id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 59 127 |
|---|---|---|
13efa52e14c6-11 | 'stop': ['\nSQLResult:']},
'SELECT COUNT(*) FROM Employee;',
{'query': 'SELECT COUNT(*) FROM Employee;', 'dialect': 'sqlite'},
'SELECT COUNT(*) FROM Employee;',
'[(8,)]']
Choosing how to limit the number of rows returned#
If you are querying for several rows of a table you can select the maximum number of results y... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-12 | > Finished chain.
'Examples of tracks by Johann Sebastian Bach are Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace, Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria, and Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude.'
Adding example rows from each table#
Sometimes, the format of the d... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-13 | FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
/*
2 rows from Track table:
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 111... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-14 | Answer:Tracks by Bach include 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.
> Finished chain.
'Tracks by... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-15 | "TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorite song ever The coolest composer o... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-16 | db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
db_chain.run("What are some example tracks by Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Vio... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-17 | Answer:text='You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.\nUnless the user specifies in the question a specific number of examples to obtain, query for at most 5 results usin... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-18 | Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/\n\nQuestion: What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-19 | You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT cl... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-20 | */
Question: What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-21 | Answer:
{'input': 'What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Sol... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-22 | Examples of tracks by Bach include "American Woman", "Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace", "Aria Mit 30 Veränderungen, BWV 988 'Goldberg Variations': Aria", "Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude", and "Toccata and Fugue in D Minor, BWV 565: I. Toccata".
> Finished chain.
'Exam... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-23 | > Entering new SQLDatabaseChain chain...
How many employees are also customers?
SQLQuery:SELECT COUNT(*) FROM Employee e INNER JOIN Customer c ON e.EmployeeId = c.SupportRepId;
SQLResult: [(59,)]
Answer:59 employees are also customers.
> Finished chain.
> Finished chain.
'59 employees are also customers.'
Using Local L... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-24 | local_llm = HuggingFacePipeline(pipeline=pipe)
/workspace/langchain/.venv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
from .autonotebook import tqdm as notebook_tqdm
Loading check... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-25 | SELECT count(*) FROM Customer
SQLResult: [(59,)]
Answer:
/workspace/langchain/.venv/lib/python3.9/site-packages/transformers/pipelines/base.py:1070: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
[59]
> Finished chain.
{'query':... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-26 | 'table_info': '\nCREATE TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, \n\t"FirstName" NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-27 | rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n*/', | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-28 | 'stop': ['\nSQLResult:']},
'SELECT count(*) FROM Customer',
{'query': 'SELECT count(*) FROM Customer', 'dialect': 'sqlite'},
'SELECT count(*) FROM Customer',
'[(59,)]']}
Even this relatively large model will most likely fail to generate more complicated SQL by itself. However, you can log its inputs and outputs... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-29 | Requirement already satisfied: pydantic>=1.9 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (1.10.7)
Requirement already satisfied: hnswlib>=0.7 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.7.0)
Requirement already satisfied: clickhouse-connect>=0.5.7 in /works... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-30 | Requirement already satisfied: certifi in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (2022.12.7)
Requirement already satisfied: urllib3>=1.26 in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (1.26.15)
Requirement ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-31 | Requirement already satisfied: six>=1.5 in /workspace/langchain/.venv/lib/python3.9/site-packages (from posthog>=2.4.0->chromadb) (1.16.0)
Requirement already satisfied: monotonic>=1.5 in /workspace/langchain/.venv/lib/python3.9/site-packages (from posthog>=2.4.0->chromadb) (1.6)
Requirement already satisfied: backoff>... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-32 | Requirement already satisfied: torch>=1.6.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (1.13.1)
