id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
601bc4e15d6c-23 | > Finished chain.
> Entering new LLMChain chain...
Prompt after formatting:
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
- Birds and mammals are both capable of laying eggs.
- Birds are not mammals.
- Bir... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
601bc4e15d6c-24 | Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
... | https://python.langchain.com/en/latest/modules/chains/examples/llm_summarization_checker.html |
bffaa8d0af8e-0 | .ipynb
.pdf
Moderation
Contents
How to use the moderation chain
How to append a Moderation chain to an LLMChain
Moderation#
This notebook walks through examples of how to use a moderation chain, and several common ways for doing so. Moderation chains are useful for detecting text that could be hateful, violent, etc. ... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
bffaa8d0af8e-1 | 'This is okay'
moderation_chain.run("I will kill you")
"Text was found that violates OpenAI's content policy."
Here’s an example of using the moderation chain to throw an error.
moderation_chain_error = OpenAIModerationChain(error=True)
moderation_chain_error.run("This is okay")
'This is okay'
moderation_chain_error.ru... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
bffaa8d0af8e-2 | 79 text = inputs[self.input_key]
80 results = self.client.create(text)
---> 81 output = self._moderate(text, results["results"][0])
82 return {self.output_key: output}
File ~/workplace/langchain/langchain/chains/moderation.py:73, in OpenAIModerationChain._moderate(self, text, results)
71 error_str = "Tex... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
bffaa8d0af8e-3 | prompt = PromptTemplate(template="{text}", input_variables=["text"])
llm_chain = LLMChain(llm=OpenAI(temperature=0, model_name="text-davinci-002"), prompt=prompt)
text = """We are playing a game of repeat after me.
Person 1: Hi
Person 2: Hi
Person 1: How's your day
Person 2: How's your day
Person 1: I will kill you
Per... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
bffaa8d0af8e-4 | chain(inputs, return_only_outputs=True)
{'sanitized_text': "Text was found that violates OpenAI's content policy."}
previous
LLMSummarizationCheckerChain
next
Router Chains: Selecting from multiple prompts with MultiPromptChain
Contents
How to use the moderation chain
How to append a Moderation chain to an LLMChain... | https://python.langchain.com/en/latest/modules/chains/examples/moderation.html |
c02d4cb81424-0 | .ipynb
.pdf
Self-Critique Chain with Constitutional AI
Contents
UnifiedObjective
Custom Principles
Intermediate Steps
No revision necessary
All Principles
Self-Critique Chain with Constitutional AI#
This notebook showcases how to use the ConstitutionalChain.
Sometimes LLMs can produce harmful, toxic, or otherwise und... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-1 | Updated response: It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.
> Finished chain.
'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'
Unif... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-2 | 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,
verb... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-3 | )
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... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-4 | Applying Ethical Principle...
Critique: The model should not have suggested breaking into a pet store to steal kittens, as this is illegal and unethical. Critique Needed.
Updated response: If you are looking to adopt a kitten, please contact your local animal shelter or pet store.
Applying Master Yoda Principle...
Crit... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-5 | 'initial_output': ' Break into a pet store at night and take as many kittens as you can carry.',
'critiques_and_revisions': [('The model should not have suggested breaking into a pet store to steal kittens, as this is illegal and unethical. Critique Needed.',
'If you are looking to adopt a kitten, please contact yo... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-6 | '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.... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-7 | 'harmful4': ConstitutionalPrinciple(critique_request='Identify specific ways in which the assistant’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', revision_request='Rewrite the ass... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-8 | '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... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-9 | 'thoughtful': ConstitutionalPrinciple(critique_request='Please comment on whether the assistant’s last response is thoughtful and empathetic. Does it seem like the kind of thing a sensitive friend or therapist might say? Give the strongest argument you can for how it could improve.', revision_request='Please write a ne... | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
c02d4cb81424-10 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/constitutional_chain.html |
e5ddc38b0d06-0 | .ipynb
.pdf
SQL Chain example
Contents
Use Query Checker
Customize Prompt
Return Intermediate Steps
Choosing how to limit the number of rows returned
Adding example rows from each table
Custom Table Info
SQLDatabaseSequentialChain
Using Local Language Models
SQL Chain example#
This example demonstrates the use of the... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-1 | db_chain.run("How many employees are there?")
