id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
5c46835715c6-3 | 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 |
5c46835715c6-4 | '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 |
5c46835715c6-5 | 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 |
5c46835715c6-6 | 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 |
5c46835715c6-7 | 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 |
5c46835715c6-8 | 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 |
5c46835715c6-9 | 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 |
5c46835715c6-10 | 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 |
5c46835715c6-11 | \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 |
5c46835715c6-12 | '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 |
5c46835715c6-13 | > 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 |
5c46835715c6-14 | 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 |
5c46835715c6-15 | 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 |
5c46835715c6-16 | "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 |
5c46835715c6-17 | 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 |
5c46835715c6-18 | 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 |
5c46835715c6-19 | 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 |
5c46835715c6-20 | (\'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 |
5c46835715c6-21 | 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 |
5c46835715c6-22 | */
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 |
5c46835715c6-23 | 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 |
5c46835715c6-24 | 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 |
5c46835715c6-25 | > 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 |
5c46835715c6-26 | 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 |
5c46835715c6-27 | 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 |
5c46835715c6-28 | '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 |
5c46835715c6-29 | (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 |
5c46835715c6-30 | '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 |
5c46835715c6-31 | 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 |
5c46835715c6-32 | 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 |
5c46835715c6-33 | 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 |
5c46835715c6-34 | 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 |
5c46835715c6-35 | 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 |
5c46835715c6-36 | 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 |
5c46835715c6-37 | 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 |
5c46835715c6-38 | 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 |
5c46835715c6-39 | 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 |
5c46835715c6-40 | 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 |
5c46835715c6-41 | 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 |
5c46835715c6-42 | 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 |
5c46835715c6-43 | \ \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 |
5c46835715c6-44 | 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 |
5c46835715c6-45 | 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 |
5c46835715c6-46 | # 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 |
5c46835715c6-47 | 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 |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-7 | Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Lag... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-8 | > Finished chain.
output
{'instructions': 'whats the most expensive shirt?', | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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",... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-10 | Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Lag... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-11 | 'intermediate_steps': {'request_args': '{"q": "shirt", "max_price": null}', | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-13 | Somerton Check Shirt - Camel","url":"https://www.klarna.com/us/shopping/pl/cl10001/3201112728/Clothing/Burberry-Somerton-Check-Shirt-Camel/?utm_source=openai&ref-site=openai_plugin","price":"$450.00","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Man","Color:Beige"]},{"name":"Magellan Outdoors Lag... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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 ... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-17 | 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 arrive at their house or o... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-18 | 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 report an issue or leave feedback on the plugin."} | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-19 | > 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: | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-20 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-21 | 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 arrive at their house or o... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-22 | 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 report an issue or leave feedback on the plugin."} | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-23 | 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: ```... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-24 | '{"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... | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
29c8ab377b0d-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 |
29c8ab377b0d-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 |
29c8ab377b0d-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 28, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/openapi.html |
76579856c317-0 | .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 |
76579856c317-1 | 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 |
76579856c317-2 | 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 |
bc31d22a70fd-0 | .rst
.pdf
LLMs
LLMs#
Note
Conceptual Guide
Large Language Models (LLMs) are a core component of LangChain.
LangChain is not a provider of LLMs, but rather provides a standard interface through which
you can interact with a variety of LLMs.
The following sections of documentation are provided:
Getting Started: An overvi... | https://python.langchain.com/en/latest/modules/models/llms.html |
3e984cff55c1-0 | .ipynb
.pdf
Getting Started
Contents
Language Models
text -> text interface
messages -> message interface
Getting Started#
One of the core value props of LangChain is that it provides a standard interface to models. This allows you to swap easily between models. At a high level, there are two main types of models:
La... | https://python.langchain.com/en/latest/modules/models/getting_started.html |
3e984cff55c1-1 | Contents
Language Models
text -> text interface
messages -> message interface
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/models/getting_started.html |
bc012a70bbf1-0 | .rst
.pdf
Chat Models
Chat Models#
Note
Conceptual Guide
Chat models are a variation on language models.