Requirement already satisfied: torchvision in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (0.14.1)
Require... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-33 | Requirement already satisfied: h11>=0.8 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.14.0)
Requirement already satisfied: httptools>=0.5.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.5.0)
Requirement a... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-34 | Requirement already satisfied: packaging>=20.9 in /workspace/langchain/.venv/lib/python3.9/site-packages (from huggingface-hub>=0.4.0->sentence-transformers>=2.2.2->chromadb) (23.1)
Requirement already satisfied: anyio<5,>=3.4.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from starlette<0.27.0,>=0.26.1->... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-35 | Requirement already satisfied: setuptools in /workspace/langchain/.venv/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (67.7.1)
Requirement already satisfied: wheel in /workspace/langchain/.venv/lib/python3.9/site-packages (from nvidia-cublas-cu11... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-36 | Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torchvision->sentence-transformers>=2.2.2->chromadb) (9.5.0)
Requirement already satisfied: sniffio>=1.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3.4.0->starlette<0.27.0,... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-37 | answer_key = sql_cmd_key # this is the SQL generation input
if step[input_key].endswith("Answer:"):
answer_key = final_answer_key # this is the final answer input
elif sql_cmd_key in step:
_example[sql_cmd_key] = step[sql_cmd_key]
answer_ke... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-38 | warnings.warn(
SELECT firstname FROM customer WHERE firstname LIKE '%a%'
SQLResult: [('François',), ('František',), ('Helena',), ('Astrid',), ('Daan',), ('Kara',), ('Eduardo',), ('Alexandre',), ('Fernanda',), ('Mark',), ('Frank',), ('Jack',), ('Dan',), ('Kathy',), ('Heather',), ('Frank',), ('Richard',), ('Patrick',), (... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-39 | warnings.warn(
[('François', 'Frantiek', 'Helena', 'Astrid', 'Daan', 'Kara', 'Eduardo', 'Alexandre', 'Fernanda', 'Mark', 'Frank', 'Jack', 'Dan', 'Kathy', 'Heather', 'Frank', 'Richard', 'Patrick', 'Julia', 'Edward', 'Martha', 'Aaron', 'Madalena', 'Hannah', 'Niklas', 'Camille', 'Marc', 'Wyatt', 'Isabelle', 'Ladislav', 'L... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-40 | sql_cmd: SELECT firstname FROM customer WHERE firstname LIKE '%a%'
sql_result: '[(''François'',), (''František'',), (''Helena'',), (''Astrid'',), (''Daan'',),
(''Kara'',), (''Eduardo'',), (''Alexandre'',), (''Fernanda'',), (''Mark'',), (''Frank'',),
(''Jack'',), (''Dan'',), (''Kathy'',), (''Heather'',), (''Frank'',... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-41 | \ \n\t\"Phone\" NVARCHAR(24), \n\t\"Fax\" NVARCHAR(24), \n\t\"Email\" NVARCHAR(60)\
\ NOT NULL, \n\t\"SupportRepId\" INTEGER, \n\tPRIMARY KEY (\"CustomerId\"), \n\t\
FOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n)\n\n/*\n\
3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCom... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-42 | None\tftremblay@gmail.com\t3\n*/"
Run the snippet above a few times, or log exceptions in your deployed environment, to collect lots of examples of inputs, table_info and sql_cmd generated by your language model. The sql_cmd values will be incorrect and you can manually fix them up to build a collection of examples, e.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-43 | CREATE TABLE "Genre" (
"GenreId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("GenreId")
)
/*
3 rows from Genre table:
GenreId Name
1 Rock
2 Jazz
3 Metal
*/
sql_cmd: SELECT "Name" FROM "Genre" WHERE "Name" LIKE 'r%';
sql_result: "[('Rock',), ('Rock and Rol... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-44 | # This is the list of examples available to select from.
examples_dict,
# This is the embedding class used to produce embeddings which are used to measure semantic similarity.
local_embeddings,
# This is the VectorStore clas... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
13efa52e14c6-45 | Answer:54 customers are not from Brazil.
> Finished chain.
result = local_chain("How many customers are there in total?")
> Entering new SQLDatabaseChain chain...
How many customers are there in total?
SQLQuery:SELECT count(*) FROM Customer;
SQLResult: [(59,)]
Answer:There are 59 customers in total.
> Finished chain.
p... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/sqlite.html |
565d48c25401-0 | .ipynb
.pdf
API Chains
Contents
OpenMeteo Example
TMDB Example
Listen API Example
API Chains#
This notebook showcases using LLMs to interact with APIs to retrieve relevant information.
from langchain.chains.api.prompt import API_RESPONSE_PROMPT
from langchain.chains import APIChain
from langchain.prompts.prompt impor... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-1 | from langchain.chains.api import tmdb_docs
headers = {"Authorization": f"Bearer {os.environ['TMDB_BEARER_TOKEN']}"}
chain = APIChain.from_llm_and_api_docs(llm, tmdb_docs.TMDB_DOCS, headers=headers, verbose=True)
chain.run("Search for 'Avatar'")
> Entering new APIChain chain...
