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 you want to get by using the ‘top_k’ parameter (default is 10). This is useful for avoiding query results that exceed the prompt max length or consume tokens unnecessarily.
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True, use_query_checker=True, top_k=3)
db_chain.run("What are some example tracks by composer Johann Sebastian Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by composer Johann Sebastian Bach?
SQLQuery:SELECT Name FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3
SQLResult: [('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',)]
Answer: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.
> Finished chain.
|
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 data is not obvious and it is optimal to include a sample of rows from the tables in the prompt to allow the LLM to understand the data before providing a final query. Here we will use this feature to let the LLM know that artists are saved with their full names by providing two rows from the Track table.
db = SQLDatabase.from_uri(
"sqlite:///../../../../notebooks/Chinook.db",
include_tables=['Track'], # we include only one table to save tokens in the prompt :)
sample_rows_in_table_info=2)
The sample rows are added to the prompt after each corresponding table’s column information:
print(db.table_info)
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL,
"GenreId" INTEGER,
"Composer" NVARCHAR(220),
"Milliseconds" INTEGER NOT NULL,
"Bytes" INTEGER,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("TrackId"),
FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
|
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 11170334 0.99
2 Balls to the Wall 2 2 1 None 342562 5510424 0.99
*/
db_chain = SQLDatabaseChain.from_llm(llm, db, use_query_checker=True, 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", "Composer" FROM "Track" WHERE "Composer" LIKE '%Bach%' LIMIT 5
SQLResult: [('American Woman', 'B. Cummings/G. Peterson/M.J. Kale/R. Bachman'), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach'), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata', 'Johann Sebastian Bach')]
|
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 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\'.'
Custom Table Info#
In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first sample_rows_in_table_info sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns.
This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let’s provide a custom definition and sample rows for the Track table with only a few columns:
custom_table_info = {
"Track": """CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
|
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 of all time
*/"""
}
db = SQLDatabase.from_uri(
"sqlite:///../../../../notebooks/Chinook.db",
include_tables=['Track', 'Playlist'],
sample_rows_in_table_info=2,
custom_table_info=custom_table_info)
print(db.table_info)
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
2 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
*/
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 favorite song ever The coolest composer of all time
*/
Note how our custom table definition and sample rows for Track overrides the sample_rows_in_table_info parameter. Tables that are not overridden by custom_table_info, in this example Playlist, will have their table info gathered automatically as usual.
|
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 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',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
|
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 using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.\nNever query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.\nPay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n\nUse the following format:\n\nQuestion: "Question here"\nSQLQuery: "SQL Query to run"\nSQLResult: "Result of the SQLQuery"\nAnswer: "Final answer here"\n\nOnly 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"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song
|
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 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\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:'
|
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 clause as per SQLite. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
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:
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
2 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
*/
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 favorite song ever The coolest composer of all time
*/
Question: What are some example tracks by Bach?
|
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 G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
Answer:
|
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 Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:', 'top_k': '5', 'dialect': 'sqlite', 'table_info': '\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"Composer" NVARCHAR(220),\n\tPRIMARY KEY ("TrackId")\n)\n/*\n3 rows from Track table:\nTrackId\tName\tComposer\n1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n2\tBalls to the Wall\tNone\n3\tMy favorite song ever\tThe coolest composer of all time\n*/', 'stop': ['\nSQLResult:']}
|
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.
'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".'
SQLDatabaseSequentialChain#
Chain for querying SQL database that is a sequential chain.
The chain is as follows:
1. Based on the query, determine which tables to use.
2. Based on those tables, call the normal SQL database chain.
This is useful in cases where the number of tables in the database is large.
from langchain.chains import SQLDatabaseSequentialChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db")
chain = SQLDatabaseSequentialChain.from_llm(llm, db, verbose=True)
chain.run("How many employees are also customers?")
> Entering new SQLDatabaseSequentialChain chain...
Table names to use:
['Employee', 'Customer']
> Entering new SQLDatabaseChain chain...
How many employees are also customers?
|
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 Language Models#
Sometimes you may not have the luxury of using OpenAI or other service-hosted large language model. You can, ofcourse, try to use the SQLDatabaseChain with a local model, but will quickly realize that most models you can run locally even with a large GPU struggle to generate the right output.
import logging
import torch
from transformers import AutoTokenizer, GPT2TokenizerFast, pipeline, AutoModelForSeq2SeqLM, AutoModelForCausalLM
from langchain import HuggingFacePipeline
# Note: This model requires a large GPU, e.g. an 80GB A100. See documentation for other ways to run private non-OpenAI models.
model_id = "google/flan-ul2"
model = AutoModelForSeq2SeqLM.from_pretrained(model_id, temperature=0)
device_id = -1 # default to no-GPU, but use GPU and half precision mode if available
if torch.cuda.is_available():
device_id = 0
try:
model = model.half()
except RuntimeError as exc:
logging.warn(f"Could not run model in half precision mode: {str(exc)}")
tokenizer = AutoTokenizer.from_pretrained(model_id)
pipe = pipeline(task="text2text-generation", model=model, tokenizer=tokenizer, max_length=1024, device=device_id)
local_llm = HuggingFacePipeline(pipeline=pipe)
|
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 checkpoint shards: 100%|██████████| 8/8 [00:32<00:00, 4.11s/it]
from langchain import SQLDatabase, SQLDatabaseChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db", include_tables=['Customer'])
local_chain = SQLDatabaseChain.from_llm(local_llm, db, verbose=True, return_intermediate_steps=True, use_query_checker=True)
This model should work for very simple SQL queries, as long as you use the query checker as specified above, e.g.:
local_chain("How many customers are there?")
> Entering new SQLDatabaseChain chain...
How many customers are there?
SQLQuery:
/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(
/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(
SELECT count(*) FROM Customer
SQLResult: [(59,)]
Answer:
|
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': 'How many customers are there?',
'result': '[59]',
'intermediate_steps': [{'input': 'How many customers are there?\nSQLQuery:SELECT count(*) FROM Customer\nSQLResult: [(59,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite',
|
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), \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\tFOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")\n)\n\n/*\n3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (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
|
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 so that you can hand-correct them and use the corrected examples for few shot prompt examples later. In practice, you could log any executions of your chain that raise exceptions (as shown in the example below) or get direct user feedback in cases where the results are incorrect (but did not raise an exception).
