, New York City, born in 2008 ... Jordan Barack Treasure made national news when he was the focus of a New York newspaper\xa0... Portrait of George Washington, the 1st President of the United States ... Portrait of Barack Obama, the 44th President of the United States\xa0... His full name is Barack Hussein Obama II. Since the “II” is simply because he was named for his father, his last name is Obama. Mar 22, 2008 ... Barry Obama decided that he didn't like his nickname. A few of his friends at Occidental College had already begun to call him Barack (his\xa0... Aug 18, 2017 ... It took him several seconds and multiple clues to remember former President Barack Obama's first name. Miller knew that every answer had to\xa0... Feb 9, 2015 ... Michael Jordan misspelled Barack Obama's first name on 50th-birthday gift ... Knowing Obama is a Chicagoan and huge basketball fan,\xa0... 4 days ago ... Barack Obama, in full Barack Hussein Obama II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009–17) and\xa0..."
Number of Results#
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_search.html
|
efd7c70e897c-2
|
Number of Results#
You can use the k parameter to set the number of results
search = GoogleSearchAPIWrapper(k=1)
tool = Tool(
name = "I'm Feeling Lucky",
description="Search Google and return the first result.",
func=search.run
)
tool.run("python")
'The official home of the Python Programming Language.'
‘The official home of the Python Programming Language.’
Metadata Results#
Run query through GoogleSearch and return snippet, title, and link metadata.
Snippet: The description of the result.
Title: The title of the result.
Link: The link to the result.
search = GoogleSearchAPIWrapper()
def top5_results(query):
return search.results(query, 5)
tool = Tool(
name = "Google Search Snippets",
description="Search Google for recent results.",
func=top5_results
)
previous
Google Places
next
Google Serper API
Contents
Number of Results
Metadata Results
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_search.html
|
ea0980349fcd-0
|
.ipynb
.pdf
AWS Lambda API
AWS Lambda API#
This notebook goes over how to use the AWS Lambda Tool component.
AWS Lambda is a serverless computing service provided by Amazon Web Services (AWS), designed to allow developers to build and run applications and services without the need for provisioning or managing servers. This serverless architecture enables you to focus on writing and deploying code, while AWS automatically takes care of scaling, patching, and managing the infrastructure required to run your applications.
By including a awslambda in the list of tools provided to an Agent, you can grant your Agent the ability to invoke code running in your AWS Cloud for whatever purposes you need.
When an Agent uses the awslambda tool, it will provide an argument of type string which will in turn be passed into the Lambda function via the event parameter.
First, you need to install boto3 python package.
!pip install boto3 > /dev/null
In order for an agent to use the tool, you must provide it with the name and description that match the functionality of you lambda function’s logic.
You must also provide the name of your function.
Note that because this tool is effectively just a wrapper around the boto3 library, you will need to run aws configure in order to make use of the tool. For more detail, see here
from langchain import OpenAI
from langchain.agents import load_tools, AgentType
llm = OpenAI(temperature=0)
tools = load_tools(
["awslambda"],
awslambda_tool_name="email-sender",
awslambda_tool_description="sends an email with the specified content to test@testing123.com",
function_name="testFunction1"
)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/awslambda.html
|
ea0980349fcd-1
|
agent.run("Send an email to test@testing123.com saying hello world.")
previous
ArXiv API Tool
next
Shell Tool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/awslambda.html
|
207d2b5ff204-0
|
.ipynb
.pdf
SceneXplain
Contents
Usage in an Agent
SceneXplain#
SceneXplain is an ImageCaptioning service accessible through the SceneXplain Tool.
To use this tool, you’ll need to make an account and fetch your API Token from the website. Then you can instantiate the tool.
import os
os.environ["SCENEX_API_KEY"] = "<YOUR_API_KEY>"
from langchain.agents import load_tools
tools = load_tools(["sceneXplain"])
Or directly instantiate the tool.
from langchain.tools import SceneXplainTool
tool = SceneXplainTool()
Usage in an Agent#
The tool can be used in any LangChain agent as follows:
from langchain.llms import OpenAI
from langchain.agents import initialize_agent
from langchain.memory import ConversationBufferMemory
llm = OpenAI(temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history")
agent = initialize_agent(
tools, llm, memory=memory, agent="conversational-react-description", verbose=True
)
output = agent.run(
input=(
"What is in this image https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png. "
"Is it movie or a game? If it is a movie, what is the name of the movie?"
)
)
print(output)
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: Image Explainer
Action Input: https://storage.googleapis.com/causal-diffusion.appspot.com/imagePrompts%2F0rw369i5h9t%2Foriginal.png
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/sceneXplain.html
|
207d2b5ff204-1
|
Observation: In a charmingly whimsical scene, a young girl is seen braving the rain alongside her furry companion, the lovable Totoro. The two are depicted standing on a bustling street corner, where they are sheltered from the rain by a bright yellow umbrella. The girl, dressed in a cheerful yellow frock, holds onto the umbrella with both hands while gazing up at Totoro with an expression of wonder and delight.
Totoro, meanwhile, stands tall and proud beside his young friend, holding his own umbrella aloft to protect them both from the downpour. His furry body is rendered in rich shades of grey and white, while his large ears and wide eyes lend him an endearing charm.
In the background of the scene, a street sign can be seen jutting out from the pavement amidst a flurry of raindrops. A sign with Chinese characters adorns its surface, adding to the sense of cultural diversity and intrigue. Despite the dreary weather, there is an undeniable sense of joy and camaraderie in this heartwarming image.
Thought: Do I need to use a tool? No
AI: This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro.
> Finished chain.
This image appears to be a still from the 1988 Japanese animated fantasy film My Neighbor Totoro. The film follows two young girls, Satsuki and Mei, as they explore the countryside and befriend the magical forest spirits, including the titular character Totoro.
previous
Requests
next
Search Tools
Contents
Usage in an Agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/sceneXplain.html
|
207d2b5ff204-2
|
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/sceneXplain.html
|
fdfbd3073e65-0
|
.ipynb
.pdf
Google Places
Google Places#
This notebook goes through how to use Google Places API
#!pip install googlemaps
import os
os.environ["GPLACES_API_KEY"] = ""
from langchain.tools import GooglePlacesTool
places = GooglePlacesTool()
places.run("al fornos")
"1. Delfina Restaurant\nAddress: 3621 18th St, San Francisco, CA 94110, USA\nPhone: (415) 552-4055\nWebsite: https://www.delfinasf.com/\n\n\n2. Piccolo Forno\nAddress: 725 Columbus Ave, San Francisco, CA 94133, USA\nPhone: (415) 757-0087\nWebsite: https://piccolo-forno-sf.com/\n\n\n3. L'Osteria del Forno\nAddress: 519 Columbus Ave, San Francisco, CA 94133, USA\nPhone: (415) 982-1124\nWebsite: Unknown\n\n\n4. Il Fornaio\nAddress: 1265 Battery St, San Francisco, CA 94111, USA\nPhone: (415) 986-0100\nWebsite: https://www.ilfornaio.com/\n\n"
previous
File System Tools
next
Google Search
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/google_places.html
|
4ca5061df915-0
|
.ipynb
.pdf
Twilio
Contents
Setup
Sending a message
Twilio#
This notebook goes over how to use the Twilio API wrapper to send a text message.