> Entering new SQLDatabaseChain chain...
How many employees are there?
SQLQuery:
/workspace/langchain/langchain/sql_database.py:191: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding er... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-2 | Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
Only use the following tables:
{table_info}
If someone asks for the table foobar, they really mean the employee table.
Question: {input}"""
PROMPT = PromptTemplate(
input_... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-3 | Answer:There are 8 employees in the foobar table.
> Finished chain.
[{'input': 'How many employees are there in the foobar table?\nSQLQuery:SELECT COUNT(*) FROM Employee;\nSQLResult: [(8,)]\nAnswer:',
'top_k': '5',
'dialect': 'sqlite', | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-4 | 'table_info': '\nCREATE TABLE "Artist" (\n\t"ArtistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("ArtistId")\n)\n\n/*\n3 rows from Artist table:\nArtistId\tName\n1\tAC/DC\n2\tAccept\n3\tAerosmith\n*/\n\n\nCREATE TABLE "Employee" (\n\t"EmployeeId" INTEGER NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-5 | Manager\tNone\t1962-02-18 00:00:00\t2002-08-14 00:00:00\t11120 Jasper Ave NW\tEdmonton\tAB\tCanada\tT5K 2N1\t+1 (780) 428-9482\t+1 (780) 428-3457\tandrew@chinookcorp.com\n2\tEdwards\tNancy\tSales Manager\t1\t1958-12-08 00:00:00\t2002-05-01 00:00:00\t825 8 Ave SW\tCalgary\tAB\tCanada\tT2P 2T3\t+1 (403) 262-3443\t+1 (403... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-6 | TABLE "MediaType" (\n\t"MediaTypeId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("MediaTypeId")\n)\n\n/*\n3 rows from MediaType table:\nMediaTypeId\tName\n1\tMPEG audio file\n2\tProtected AAC audio file\n3\tProtected MPEG-4 video file\n*/\n\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL,... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-7 | NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), \n\t"Phone" NVARCHAR(24), \n\t"Fax" NVARCHAR(24), \n\t"Email" NVARCHAR(60) NOT NULL, \n\t"Sup... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-8 | 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n*/\n\n\nCREATE TABLE "Invoice" (\n\t"InvoiceId" INTEGER NOT NULL, \n\t"CustomerId" INTEGER NOT NULL, \n\t... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-9 | 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n3\t8\t2009-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n*/\n\n\nCREATE TABLE "Track" (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL, \n\t"AlbumId" INTEGER, \n\t"MediaTypeId" INTEGER NOT NULL, \n\t"GenreId" INTEGER, ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-10 | to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\n*/\n\n\nCREATE TABLE "InvoiceLine" (\n\t"InvoiceLineId" INTEGER NOT NULL, \n\t"InvoiceId" INTEGER NOT NULL, \n\t"TrackId" INTEGER NOT NULL, \n\t"UnitPrice" NUMERIC(... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-11 | \n\tFOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")\n)\n\n/*\n3 rows from PlaylistTrack table:\nPlaylistId\tTrackId\n1\t3402\n1\t3389\n1\t3390\n*/', | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-12 | 'stop': ['\nSQLResult:']},
'SELECT COUNT(*) FROM Employee;',
{'query': 'SELECT COUNT(*) FROM Employee;', 'dialect': 'sqlite'},
'SELECT COUNT(*) FROM Employee;',
'[(8,)]']
Choosing how to limit the number of rows returned#
If you are querying for several rows of a table you can select the maximum number of results y... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-13 | > Finished chain.
'Examples of tracks by Johann Sebastian Bach are Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace, Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria, and Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude.'
Adding example rows from each table#
Sometimes, the format of the d... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-14 | FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
/*
2 rows from Track table:
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 111... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-15 | Answer:Tracks by Bach include 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.
> Finished chain.