While chat models use language models under the hood, the interface they expose is a bit different.
Rather than expose a “text in, text out” API, they expose an interface where “chat messages” are the inputs and out... | https://python.langchain.com/en/latest/modules/models/chat.html |
067765e15b39-0 | .rst
.pdf
Text Embedding Models
Text Embedding Models#
Note
Conceptual Guide
This documentation goes over how to use the Embedding class in LangChain.
The Embedding class is a class designed for interfacing with embeddings. There are lots of Embedding providers (OpenAI, Cohere, Hugging Face, etc) - this class is design... | https://python.langchain.com/en/latest/modules/models/text_embedding.html |
5b413672b69a-0 | .ipynb
.pdf
Getting Started
Getting Started#
This notebook goes over how to use the LLM class in LangChain.
The LLM class is a class designed for interfacing with LLMs. There are lots of LLM providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them. In this p... | https://python.langchain.com/en/latest/modules/models/llms/getting_started.html |
5b413672b69a-1 | llm_result.generations[-1]
[Generation(text="\n\nWhat if love neverspeech\n\nWhat if love never ended\n\nWhat if love was only a feeling\n\nI'll never know this love\n\nIt's not a feeling\n\nBut it's what we have for each other\n\nWe just know that love is something strong\n\nAnd we can't help but be happy\n\nWe just f... | https://python.langchain.com/en/latest/modules/models/llms/getting_started.html |
5b413672b69a-2 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/models/llms/getting_started.html |
a0ccd6b11e13-0 | .rst
.pdf
Generic Functionality
Generic Functionality#
The examples here all address certain “how-to” guides for working with LLMs.
How to use the async API for LLMs
How to write a custom LLM wrapper
How (and why) to use the fake LLM
How (and why) to use the human input LLM
How to cache LLM calls
How to serialize LLM c... | https://python.langchain.com/en/latest/modules/models/llms/how_to_guides.html |
1b878c340b41-0 | .rst
.pdf
Integrations
Integrations#
The examples here are all “how-to” guides for how to integrate with various LLM providers.
AI21
Aleph Alpha
Anyscale
Azure OpenAI
Banana
Beam integration for langchain
CerebriumAI
Cohere
C Transformers
Databricks
DeepInfra
ForefrontAI
Google Cloud Platform Vertex AI PaLM
GooseAI
GPT... | https://python.langchain.com/en/latest/modules/models/llms/integrations.html |
c6ad6dc1fedc-0 | .ipynb
.pdf
Modal
Modal#
The Modal Python Library provides convenient, on-demand access to serverless cloud compute from Python scripts on your local computer.
The Modal itself does not provide any LLMs but only the infrastructure.
This example goes over how to use LangChain to interact with Modal.
Here is another exam... | https://python.langchain.com/en/latest/modules/models/llms/integrations/modal.html |
c6ad6dc1fedc-1 | llm_chain.run(question)
previous
Manifest
next
MosaicML
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/models/llms/integrations/modal.html |
2c1e1e482aac-0 | .ipynb
.pdf
PipelineAI
Contents
Install pipeline-ai
Imports
Set the Environment API Key
Create the PipelineAI instance
Create a Prompt Template
Initiate the LLMChain
Run the LLMChain
PipelineAI#
PipelineAI allows you to run your ML models at scale in the cloud. It also provides API access to several LLM models.
This ... | https://python.langchain.com/en/latest/modules/models/llms/integrations/pipelineai_example.html |
2c1e1e482aac-1 | Run the LLMChain#
Provide a question and run the LLMChain.
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
llm_chain.run(question)
previous
Petals
next
PredictionGuard
Contents
Install pipeline-ai
Imports
Set the Environment API Key
Create the PipelineAI instance
Create a Prompt Te... | https://python.langchain.com/en/latest/modules/models/llms/integrations/pipelineai_example.html |
ea0913e3af34-0 | .ipynb
.pdf
Llama-cpp
Llama-cpp#
llama-cpp is a Python binding for llama.cpp.
It supports several LLMs.
This notebook goes over how to run llama-cpp within LangChain.
