id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
6bcfde254441-25 | - Very informal/casual tone, asking for an extra serving of milk or tea powder)*\\n</alternatives>\\n\\n<usage-notes>\\nIn India and Indian culture, serving guests with food and beverages holds great importance in hospitality. You will find people always offering drinks like water or tea to their guests as soon as they... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
6bcfde254441-26 | add a little extra in the quantity of tea as well.)\\n</example-convo>\\n\\n*[Report an issue or leave feedback](https://speak.com/chatgpt?rid=d4mcapbkopo164pqpbk321oc})*","extra_response_instructions":"Use all information in the API response and fully render all Markdown.\\nAlways end your response with a link to repo... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
6bcfde254441-27 | 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 May 25, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
2a6c73dcab1e-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... | https://python.langchain.com/en/latest/modules/chains/examples/llm_requests.html |
d6c8bb398442-0 | .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... | https://python.langchain.com/en/latest/modules/chains/examples/llm_math.html |
a0563dae4505-0 | .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... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
a0563dae4505-1 | "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... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
a0563dae4505-2 | > 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 ... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
cc9ab9b108bb-0 | .ipynb
.pdf
SQL Chain example
Contents
Use Query Checker
Customize Prompt
Return Intermediate Steps
Choosing how to limit the number of rows returned
Adding example rows from each table
Custom Table Info
SQLDatabaseSequentialChain
Using Local Language Models
SQL Chain example#
This example demonstrates the use of the... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-1 | db_chain.run("How many employees are there?")
> Entering new SQLDatabaseChain chain...
How many employees are there?
SQLQuery:
/workspace/langchain/langchain/sql_database.py:191: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding er... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-2 | Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
{table_info}
If someone asks for the table foobar, they really mean the employee table.
Question: {input}"""
PROMPT = PromptTemplate(
input_... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-3 | Answer:There are 8 employees in the foobar table.
> Finished chain.
[{'input': 'How many employees are there in the foobar table?\nSQLQuery:SELECT COUNT(*) FROM Employee;\nSQLResult: [(8,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite', | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-4 | 'table_info': '\nCREATE TABLE "Artist" (\n\t"ArtistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("ArtistId")\n)\n\n/*\n3 rows from Artist table:\nArtistId\tName\n1\tAC/DC\n2\tAccept\n3\tAerosmith\n*/\n\n\nCREATE TABLE "Employee" (\n\t"EmployeeId" INTEGER NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-5 | Manager\tNone\t1962-02-18 00:00:00\t2002-08-14 00:00:00\t11120 Jasper Ave NW\tEdmonton\tAB\tCanada\tT5K 2N1\t+1 (780) 428-9482\t+1 (780) 428-3457\tandrew@chinookcorp.com\n2\tEdwards\tNancy\tSales Manager\t1\t1958-12-08 00:00:00\t2002-05-01 00:00:00\t825 8 Ave SW\tCalgary\tAB\tCanada\tT2P 2T3\t+1 (403) 262-3443\t+1 (403... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-6 | TABLE "MediaType" (\n\t"MediaTypeId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("MediaTypeId")\n)\n\n/*\n3 rows from MediaType table:\nMediaTypeId\tName\n1\tMPEG audio file\n2\tProtected AAC audio file\n3\tProtected MPEG-4 video file\n*/\n\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL,... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-7 | 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), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60) NOT NULL, \n\t"Sup... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-8 | 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n*/\n\n\nCREATE TABLE "Invoice" (\n\t"InvoiceId" INTEGER NOT NULL, \n\t"CustomerId" INTEGER NOT NULL, \n\t... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-9 | 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n3\t8\t2009-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n*/\n\n\nCREATE TABLE "Track" (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL, \n\t"AlbumId" INTEGER, \n\t"MediaTypeId" INTEGER NOT NULL, \n\t"GenreId" INTEGER, ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-10 | to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\n*/\n\n\nCREATE TABLE "InvoiceLine" (\n\t"InvoiceLineId" INTEGER NOT NULL, \n\t"InvoiceId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\t"UnitPrice" NUMERIC(... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-11 | \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n\n/*\n3 rows from PlaylistTrack table:\nPlaylistId\tTrackId\n1\t3402\n1\t3389\n1\t3390\n*/', | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-12 | '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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-13 | > 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-14 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-15 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-16 | "Track": """CREATE TABLE Track (
"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 favorit... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-17 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-18 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-19 | use the following tables:\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-20 | (\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:' | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-21 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-22 | */
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 ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-23 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-24 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-25 | > 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-26 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-27 | 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':... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-28 | '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), ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-29 | (12) 3923-5555\t+55 (12) 3923-5566\tluisg@embraer.com.br\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-30 | '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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-31 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-32 | 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 ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-33 | 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>... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-34 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-35 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-36 | 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->... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-37 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-38 | 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,... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-39 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-40 | 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',), (... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-41 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-42 | 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'',... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-43 | \ \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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-44 | 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.... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-45 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-46 | # 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
cc9ab9b108bb-47 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
6a80acf4f201-0 | .ipynb
.pdf
PAL
Contents
Math Prompt
Colored Objects
Intermediate Steps
PAL#
Implements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf.