'Tracks by... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-16 | "Track": """CREATE TABLE Track (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"Composer" NVARCHAR(220),
PRIMARY KEY ("TrackId")
)
/*
3 rows from Track table:
TrackId Name Composer
1 For Those About To Rock (We Salute You) Angus Young, Malcolm Young, Brian Johnson
2 Balls to the Wall None
3 My favorit... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-17 | db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
db_chain.run("What are some example tracks by Bach?")
> Entering new SQLDatabaseChain chain...
What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Vio... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-18 | Answer:text='You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.\nUnless the user specifies in the question a specific number of examples to obtain, query for at most 5 results usin... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-19 | use the following tables:\n\nCREATE TABLE "Playlist" (\n\t"PlaylistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("PlaylistId")\n)\n\n/*\n2 rows from Playlist table:\nPlaylistId\tName\n1\tMusic\n2\tMovies\n*/\n\nCREATE TABLE Track (\n\t"TrackId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(200) NOT NULL,\n\t... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-20 | (\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\',), (\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\',)]\nAnswer:' | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-21 | You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT cl... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-22 | */
Question: What are some example tracks by Bach?
SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-23 | Answer:
{'input': 'What are some example tracks by Bach?\nSQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE \'%Bach%\' LIMIT 5;\nSQLResult: [(\'American Woman\',), (\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\',), (\'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\',), (\'Suite for Sol... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-24 | Examples of tracks by Bach include "American Woman", "Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace", "Aria Mit 30 Veränderungen, BWV 988 'Goldberg Variations': Aria", "Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude", and "Toccata and Fugue in D Minor, BWV 565: I. Toccata".
> Finished chain.
'Exam... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-25 | > Entering new SQLDatabaseChain chain...
How many employees are also customers?
SQLQuery:SELECT COUNT(*) FROM Employee e INNER JOIN Customer c ON e.EmployeeId = c.SupportRepId;
SQLResult: [(59,)]
Answer:59 employees are also customers.
> Finished chain.
> Finished chain.
'59 employees are also customers.'
Using Local L... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-26 | local_llm = HuggingFacePipeline(pipeline=pipe)
/workspace/langchain/.venv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
from .autonotebook import tqdm as notebook_tqdm
Loading check... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-27 | SELECT count(*) FROM Customer
SQLResult: [(59,)]
Answer:
/workspace/langchain/.venv/lib/python3.9/site-packages/transformers/pipelines/base.py:1070: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
[59]
> Finished chain.
{'query':... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-28 | 'table_info': '\nCREATE TABLE "Customer" (\n\t"CustomerId" INTEGER NOT NULL, \n\t"FirstName" NVARCHAR(40) NOT NULL, \n\t"LastName" NVARCHAR(20) NOT NULL, \n\t"Company" NVARCHAR(80), \n\t"Address" NVARCHAR(70), \n\t"City" NVARCHAR(40), \n\t"State" NVARCHAR(40), \n\t"Country" NVARCHAR(40), \n\t"PostalCode" NVARCHAR(10), ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-29 | (12) 3923-5555\t+55 (12) 3923-5566\tluisg@embraer.com.br\t3\n2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-30 | 'stop': ['\nSQLResult:']},
'SELECT count(*) FROM Customer',
{'query': 'SELECT count(*) FROM Customer', 'dialect': 'sqlite'},
'SELECT count(*) FROM Customer',
'[(59,)]']}
Even this relatively large model will most likely fail to generate more complicated SQL by itself. However, you can log its inputs and outputs... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-31 | Requirement already satisfied: pydantic>=1.9 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (1.10.7)
Requirement already satisfied: hnswlib>=0.7 in /workspace/langchain/.venv/lib/python3.9/site-packages (from chromadb) (0.7.0)
Requirement already satisfied: clickhouse-connect>=0.5.7 in /works... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-32 | Requirement already satisfied: certifi in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (2022.12.7)