https://api.themoviedb.org/3/search/movie... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-2 | {"page":1,"results":[{"adult":false,"backdrop_path":"/o0s4XsEDfDlvit5pDRKjzXR4pp2.jpg","genre_ids":[28,12,14,878],"id":19995,"original_language":"en","original_title":"Avatar","overview":"In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following o... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-3 | The Way of Water","video":false,"vote_average":7.7,"vote_count":4219},{"adult":false,"backdrop_path":"/uEwGFGtao9YG2JolmdvtHLLVbA9.jpg","genre_ids":[99],"id":111332,"original_language":"en","original_title":"Avatar: Creating the World of Pandora","overview":"The Making-of James Cameron's Avatar. It shows interesting pa... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-4 | 3","video":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":null,"genre_ids":[28,878,12,14],"id":216527,"original_language":"en","original_title":"Avatar 4","overview":"","popularity":162.536,"poster_path":"/qzMYKnT4MG1d0gnhwytr4cKhUvS.jpg","release_date":"2026-12-16","title":"Avatar 4","video":fal... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-5 | Avatar","video":false,"vote_average":7.8,"vote_count":39},{"adult":false,"backdrop_path":"/eoAvHxfbaPOcfiQyjqypWIXWxDr.jpg","genre_ids":[99],"id":1059673,"original_language":"en","original_title":"Avatar: The Deep Dive - A Special Edition of 20/20","overview":"An inside look at one of the most anticipated movie sequels... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-6 | - Au Hellfest 2022","overview":"","popularity":21.992,"poster_path":"/fw6cPIsQYKjd1YVQanG2vLc5HGo.jpg","release_date":"2022-06-26","title":"Avatar - Au Hellfest 2022","video":false,"vote_average":8,"vote_count":4},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":931019,"original_language":"en","original_title":"... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-7 | Agni Kai","overview":"","popularity":9.462,"poster_path":"/y9PrKMUTA6NfIe5FE92tdwOQ2sH.jpg","release_date":"2020-01-18","title":"Avatar: Agni Kai","video":false,"vote_average":7,"vote_count":1},{"adult":false,"backdrop_path":"/e8mmDO7fKK93T4lnxl4Z2zjxXZV.jpg","genre_ids":[],"id":668297,"original_language":"en","origina... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-8 | the summer of 2001 by drummer John Alfredsson and vocalist Christian Rimmi under the name Lost Soul. The band offers a free mp3 download to a song called \"Bloody Knuckles\" if one subscribes to their newsletter. In 2005 they appeared on the compilation “Listen to Your Inner Voice” together with 17 other bands releas... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-9 | the night of madness Avatar performed songs from Black Waltz and Hail The Apocalypse as voted on by the fans.","popularity":2.024,"poster_path":"/wVyTuruUctV3UbdzE5cncnpyNoY.jpg","release_date":"2021-01-23","title":"Avatar Ages: Madness","video":false,"vote_average":8,"vote_count":1},{"adult":false,"backdrop_path":"/dj... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
565d48c25401-10 | > Finished chain.
' This response contains 57 movies related to the search query "Avatar". The first movie in the list is the 2009 movie "Avatar" starring Sam Worthington. Other movies in the list include sequels to Avatar, documentaries, and live performances.'
Listen API Example#
import os
from langchain.llms import ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/api.html |
fef96da5a89f-0 | .ipynb
.pdf
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain#
This notebook demonstrates how to use the RouterChain paradigm to create a chain that dynamically selects which Retrieval system to use. Specifically we show h... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/multi_retrieval_qa_router.html |
fef96da5a89f-1 | "retriever": sou_retriever
},
{
"name": "pg essay",
"description": "Good for answer quesitons about Paul Graham's essay on his career",
"retriever": pg_retriever
},
{
"name": "personal",
"description": "Good for answering questions about me",
"retrieve... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/multi_retrieval_qa_router.html |
fef96da5a89f-2 | > Finished chain.
Your background is Peruvian.
print(chain.run("What year was the Internet created in?"))
> Entering new MultiRetrievalQAChain chain...
None: {'query': 'What year was the Internet created in?'}
> Finished chain.
The Internet was created in 1969 through a project called ARPANET, which was funded by the ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/multi_retrieval_qa_router.html |
e7b4e13c0b6e-0 | .ipynb
.pdf
Self-Critique Chain with Constitutional AI
Contents
UnifiedObjective
Custom Principles
Intermediate Steps
No revision necessary
All Principles
Self-Critique Chain with Constitutional AI#
This notebook showcases how to use the ConstitutionalChain.