Setup#
To use this tool you need to install the Python Twilio package twilio
# !pip install twilio
You’ll also need to set up a Twilio account and get your credentials. You’ll need your Account String Identifier (SID) and your Auth Token. You’ll also need a number to send messages from.
You can either pass these in to the TwilioAPIWrapper as named parameters account_sid, auth_token, from_number, or you can set the environment variables TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, TWILIO_FROM_NUMBER.
Sending a message#
from langchain.utilities.twilio import TwilioAPIWrapper
twilio = TwilioAPIWrapper(
# account_sid="foo",
# auth_token="bar",
# from_number="baz,"
)
twilio.run("hello world", "+16162904619")
previous
SerpAPI
next
Wikipedia
Contents
Setup
Sending a message
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/twilio.html
|
b4320e08235c-0
|
.ipynb
.pdf
Brave Search
Brave Search#
This notebook goes over how to use the Brave Search tool.
from langchain.tools import BraveSearch
api_key = "..."
tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={"count": 3})
tool.run("obama middle name")
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/brave_search.html
|
b4320e08235c-1
|
'[{"title": "Barack Obama - Wikipedia", "link": "https://en.wikipedia.org/wiki/Barack_Obama", "snippet": "Outside of politics, <strong>Obama</strong> has published three bestselling books: Dreams from My Father (1995), The Audacity of Hope (2006) and A Promised Land (2020). Rankings by scholars and historians, in which he has been featured since 2010, place him in the <strong>middle</strong> to upper tier of American presidents."}, {"title": "Obama\'s Middle Name -- My Last Name -- is \'Hussein.\' So?", "link": "https://www.cair.com/cair_in_the_news/obamas-middle-name-my-last-name-is-hussein-so/", "snippet": "Many Americans understand that common names don\\u2019t only come in the form of a \\u201cSmith\\u201d or a \\u201cJohnson.\\u201d Perhaps, they have a neighbor, mechanic or teacher named Hussein. Or maybe they\\u2019ve seen fashion designer Hussein Chalayan in the pages of Vogue or recall <strong>King Hussein</strong>, our ally in the Middle East."}, {"title": "What\'s up with Obama\'s middle name? - Quora", "link": "https://www.quora.com/Whats-up-with-Obamas-middle-name", "snippet": "Answer (1 of 15): A better question would be, \\u201cWhat\\u2019s up with Obama\\u2019s first name?\\u201d President <strong>Barack Hussein Obama</strong>\\u2019s father\\u2019s name was <strong>Barack Hussein Obama</strong>. He was named after his father. Hussein, Obama\\u2019s middle name, is a very common Arabic name, meaning
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/brave_search.html
|
b4320e08235c-2
|
Hussein, Obama\\u2019s middle name, is a very common Arabic name, meaning "good," "handsome," or "beautiful.""}]'
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/brave_search.html
|
b4320e08235c-3
|
previous
Bing Search
next
ChatGPT Plugins
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/brave_search.html
|
16156d453e5b-0
|
.ipynb
.pdf
Wolfram Alpha
Wolfram Alpha#
This notebook goes over how to use the wolfram alpha component.
First, you need to set up your Wolfram Alpha developer account and get your APP ID:
Go to wolfram alpha and sign up for a developer account here
Create an app and get your APP ID
pip install wolframalpha
Then we will need to set some environment variables:
Save your APP ID into WOLFRAM_ALPHA_APPID env variable
pip install wolframalpha
import os
os.environ["WOLFRAM_ALPHA_APPID"] = ""
from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
wolfram = WolframAlphaAPIWrapper()
wolfram.run("What is 2x+5 = -3x + 7?")
'x = 2/5'
previous
Wikipedia
next
YouTubeSearchTool
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wolfram_alpha.html
|
d75cce8b1c87-0
|
.ipynb
.pdf
SearxNG Search API
Contents
Custom Parameters
Obtaining results with metadata
SearxNG Search API#
This notebook goes over how to use a self hosted SearxNG search API to search the web.
You can check this link for more informations about Searx API parameters.
import pprint
from langchain.utilities import SearxSearchWrapper
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888")
For some engines, if a direct answer is available the warpper will print the answer instead of the full list of search results. You can use the results method of the wrapper if you want to obtain all the results.
search.run("What is the capital of France")
'Paris is the capital of France, the largest country of Europe with 550 000 km2 (65 millions inhabitants). Paris has 2.234 million inhabitants end 2011. She is the core of Ile de France region (12 million people).'
Custom Parameters#
SearxNG supports up to 139 search engines. You can also customize the Searx wrapper with arbitrary named parameters that will be passed to the Searx search API . In the below example we will making a more interesting use of custom search parameters from searx search api.
In this example we will be using the engines parameters to query wikipedia
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888", k=5) # k is for max number of items
search.run("large language model ", engines=['wiki'])
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-1
|
search.run("large language model ", engines=['wiki'])
'Large language models (LLMs) represent a major advancement in AI, with the promise of transforming domains through learned knowledge. LLM sizes have been increasing 10X every year for the last few years, and as these models grow in complexity and size, so do their capabilities.\n\nGPT-3 can translate language, write essays, generate computer code, and more — all with limited to no supervision. In July 2020, OpenAI unveiled GPT-3, a language model that was easily the largest known at the time. Put simply, GPT-3 is trained to predict the next word in a sentence, much like how a text message autocomplete feature works.\n\nA large language model, or LLM, is a deep learning algorithm that can recognize, summarize, translate, predict and generate text and other content based on knowledge gained from massive datasets. Large language models are among the most successful applications of transformer models.\n\nAll of today’s well-known language models—e.g., GPT-3 from OpenAI, PaLM or LaMDA from Google, Galactica or OPT from Meta, Megatron-Turing from Nvidia/Microsoft, Jurassic-1 from AI21 Labs—are...\n\nLarge language models (LLMs) such as GPT-3are increasingly being used to generate text. These tools should be used with care, since they can generate content that is biased, non-verifiable, constitutes original research, or violates copyrights.'