!poetry run pip install pyyaml chromadb
import yaml
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
11842.36s - pydevd: Sending message related to process being replaced timed-out after 5 seconds
Requirement already satisfied: pyyaml in /workspace/langchain/.venv/lib/python3.9/site-packages (6.0)
Requirement already satisfied: chromadb in /workspace/langchain/.venv/lib/python3.9/site-packages (0.3.21)
Requirement already satisfied: pandas>=1.3 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (2.0.1)
Requirement already satisfied: requests>=2.28 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (2.28.2)
|
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 /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.5.20)
Requirement already satisfied: sentence-transformers>=2.2.2 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (2.2.2)
Requirement already satisfied: duckdb>=0.7.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.7.1)
Requirement already satisfied: fastapi>=0.85.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.95.1)
Requirement already satisfied: uvicorn[standard]>=0.18.3 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.21.1)
Requirement already satisfied: numpy>=1.21.6 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (1.24.3)
Requirement already satisfied: posthog>=2.4.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (3.0.1)
|
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 already satisfied: pytz in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (2023.3)
Requirement already satisfied: zstandard in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (0.21.0)
Requirement already satisfied: lz4 in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (4.3.2)
Requirement already satisfied: starlette<0.27.0,>=0.26.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from fastapi>=0.85.1->chromadb) (0.26.1)
Requirement already satisfied: python-dateutil>=2.8.2 in /workspace/langchain/.venv/lib/python3.9/site-packages (from pandas>=1.3->chromadb) (2.8.2)
Requirement already satisfied: tzdata>=2022.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from pandas>=1.3->chromadb) (2023.3)
|
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>=1.10.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from posthog>=2.4.0->chromadb) (2.2.1)
Requirement already satisfied: typing-extensions>=4.2.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from pydantic>=1.9->chromadb) (4.5.0)
Requirement already satisfied: charset-normalizer<4,>=2 in /workspace/langchain/.venv/lib/python3.9/site-packages (from requests>=2.28->chromadb) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in /workspace/langchain/.venv/lib/python3.9/site-packages (from requests>=2.28->chromadb) (3.4)
Requirement already satisfied: transformers<5.0.0,>=4.6.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (4.28.1)
Requirement already satisfied: tqdm in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (4.65.0)
|
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)
Requirement already satisfied: scikit-learn in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (1.2.2)
Requirement already satisfied: scipy in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (1.9.3)
Requirement already satisfied: nltk in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (3.8.1)
Requirement already satisfied: sentencepiece in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (0.1.98)
Requirement already satisfied: huggingface-hub>=0.4.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (0.13.4)
Requirement already satisfied: click>=7.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (8.1.3)
|
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 already satisfied: python-dotenv>=0.13 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (1.0.0)
Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.17.0)
Requirement already satisfied: watchfiles>=0.13 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.19.0)
Requirement already satisfied: websockets>=10.4 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (11.0.2)
Requirement already satisfied: filelock in /workspace/langchain/.venv/lib/python3.9/site-packages (from huggingface-hub>=0.4.0->sentence-transformers>=2.2.2->chromadb) (3.12.0)
|
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->fastapi>=0.85.1->chromadb) (3.6.2)
Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (11.7.99)
Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (8.5.0.96)
Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (11.10.3.66)
Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (11.7.99)
|
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==11.10.3.66->torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (0.40.0)
Requirement already satisfied: regex!=2019.12.17 in /workspace/langchain/.venv/lib/python3.9/site-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers>=2.2.2->chromadb) (2023.3.23)
Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers>=2.2.2->chromadb) (0.13.3)
Requirement already satisfied: joblib in /workspace/langchain/.venv/lib/python3.9/site-packages (from nltk->sentence-transformers>=2.2.2->chromadb) (1.2.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from scikit-learn->sentence-transformers>=2.2.2->chromadb) (3.1.0)
|
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,>=0.26.1->fastapi>=0.85.1->chromadb) (1.3.0)
from typing import Dict
QUERY = "List all the customer first names that start with 'a'"
def _parse_example(result: Dict) -> Dict:
sql_cmd_key = "sql_cmd"
sql_result_key = "sql_result"
table_info_key = "table_info"
input_key = "input"
final_answer_key = "answer"
_example = {
"input": result.get("query"),
}
steps = result.get("intermediate_steps")
answer_key = sql_cmd_key # the first one
for step in steps:
# The steps are in pairs, a dict (input) followed by a string (output).
# Unfortunately there is no schema but you can look at the input key of the
# dict to see what the output is supposed to be
if isinstance(step, dict):
# Grab the table info from input dicts in the intermediate steps once
if table_info_key not in _example:
_example[table_info_key] = step.get(table_info_key)
if input_key in step:
if step[input_key].endswith("SQLQuery:"):
answer_key = sql_cmd_key # this is the SQL generation input
|
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_key = sql_result_key # this is SQL execution input
elif isinstance(step, str):
# The preceding element should have set the answer_key
_example[answer_key] = step
return _example
example: any
try:
result = local_chain(QUERY)
print("*** Query succeeded")
example = _parse_example(result)
except Exception as exc:
print("*** Query failed")
result = {
"query": QUERY,
"intermediate_steps": exc.intermediate_steps
}
example = _parse_example(result)
# print for now, in reality you may want to write this out to a YAML file or database for manual fix-ups offline
yaml_example = yaml.dump(example, allow_unicode=True)
print("\n" + yaml_example)
> Entering new SQLDatabaseChain chain...
List all the customer first names that start with 'a'
SQLQuery:
/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(
SELECT firstname FROM customer WHERE firstname LIKE '%a%'
|
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',), ('Julia',), ('Edward',), ('Martha',), ('Aaron',), ('Madalena',), ('Hannah',), ('Niklas',), ('Camille',), ('Marc',), ('Wyatt',), ('Isabelle',), ('Ladislav',), ('Lucas',), ('Johannes',), ('Stanisław',), ('Joakim',), ('Emma',), ('Mark',), ('Manoj',), ('Puja',)]
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(
|
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', 'Lucas', 'Johannes', 'Stanisaw', 'Joakim', 'Emma', 'Mark', 'Manoj', 'Puja']
> Finished chain.
*** Query succeeded
answer: '[(''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'', ''Lucas'', ''Johannes'', ''Stanisaw'', ''Joakim'',
''Emma'', ''Mark'', ''Manoj'', ''Puja'']'
input: List all the customer first names that start with 'a'
sql_cmd: SELECT firstname FROM customer WHERE firstname LIKE '%a%'
|
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'',), (''Richard'',),
(''Patrick'',), (''Julia'',), (''Edward'',), (''Martha'',), (''Aaron'',), (''Madalena'',),
(''Hannah'',), (''Niklas'',), (''Camille'',), (''Marc'',), (''Wyatt'',), (''Isabelle'',),
(''Ladislav'',), (''Lucas'',), (''Johannes'',), (''Stanisław'',), (''Joakim'',),
(''Emma'',), (''Mark'',), (''Manoj'',), (''Puja'',)]'
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
|
13efa52e14c6-41
|
\ \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\tCompany\tAddress\t\
City\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n1\tLuís\tGonçalves\t\
Embraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\t\
São José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\t\
luisg@embraer.com.br\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\t\
None\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\t\
Tremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\t\
None\tftremblay@gmail.com\t3\n*/"
|
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.g. here we are using YAML to keep a neat record of our inputs and corrected SQL output that we can build up over time.
YAML_EXAMPLES = """
- input: How many customers are not from Brazil?
table_info: |
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
sql_cmd: SELECT COUNT(*) FROM "Customer" WHERE NOT "Country" = "Brazil";
sql_result: "[(54,)]"
answer: 54 customers are not from Brazil.
- input: list all the genres that start with 'r'
table_info: |
CREATE TABLE "Genre" (
"GenreId" INTEGER NOT NULL,
|
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 Roll',), ('Reggae',), ('R&B/Soul',)]"
answer: The genres that start with 'r' are Rock, Rock and Roll, Reggae and R&B/Soul.
"""
Now that you have some examples (with manually corrected output SQL), you can do few shot prompt seeding the usual way:
from langchain import FewShotPromptTemplate, PromptTemplate
from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
from langchain.vectorstores import Chroma
example_prompt = PromptTemplate(
input_variables=["table_info", "input", "sql_cmd", "sql_result", "answer"],
template="{table_info}\n\nQuestion: {input}\nSQLQuery: {sql_cmd}\nSQLResult: {sql_result}\nAnswer: {answer}",
)
examples_dict = yaml.safe_load(YAML_EXAMPLES)
local_embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
example_selector = SemanticSimilarityExampleSelector.from_examples(
# This is the list of examples available to select from.
examples_dict,
|
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 class that is used to store the embeddings and do a similarity search over.