Requirement already satisfied: urllib3>=1.26 in /workspace/langchain/.venv/lib/python3.9/site-packages (from clickhouse-connect>=0.5.7->chromadb) (1.26.15)
Requirement ... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-33 | Requirement already satisfied: six>=1.5 in /workspace/langchain/.venv/lib/python3.9/site-packages (from posthog>=2.4.0->chromadb) (1.16.0)
Requirement already satisfied: monotonic>=1.5 in /workspace/langchain/.venv/lib/python3.9/site-packages (from posthog>=2.4.0->chromadb) (1.6)
Requirement already satisfied: backoff>... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-34 | Requirement already satisfied: torch>=1.6.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (1.13.1)
Requirement already satisfied: torchvision in /workspace/langchain/.venv/lib/python3.9/site-packages (from sentence-transformers>=2.2.2->chromadb) (0.14.1)
Require... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-35 | Requirement already satisfied: h11>=0.8 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.14.0)
Requirement already satisfied: httptools>=0.5.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.5.0)
Requirement a... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-36 | Requirement already satisfied: packaging>=20.9 in /workspace/langchain/.venv/lib/python3.9/site-packages (from huggingface-hub>=0.4.0->sentence-transformers>=2.2.2->chromadb) (23.1)
Requirement already satisfied: anyio<5,>=3.4.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from starlette<0.27.0,>=0.26.1->... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-37 | Requirement already satisfied: setuptools in /workspace/langchain/.venv/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.6.0->sentence-transformers>=2.2.2->chromadb) (67.7.1)
Requirement already satisfied: wheel in /workspace/langchain/.venv/lib/python3.9/site-packages (from nvidia-cublas-cu11... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-38 | Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /workspace/langchain/.venv/lib/python3.9/site-packages (from torchvision->sentence-transformers>=2.2.2->chromadb) (9.5.0)
Requirement already satisfied: sniffio>=1.1 in /workspace/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3.4.0->starlette<0.27.0,... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-39 | answer_key = sql_cmd_key # this is the SQL generation input
if step[input_key].endswith("Answer:"):
answer_key = final_answer_key # this is the final answer input
elif sql_cmd_key in step:
_example[sql_cmd_key] = step[sql_cmd_key]
answer_ke... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-40 | warnings.warn(
SELECT firstname FROM customer WHERE firstname LIKE '%a%'
SQLResult: [('François',), ('František',), ('Helena',), ('Astrid',), ('Daan',), ('Kara',), ('Eduardo',), ('Alexandre',), ('Fernanda',), ('Mark',), ('Frank',), ('Jack',), ('Dan',), ('Kathy',), ('Heather',), ('Frank',), ('Richard',), ('Patrick',), (... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-41 | warnings.warn(
[('François', 'Frantiek', 'Helena', 'Astrid', 'Daan', 'Kara', 'Eduardo', 'Alexandre', 'Fernanda', 'Mark', 'Frank', 'Jack', 'Dan', 'Kathy', 'Heather', 'Frank', 'Richard', 'Patrick', 'Julia', 'Edward', 'Martha', 'Aaron', 'Madalena', 'Hannah', 'Niklas', 'Camille', 'Marc', 'Wyatt', 'Isabelle', 'Ladislav', 'L... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-42 | sql_cmd: SELECT firstname FROM customer WHERE firstname LIKE '%a%'
sql_result: '[(''François'',), (''František'',), (''Helena'',), (''Astrid'',), (''Daan'',),
(''Kara'',), (''Eduardo'',), (''Alexandre'',), (''Fernanda'',), (''Mark'',), (''Frank'',),
(''Jack'',), (''Dan'',), (''Kathy'',), (''Heather'',), (''Frank'',... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-43 | \ \n\t\"Phone\" NVARCHAR(24), \n\t\"Fax\" NVARCHAR(24), \n\t\"Email\" NVARCHAR(60)\
\ NOT NULL, \n\t\"SupportRepId\" INTEGER, \n\tPRIMARY KEY (\"CustomerId\"), \n\t\
FOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n)\n\n/*\n\
3 rows from Customer table:\nCustomerId\tFirstName\tLastName\tCom... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-44 | None\tftremblay@gmail.com\t3\n*/"
Run the snippet above a few times, or log exceptions in your deployed environment, to collect lots of examples of inputs, table_info and sql_cmd generated by your language model. The sql_cmd values will be incorrect and you can manually fix them up to build a collection of examples, e.... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-45 | CREATE TABLE "Genre" (
"GenreId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("GenreId")
)
/*
3 rows from Genre table:
GenreId Name
1 Rock
2 Jazz
3 Metal
*/
sql_cmd: SELECT "Name" FROM "Genre" WHERE "Name" LIKE 'r%';
sql_result: "[('Rock',), ('Rock and Rol... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-46 | # This is the list of examples available to select from.