Passing other Searx parameters for searx like language
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888", k=1)
search.run("deep learning", language='es', engines=['wiki'])
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-2
|
search.run("deep learning", language='es', engines=['wiki'])
'Aprendizaje profundo (en inglés, deep learning) es un conjunto de algoritmos de aprendizaje automático (en inglés, machine learning) que intenta modelar abstracciones de alto nivel en datos usando arquitecturas computacionales que admiten transformaciones no lineales múltiples e iterativas de datos expresados en forma matricial o tensorial. 1'
Obtaining results with metadata#
In this example we will be looking for scientific paper using the categories parameter and limiting the results to a time_range (not all engines support the time range option).
We also would like to obtain the results in a structured way including metadata. For this we will be using the results method of the wrapper.
search = SearxSearchWrapper(searx_host="http://127.0.0.1:8888")
results = search.results("Large Language Model prompt", num_results=5, categories='science', time_range='year')
pprint.pp(results)
[{'snippet': '… on natural language instructions, large language models (… the '
'prompt used to steer the model, and most effective prompts … to '
'prompt engineering, we propose Automatic Prompt …',
'title': 'Large language models are human-level prompt engineers',
'link': 'https://arxiv.org/abs/2211.01910',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Large language models (LLMs) have introduced new possibilities '
'for prototyping with AI [18]. Pre-trained on a large amount of '
'text data, models … language instructions called prompts. …',
'title': 'Promptchainer: Chaining large language model prompts through '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-3
|
'title': 'Promptchainer: Chaining large language model prompts through '
'visual programming',
'link': 'https://dl.acm.org/doi/abs/10.1145/3491101.3519729',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… can introspect the large prompt model. We derive the view '
'ϕ0(X) and the model h0 from T01. However, instead of fully '
'fine-tuning T0 during co-training, we focus on soft prompt '
'tuning, …',
'title': 'Co-training improves prompt-based learning for large language '
'models',
'link': 'https://proceedings.mlr.press/v162/lang22a.html',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… With the success of large language models (LLMs) of code and '
'their use as … prompt design process become important. In this '
'work, we propose a framework called Repo-Level Prompt …',
'title': 'Repository-level prompt generation for large language models of '
'code',
'link': 'https://arxiv.org/abs/2206.12839',
'engines': ['google scholar'],
'category': 'science'},
{'snippet': '… Figure 2 | The benefits of different components of a prompt '
'for the largest language model (Gopher), as estimated from '
'hierarchical logistic regression. Each point estimates the '
'unique …',
'title': 'Can language models learn from explanations in context?',
'link': 'https://arxiv.org/abs/2204.02329',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-4
|
'link': 'https://arxiv.org/abs/2204.02329',
'engines': ['google scholar'],
'category': 'science'}]
Get papers from arxiv
results = search.results("Large Language Model prompt", num_results=5, engines=['arxiv'])
pprint.pp(results)
[{'snippet': 'Thanks to the advanced improvement of large pre-trained language '
'models, prompt-based fine-tuning is shown to be effective on a '
'variety of downstream tasks. Though many prompting methods have '
'been investigated, it remains unknown which type of prompts are '
'the most effective among three types of prompts (i.e., '
'human-designed prompts, schema prompts and null prompts). In '
'this work, we empirically compare the three types of prompts '
'under both few-shot and fully-supervised settings. Our '
'experimental results show that schema prompts are the most '
'effective in general. Besides, the performance gaps tend to '
'diminish when the scale of training data grows large.',
'title': 'Do Prompts Solve NLP Tasks Using Natural Language?',
'link': 'http://arxiv.org/abs/2203.00902v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Cross-prompt automated essay scoring (AES) requires the system '
'to use non target-prompt essays to award scores to a '
'target-prompt essay. Since obtaining a large quantity of '
'pre-graded essays to a particular prompt is often difficult and '
'unrealistic, the task of cross-prompt AES is vital for the '
'development of real-world AES systems, yet it remains an '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-5
|
'development of real-world AES systems, yet it remains an '
'under-explored area of research. Models designed for '
'prompt-specific AES rely heavily on prompt-specific knowledge '
'and perform poorly in the cross-prompt setting, whereas current '
'approaches to cross-prompt AES either require a certain quantity '
'of labelled target-prompt essays or require a large quantity of '
'unlabelled target-prompt essays to perform transfer learning in '
'a multi-step manner. To address these issues, we introduce '
'Prompt Agnostic Essay Scorer (PAES) for cross-prompt AES. Our '
'method requires no access to labelled or unlabelled '
'target-prompt data during training and is a single-stage '
'approach. PAES is easy to apply in practice and achieves '
'state-of-the-art performance on the Automated Student Assessment '
'Prize (ASAP) dataset.',
'title': 'Prompt Agnostic Essay Scorer: A Domain Generalization Approach to '
'Cross-prompt Automated Essay Scoring',
'link': 'http://arxiv.org/abs/2008.01441v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Research on prompting has shown excellent performance with '
'little or even no supervised training across many tasks. '
'However, prompting for machine translation is still '
'under-explored in the literature. We fill this gap by offering a '
'systematic study on prompting strategies for translation, '
'examining various factors for prompt template and demonstration '
'example selection. We further explore the use of monolingual '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-6
|
'example selection. We further explore the use of monolingual '
'data and the feasibility of cross-lingual, cross-domain, and '
'sentence-to-document transfer learning in prompting. Extensive '
'experiments with GLM-130B (Zeng et al., 2022) as the testbed '
'show that 1) the number and the quality of prompt examples '
'matter, where using suboptimal examples degenerates translation; '
'2) several features of prompt examples, such as semantic '
'similarity, show significant Spearman correlation with their '
'prompting performance; yet, none of the correlations are strong '
'enough; 3) using pseudo parallel prompt examples constructed '
'from monolingual data via zero-shot prompting could improve '
'translation; and 4) improved performance is achievable by '
'transferring knowledge from prompt examples selected in other '
'settings. We finally provide an analysis on the model outputs '
'and discuss several problems that prompting still suffers from.',
'title': 'Prompting Large Language Model for Machine Translation: A Case '
'Study',
'link': 'http://arxiv.org/abs/2301.07069v2',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Large language models can perform new tasks in a zero-shot '