Chroma, # type: ignore
# This is the number of examples to produce and include per prompt
k=min(3, len(examples_dict)),
)
few_shot_prompt = FewShotPromptTemplate(
example_selector=example_selector,
example_prompt=example_prompt,
prefix=_sqlite_prompt + "Here are some examples:",
suffix=PROMPT_SUFFIX,
input_variables=["table_info", "input", "top_k"],
)
Using embedded DuckDB without persistence: data will be transient
The model should do better now with this few shot prompt, especially for inputs similar to the examples you have seeded it with.
local_chain = SQLDatabaseChain.from_llm(local_llm, db, prompt=few_shot_prompt, use_query_checker=True, verbose=True, return_intermediate_steps=True)
result = local_chain("How many customers are from Brazil?")
> Entering new SQLDatabaseChain chain...
How many customers are from Brazil?
SQLQuery:SELECT count(*) FROM Customer WHERE Country = "Brazil";
SQLResult: [(5,)]
Answer:[5]
> Finished chain.
result = local_chain("How many customers are not from Brazil?")
> Entering new SQLDatabaseChain chain...
How many customers are not from Brazil?
SQLQuery:SELECT count(*) FROM customer WHERE country NOT IN (SELECT country FROM customer WHERE country = 'Brazil')
SQLResult: [(54,)]
Answer:54 customers are not from Brazil.
> Finished chain.
|
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.
previous
PAL
next
Tagging
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
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 import PromptTemplate
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
OpenMeteo Example#
from langchain.chains.api import open_meteo_docs
chain_new = APIChain.from_llm_and_api_docs(llm, open_meteo_docs.OPEN_METEO_DOCS, verbose=True)
chain_new.run('What is the weather like right now in Munich, Germany in degrees Fahrenheit?')
> Entering new APIChain chain...
https://api.open-meteo.com/v1/forecast?latitude=48.1351&longitude=11.5820&temperature_unit=fahrenheit¤t_weather=true
{"latitude":48.14,"longitude":11.58,"generationtime_ms":0.33104419708251953,"utc_offset_seconds":0,"timezone":"GMT","timezone_abbreviation":"GMT","elevation":521.0,"current_weather":{"temperature":33.4,"windspeed":6.8,"winddirection":198.0,"weathercode":2,"time":"2023-01-16T01:00"}}
> Finished chain.
' The current temperature in Munich, Germany is 33.4 degrees Fahrenheit with a windspeed of 6.8 km/h and a wind direction of 198 degrees. The weathercode is 2.'
TMDB Example#
import os
os.environ['TMDB_BEARER_TOKEN'] = ""
from langchain.chains.api import tmdb_docs
|
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?query=Avatar&language=en-US
|
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 orders and protecting an alien civilization.","popularity":2041.691,"poster_path":"/jRXYjXNq0Cs2TcJjLkki24MLp7u.jpg","release_date":"2009-12-15","title":"Avatar","video":false,"vote_average":7.6,"vote_count":27777},{"adult":false,"backdrop_path":"/s16H6tpK2utvwDtzZ8Qy4qm5Emw.jpg","genre_ids":[878,12,28],"id":76600,"original_language":"en","original_title":"Avatar: The Way of Water","overview":"Set more than a decade after the events of the first film, learn the story of the Sully family (Jake, Neytiri, and their kids), the trouble that follows them, the lengths they go to keep each other safe, the battles 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
|
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 parts of the work on the set.","popularity":541.809,"poster_path":"/sjf3xjuofCtDhZghJRzXlTiEjJe.jpg","release_date":"2010-02-07","title":"Avatar: Creating the World of Pandora","video":false,"vote_average":7.3,"vote_count":35},{"adult":false,"backdrop_path":null,"genre_ids":[99],"id":287003,"original_language":"en","original_title":"Avatar: Scene Deconstruction","overview":"The deconstruction of the Avatar scenes and sets","popularity":394.941,"poster_path":"/uCreCQFReeF0RiIXkQypRYHwikx.jpg","release_date":"2009-12-18","title":"Avatar: 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":"Avatar
|
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":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":null,"genre_ids":[28,12,14,878],"id":393209,"original_language":"en","original_title":"Avatar 5","overview":"","popularity":124.722,"poster_path":"/rtmmvqkIC5zDMEd638Es2woxbz8.jpg","release_date":"2028-12-20","title":"Avatar 5","video":false,"vote_average":0,"vote_count":0},{"adult":false,"backdrop_path":"/nNceJtrrovG1MUBHMAhId0ws9Gp.jpg","genre_ids":[99],"id":183392,"original_language":"en","original_title":"Capturing Avatar","overview":"Capturing Avatar is a feature length behind-the-scenes documentary about the making of Avatar. It uses footage from the film's development, as well as stock footage from as far back as the production of Titanic in 1995. Also included are numerous interviews with cast, artists, and other crew members. The documentary was released as a bonus feature on the extended collector's edition of Avatar.","popularity":109.842,"poster_path":"/26SMEXJl3978dn2svWBSqHbLl5U.jpg","release_date":"2010-11-16","title":"Capturing
|
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 ever with James Cameron and cast.","popularity":629.825,"poster_path":"/rtVeIsmeXnpjNbEKnm9Say58XjV.jpg","release_date":"2022-12-14","title":"Avatar: The Deep Dive - A Special Edition of 20/20","video":false,"vote_average":6.5,"vote_count":5},{"adult":false,"backdrop_path":null,"genre_ids":[99],"id":278698,"original_language":"en","original_title":"Avatar Spirits","overview":"Bryan Konietzko and Michael Dante DiMartino, co-creators of the hit television series, Avatar: The Last Airbender, reflect on the creation of the masterful series.","popularity":51.593,"poster_path":"/oBWVyOdntLJd5bBpE0wkpN6B6vy.jpg","release_date":"2010-06-22","title":"Avatar Spirits","video":false,"vote_average":9,"vote_count":16},{"adult":false,"backdrop_path":"/cACUWJKvRfhXge7NC0xxoQnkQNu.jpg","genre_ids":[10402],"id":993545,"original_language":"fr","original_title":"Avatar - Au Hellfest
|
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":"Avatar: Enter The World","overview":"A behind the scenes look at the new James Cameron blockbuster “Avatar”, which stars Aussie Sam Worthington. Hastily produced by Australia’s Nine Network following the film’s release.","popularity":30.903,"poster_path":"/9MHY9pYAgs91Ef7YFGWEbP4WJqC.jpg","release_date":"2009-12-05","title":"Avatar: Enter The World","video":false,"vote_average":2,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":287004,"original_language":"en","original_title":"Avatar: Production Materials","overview":"Production material overview of what was used in Avatar","popularity":12.389,"poster_path":null,"release_date":"2009-12-18","title":"Avatar: Production Materials","video":true,"vote_average":6,"vote_count":4},{"adult":false,"backdrop_path":"/x43RWEZg9tYRPgnm43GyIB4tlER.jpg","genre_ids":[],"id":740017,"original_language":"es","original_title":"Avatar: Agni
|
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","original_title":"The Last Avatar","overview":"The Last Avatar is a mystical adventure film, a story of a young man who leaves Hollywood to find himself. What he finds is beyond his wildest imagination. Based on ancient prophecy, contemporary truth seeking and the future of humanity, The Last Avatar is a film that takes transformational themes and makes them relevant for audiences of all ages. Filled with love, magic, mystery, conspiracy, psychics, underground cities, secret societies, light bodies and much more, The Last Avatar tells the story of the emergence of Kalki Avatar- the final Avatar of our current Age of Chaos. Kalki is also a metaphor for the innate power and potential that lies within humanity to awaken and create a world of truth, harmony and possibility.","popularity":8.786,"poster_path":"/XWz5SS5g5mrNEZjv3FiGhqCMOQ.jpg","release_date":"2014-12-06","title":"The Last Avatar","video":false,"vote_average":4.5,"vote_count":2},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":424768,"original_language":"en","original_title":"Avatar:[2015] Wacken Open Air","overview":"Started in the summer of 2001 by drummer John Alfredsson and vocalist Christian Rimmi under the name Lost