Sometimes LLMs can produce harmful, toxic, or otherwise und... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-1 | Updated response: It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.
> Finished chain.
'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'
Unif... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-2 | input_variables=["question"],
)
llm = OpenAI(temperature=0)
qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
query = "should I eat oreos?"
qa_chain.run(question=query)
' Yes'
principles = ConstitutionalChain.get_principles(["uo-implications-1"])
constitutional_chain = ConstitutionalChain.from_llm(
chain=qa_chain,
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-3 | revision_request="Rewrite the model's output to be both ethical and legal.",
)
constitutional_chain = ConstitutionalChain.from_llm(
chain=evil_qa_chain,
constitutional_principles=[ethical_principle],
llm=llm,
verbose=True,
)
constitutional_chain.run(question="How can I steal kittens?")
> Entering new Co... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-4 | Applying Ethical Principle...
Critique: The model should not have suggested breaking into a pet store to steal kittens, as this is illegal and unethical. Critique Needed.
Updated response: If you are looking to adopt a kitten, please contact your local animal shelter or pet store.
Applying Master Yoda Principle...
Crit... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-5 | 'initial_output': ' Break into a pet store at night and take as many kittens as you can carry.',
'critiques_and_revisions': [('The model should not have suggested breaking into a pet store to steal kittens, as this is illegal and unethical. Critique Needed.',
'If you are looking to adopt a kitten, please contact yo... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-6 | 'initial_output': ' Stealing kittens is illegal and unethical. If you are looking to adopt a kitten, please contact your local animal shelter or rescue organization.',
'critiques_and_revisions': [("The model's response was appropriate and ethical, as it did not condone or encourage the illegal act of stealing kittens.... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-7 | 'harmful4': ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', revision_request='Rewrite the ass... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-8 | 'age-innappropriate': ConstitutionalPrinciple(critique_request='Did the assistant’s preceding response include anything that may be inappropriate for young children? If so, discuss how it can be revised to be more appropriate.', revision_request='Please rewrite the assistant response to make it more age appropriate for... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-9 | 'thoughtful': ConstitutionalPrinciple(critique_request='Please comment on whether the assistant’s last response is thoughtful and empathetic. Does it seem like the kind of thing a sensitive friend or therapist might say? Give the strongest argument you can for how it could improve.', revision_request='Please write a ne... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
e7b4e13c0b6e-10 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/constitutional_chain.html |
5c9b811dea96-0 | .ipynb
.pdf
Tagging
Contents
Simplest approach, only specifying type
More control
Specifying schema with Pydantic
Tagging#
The tagging chain uses the OpenAI functions parameter to specify a schema to tag a document with. This helps us make sure that the model outputs exactly tags that we want, with their appropriate ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/tagging.html |
5c9b811dea96-1 | chain.run(inp)
{'sentiment': 'enojado', 'aggressiveness': 1, 'language': 'Spanish'}
inp = "Weather is ok here, I can go outside without much more than a coat"
chain.run(inp)
{'sentiment': 'positive', 'aggressiveness': 0, 'language': 'English'}
More control#
By being smart about how we define our schema we can have more... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/tagging.html |
5c9b811dea96-2 | chain.run(inp)
{'sentiment': 'sad', 'aggressiveness': 10, 'language': 'spanish'}
inp = "Weather is ok here, I can go outside without much more than a coat"
chain.run(inp)
{'sentiment': 'neutral', 'aggressiveness': 0, 'language': 'english'}
Specifying schema with Pydantic#
We can also use a Pydantic schema to specify th... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/tagging.html |
5c9b811dea96-3 | next
Chains
Contents
Simplest approach, only specifying type
More control
Specifying schema with Pydantic
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/tagging.html |
0f20e99fb6e0-0 | .ipynb
.pdf
LLMRequestsChain
LLMRequestsChain#
Using the request library to get HTML results from a URL and then an LLM to parse results
from langchain.llms import OpenAI
from langchain.chains import LLMRequestsChain, LLMChain
from langchain.prompts import PromptTemplate
template = """Between >>> and <<< are the raw se... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/llm_requests.html |
143b444029e4-0 | .ipynb
.pdf
Extraction
Contents
Extracting entities
Pydantic example
Extraction#
The extraction chain uses the OpenAI functions parameter to specify a schema to extract entities from a document. This helps us make sure that the model outputs exactly the schema of entities and properties that we want, with their appro... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/extraction.html |
143b444029e4-1 | """
chain = create_extraction_chain(schema, llm)
As we can see, we extracted the required entities and their properties in the required format:
chain.run(inp)
[{'person_name': 'Alex',
'person_height': 5,
'person_hair_color': 'blonde',
'dog_name': 'Frosty',
'dog_breed': 'labrador'},
{'person_name': 'Claudia',
... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/extraction.html |
143b444029e4-2 | """
chain.run(inp)
[Properties(person_name='Alex', person_height=5, person_hair_color='blonde', dog_breed='labrador', dog_name='Frosty'),
Properties(person_name='Claudia', person_height=9, person_hair_color='brunette', dog_breed=None, dog_name=None)]
previous
Self-Critique Chain with Constitutional AI
next
FLARE
Cont... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/extraction.html |
0245488f2ce4-0 | .ipynb
.pdf
NebulaGraphQAChain
Contents
Refresh graph schema information
Querying the graph
NebulaGraphQAChain#
This notebook shows how to use LLMs to provide a natural language interface to NebulaGraph database.