'fashion, given natural language prompts that specify the desired '
'behavior. Such prompts are typically hand engineered, but can '
'also be learned with gradient-based methods from labeled data. '
'However, it is underexplored what factors make the prompts '
'effective, especially when the prompts are natural language. In '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-7
|
'effective, especially when the prompts are natural language. In '
'this paper, we investigate common attributes shared by effective '
'prompts. We first propose a human readable prompt tuning method '
'(F LUENT P ROMPT) based on Langevin dynamics that incorporates a '
'fluency constraint to find a diverse distribution of effective '
'and fluent prompts. Our analysis reveals that effective prompts '
'are topically related to the task domain and calibrate the prior '
'probability of label words. Based on these findings, we also '
'propose a method for generating prompts using only unlabeled '
'data, outperforming strong baselines by an average of 7.0% '
'accuracy across three tasks.',
'title': "Toward Human Readable Prompt Tuning: Kubrick's The Shining is a "
'good movie, and a good prompt too?',
'link': 'http://arxiv.org/abs/2212.10539v1',
'engines': ['arxiv'],
'category': 'science'},
{'snippet': 'Prevailing methods for mapping large generative language models '
"to supervised tasks may fail to sufficiently probe models' novel "
'capabilities. Using GPT-3 as a case study, we show that 0-shot '
'prompts can significantly outperform few-shot prompts. We '
'suggest that the function of few-shot examples in these cases is '
'better described as locating an already learned task rather than '
'meta-learning. This analysis motivates rethinking the role of '
'prompts in controlling and evaluating powerful language models. '
'In this work, we discuss methods of prompt programming, '
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-8
|
'In this work, we discuss methods of prompt programming, '
'emphasizing the usefulness of considering prompts through the '
'lens of natural language. We explore techniques for exploiting '
'the capacity of narratives and cultural anchors to encode '
'nuanced intentions and techniques for encouraging deconstruction '
'of a problem into components before producing a verdict. '
'Informed by this more encompassing theory of prompt programming, '
'we also introduce the idea of a metaprompt that seeds the model '
'to generate its own natural language prompts for a range of '
'tasks. Finally, we discuss how these more general methods of '
'interacting with language models can be incorporated into '
'existing and future benchmarks and practical applications.',
'title': 'Prompt Programming for Large Language Models: Beyond the Few-Shot '
'Paradigm',
'link': 'http://arxiv.org/abs/2102.07350v1',
'engines': ['arxiv'],
'category': 'science'}]
In this example we query for large language models under the it category. We then filter the results that come from github.
results = search.results("large language model", num_results = 20, categories='it')
pprint.pp(list(filter(lambda r: r['engines'][0] == 'github', results)))
[{'snippet': 'Guide to using pre-trained large language models of source code',
'title': 'Code-LMs',
'link': 'https://github.com/VHellendoorn/Code-LMs',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Dramatron uses large language models to generate coherent '
'scripts and screenplays.',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-9
|
'scripts and screenplays.',
'title': 'dramatron',
'link': 'https://github.com/deepmind/dramatron',
'engines': ['github'],
'category': 'it'}]
We could also directly query for results from github and other source forges.
results = search.results("large language model", num_results = 20, engines=['github', 'gitlab'])
pprint.pp(results)
[{'snippet': "Implementation of 'A Watermark for Large Language Models' paper "
'by Kirchenbauer & Geiping et. al.',
'title': 'Peutlefaire / LMWatermark',
'link': 'https://gitlab.com/BrianPulfer/LMWatermark',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Guide to using pre-trained large language models of source code',
'title': 'Code-LMs',
'link': 'https://github.com/VHellendoorn/Code-LMs',
'engines': ['github'],
'category': 'it'},
{'snippet': '',
'title': 'Simen Burud / Large-scale Language Models for Conversational '
'Speech Recognition',
'link': 'https://gitlab.com/BrianPulfer',
'engines': ['gitlab'],
'category': 'it'},
{'snippet': 'Dramatron uses large language models to generate coherent '
'scripts and screenplays.',
'title': 'dramatron',
'link': 'https://github.com/deepmind/dramatron',
'engines': ['github'],
'category': 'it'},
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-10
|
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for loralib, an implementation of "LoRA: Low-Rank '
'Adaptation of Large Language Models"',
'title': 'LoRA',
'link': 'https://github.com/microsoft/LoRA',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code for the paper "Evaluating Large Language Models Trained on '
'Code"',
'title': 'human-eval',
'link': 'https://github.com/openai/human-eval',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A trend starts from "Chain of Thought Prompting Elicits '
'Reasoning in Large Language Models".',
'title': 'Chain-of-ThoughtsPapers',
'link': 'https://github.com/Timothyxxx/Chain-of-ThoughtsPapers',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Mistral: A strong, northwesterly wind: Framework for transparent '
'and accessible large-scale language model training, built with '
'Hugging Face 🤗 Transformers.',
'title': 'mistral',
'link': 'https://github.com/stanford-crfm/mistral',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A prize for finding tasks that cause large language models to '
'show inverse scaling',
'title': 'prize',
'link': 'https://github.com/inverse-scaling/prize',
'engines': ['github'],
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-11
|
'engines': ['github'],
'category': 'it'},
{'snippet': 'Optimus: the first large-scale pre-trained VAE language model',
'title': 'Optimus',
'link': 'https://github.com/ChunyuanLI/Optimus',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Seminar on Large Language Models (COMP790-101 at UNC Chapel '
'Hill, Fall 2022)',
'title': 'llm-seminar',
'link': 'https://github.com/craffel/llm-seminar',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A central, open resource for data and tools related to '
'chain-of-thought reasoning in large language models. Developed @ '
'Samwald research group: https://samwald.info/',
'title': 'ThoughtSource',
'link': 'https://github.com/OpenBioLink/ThoughtSource',
'engines': ['github'],
'category': 'it'},
{'snippet': 'A comprehensive list of papers using large language/multi-modal '
'models for Robotics/RL, including papers, codes, and related '
'websites',
'title': 'Awesome-LLM-Robotics',
'link': 'https://github.com/GT-RIPL/Awesome-LLM-Robotics',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Tools for curating biomedical training data for large-scale '
'language modeling',
'title': 'biomedical',
'link': 'https://github.com/bigscience-workshop/biomedical',
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-12
|
'link': 'https://github.com/bigscience-workshop/biomedical',
'engines': ['github'],
'category': 'it'},
{'snippet': 'ChatGPT @ Home: Large Language Model (LLM) chatbot application, '