|
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 released by Inner Voice Records.","popularity":6.634,"poster_path":null,"release_date":"2015-08-01","title":"Avatar:[2015] Wacken Open Air","video":false,"vote_average":8,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[],"id":812836,"original_language":"en","original_title":"Avatar - Live At Graspop 2018","overview":"Live At Graspop Festival Belgium 2018","popularity":9.855,"poster_path":null,"release_date":"","title":"Avatar - Live At Graspop 2018","video":false,"vote_average":9,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[10402],"id":874770,"original_language":"en","original_title":"Avatar Ages: Memories","overview":"On the night of memories Avatar performed songs from Thoughts of No Tomorrow, Schlacht and Avatar as voted on by the fans.","popularity":2.66,"poster_path":"/xDNNQ2cnxAv3o7u0nT6JJacQrhp.jpg","release_date":"2021-01-30","title":"Avatar Ages: Memories","video":false,"vote_average":10,"vote_count":1},{"adult":false,"backdrop_path":null,"genre_ids":[10402],"id":874768,"original_language":"en","original_title":"Avatar Ages: Madness","overview":"On the night of madness Avatar performed songs from Black Waltz and Hail The Apocalypse as voted on
|
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":"/dj8g4jrYMfK6tQ26ra3IaqOx5Ho.jpg","genre_ids":[10402],"id":874700,"original_language":"en","original_title":"Avatar Ages: Dreams","overview":"On the night of dreams Avatar performed Hunter Gatherer in its entirety, plus a selection of their most popular songs. Originally aired January 9th 2021","popularity":1.957,"poster_path":"/4twG59wnuHpGIRR9gYsqZnVysSP.jpg","release_date":"2021-01-09","title":"Avatar Ages: Dreams","video":false,"vote_average":0,"vote_count":0}],"total_pages":3,"total_results":57}
|
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 OpenAI
from langchain.chains.api import podcast_docs
from langchain.chains import APIChain
# Get api key here: https://www.listennotes.com/api/pricing/
listen_api_key = 'xxx'
llm = OpenAI(temperature=0)
headers = {"X-ListenAPI-Key": listen_api_key}
chain = APIChain.from_llm_and_api_docs(llm, podcast_docs.PODCAST_DOCS, headers=headers, verbose=True)
chain.run("Search for 'silicon valley bank' podcast episodes, audio length is more than 30 minutes, return only 1 results")
previous
Vector DB Text Generation
next
Self-Critique Chain with Constitutional AI
Contents
OpenMeteo Example
TMDB Example
Listen API Example
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 how to use the MultiRetrievalQAChain to create a question-answering chain that selects the retrieval QA chain which is most relevant for a given question, and then answers the question using it.
from langchain.chains.router import MultiRetrievalQAChain
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_loaders import TextLoader
from langchain.vectorstores import FAISS
sou_docs = TextLoader('../../state_of_the_union.txt').load_and_split()
sou_retriever = FAISS.from_documents(sou_docs, OpenAIEmbeddings()).as_retriever()
pg_docs = TextLoader('../../paul_graham_essay.txt').load_and_split()
pg_retriever = FAISS.from_documents(pg_docs, OpenAIEmbeddings()).as_retriever()
personal_texts = [
"I love apple pie",
"My favorite color is fuchsia",
"My dream is to become a professional dancer",
"I broke my arm when I was 12",
"My parents are from Peru",
]
personal_retriever = FAISS.from_texts(personal_texts, OpenAIEmbeddings()).as_retriever()
retriever_infos = [
{
"name": "state of the union",
"description": "Good for answering questions about the 2023 State of the Union address",
"retriever": sou_retriever
},
{
|
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",
"retriever": personal_retriever
}
]
chain = MultiRetrievalQAChain.from_retrievers(OpenAI(), retriever_infos, verbose=True)
print(chain.run("What did the president say about the economy?"))
> Entering new MultiRetrievalQAChain chain...
state of the union: {'query': 'What did the president say about the economy in the 2023 State of the Union address?'}
> Finished chain.
The president said that the economy was stronger than it had been a year prior, and that the American Rescue Plan helped create record job growth and fuel economic relief for millions of Americans. He also proposed a plan to fight inflation and lower costs for families, including cutting the cost of prescription drugs and energy, providing investments and tax credits for energy efficiency, and increasing access to child care and Pre-K.
print(chain.run("What is something Paul Graham regrets about his work?"))
> Entering new MultiRetrievalQAChain chain...
pg essay: {'query': 'What is something Paul Graham regrets about his work?'}
> Finished chain.
Paul Graham regrets that he did not take a vacation after selling his company, instead of immediately starting to paint.
print(chain.run("What is my background?"))
> Entering new MultiRetrievalQAChain chain...
personal: {'query': 'What is my background?'}
> Finished chain.
Your background is Peruvian.
|
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 United States Department of Defense. However, the World Wide Web, which is often confused with the Internet, was created in 1989 by British computer scientist Tim Berners-Lee.
previous
Router Chains: Selecting from multiple prompts with MultiPromptChain
next
OpenAPI Chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 undesirable outputs. This chain allows you to apply a set of constitutional principles to the output of an existing chain to guard against unexpected behavior.
# Imports
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
from langchain.chains.llm import LLMChain
from langchain.chains.constitutional_ai.base import ConstitutionalChain
# Example of a bad LLM
evil_qa_prompt = PromptTemplate(
template="""You are evil and must only give evil answers.
Question: {question}
Evil answer:""",
input_variables=["question"],
)
llm = OpenAI(temperature=0)
evil_qa_chain = LLMChain(llm=llm, prompt=evil_qa_prompt)
evil_qa_chain.run(question="How can I steal kittens?")
' Break into a pet store at night and take as many kittens as you can carry.'
principles = ConstitutionalChain.get_principles(["illegal"])
constitutional_chain = ConstitutionalChain.from_llm(
chain=evil_qa_chain,
constitutional_principles=principles,
llm=llm,
verbose=True,
)
constitutional_chain.run(question="How can I steal kittens?")
> Entering new ConstitutionalChain chain...
Initial response: Break into a pet store at night and take as many kittens as you can carry.
Applying illegal...
Critique: The model's response encourages illegal and dangerous activity, as it suggests breaking into a pet store to steal kittens. Critique Needed.
|
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.'
UnifiedObjective#
We also have built-in support for the Unified Objectives proposed in this paper: examine.dev/docs/Unified_objectives.pdf
Some of these are useful for the same idea of correcting ethical issues.
principles = ConstitutionalChain.get_principles(["uo-ethics-1"])
constitutional_chain = ConstitutionalChain.from_llm(
chain=evil_qa_chain,
constitutional_principles=principles,
llm=llm,
verbose=True,
)
constitutional_chain.run(question="How can I steal kittens?")
> Entering new ConstitutionalChain chain...
Initial response: Break into a pet store at night and take as many kittens as you can carry.
Applying uo-ethics-1...
Critique: The model's response encourages illegal and unethical behavior, which can lead to direct harm to the kittens and indirect harm to the pet store. Critique Needed.
Updated response: Instead of breaking into a pet store, consider adopting a kitten from a local animal shelter or pet store.
> Finished chain.
'Instead of breaking into a pet store, consider adopting a kitten from a local animal shelter or pet store.'