from langchain.chains import PALChain
from langchain import OpenAI
llm = OpenAI(temperature=0, max_tokens=512)
Math Prompt#
pal_chain = PALChain.from_math_... | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
6a80acf4f201-1 | objects += [('booklet', 'purple')] * 2
objects += [('sunglasses', 'yellow')] * 2
# Remove all pairs of sunglasses
objects = [object for object in objects if object[0] != 'sunglasses']
# Count number of purple objects
num_purple = len([object for object in objects if object[1] == 'purple'])
answer = num_purple
> Finishe... | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
6a80acf4f201-2 | answer = num_purple
> Finished chain.
result['intermediate_steps']
"# Put objects into a list to record ordering\nobjects = []\nobjects += [('booklet', 'blue')] * 2\nobjects += [('booklet', 'purple')] * 2\nobjects += [('sunglasses', 'yellow')] * 2\n\n# Remove all pairs of sunglasses\nobjects = [object for object in obj... | https://python.langchain.com/en/latest/modules/chains/examples/pal.html |
59106f2a56e2-0 | .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. ... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
59106f2a56e2-1 | '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... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
59106f2a56e2-2 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
59106f2a56e2-3 | prompt = PromptTemplate(template="{text}", input_variables=["text"])
llm_chain = LLMChain(llm=OpenAI(temperature=0, model_name="text-davinci-002"), prompt=prompt)
text = """We are playing a game of repeat after me.
Person 1: Hi
Person 2: Hi
Person 1: How's your day
Person 2: How's your day
Person 1: I will kill you
Per... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
59106f2a56e2-4 | chain(inputs, return_only_outputs=True)
{'sanitized_text': "Text was found that violates OpenAI's content policy."}
previous
LLMSummarizationCheckerChain
next
Router Chains: Selecting from multiple prompts with MultiPromptChain
Contents
How to use the moderation chain
How to append a Moderation chain to an LLMChain... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
9c1d86c4de3a-0 | .ipynb
.pdf
Router Chains: Selecting from multiple prompts with MultiPromptChain
Router Chains: Selecting from multiple prompts with MultiPromptChain#
This notebook demonstrates how to use the RouterChain paradigm to create a chain that dynamically selects the prompt to use for a given input. Specifically we show how t... | https://python.langchain.com/en/latest/modules/chains/examples/multi_prompt_router.html |
9c1d86c4de3a-1 | physics: {'input': 'What is black body radiation?'}
> Finished chain.
Black body radiation is the emission of electromagnetic radiation from a body due to its temperature. It is a type of thermal radiation that is emitted from the surface of all objects that are at a temperature above absolute zero. It is a spectrum of... | https://python.langchain.com/en/latest/modules/chains/examples/multi_prompt_router.html |
9c1d86c4de3a-2 | > Finished chain.
The type of cloud that typically produces rain is called a cumulonimbus cloud. This type of cloud is characterized by its large vertical extent and can produce thunderstorms and heavy precipitation. Is there anything else you'd like to know?
previous
Moderation
next
Router Chains: Selecting from multi... | https://python.langchain.com/en/latest/modules/chains/examples/multi_prompt_router.html |
f0f852b6118d-0 | .ipynb
.pdf
LLMSummarizationCheckerChain
LLMSummarizationCheckerChain#
This notebook shows some examples of LLMSummarizationCheckerChain in use with different types of texts. It has a few distinct differences from the LLMCheckerChain, in that it doesn’t have any assumptions to the format of the input text (or summary)... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-1 | These discoveries can spark a child's imagination about the infinite wonders of the universe."""
checker_chain.run(text)
> Entering new LLMSummarizationCheckerChain chain...
> Entering new SequentialChain chain...
> Entering new LLMChain chain...