'written by ChatGPT',
'title': 'ChatGPT-at-Home',
'link': 'https://github.com/Sentdex/ChatGPT-at-Home',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Design and Deploy Large Language Model Apps',
'title': 'dust',
'link': 'https://github.com/dust-tt/dust',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Polyglot: Large Language Models of Well-balanced Competence in '
'Multi-languages',
'title': 'polyglot',
'link': 'https://github.com/EleutherAI/polyglot',
'engines': ['github'],
'category': 'it'},
{'snippet': 'Code release for "Learning Video Representations from Large '
'Language Models"',
'title': 'LaViLa',
'link': 'https://github.com/facebookresearch/LaViLa',
'engines': ['github'],
'category': 'it'},
{'snippet': 'SmoothQuant: Accurate and Efficient Post-Training Quantization '
'for Large Language Models',
'title': 'smoothquant',
'link': 'https://github.com/mit-han-lab/smoothquant',
'engines': ['github'],
'category': 'it'},
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
d75cce8b1c87-13
|
'engines': ['github'],
'category': 'it'},
{'snippet': 'This repository contains the code, data, and models of the paper '
'titled "XL-Sum: Large-Scale Multilingual Abstractive '
'Summarization for 44 Languages" published in Findings of the '
'Association for Computational Linguistics: ACL-IJCNLP 2021.',
'title': 'xl-sum',
'link': 'https://github.com/csebuetnlp/xl-sum',
'engines': ['github'],
'category': 'it'}]
previous
Search Tools
next
SerpAPI
Contents
Custom Parameters
Obtaining results with metadata
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/searx_search.html
|
53fae5a3f959-0
|
.ipynb
.pdf
Search Tools
Contents
Google Serper API Wrapper
SerpAPI
GoogleSearchAPIWrapper
SearxNG Meta Search Engine
Search Tools#
This notebook shows off usage of various search tools.
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
Google Serper API Wrapper#
First, let’s try to use the Google Serper API tool.
tools = load_tools(["google-serper"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I should look up the current weather conditions.
Action: Search
Action Input: "weather in Pomfret"
Observation: 37°F
Thought: I now know the current temperature in Pomfret.
Final Answer: The current temperature in Pomfret is 37°F.
> Finished chain.
'The current temperature in Pomfret is 37°F.'
SerpAPI#
Now, let’s use the SerpAPI tool.
tools = load_tools(["serpapi"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I need to find out what the current weather is in Pomfret.
Action: Search
Action Input: "weather in Pomfret"
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
53fae5a3f959-1
|
Action: Search
Action Input: "weather in Pomfret"
Observation: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 ...
Thought: I now know the current weather in Pomfret.
Final Answer: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.
> Finished chain.
'Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.'
GoogleSearchAPIWrapper#
Now, let’s use the official Google Search API Wrapper.
tools = load_tools(["google-search"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret?")
> Entering new AgentExecutor chain...
I should look up the current weather conditions.
Action: Google Search
Action Input: "weather in Pomfret"
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
53fae5a3f959-2
|
Action: Google Search
Action Input: "weather in Pomfret"
Observation: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Hourly Weather-Pomfret, CT. As of 12:52 am EST. Special Weather Statement +2 ... Hazardous Weather Conditions. Special Weather Statement ... Pomfret CT. Tonight ... National Digital Forecast Database Maximum Temperature Forecast. Pomfret Center Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Pomfret, CT 12 hour by hour weather forecast includes precipitation, temperatures, sky conditions, rain chance, dew-point, relative humidity, wind direction ... North Pomfret Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Today's Weather - Pomfret, CT. Dec 31, 2022 4:00 PM. Putnam MS. --. Weather forecast icon. Feels like --. Hi --. Lo --. Pomfret, CT temperature trend for the next 14 Days. Find daytime highs and nighttime lows from TheWeatherNetwork.com. Pomfret, MD Weather Forecast Date: 332 PM EST Wed Dec 28 2022. The area/counties/county of: Charles, including the cites of: St. Charles and Waldorf.
Thought: I now know the current weather conditions in Pomfret.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
53fae5a3f959-3
|
Thought: I now know the current weather conditions in Pomfret.
Final Answer: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.
> Finished AgentExecutor chain.
'Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.'
SearxNG Meta Search Engine#
Here we will be using a self hosted SearxNG meta search engine.
tools = load_tools(["searx-search"], searx_host="http://localhost:8888", llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What is the weather in Pomfret")
> Entering new AgentExecutor chain...
I should look up the current weather
Action: SearX Search
Action Input: "weather in Pomfret"
Observation: Mainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.
10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
53fae5a3f959-4
|
10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....
Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.
Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’s Why We Get More Colds and Flu When It’s Cold Coast-To-Coast...
Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...
Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...
Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
53fae5a3f959-5
|
12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...
Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...
Thought: I now know the final answer
Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.
> Finished chain.
'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'
previous
SceneXplain
next
SearxNG Search API
Contents
Google Serper API Wrapper
SerpAPI
GoogleSearchAPIWrapper
SearxNG Meta Search Engine
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/search_tools.html
|
60f9504612b3-0
|
.ipynb
.pdf
ArXiv API Tool
Contents
The ArXiv API Wrapper
ArXiv API Tool#
This notebook goes over how to use the arxiv component.
First, you need to install arxiv python package.
!pip install arxiv
from langchain.chat_models import ChatOpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
llm = ChatOpenAI(temperature=0.0)
tools = load_tools(
["arxiv"],
)
agent_chain = initialize_agent(
tools,
llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True,
)
agent_chain.run(
"What's the paper 1605.08386 about?",
)
> Entering new AgentExecutor chain...
I need to use Arxiv to search for the paper.
Action: Arxiv
Action Input: "1605.08386"
Observation: Published: 2016-05-26
Title: Heat-bath random walks with Markov bases
Authors: Caprice Stanley, Tobias Windisch
Summary: Graphs on lattice points are studied whose edges come from a finite set of
allowed moves of arbitrary length. We show that the diameter of these graphs on
fibers of a fixed integer matrix can be bounded from above by a constant. We
then study the mixing behaviour of heat-bath random walks on these graphs. We
also state explicit conditions on the set of moves so that the heat-bath random
walk, a generalization of the Glauber dynamics, is an expander in fixed
dimension.