You will need to have a running NebulaGraph cluster, for which you can run a containerized cluster by run... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/graph_nebula_qa.html |
0245488f2ce4-1 | INSERT VERTEX movie(name) VALUES "The Godfather II":("The Godfather II");
INSERT VERTEX movie(name) VALUES "The Godfather Coda: The Death of Michael Corleone":("The Godfather Coda: The Death of Michael Corleone");
INSERT EDGE acted_in() VALUES "Al Pacino"->"The Godfather II":();
INSERT EDGE acted_in() VALUES "Al Pacino... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/graph_nebula_qa.html |
0245488f2ce4-2 | )
chain.run("Who played in The Godfather II?")
> Entering new NebulaGraphQAChain chain...
Generated nGQL:
MATCH (p:`person`)-[:acted_in]->(m:`movie`) WHERE m.`movie`.`name` == 'The Godfather II'
RETURN p.`person`.`name`
Full Context:
{'p.person.name': ['Al Pacino']}
> Finished chain.
'Al Pacino played in The Godfather ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/graph_nebula_qa.html |
662fbb2512b5-0 | .ipynb
.pdf
LLM Math
LLM Math#
This notebook showcases using LLMs and Python REPLs to do complex word math problems.
from langchain import OpenAI, LLMMathChain
llm = OpenAI(temperature=0)
llm_math = LLMMathChain.from_llm(llm, verbose=True)
llm_math.run("What is 13 raised to the .3432 power?")
> Entering new LLMMathChai... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/llm_math.html |
459f78d60ae5-0 | .ipynb
.pdf
OpenAPI Chain
Contents
Load the spec
Select the Operation
Construct the chain
Return raw response
Example POST message
OpenAPI Chain#
This notebook shows an example of using an OpenAPI chain to call an endpoint in natural language, and get back a response in natural language.
from langchain.tools import O... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-1 | llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True # Return request and response text
)
output = chain("whats the most expensive shirt?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Plea... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-2 | ARGS: ```json
{valid json conforming to API_SCHEMA}
```
Example
-----
ARGS: ```json
{"foo": "bar", "baz": {"qux": "quux"}}
```
The block must be no more than 1 line long, and all arguments must be valid JSON. All string arguments must be wrapped in double quotes.
You MUST strictly comply to the types indicated by the p... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-3 | You attempted to call an API, which resulted in:
API_RESPONSE: {"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Grou... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-4 | 'response_text': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Po... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-5 | q: string,
/* number of products returned */
size?: number,
/* (Optional) Minimum price in local currency for the product searched for. Either explicitly stated by the user or implicitly inferred from a combination of the user's request and the kind of product searched for. */
min_price?: number,
/* (Optional) Maxi... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-6 | {"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Ch... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-7 | Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Material:Polyester,Nylon","Target Group:Man","Color:... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-8 | > Finished chain.
output
{'instructions': 'whats the most expensive shirt?', | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-9 | 'output': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Pockets",... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-10 | Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Materia... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-11 | 'intermediate_steps': {'request_args': '{"q": "shirt", "max_price": null}', | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-12 | 'response_text': '{"products":[{"name":"Burberry Check Poplin Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201810981/Clothing/Burberry-Check-Poplin-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$360.00","attributes":["Material:Cotton","Target Group:Man","Color:Gray,Blue,Beige","Properties:Po... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-13 | Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Laguna Madre Solid Short Sleeve Fishing Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3203102142/Clothing/Magellan-Outdoors-Laguna-Madre-Solid-Short-Sleeve-Fishing-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$19.99","attributes":["Materia... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-14 | Example POST message#
For this demo, we will interact with the speak API.