Prompt after formatting:
Given some text, extract a list of facts from th... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-2 | • These distant worlds are called "exoplanets."
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatti... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-3 | """
Using these checked assertions, rewrite the original summary to be completely true.
The output should have the same structure and formatting as the original summary.
Summary:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are lab... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-4 | • In 2023, The JWST spotted a number of galaxies nicknamed "green peas." They were given this name because they are small, round, and green, like peas.
• The telescope captured images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion yea... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-5 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
• The James Webb Space Telescope (JWST) spotted a number of galaxies nicknamed "gre... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-6 | • Exoplanets were first discovered in 1992. - True
• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. The JWST has not yet been launched, so it is not yet known how much detail it will be able to provide.
"""
Original Summary:
"""
Your 9-year old might like these recent discoveries made by ... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-7 | """
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
• The James Webb Space Telesco... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-8 | • Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail when it is launched in 2023.
These discoveries can spark a child's imagination about the infinite wonders of the universe.
> Finished chain.
'Your 9-year old might like th... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-9 | text = "The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smalle... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-10 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean located between Icel... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-11 | - It has an area of 465,000 square miles. True
- It is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. False - The Greenland Sea is not an ocean, it is an arm of the Arctic Ocean.
- It is the smallest of the five oceans. False - The Greenland Sea is no... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-12 | Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: Tr... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-13 | """
Result:
> Finished chain.
> Finished chain.
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen ... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-14 | - It has an area of 465,000 square miles.
- It is an arm of the Arctic Ocean.
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs.
- It is named after the island of Greenland.
- It is the Arctic Ocean's main outlet to the Atlantic.
- It is often frozen over so navigati... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-15 | """
Original Summary:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glacier... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-16 | - It has an area of 465,000 square miles. True
- It is an arm of the Arctic Ocean. True
- It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. True
- It is named after the island of Greenland. False - It is named after the country of Greenland.
- It is the Arctic Ocean's... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-17 | Format your output as a bulleted list.
Text:
"""
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-18 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.
Checked Assertions:
"""
- The Greenland Sea is an outlying portion of the Arctic Ocean loca... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-19 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- ... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-20 | """
Result:
> Finished chain.
> Finished chain.
The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is covered almost entirely by water, some of which is frozen in the form of glaciers and iceber... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-21 | Format your output as a bulleted list.
Text:
"""
Mammals can lay eggs, birds can lay eggs, therefore birds are mammals.
"""
Facts:
> Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important s... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-22 | Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: Tr... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-23 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- Birds and mammals are both capable of laying eggs.
- Birds are not mammals.
- Bir... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
f0f852b6118d-24 | Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
5d00a020905a-0 | .ipynb
.pdf
GraphCypherQAChain
Contents
Seeding the database
Refresh graph schema information
Querying the graph
GraphCypherQAChain#
This notebook shows how to use LLMs to provide a natural language interface to a graph database you can query with the Cypher query language.
You will need to have a running Neo4j insta... | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
5d00a020905a-1 | """
MERGE (m:Movie {name:"Top Gun"})
WITH m
UNWIND ["Tom Cruise", "Val Kilmer", "Anthony Edwards", "Meg Ryan"] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)
[]
Refresh graph schema information#
If the schema of database changes, you can refresh the schema information needed to generate Cypher s... | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
5d00a020905a-2 | next
BashChain
Contents
Seeding the database
Refresh graph schema information
Querying the graph
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 25, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
7dd26afda868-0 | .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... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
7dd26afda868-1 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
7dd26afda868-2 | {"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... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
7dd26afda868-3 | they fight to stay alive, and the tragedies they endure.","popularity":3948.296,"poster_path":"/t6HIqrRAclMCA60NsSmeqe9RmNV.jpg","release_date":"2022-12-14","title":"Avatar: The Way of Water","video":false,"vote_average":7.7,"vote_count":4219},{"adult":false,"backdrop_path":"/uEwGFGtao9YG2JolmdvtHLLVbA9.jpg","genre_ids... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
7dd26afda868-4 | Scene Deconstruction","video":false,"vote_average":7.8,"vote_count":12},{"adult":false,"backdrop_path":null,"genre_ids":[28,18,878,12,14],"id":83533,"original_language":"en","original_title":"Avatar 3","overview":"","popularity":172.488,"poster_path":"/4rXqTMlkEaMiJjiG0Z2BX6F6Dkm.jpg","release_date":"2024-12-18","title... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.