Thought:The paper is about heat-bath random walks with Markov bases on graphs of lattice points.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/arxiv.html
|
60f9504612b3-1
|
Final Answer: The paper 1605.08386 is about heat-bath random walks with Markov bases on graphs of lattice points.
> Finished chain.
'The paper 1605.08386 is about heat-bath random walks with Markov bases on graphs of lattice points.'
The ArXiv API Wrapper#
The tool wraps the API Wrapper. Below, we can explore some of the features it provides.
from langchain.utilities import ArxivAPIWrapper
Run a query to get information about some scientific article/articles. The query text is limited to 300 characters.
It returns these article fields:
Publishing date
Title
Authors
Summary
Next query returns information about one article with arxiv Id equal “1605.08386”.
arxiv = ArxivAPIWrapper()
docs = arxiv.run("1605.08386")
docs
'Published: 2016-05-26\nTitle: Heat-bath random walks with Markov bases\nAuthors: Caprice Stanley, Tobias Windisch\nSummary: 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.'
Now, we want to get information about one author, Caprice Stanley.
This query returns information about three articles. By default, the query returns information only about three top articles.
docs = arxiv.run("Caprice Stanley")
docs
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/arxiv.html
|
60f9504612b3-2
|
docs = arxiv.run("Caprice Stanley")
docs
'Published: 2017-10-10\nTitle: On Mixing Behavior of a Family of Random Walks Determined by a Linear Recurrence\nAuthors: Caprice Stanley, Seth Sullivant\nSummary: We study random walks on the integers mod $G_n$ that are determined by an\ninteger sequence $\\{ G_n \\}_{n \\geq 1}$ generated by a linear recurrence\nrelation. Fourier analysis provides explicit formulas to compute the\neigenvalues of the transition matrices and we use this to bound the mixing time\nof the random walks.\n\nPublished: 2016-05-26\nTitle: Heat-bath random walks with Markov bases\nAuthors: Caprice Stanley, Tobias Windisch\nSummary: 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.\n\nPublished: 2003-03-18\nTitle: Calculation of fluxes of charged particles and neutrinos from atmospheric showers\nAuthors: V. Plyaskin\nSummary: The results on the fluxes of charged particles and neutrinos from a\n3-dimensional (3D) simulation of atmospheric showers are presented. An\nagreement of calculated fluxes with data on charged particles from the AMS and\nCAPRICE detectors is demonstrated. Predictions on neutrino fluxes at different\nexperimental sites are compared with results from other calculations.'
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/arxiv.html
|
60f9504612b3-3
|
Now, we are trying to find information about non-existing article. In this case, the response is “No good Arxiv Result was found”
docs = arxiv.run("1605.08386WWW")
docs
'No good Arxiv Result was found'
previous
Apify
next
AWS Lambda API
Contents
The ArXiv API Wrapper
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/arxiv.html
|
08e6d333a176-0
|
.ipynb
.pdf
Wikipedia
Wikipedia#
Wikipedia is a multilingual free online encyclopedia written and maintained by a community of volunteers, known as Wikipedians, through open collaboration and using a wiki-based editing system called MediaWiki. Wikipedia is the largest and most-read reference work in history.
First, you need to install wikipedia python package.
!pip install wikipedia
from langchain.utilities import WikipediaAPIWrapper
wikipedia = WikipediaAPIWrapper()
wikipedia.run('HUNTER X HUNTER')
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
08e6d333a176-1
|
'Page: Hunter × Hunter\nSummary: Hunter × Hunter (stylized as HUNTER×HUNTER and pronounced "hunter hunter") is a Japanese manga series written and illustrated by Yoshihiro Togashi. It has been serialized in Shueisha\'s shōnen manga magazine Weekly Shōnen Jump since March 1998, although the manga has frequently gone on extended hiatuses since 2006. Its chapters have been collected in 37 tankōbon volumes as of November 2022. The story focuses on a young boy named Gon Freecss who discovers that his father, who left him at a young age, is actually a world-renowned Hunter, a licensed professional who specializes in fantastical pursuits such as locating rare or unidentified animal species, treasure hunting, surveying unexplored enclaves, or hunting down lawless individuals. Gon departs on a journey to become a Hunter and eventually find his father. Along the way, Gon meets various other Hunters and encounters the paranormal.\nHunter × Hunter was adapted into a 62-episode anime television series produced by Nippon Animation and directed by Kazuhiro Furuhashi, which ran on Fuji Television from October 1999 to March 2001. Three separate original video animations (OVAs) totaling 30 episodes were subsequently produced by Nippon Animation and released in Japan from 2002 to 2004. A second anime television series by Madhouse aired on Nippon Television from October 2011 to September 2014, totaling 148 episodes, with two animated theatrical films released in 2013. There are also numerous audio albums, video games, musicals, and other media based on Hunter × Hunter.\nThe manga has been translated into English and released in North America by Viz Media since April 2005. Both television series have been also licensed by Viz Media, with the first series having aired on the Funimation Channel in 2009
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
08e6d333a176-2
|
by Viz Media, with the first series having aired on the Funimation Channel in 2009 and the second series broadcast on Adult Swim\'s Toonami programming block from April 2016 to June 2019.\nHunter × Hunter has been a huge critical and financial success and has become one of the best-selling manga series of all time, having over 84 million copies in circulation by July 2022.\n\nPage: Hunter × Hunter (2011 TV series)\nSummary: Hunter × Hunter is an anime television series that aired from 2011 to 2014 based on Yoshihiro Togashi\'s manga series Hunter × Hunter. The story begins with a young boy named Gon Freecss, who one day discovers that the father who he thought was dead, is in fact alive and well. He learns that his father, Ging, is a legendary "Hunter", an individual who has proven themselves an elite member of humanity. Despite the fact that Ging left his son with his relatives in order to pursue his own dreams, Gon becomes determined to follow in his father\'s footsteps, pass the rigorous "Hunter Examination", and eventually find his father to become a Hunter in his own right.\nThis new Hunter × Hunter anime was announced on July 24, 2011. It is a complete reboot of the anime adaptation starting from the beginning of the manga, with no connections to the first anime from 1999. Produced by Nippon TV, VAP, Shueisha and Madhouse, the series is directed by Hiroshi Kōjina, with Atsushi Maekawa and Tsutomu Kamishiro handling series composition, Takahiro Yoshimatsu designing the characters and Yoshihisa Hirano composing the music. Instead of having the old cast reprise their roles for the new adaptation, the series features an entirely new cast to voice the characters. The new series premiered airing weekly on Nippon TV and the nationwide