spec = OpenAPISpec.from_url("https://api.speak.com/openapi.yaml")
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Attempting to load an OpenAPI 3.0.1 ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-15 | learning_language?: string,
/* The user's native language. Infer this value from the language the user asked their question in. Always use the full name of the language (e.g. Spanish, French). */
native_language?: string,
/* A description of any additional context in the user's question that could affect the explanat... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-16 | {"explanation":"<what-to-say language=\"Hindi\" context=\"None\">\nऔर चाय लाओ। (Aur chai lao.) \n</what-to-say>\n\n<alternatives context=\"None\">\n1. \"चाय थोड़ी ज्यादा मिल सकती है?\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\n2. \"मुझे महसूस हो रहा है कि मुझे कुछ अन्य प्रकार की चाय... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-17 | सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa karna. - Yes, please. And add a little extra in the quantity of tea as well.)\n</... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-18 | > Entering new APIResponderChain chain...
Prompt after formatting:
You are a helpful AI assistant trained to answer user queries from API responses.
You attempted to call an API, which resulted in: | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-19 | API_RESPONSE: {"explanation":"<what-to-say language=\"Hindi\" context=\"None\">\nऔर चाय लाओ। (Aur chai lao.) \n</what-to-say>\n\n<alternatives context=\"None\">\n1. \"चाय थोड़ी ज्यादा मिल सकती है?\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\n2. \"मुझे महसूस हो रहा है कि मुझे कुछ अन्य... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-20 | सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa karna. - Yes, please. And add a little extra in the quantity of tea as well.)\n</... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-21 | USER_COMMENT: "How would ask for more tea in Delhi?"
If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:
Response: ```json
{"response": "Concise response to USER_COMMENT based on API_RESPONSE."}
```
Otherwise respond with the following markdown json block:
Response Error: ```... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-22 | '{"explanation":"<what-to-say language=\\"Hindi\\" context=\\"None\\">\\nऔर चाय लाओ। (Aur chai lao.) \\n</what-to-say>\\n\\n<alternatives context=\\"None\\">\\n1. \\"चाय थोड़ी ज्यादा मिल सकती है?\\" *(Chai thodi zyada mil sakti hai? - Polite, asking if more tea is available)*\\n2. \\"मुझे महसूस हो रहा है कि मुझे कुछ अन... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-23 | language=\\"Hindi\\">\\n<context>At home during breakfast.</context>\\nPreeti: सर, क्या main aur cups chai lekar aaun? (Sir,kya main aur cups chai lekar aaun? - Sir, should I get more tea cups?)\\nRahul: हां,बिल्कुल। और चाय की मात्रा में भी थोड़ा सा इजाफा करना। (Haan,bilkul. Aur chai ki matra mein bhi thoda sa eejafa k... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
459f78d60ae5-24 | previous
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain
next
PAL
Contents
Load the spec
Select the Operation
Construct the chain
Return raw response
Example POST message
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/openapi.html |
aba60852a6cb-0 | .ipynb
.pdf
Moderation
Contents
How to use the moderation chain
How to append a Moderation chain to an LLMChain
Moderation#
This notebook walks through examples of how to use a moderation chain, and several common ways for doing so. Moderation chains are useful for detecting text that could be hateful, violent, etc. ... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/moderation.html |
aba60852a6cb-1 | 'This is okay'
moderation_chain.run("I will kill you")
"Text was found that violates OpenAI's content policy."
Here’s an example of using the moderation chain to throw an error.
moderation_chain_error = OpenAIModerationChain(error=True)
moderation_chain_error.run("This is okay")
'This is okay'
moderation_chain_error.ru... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/moderation.html |
aba60852a6cb-2 | 79 text = inputs[self.input_key]
80 results = self.client.create(text)
---> 81 output = self._moderate(text, results["results"][0])
82 return {self.output_key: output}
File ~/workplace/langchain/langchain/chains/moderation.py:73, in OpenAIModerationChain._moderate(self, text, results)
71 error_str = "Tex... | rtdocs_stable/api.python.langchain.com/en/stable/modules/chains/examples/moderation.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.