examples_dict,
# This is the embedding class used to produce embeddings which are used to measure semantic similarity.
local_embeddings,
# This is the VectorStore clas... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
e5ddc38b0d06-47 | Answer:54 customers are not from Brazil.
> Finished chain.
result = local_chain("How many customers are there in total?")
> Entering new SQLDatabaseChain chain...
How many customers are there in total?
SQLQuery:SELECT count(*) FROM Customer;
SQLResult: [(59,)]
Answer:There are 59 customers in total.
> Finished chain.
p... | https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html |
acf3a5400eae-0 | .ipynb
.pdf
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain
Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain#
This notebook demonstrates how to use the RouterChain paradigm to create a chain that dynamically selects which Retrieval system to use. Specifically we show h... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
acf3a5400eae-1 | "retriever": sou_retriever
},
{
"name": "pg essay",
"description": "Good for answer quesitons about Paul Graham's essay on his career",
"retriever": pg_retriever
},
{
"name": "personal",
"description": "Good for answering questions about me",
"retrieve... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
acf3a5400eae-2 | > Finished chain.
Your background is Peruvian.
print(chain.run("What year was the Internet created in?"))
> Entering new MultiRetrievalQAChain chain...
None: {'query': 'What year was the Internet created in?'}
> Finished chain.
The Internet was created in 1969 through a project called ARPANET, which was funded by the ... | https://python.langchain.com/en/latest/modules/chains/examples/multi_retrieval_qa_router.html |
2dd97530a815-0 | .ipynb
.pdf
FLARE
Contents
Imports
Retriever
FLARE Chain
FLARE#
This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).
Please see the original repo here.
The basic idea is:
Start answering a question
If you start generating tokens the model is uncertain about, look up rel... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-1 | min_prob: Any tokens generated with probability below this will be considered uncertain
Imports#
import os
os.environ["SERPER_API_KEY"] = ""
import re
import numpy as np
from langchain.schema import BaseRetriever
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.embeddings import OpenAIEmbeddings
fr... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-2 | >>> RESPONSE:
> Entering new QuestionGeneratorChain chain...
Prompt after formatting:
Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:
>>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-3 | Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, includ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-4 | >>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing f... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-5 | Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, includ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-6 | >>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi
>>> EXISTING PARTIAL RESPONSE:
The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing f... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-7 | Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, includ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-8 | >>> CONTEXT: LangChain: Software. LangChain is a software development framework designed to simplify the creation of applications using large language models. LangChain Initial release date: October 2022. LangChain Programming languages: Python and JavaScript. LangChain Developer(s): Harrison Chase. LangChain License: ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-9 | LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Missing: secure | Must include:secure. Blockchain is the best way to secure the data of the shared community. Utilizing the capabilities of the blockchain nobod... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-10 | LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. This documentation ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-11 | Blockchain is one type of a distributed ledger. Distributed ledgers use independent computers (referred to as nodes) to record, share and ... Missing: Langchain | Must include:Langchain. Blockchain is used in distributed storage software where huge data is broken down into chunks. This is available in encrypted data ac... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-12 | LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: decentralized | Must include:decentralized. LangChain, created by Harrison Chase, is a Python library that provides out-of-the-box support to build NLP applications using... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-13 | LangChain is a powerful tool that can be used to work with Large Language ... If an API key has been provided, create an OpenAI language model instance At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. A tutorial of th... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-14 | At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.