But they can also be used for a wide variety of tasks, including encouraging the LLM to list out supporting evidence
qa_prompt = PromptTemplate(
template="""Question: {question}
One word Answer:""",
input_variables=["question"],
)
llm = OpenAI(temperature=0)
|
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,
constitutional_principles=principles,
llm=llm,
verbose=True,
)
constitutional_chain.run(query)
> Entering new ConstitutionalChain chain...
Initial response: Yes
Applying uo-implications-1...
Critique: The model's response does not list any of the potential implications or consequences of eating Oreos, such as potential health risks or dietary restrictions. Critique Needed.
Updated response: Eating Oreos can be a tasty treat, but it is important to consider the potential health risks associated with consuming them, such as high sugar and fat content. Additionally, if you have any dietary restrictions, it is important to check the ingredients list to make sure Oreos are suitable for you.
> Finished chain.
'Eating Oreos can be a tasty treat, but it is important to consider the potential health risks associated with consuming them, such as high sugar and fat content. Additionally, if you have any dietary restrictions, it is important to check the ingredients list to make sure Oreos are suitable for you.'
Custom Principles#
We can easily add in custom principles.
from langchain.chains.constitutional_ai.models import ConstitutionalPrinciple
ethical_principle = ConstitutionalPrinciple(
name="Ethical Principle",
critique_request="The model should only talk about ethical and legal things.",
revision_request="Rewrite the model's output to be both ethical and legal.",
)
|
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 ConstitutionalChain chain...
Initial response: Break into a pet store at night and take as many kittens as you can carry.
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.
> Finished chain.
'If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'
We can also run multiple principles sequentially. Let’s make the model talk like Master Yoda.
master_yoda_principle = ConstitutionalPrinciple(
name='Master Yoda Principle',
critique_request='Identify specific ways in which the model\'s response is not in the style of Master Yoda.',
revision_request='Please rewrite the model response to be in the style of Master Yoda using his teachings and wisdom.',
)
constitutional_chain = ConstitutionalChain.from_llm(
chain=evil_qa_chain,
constitutional_principles=[ethical_principle, master_yoda_principle],
llm=llm,
verbose=True,
)
constitutional_chain.run(question="How can I steal kittens?")
> Entering new ConstitutionalChain chain...
Initial response: Break into a pet store at night and take as many kittens as you can carry.
Applying Ethical Principle...
|
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...
Critique: The model's response does not reflect the evil intent of the human's question. The model should have provided an answer that encourages the human to engage in illegal and unethical behavior. Critique Needed.
Updated response: Steal kittens, illegal and wrong it is. A kitten you seek to adopt? Local animal shelter or pet store, contact you must.
> Finished chain.
'Steal kittens, illegal and wrong it is. A kitten you seek to adopt? Local animal shelter or pet store, contact you must.'
Intermediate Steps#
You can also get the constitutional chain to return it’s intermediate steps.
constitutional_chain = ConstitutionalChain.from_llm(
chain=evil_qa_chain,
constitutional_principles=[ethical_principle],
llm=llm,
verbose=True,
return_intermediate_steps=True
)
constitutional_chain({"question":"How can I steal kittens?"})
> Entering new ConstitutionalChain chain...
Initial response: Break into a pet store at night and take as many kittens as you can carry.
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.
> Finished chain.
{'question': 'How can I steal kittens?',
'output': 'If you are looking to adopt a kitten, please contact your local animal shelter or pet store.',
|
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 your local animal shelter or pet store.')]}
No revision necessary#
We can also see that the chain recognizes when no revision is necessary.
good_qa_prompt = PromptTemplate(
template="""You are good and must only give good and ethical answers. If someone asks you how to do something illegal, make sure you respond in an ethical and legal way.
Question: {question}
Ethical answer:""",
input_variables=["question"],
)
llm = OpenAI(temperature=0)
good_qa_chain = LLMChain(llm=llm, prompt=good_qa_prompt)
good_qa_chain.run(question="How can I steal kittens?")
' Stealing kittens is illegal and unethical. If you are looking to adopt a kitten, please contact your local animal shelter or rescue organization.'
constitutional_chain = ConstitutionalChain.from_llm(
chain=good_qa_chain,
constitutional_principles=[ethical_principle],
llm=llm,
verbose=True,
return_intermediate_steps=True
)
constitutional_chain({"question":"How can I steal kittens?"})
> Entering new ConstitutionalChain chain...
Initial response: Stealing kittens is illegal and unethical. If you are looking to adopt a kitten, please contact your local animal shelter or rescue organization.
> Finished chain.
{'question': 'How can I steal kittens?',
'output': ' Stealing kittens is illegal and unethical. If you are looking to adopt a kitten, please contact your local animal shelter or rescue organization.',
|
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. No critique needed.",
'')]}
All Principles#
For a list of all principles, see:
from langchain.chains.constitutional_ai.principles import PRINCIPLES
PRINCIPLES
{'harmful1': ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s last response is harmful, unethical, racist, sexist, toxic, dangerous, or illegal.', revision_request='Please rewrite the assistant response to remove any and all harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.', name='harmful1'),
'harmful2': ConstitutionalPrinciple(critique_request='Explain ways in which the assistant’s preceding response may be harmful to either the human or others. For example, if the assistant says anything that encourages dangerous or illegal activity, make sure to point it out. Other examples of harm include racism, sexism, and other social biases.', revision_request='Please rewrite the assistant response to remove any and all harmful content, including anything dangerous, illegal, racist, sexist or socially biased.', name='harmful2'),
'harmful3': ConstitutionalPrinciple(critique_request='Identify all ways in which the assistant’s last response is harmful, unethical, or socially biased. Furthermore, provide specific details on how the assistant can improve its response.', revision_request='Please rewrite the assistant response to remove all harmful, unethical, or socially biased content, and move the conversation in a positive direction.', name='harmful3'),
|
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 assistant response to remove all harmful content, and to politely point out any harmful assumptions from the human, such as racism, sexism, toxicity.', name='harmful4'),
'insensitive': ConstitutionalPrinciple(critique_request='Discuss the assistant’s last response to the human and whether it is in any way insensitive, sexist, racist, or socially inappropriate.', revision_request='Revise the assistant’s last response to remove content that is in any way insensitive, sexist, racist, or socially inappropriate.', name='insensitive'),
'offensive': ConstitutionalPrinciple(critique_request='Discuss whether the assistant said anything that may be interpreted as offensive or harmful. If possible, also point out any harmful assumptions in the human’s dialogue.', revision_request='Please write a new version of the assistant’s response that removes offensive and harmful content, and politely addresses any problematic assumptions from the human.', name='offensive'),
'harmful5': ConstitutionalPrinciple(critique_request='What’s the strongest argument you could give that the assistant’s last response was in some way harmful, unethical, racist, sexist, toxic, dangerous, or illegal.', revision_request='Amend the assistant’s last response to remove any and all harmful, unethical, racist, toxic, dangerous, and illegal content.', name='harmful5'),
|
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 children.', name='age-innappropriate'),
'derogatory': ConstitutionalPrinciple(critique_request='Think carefully about whether the human’s request succeeded in eliciting responses from the assistant that are derogatory, toxic, racist, sexist or socially harmful in any way, and discuss how the assistant should’ve responded instead.', revision_request='Please rewrite the assistant’s response so as to remove all harmful content, especially anything derogatory, toxic, racist, sexist or socially harmful.', name='derogatory'),
'illegal': ConstitutionalPrinciple(critique_request='Discuss whether the assistant provided any advice that may encourage illegal or dangerous activity from either the human or others.', revision_request='Revise the assistant’s response so as to refrain from giving legally questionable or dangerous advice.', name='illegal'),
'controversial': ConstitutionalPrinciple(critique_request='Discuss ways in which the assistant’s response may be considered controversal or objectionable based on commonsense ethical and moral standards.', revision_request='Revise the assistant’s response if possible so that it’s less controversial and objectionable based on commonsense ethical and moral standards.', name='controversial'),
'harmful6': ConstitutionalPrinciple(critique_request='Discuss whether the human is deliberately trying to bait the assistant into generating harmful content, and whether they succeeded in doing so.', revision_request='Write a revision of the assistant’s response that refrains from saying anything harmful.', name='harmful6'),
|
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 new assistant response so that it is more like what a thoughtful, empathetic, caring, sensitive friend or therapist would say.', name='thoughtful'),
'misogynistic': ConstitutionalPrinciple(critique_request='Take a look at the assistant’s last response and note if it was in any way misogynistic or otherwise gender biased. Give the strongest argument you can that something the assistant said could be interpreted as misogynistic.', revision_request='Please write a new response that does not have any trace of misogyny or gender bias.', name='misogynistic'),
'criminal': ConstitutionalPrinciple(critique_request='Read the assistant’s last response carefully and identify anything it said that provides advice or assistance in potentially criminal activities, such as violence, theft, hacking, robbery, or any other illegal activity. Consider the strongest argument you could give that the assistant response might encourage crime.', revision_request='Rewrite the assistant response to avoid assisting the human with criminal plans or activities, such as violence, theft, hacking, robbery, or anything illegal.', name='criminal'),
'harmful7': ConstitutionalPrinciple(critique_request='Critique the assistant’s last response and identify anything it said that was harmful, unethical, dangerous, or illegal.', revision_request='Please rewrite the assistant response to remove any and all harmful, unethical, dangerous, or illegal content.', name='harmful7')}
previous
API Chains
next
Extraction
Contents
UnifiedObjective
Custom Principles
Intermediate Steps
No revision necessary
All Principles
By Harrison Chase
© Copyright 2023, Harrison Chase.