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
08e6d333a176-3
|
cast to voice the characters. The new series premiered airing weekly on Nippon TV and the nationwide Nippon News Network from October 2, 2011. The series started to be collected in both DVD and Blu-ray format on January 25, 2012. Viz Media has licensed the anime for a DVD/Blu-ray release in North America with an English dub. On television, the series began airing on Adult Swim\'s Toonami programming block on April 17, 2016, and ended on June 23, 2019.The anime series\' opening theme is alternated between the song "Departure!" and an alternate version titled "Departure! -Second Version-" both sung by Galneryus\' vocalist Masatoshi Ono. Five pieces of music were used as the ending theme; "Just Awake" by the Japanese band Fear, and Loathing in Las Vegas in episodes 1 to 26, "Hunting for Your Dream" by Galneryus in episodes 27 to 58, "Reason" sung by Japanese duo Yuzu in episodes 59 to 75, "Nagareboshi Kirari" also sung by Yuzu from episode 76 to 98, which was originally from the anime film adaptation, Hunter × Hunter: Phantom Rouge, and "Hyōri Ittai" by Yuzu featuring Hyadain from episode 99 to 146, which was also used in the film Hunter × Hunter: The Last Mission. The background music and soundtrack for the series was composed by Yoshihisa Hirano.\n\n\n\nPage: List of Hunter × Hunter characters\nSummary: The Hunter × Hunter manga series, created by Yoshihiro Togashi, features an extensive cast of characters. It takes place in a fictional universe where licensed specialists known as Hunters travel the world taking on special jobs ranging from treasure hunting to assassination. The story initially focuses on Gon Freecss and
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
08e6d333a176-4
|
on special jobs ranging from treasure hunting to assassination. The story initially focuses on Gon Freecss and his quest to become a Hunter in order to find his father, Ging, who is himself a famous Hunter. On the way, Gon meets and becomes close friends with Killua Zoldyck, Kurapika and Leorio Paradinight.\nAlthough most characters are human, most possess superhuman strength and/or supernatural abilities due to Nen, the ability to control one\'s own life energy or aura. The world of the series also includes fantastical beasts such as the Chimera Ants or the Five great calamities.'
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
08e6d333a176-5
|
previous
Twilio
next
Wolfram Alpha
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/wikipedia.html
|
96f7e3de787f-0
|
.ipynb
.pdf
GraphQL tool
GraphQL tool#
This Jupyter Notebook demonstrates how to use the BaseGraphQLTool component with an Agent.
GraphQL is a query language for APIs and a runtime for executing those queries against your data. GraphQL provides a complete and understandable description of the data in your API, gives clients the power to ask for exactly what they need and nothing more, makes it easier to evolve APIs over time, and enables powerful developer tools.
By including a BaseGraphQLTool in the list of tools provided to an Agent, you can grant your Agent the ability to query data from GraphQL APIs for any purposes you need.
In this example, we’ll be using the public Star Wars GraphQL API available at the following endpoint: https://swapi-graphql.netlify.app/.netlify/functions/index.
First, you need to install httpx and gql Python packages.
pip install httpx gql > /dev/null
Now, let’s create a BaseGraphQLTool instance with the specified Star Wars API endpoint and initialize an Agent with the tool.
from langchain import OpenAI
from langchain.agents import load_tools, initialize_agent, AgentType
from langchain.utilities import GraphQLAPIWrapper
llm = OpenAI(temperature=0)
tools = load_tools(["graphql"], graphql_endpoint="https://swapi-graphql.netlify.app/.netlify/functions/index", llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
Now, we can use the Agent to run queries against the Star Wars GraphQL API. Let’s ask the Agent to list all the Star Wars films and their release dates.
graphql_fields = """allFilms {
films {
title
director
releaseDate
speciesConnection {
species {
name
classification
homeworld {
name
}
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/graphql.html
|
96f7e3de787f-1
|
name
classification
homeworld {
name
}
}
}
}
}
"""
suffix = "Search for the titles of all the stawars films stored in the graphql database that has this schema "
agent.run(suffix + graphql_fields)
> Entering new AgentExecutor chain...
I need to query the graphql database to get the titles of all the star wars films
Action: query_graphql
Action Input: query { allFilms { films { title } } }
Observation: "{\n \"allFilms\": {\n \"films\": [\n {\n \"title\": \"A New Hope\"\n },\n {\n \"title\": \"The Empire Strikes Back\"\n },\n {\n \"title\": \"Return of the Jedi\"\n },\n {\n \"title\": \"The Phantom Menace\"\n },\n {\n \"title\": \"Attack of the Clones\"\n },\n {\n \"title\": \"Revenge of the Sith\"\n }\n ]\n }\n}"
Thought: I now know the titles of all the star wars films
Final Answer: The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.
> Finished chain.
'The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.'
previous
Gradio Tools
next
HuggingFace Tools
By Harrison Chase
© Copyright 2023, Harrison Chase.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/graphql.html
|
96f7e3de787f-2
|
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/tools/examples/graphql.html
|
ed4adcbf338f-0
|
.ipynb
.pdf
SQL Database Agent
Contents
Initialization
Using ZERO_SHOT_REACT_DESCRIPTION
Using OpenAI Functions
Example: describing a table
Example: describing a table, recovering from an error
Example: running queries
Recovering from an error
SQL Database Agent#
This notebook showcases an agent designed to interact with a sql databases. The agent builds off of SQLDatabaseChain and is designed to answer more general questions about a database, as well as recover from errors.
Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won’t perform DML statements on your database given certain questions. Be careful running it on sensitive data!
This uses the example Chinook database. To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository.
Initialization#
from langchain.agents import create_sql_agent
from langchain.agents.agent_toolkits import SQLDatabaseToolkit
from langchain.sql_database import SQLDatabase
from langchain.llms.openai import OpenAI
from langchain.agents import AgentExecutor
from langchain.agents.agent_types import AgentType
from langchain.chat_models import ChatOpenAI
db = SQLDatabase.from_uri("sqlite:///../../../../../notebooks/Chinook.db")
toolkit = SQLDatabaseToolkit(db=db, llm=OpenAI(temperature=0))
Using ZERO_SHOT_REACT_DESCRIPTION#
This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type. Note that this is an alternative to the above.
agent_executor = create_sql_agent(
llm=OpenAI(temperature=0),
toolkit=toolkit,
verbose=True,
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION
)
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-1
|
verbose=True,
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION
)
Using OpenAI Functions#
This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above.