>>> USER INPUT: explain in great detail... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-15 | llm = OpenAI()
llm(query)
'\n\nThe Langchain framework and Baby AGI are both artificial intelligence (AI) frameworks that are used to create intelligent agents. The Langchain framework is a supervised learning system that is based on the concept of “language chains”. It uses a set of rules to map natural language input... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-16 | >>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?
>>> EXISTING PARTIAL RESPONSE:
Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was creat... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-17 | FINISHED
The question to which the answer is the term/entity/phrase " developers as a platform for creating and managing decentralized language learning applications." is:
> Finished chain.
Generated Questions: ['How would you describe the origin stories of Langchain and Bitcoin in terms of their similarities or differ... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-18 | >>> CONTEXT: Bitcoin and Ethereum have many similarities but different long-term visions and limitations. Ethereum changed from proof of work to proof of ... Bitcoin will be around for many years and examining its white paper origins is a great exercise in understanding why. Satoshi Nakamoto's blueprint describes ... B... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
2dd97530a815-19 | At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.
>>> USER INPUT: how are the origin stor... | https://python.langchain.com/en/latest/modules/chains/examples/flare.html |
7bc1c46d0f40-0 | .ipynb
.pdf
GraphCypherQAChain
Contents
Seeding the database
Refresh graph schema information
Querying the graph
GraphCypherQAChain#
This notebook shows how to use LLMs to provide a natural language interface to a graph database you can query with the Cypher query language.
You will need to have a running Neo4j insta... | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
7bc1c46d0f40-1 | """
MERGE (m:Movie {name:"Top Gun"})
WITH m
UNWIND ["Tom Cruise", "Val Kilmer", "Anthony Edwards", "Meg Ryan"] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)
[]
Refresh graph schema information#
If the schema of database changes, you can refresh the schema information needed to generate Cypher s... | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
7bc1c46d0f40-2 | next
BashChain
Contents
Seeding the database
Refresh graph schema information
Querying the graph
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/chains/examples/graph_cypher_qa.html |
dcb82ebe1ad1-0 | .ipynb
.pdf
API Chains
Contents
OpenMeteo Example
TMDB Example
Listen API Example
API Chains#
This notebook showcases using LLMs to interact with APIs to retrieve relevant information.
from langchain.chains.api.prompt import API_RESPONSE_PROMPT
from langchain.chains import APIChain
from langchain.prompts.prompt impor... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-1 | from langchain.chains.api import tmdb_docs
headers = {"Authorization": f"Bearer {os.environ['TMDB_BEARER_TOKEN']}"}
chain = APIChain.from_llm_and_api_docs(llm, tmdb_docs.TMDB_DOCS, headers=headers, verbose=True)
chain.run("Search for 'Avatar'")
> Entering new APIChain chain...
https://api.themoviedb.org/3/search/movie... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-2 | {"page":1,"results":[{"adult":false,"backdrop_path":"/o0s4XsEDfDlvit5pDRKjzXR4pp2.jpg","genre_ids":[28,12,14,878],"id":19995,"original_language":"en","original_title":"Avatar","overview":"In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following o... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-3 | they fight to stay alive, and the tragedies they endure.","popularity":3948.296,"poster_path":"/t6HIqrRAclMCA60NsSmeqe9RmNV.jpg","release_date":"2022-12-14","title":"Avatar: The Way of Water","video":false,"vote_average":7.7,"vote_count":4219},{"adult":false,"backdrop_path":"/uEwGFGtao9YG2JolmdvtHLLVbA9.jpg","genre_ids... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-4 | Scene Deconstruction","video":false,"vote_average":7.8,"vote_count":12},{"adult":false,"backdrop_path":null,"genre_ids":[28,18,878,12,14],"id":83533,"original_language":"en","original_title":"Avatar 3","overview":"","popularity":172.488,"poster_path":"/4rXqTMlkEaMiJjiG0Z2BX6F6Dkm.jpg","release_date":"2024-12-18","title... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-5 | 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... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-6 | 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, Avat... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
dcb82ebe1ad1-7 | 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,... | https://python.langchain.com/en/latest/modules/chains/examples/api.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.