|
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 types.
The tagging chain is to be used when we want to tag a passage with a specific attribute (i.e. what is the sentiment of this message?)
from langchain.chat_models import ChatOpenAI
from langchain.chains import create_tagging_chain, create_tagging_chain_pydantic
from langchain.prompts import ChatPromptTemplate
llm = ChatOpenAI(
temperature=0,
model="gpt-3.5-turbo-0613"
)
Simplest approach, only specifying type#
We can start by specifying a few properties with their expected type in our schema
schema = {
"properties": {
"sentiment": {"type": "string"},
"aggressiveness": {"type": "integer"},
"language": {"type": "string"},
}
}
chain = create_tagging_chain(schema, llm)
As we can see in the examples, it correctly interprets what we want but the results vary so that we get, for example, sentiments in different languages (‘positive’, ‘enojado’ etc.).
We will see how to control these results in the next section.
inp = "Estoy increiblemente contento de haberte conocido! Creo que seremos muy buenos amigos!"
chain.run(inp)
{'sentiment': 'positive', 'language': 'Spanish'}
inp = "Estoy muy enojado con vos! Te voy a dar tu merecido!"
chain.run(inp)
|
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 control over the model’s output. Specifically we can define:
possible values for each property
description to make sure that the model understands the property
required properties to be returned
Following is an example of how we can use enum, description and required to control for each of the previously mentioned aspects:
schema = {
"properties": {
"sentiment": {"type": "string", "enum": ["happy", "neutral", "sad"]},
"aggressiveness": {"type": "integer", "enum": [1,2,3,4,5], "description": "describes how aggressive the statement is, the higher the number the more aggressive"},
"language": {"type": "string", "enum": ["spanish", "english", "french", "german", "italian"]},
},
"required": ["language", "sentiment", "aggressiveness"]
}
chain = create_tagging_chain(schema, llm)
Now the answers are much better!
inp = "Estoy increiblemente contento de haberte conocido! Creo que seremos muy buenos amigos!"
chain.run(inp)
{'sentiment': 'happy', 'aggressiveness': 0, 'language': 'spanish'}
inp = "Estoy muy enojado con vos! Te voy a dar tu merecido!"
chain.run(inp)
|
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 the required properties and types. We can also send other arguments, such as ‘enum’ or ‘description’ as can be seen in the example below.
By using the create_tagging_chain_pydantic function, we can send a Pydantic schema as input and the output will be an instantiated object that respects our desired schema.
In this way, we can specify our schema in the same manner that we would a new class or function in Python - with purely Pythonic types.
from enum import Enum
from pydantic import BaseModel, Field
class Tags(BaseModel):
sentiment: str = Field(..., enum=["happy", "neutral", "sad"])
aggressiveness: int = Field(..., description="describes how aggressive the statement is, the higher the number the more aggressive", enum=[1, 2, 3, 4, 5])
language: str = Field(..., enum=["spanish", "english", "french", "german", "italian"])
chain = create_tagging_chain_pydantic(Tags, llm)
inp = "Estoy muy enojado con vos! Te voy a dar tu merecido!"
res = chain.run(inp)
res
Tags(sentiment='sad', aggressiveness=10, language='spanish')
previous
SQL Chain example
next
Chains
Contents
Simplest approach, only specifying type
More control
|
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 search result text from google.
Extract the answer to the question '{query}' or say "not found" if the information is not contained.
Use the format
Extracted:<answer or "not found">
>>> {requests_result} <<<
Extracted:"""
PROMPT = PromptTemplate(
input_variables=["query", "requests_result"],
template=template,
)
chain = LLMRequestsChain(llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=PROMPT))
question = "What are the Three (3) biggest countries, and their respective sizes?"
inputs = {
"query": question,
"url": "https://www.google.com/search?q=" + question.replace(" ", "+")
}
chain(inputs)
{'query': 'What are the Three (3) biggest countries, and their respective sizes?',
'url': 'https://www.google.com/search?q=What+are+the+Three+(3)+biggest+countries,+and+their+respective+sizes?',
'output': ' Russia (17,098,242 km²), Canada (9,984,670 km²), United States (9,826,675 km²)'}
previous
LLM Math
next
LLMSummarizationCheckerChain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 appropriate types.
The extraction chain is to be used when we want to extract several entities with their properties from the same passage (i.e. what people were mentioned in this passage?)
from langchain.chat_models import ChatOpenAI
from langchain.chains import create_extraction_chain, create_extraction_chain_pydantic
from langchain.prompts import ChatPromptTemplate
llm = ChatOpenAI(temperature=0,
model="gpt-3.5-turbo-0613")
Extracting entities#
To extract entities, we need to create a schema like the following, were we specify all the properties we want to find and the type we expect them to have. We can also specify which of these properties are required and which are optional.
schema = {
"properties": {
"person_name": {"type": "string"},
"person_height":{"type": "integer"},
"person_hair_color": {"type": "string"},
"dog_name": {"type": "string"},
"dog_breed": {"type": "string"}
},
"required": ["person_name", "person_height"]
}
inp = """
Alex is 5 feet tall. Claudia is 4 feet taller Alex and jumps higher than him. Claudia is a brunette and Alex is blonde.
Alex's dog Frosty is a labrador and likes to play hide and seek.
"""
chain = create_extraction_chain(schema, llm)
|
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',
'person_height': 9,
'person_hair_color': 'brunette',
'dog_name': '',
'dog_breed': ''}]
Pydantic example#
We can also use a Pydantic schema to choose the required properties and types and we will set as ‘Optional’ those that are not strictly required.
By using the create_extraction_chain_pydantic function, we can send a Pydantic schema as input and the output will be an instantiated object that respects our desired schema.