!pip install llama-cpp-python
Make sure you are following all instructions to install all necessary model files.
You don’t need an API_TOKEN!
from langch... | https://python.langchain.com/en/latest/modules/models/llms/integrations/llamacpp.html |
ea0913e3af34-1 | ' First we need to identify what year Justin Beiber was born in. A quick google search reveals that he was born on March 1st, 1994. Now we know when the Super Bowl was played in, so we can look up which NFL team won it. The NFL Superbowl of the year 1994 was won by the San Francisco 49ers against the San Diego Chargers... | https://python.langchain.com/en/latest/modules/models/llms/integrations/llamacpp.html |
da82db2eb757-0 | .ipynb
.pdf
Cohere
Cohere#
Cohere is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions.
This example goes over how to use LangChain to interact with Cohere models.
# Install the package
!pip install cohere
# get a new token: https://dashboard.cohe... | https://python.langchain.com/en/latest/modules/models/llms/integrations/cohere.html |
da82db2eb757-1 | llm_chain.run(question)
" Let's start with the year that Justin Beiber was born. You know that he was born in 1994. We have to go back one year. 1993.\n\n1993 was the year that the Dallas Cowboys won the Super Bowl. They won over the Buffalo Bills in Super Bowl 26.\n\nNow, let's do it backwards. According to our inform... | https://python.langchain.com/en/latest/modules/models/llms/integrations/cohere.html |
b91e4e496527-0 | .ipynb
.pdf
OpenLM
Contents
Setup
Using LangChain with OpenLM
OpenLM#
OpenLM is a zero-dependency OpenAI-compatible LLM provider that can call different inference endpoints directly via HTTP.
It implements the OpenAI Completion class so that it can be used as a drop-in replacement for the OpenAI API. This changeset u... | https://python.langchain.com/en/latest/modules/models/llms/integrations/openlm.html |
b91e4e496527-1 | for model in ["text-davinci-003", "huggingface.co/gpt2"]:
llm = OpenLM(model=model)
llm_chain = LLMChain(prompt=prompt, llm=llm)
result = llm_chain.run(question)
print("""Model: {}
Result: {}""".format(model, result))
Model: text-davinci-003
Result: France is a country in Europe. The capital of France ... | https://python.langchain.com/en/latest/modules/models/llms/integrations/openlm.html |
9c5f2eb08faa-0 | .ipynb
.pdf
CerebriumAI
Contents
Install cerebrium
Imports
Set the Environment API Key
Create the CerebriumAI instance
Create a Prompt Template
Initiate the LLMChain
Run the LLMChain
CerebriumAI#
Cerebrium is an AWS Sagemaker alternative. It also provides API access to several LLM models.
This notebook goes over how ... | https://python.langchain.com/en/latest/modules/models/llms/integrations/cerebriumai_example.html |
9c5f2eb08faa-1 | Run the LLMChain#
Provide a question and run the LLMChain.
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
llm_chain.run(question)
previous
Beam integration for langchain
next
Cohere
Contents
Install cerebrium
Imports
Set the Environment API Key
Create the CerebriumAI instance
Crea... | https://python.langchain.com/en/latest/modules/models/llms/integrations/cerebriumai_example.html |
65cf0d63959d-0 | .ipynb
.pdf
Petals
Contents
Install petals
Imports
Set the Environment API Key
Create the Petals instance
Create a Prompt Template
Initiate the LLMChain
Run the LLMChain
Petals#
Petals runs 100B+ language models at home, BitTorrent-style.
This notebook goes over how to use Langchain with Petals.
Install petals#
The p... | https://python.langchain.com/en/latest/modules/models/llms/integrations/petals_example.html |
65cf0d63959d-1 | Run the LLMChain#
Provide a question and run the LLMChain.
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
llm_chain.run(question)
previous
OpenLM
next
PipelineAI
Contents
Install petals
Imports
Set the Environment API Key
Create the Petals instance
Create a Prompt Template
Initiat... | https://python.langchain.com/en/latest/modules/models/llms/integrations/petals_example.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.