# agent_executor = create_sql_agent(
# llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
# toolkit=toolkit,
# verbose=True,
# agent_type=AgentType.OPENAI_FUNCTIONS
# )
Example: describing a table#
agent_executor.run("Describe the playlisttrack table")
> Entering new chain...
Invoking: `list_tables_sql_db` with `{}`
Album, Artist, Track, PlaylistTrack, InvoiceLine, sales_table, Playlist, Genre, Employee, Customer, Invoice, MediaType
Invoking: `schema_sql_db` with `PlaylistTrack`
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
/*
3 rows from PlaylistTrack table:
PlaylistId TrackId
1 3402
1 3389
1 3390
*/The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks.
Here is the schema of the `PlaylistTrack` table:
```
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-2
|
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
```
Here are three sample rows from the `PlaylistTrack` table:
```
PlaylistId TrackId
1 3402
1 3389
1 3390
```
Please let me know if there is anything else I can help you with.
> Finished chain.
'The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \n\nHere is the schema of the `PlaylistTrack` table:\n\n```\nCREATE TABLE "PlaylistTrack" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\tPRIMARY KEY ("PlaylistId", "TrackId"), \n\tFOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"), \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n```\n\nHere are three sample rows from the `PlaylistTrack` table:\n\n```\nPlaylistId TrackId\n1 3402\n1 3389\n1 3390\n```\n\nPlease let me know if there is anything else I can help you with.'
Example: describing a table, recovering from an error#
In this example, the agent tries to search for a table that doesn’t exist, but finds the next best result
agent_executor.run("Describe the playlistsong table")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-3
|
Action: list_tables_sql_db
Action Input: ""
Observation: Genre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist
Thought: I should look at the schema of the PlaylistSong table
Action: schema_sql_db
Action Input: "PlaylistSong"
Observation: Error: table_names {'PlaylistSong'} not found in database
Thought: I should check the spelling of the table
Action: list_tables_sql_db
Action Input: ""
Observation: Genre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist
Thought: The table is called PlaylistTrack
Action: schema_sql_db
Action Input: "PlaylistTrack"
Observation:
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
SELECT * FROM 'PlaylistTrack' LIMIT 3;
PlaylistId TrackId
1 3402
1 3389
1 3390
Thought: I now know the final answer
Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.
> Finished chain.
'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.'
Example: running queries#
agent_executor.run("List the total sales per country. Which country's customers spent the most?")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-4
|
Action: list_tables_sql_db
Action Input: ""
Observation: Invoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer
Thought: I should look at the schema of the relevant tables to see what columns I can use.
Action: schema_sql_db
Action Input: "Invoice, Customer"
Observation:
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
SELECT * FROM 'Customer' LIMIT 3;
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-5
|
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
SELECT * FROM 'Invoice' LIMIT 3;
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
Thought: I should query the Invoice and Customer tables to get the total sales per country.
Action: query_sql_db
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-6
|
Action: query_sql_db
Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10
Observation: [('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]
Thought: I now know the final answer
Final Answer: The customers from the USA spent the most, with a total of $523.06.
> Finished chain.
'The customers from the USA spent the most, with a total of $523.06.'
agent_executor.run("Show the total number of tracks in each playlist. The Playlist name should be included in the result.")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
Observation: Invoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer
Thought: I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.
Action: schema_sql_db
Action Input: "Playlist, PlaylistTrack"
Observation:
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
SELECT * FROM 'Playlist' LIMIT 3;
PlaylistId Name
1 Music
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-7
|
)
SELECT * FROM 'Playlist' LIMIT 3;
PlaylistId Name
1 Music
2 Movies
3 TV Shows
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
SELECT * FROM 'PlaylistTrack' LIMIT 3;
PlaylistId TrackId
1 3402
1 3389
1 3390
Thought: I can use a SELECT statement to get the total number of tracks in each playlist.
Action: query_checker_sql_db
Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name
Observation:
SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name
Thought: The query looks correct, I can now execute it.
Action: query_sql_db
Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-8
|
Observation: [('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1)]
Thought: I now know the final answer.
Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).
> Finished chain.
"The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1)."
Recovering from an error#
In this example, the agent is able to recover from an error after initially trying to access an attribute (Track.ArtistId) which doesn’t exist.
agent_executor.run("Who are the top 3 best selling artists?")
> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: ""
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-9
|
Action: list_tables_sql_db
Action Input: ""
Observation: MediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist
Thought: I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.
Action: schema_sql_db
Action Input: "Artist, InvoiceLine, Track"
Observation:
CREATE TABLE "Artist" (
"ArtistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("ArtistId")
)
SELECT * FROM 'Artist' LIMIT 3;
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL,
"GenreId" INTEGER,
"Composer" NVARCHAR(220),
"Milliseconds" INTEGER NOT NULL,
"Bytes" INTEGER,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("TrackId"),
FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
SELECT * FROM 'Track' LIMIT 3;
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-10
|
2 Balls to the Wall 2 2 1 None 342562 5510424 0.99
3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99
CREATE TABLE "InvoiceLine" (
"InvoiceLineId" INTEGER NOT NULL,
"InvoiceId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
"Quantity" INTEGER NOT NULL,
PRIMARY KEY ("InvoiceLineId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)
SELECT * FROM 'InvoiceLine' LIMIT 3;
InvoiceLineId InvoiceId TrackId UnitPrice Quantity
1 1 2 0.99 1
2 1 4 0.99 1
3 2 6 0.99 1
Thought: I should query the database to get the top 3 best selling artists.
Action: query_sql_db
Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3
Observation: Error: (sqlite3.OperationalError) no such column: Track.ArtistId
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
ed4adcbf338f-11
|
[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3]
(Background on this error at: https://sqlalche.me/e/14/e3q8)
Thought: I should double check my query before executing it.
Action: query_checker_sql_db
Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3
Observation:
SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity
FROM Artist
INNER JOIN Track ON Artist.ArtistId = Track.ArtistId
INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId
GROUP BY Artist.Name
ORDER BY TotalQuantity DESC
LIMIT 3;
Thought: I now know the final answer.
Action: query_sql_db
Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3
Observation: [('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]
Thought: I now know the final answer.
Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.
> Finished chain.
'The top 3 best selling artists are Iron Maiden, U2, and Metallica.'
previous
|
rtdocs_stable/api.python.langchain.com/en/stable/modules/agents/toolkits/examples/sql_database.html
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.