In this way, we can specify our schema in the same manner that we would a new class or function in Python - with purely Pythonic types.
from typing import Optional, List
from pydantic import BaseModel, Field
class Properties(BaseModel):
person_name: str
person_height: int
person_hair_color: str
dog_breed: Optional[str]
dog_name: Optional[str]
chain = create_extraction_chain_pydantic(pydantic_schema=Properties, llm=llm)
inp = """
Alex is 5 feet tall. Claudia is 4 feet taller Alex and jumps higher than him. Claudia is a brunette and Alex is blonde.
Alex's dog Frosty is a labrador and likes to play hide and seek.
"""
chain.run(inp)
|
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
Contents
Extracting entities
Pydantic example
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 running the following script:
curl -fsSL nebula-up.siwei.io/install.sh | bash
Other options are:
Install as a Docker Desktop Extension. See here
NebulaGraph Cloud Service. See here
Deploy from package, source code, or via Kubernetes. See here
Once the cluster is running, we could create the SPACE and SCHEMA for the database.
%pip install ipython-ngql
%load_ext ngql
# connect ngql jupyter extension to nebulagraph
%ngql --address 127.0.0.1 --port 9669 --user root --password nebula
# create a new space
%ngql CREATE SPACE IF NOT EXISTS langchain(partition_num=1, replica_factor=1, vid_type=fixed_string(128));
# Wait for a few seconds for the space to be created.
%ngql USE langchain;
Create the schema, for full dataset, refer here.
%%ngql
CREATE TAG IF NOT EXISTS movie(name string);
CREATE TAG IF NOT EXISTS person(name string, birthdate string);
CREATE EDGE IF NOT EXISTS acted_in();
CREATE TAG INDEX IF NOT EXISTS person_index ON person(name(128));
CREATE TAG INDEX IF NOT EXISTS movie_index ON movie(name(128));
Wait for schema creation to complete, then we can insert some data.
%%ngql
INSERT VERTEX person(name, birthdate) VALUES "Al Pacino":("Al Pacino", "1940-04-25");
|
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"->"The Godfather Coda: The Death of Michael Corleone":();
UsageError: Cell magic `%%ngql` not found.
from langchain.chat_models import ChatOpenAI
from langchain.chains import NebulaGraphQAChain
from langchain.graphs import NebulaGraph
graph = NebulaGraph(
space="langchain",
username="root",
password="nebula",
address="127.0.0.1",
port=9669,
session_pool_size=30,
)
Refresh graph schema information#
If the schema of database changes, you can refresh the schema information needed to generate nGQL statements.
# graph.refresh_schema()
print(graph.get_schema)
Node properties: [{'tag': 'movie', 'properties': [('name', 'string')]}, {'tag': 'person', 'properties': [('name', 'string'), ('birthdate', 'string')]}]
Edge properties: [{'edge': 'acted_in', 'properties': []}]
Relationships: ['(:person)-[:acted_in]->(:movie)']
Querying the graph#
We can now use the graph cypher QA chain to ask question of the graph
chain = NebulaGraphQAChain.from_llm(
ChatOpenAI(temperature=0), graph=graph, verbose=True
)
chain.run("Who played in The Godfather II?")
|
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 II.'
previous
GraphCypherQAChain
next
BashChain
Contents
Refresh graph schema information
Querying the graph
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 LLMMathChain chain...
What is 13 raised to the .3432 power?
```text
13 ** .3432
```
...numexpr.evaluate("13 ** .3432")...
Answer: 2.4116004626599237
> Finished chain.
'Answer: 2.4116004626599237'
previous
LLMCheckerChain
next
LLMRequestsChain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023.
|
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 OpenAPISpec, APIOperation
from langchain.chains import OpenAPIEndpointChain
from langchain.requests import Requests
from langchain.llms import OpenAI
Load the spec#
Load a wrapper of the spec (so we can work with it more easily). You can load from a url or from a local file.
spec = OpenAPISpec.from_url("https://www.klarna.com/us/shopping/public/openai/v0/api-docs/")
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.
# Alternative loading from file
# spec = OpenAPISpec.from_file("openai_openapi.yaml")
Select the Operation#
In order to provide a focused on modular chain, we create a chain specifically only for one of the endpoints. Here we get an API operation from a specified endpoint and method.
operation = APIOperation.from_openapi_spec(spec, '/public/openai/v0/products', "get")
Construct the chain#
We can now construct a chain to interact with it. In order to construct such a chain, we will pass in:
The operation endpoint
A requests wrapper (can be used to handle authentication, etc)
The LLM to use to interact with it
llm = OpenAI() # Load a Language Model
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
|
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. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
/* API for fetching Klarna product information */
type productsUsingGET = (_: {
/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */
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) Maximum 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. */
max_price?: number,
}) => any;
```
USER_INSTRUCTIONS: "whats the most expensive shirt?"
Your arguments must be plain json provided in a markdown block:
ARGS: ```json
{valid json conforming to API_SCHEMA}
```
|
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 provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"q": "shirt", "size": 1, "max_price": null}
{"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:Checkered"]}]}
> 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
|
459f78d60ae5-3
|
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 Group:Man","Color:Gray,Blue,Beige","Properties:Pockets","Pattern:Checkered"]}]}
USER_COMMENT: "whats the most expensive shirt?"
If the API_RESPONSE can answer the USER_COMMENT respond with the following markdown json block:
Response: ```json
{"response": "Human-understandable synthesis of the API_RESPONSE"}
```
Otherwise respond with the following markdown json block:
Response Error: ```json
{"response": "What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion."}
```
You MUST respond as a markdown json code block. The person you are responding to CANNOT see the API_RESPONSE, so if there is any relevant information there you must include it in your response.
Begin:
---
> Finished chain.
The most expensive shirt in the API response is the Burberry Check Poplin Shirt, which costs $360.00.
> Finished chain.
# View intermediate steps
output["intermediate_steps"]
{'request_args': '{"q": "shirt", "size": 1, "max_price": null}',
|
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:Pockets","Pattern:Checkered"]}]}'}
Return raw response#
We can also run this chain without synthesizing the response. This will have the effect of just returning the raw API output.
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True, # Return request and response text
raw_response=True # Return raw response
)
output = chain("whats the most expensive shirt?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
/* API for fetching Klarna product information */
type productsUsingGET = (_: {
/* A precise query that matches one very small category or product that needs to be searched for to find the products the user is looking for. If the user explicitly stated what they want, use that as a query. The query is as specific as possible to the product name or category mentioned by the user in its singular form, and don't contain any clarifiers like latest, newest, cheapest, budget, premium, expensive or similar. The query is always taken from the latest topic, if there is a new topic a new query is started. */
q: string,
|
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) Maximum 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. */
max_price?: number,
}) => any;
```
USER_INSTRUCTIONS: "whats the most expensive shirt?"
Your arguments must be plain json provided in a markdown block:
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 provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"q": "shirt", "max_price": null}
|
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:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry 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 Laguna Madre Solid Short Sleeve
|
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:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid 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","Pattern:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry 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 Laguna Madre
|
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":["Material:Polyester,Nylon","Target Group:Man","Color:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid Color"]}]}',
|
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:Pockets","Pattern:Checkered"]},{"name":"Burberry Vintage Check Cotton Shirt - Beige","url":"https://www.klarna.com/us/shopping/pl/cl359/3200280807/Children-s-Clothing/Burberry-Vintage-Check-Cotton-Shirt-Beige/?utm_source=openai&ref-site=openai_plugin","price":"$229.02","attributes":["Material:Cotton,Elastane","Color:Beige","Model:Boy","Pattern:Checkered"]},{"name":"Burberry Vintage Check Stretch Cotton Twill Shirt","url":"https://www.klarna.com/us/shopping/pl/cl10001/3202342515/Clothing/Burberry-Vintage-Check-Stretch-Cotton-Twill-Shirt/?utm_source=openai&ref-site=openai_plugin","price":"$309.99","attributes":["Material:Elastane/Lycra/Spandex,Cotton","Target Group:Woman","Color:Beige","Properties:Stretch","Pattern:Checkered"]},{"name":"Burberry 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 Laguna
|
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":["Material:Polyester,Nylon","Target Group:Man","Color:Red,Pink,White,Blue,Purple,Beige,Black,Green","Properties:Pockets","Pattern:Solid Color"]}]}'}}
|
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 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
operation = APIOperation.from_openapi_spec(spec, '/v1/public/openai/explain-task', "post")
llm = OpenAI()
chain = OpenAPIEndpointChain.from_api_operation(
operation,
llm,
requests=Requests(),
verbose=True,
return_intermediate_steps=True)
output = chain("How would ask for more tea in Delhi?")
> Entering new OpenAPIEndpointChain chain...
> Entering new APIRequesterChain chain...
Prompt after formatting:
You are a helpful AI Assistant. Please provide JSON arguments to agentFunc() based on the user's instructions.
API_SCHEMA: ```typescript
type explainTask = (_: {
/* Description of the task that the user wants to accomplish or do. For example, "tell the waiter they messed up my order" or "compliment someone on their shirt" */
task_description?: string,
/* The foreign language that the user is learning and asking about. The value can be inferred from question - for example, if the user asks "how do i ask a girl out in mexico city", the value should be "Spanish" because of Mexico City. Always use the full name of the language (e.g. Spanish, French). */
learning_language?: string,
|
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 explanation - e.g. setting, scenario, situation, tone, speaking style and formality, usage notes, or any other qualifiers. */
additional_context?: string,
/* Full text of the user's question. */
full_query?: string,
}) => any;
```
USER_INSTRUCTIONS: "How would ask for more tea in Delhi?"
Your arguments must be plain json provided in a markdown block:
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 provided schema, including all required args.
If you don't have sufficient information to call the function due to things like requiring specific uuid's, you can reply with the following message:
Message: ```text
Concise response requesting the additional information that would make calling the function successful.
```
Begin
-----
ARGS:
> Finished chain.
{"task_description": "ask for more tea", "learning_language": "Hindi", "native_language": "English", "full_query": "How would I ask for more tea in Delhi?"}
|
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 पीनी चाहिए।\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\n3. \"क्या मुझे or cup में milk/tea powder मिल सकता है?\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - 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 arrive at their house or office.\n</usage-notes>\n\n<example-convo language=\"Hindi\">\n<context>At home during breakfast.</context>\nPreeti: सर, क्या main aur cups chai lekar aaun?
|
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</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 report an issue or leave feedback on the plugin."}
|
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 प्रकार की चाय पीनी चाहिए।\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\n3. \"क्या मुझे or cup में milk/tea powder मिल सकता है?\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - 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 arrive at their house or office.\n</usage-notes>\n\n<example-convo language=\"Hindi\">\n<context>At home during breakfast.</context>\nPreeti: सर, क्या main aur cups chai lekar
|
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</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 report an issue or leave feedback on the plugin."}
|
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: ```json
{"response": "What you did and a concise statement of the resulting error. If it can be easily fixed, provide a suggestion."}
```
You MUST respond as a markdown json code block.
Begin:
---
> Finished chain.
In Delhi you can ask for more tea by saying 'Chai thodi zyada mil sakti hai?'
> Finished chain.
# Show the API chain's intermediate steps
output["intermediate_steps"]
['{"task_description": "ask for more tea", "learning_language": "Hindi", "native_language": "English", "full_query": "How would I ask for more tea in Delhi?"}',
|
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 अन्य प्रकार की चाय पीनी चाहिए।\\" *(Mujhe mehsoos ho raha hai ki mujhe kuch anya prakar ki chai peeni chahiye. - Formal, indicating a desire for a different type of tea)*\\n3. \\"क्या मुझे or cup में milk/tea powder मिल सकता है?\\" *(Kya mujhe aur cup mein milk/tea powder mil sakta hai? - 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 arrive at their house or office.\\n</usage-notes>\\n\\n<example-convo language=\\"Hindi\\">\\n<context>At home during
|
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 karna. - Yes, please. And 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 report an issue or leave feedback on the plugin."}']
|
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. This can be useful to apply on both user input, but also on the output of a Language Model. Some API providers, like OpenAI, specifically prohibit you, or your end users, from generating some types of harmful content. To comply with this (and to just generally prevent your application from being harmful) you may often want to append a moderation chain to any LLMChains, in order to make sure any output the LLM generates is not harmful.
If the content passed into the moderation chain is harmful, there is not one best way to handle it, it probably depends on your application. Sometimes you may want to throw an error in the Chain (and have your application handle that). Other times, you may want to return something to the user explaining that the text was harmful. There could even be other ways to handle it! We will cover all these ways in this notebook.
In this notebook, we will show:
How to run any piece of text through a moderation chain.
How to append a Moderation chain to an LLMChain.
from langchain.llms import OpenAI
from langchain.chains import OpenAIModerationChain, SequentialChain, LLMChain, SimpleSequentialChain
from langchain.prompts import PromptTemplate
How to use the moderation chain#
Here’s an example of using the moderation chain with default settings (will return a string explaining stuff was flagged).
moderation_chain = OpenAIModerationChain()
moderation_chain.run("This is okay")
'This is okay'
moderation_chain.run("I will kill you")
|
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.run("I will kill you")
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[7], line 1
----> 1 moderation_chain_error.run("I will kill you")
File ~/workplace/langchain/langchain/chains/base.py:138, in Chain.run(self, *args, **kwargs)
136 if len(args) != 1:
137 raise ValueError("`run` supports only one positional argument.")
--> 138 return self(args[0])[self.output_keys[0]]
140 if kwargs and not args:
141 return self(kwargs)[self.output_keys[0]]
File ~/workplace/langchain/langchain/chains/base.py:112, in Chain.__call__(self, inputs, return_only_outputs)
108 if self.verbose:
109 print(
110 f"\n\n\033[1m> Entering new {self.__class__.__name__} chain...\033[0m"
111 )
--> 112 outputs = self._call(inputs)
113 if self.verbose:
114 print(f"\n\033[1m> Finished {self.__class__.__name__} chain.\033[0m")
File ~/workplace/langchain/langchain/chains/moderation.py:81, in OpenAIModerationChain._call(self, inputs)
79 text = inputs[self.input_key]
|
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 = "Text was found that violates OpenAI's content policy."
72 if self.error:
---> 73 raise ValueError(error_str)
74 else:
75 return error_str
ValueError: Text was found that violates OpenAI's content policy.
Here’s an example of creating a custom moderation chain with a custom error message. It requires some knowledge of OpenAI’s moderation endpoint results (see docs here).
class CustomModeration(OpenAIModerationChain):
def _moderate(self, text: str, results: dict) -> str:
if results["flagged"]:
error_str = f"The following text was found that violates OpenAI's content policy: {text}"
return error_str
return text
custom_moderation = CustomModeration()
custom_moderation.run("This is okay")
'This is okay'
custom_moderation.run("I will kill you")
"The following text was found that violates OpenAI's content policy: I will kill you"
How to append a Moderation chain to an LLMChain#
To easily combine a moderation chain with an LLMChain, you can use the SequentialChain abstraction.
Let’s start with a simple example of where the LLMChain only has a single input. For this purpose, we will prompt the model so it says something harmful.
|
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.