id stringlengths 14 16 | text stringlengths 44 2.73k | source stringlengths 49 114 |
|---|---|---|
efa37247544d-4 | Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Content-Type. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept.... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
efa37247544d-5 | Action: spoonacular_API.searchRecipes
Action Input: Italian
Observation: The API response contains 10 Italian recipes, including Turkey Tomato Cheese Pizza, Broccolini Quinoa Pilaf, Bruschetta Style Pork & Pasta, Salmon Quinoa Risotto, Italian Tuna Pasta, Roasted Brussels Sprouts With Garlic, Asparagus Lemon Risotto, I... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
efa37247544d-6 | > Finished chain.
'To present for your Italian language class, you could wear an Italian Gold Sparkle Perfectina Necklace - Gold, an Italian Design Miami Cuban Link Chain Necklace - Gold, or an Italian Gold Miami Cuban Link Chain Necklace - Gold. For a recipe, you could make Turkey Tomato Cheese Pizza, Broccolini Quino... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
79f02f1b25b0-0 | .ipynb
.pdf
Python Agent
Contents
Fibonacci Example
Training neural net
Python Agent#
This notebook showcases an agent designed to write and execute python code to answer a question.
from langchain.agents.agent_toolkits import create_python_agent
from langchain.tools.python.tool import PythonREPLTool
from langchain.p... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
79f02f1b25b0-1 | I need to write a neural network in PyTorch and train it on the given data.
Action: Python REPL
Action Input:
import torch
# Define the model
model = torch.nn.Sequential(
torch.nn.Linear(1, 1)
)
# Define the loss
loss_fn = torch.nn.MSELoss()
# Define the optimizer
optimizer = torch.optim.SGD(model.parameters(), lr... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
79f02f1b25b0-2 | Thought: I now know the final answer
Final Answer: The prediction for x = 5 is 10.0.
> Finished chain.
'The prediction for x = 5 is 10.0.'
previous
PowerBI Dataset Agent
next
SQL Database Agent
Contents
Fibonacci Example
Training neural net
By Harrison Chase
© Copyright 2023, Harrison Chase.
Las... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/python.html |
12c728a0be01-0 | .ipynb
.pdf
Pandas Dataframe Agent
Pandas Dataframe Agent#
This notebook shows how to use agents to interact with a pandas dataframe. It is mostly optimized for question answering.
NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Pyt... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/pandas.html |
12c728a0be01-1 | Action: python_repl_ast
Action Input: df['Age'].mean()
Observation: 29.69911764705882
Thought: I can now calculate the square root
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: name 'math' is not defined
Thought: I need to import the math library
Action: python_repl_ast
Action Input: im... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/pandas.html |
c13b2a17a9c9-0 | .ipynb
.pdf
PowerBI Dataset Agent
Contents
Some notes
Initialization
Example: describing a table
Example: simple query on a table
Example: running queries
Example: add your own few-shot prompts
PowerBI Dataset Agent#
This notebook showcases an agent designed to interact with a Power BI Dataset. The agent is designed ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
c13b2a17a9c9-1 | toolkit = PowerBIToolkit(
powerbi=PowerBIDataset(dataset_id="<dataset_id>", table_names=['table1', 'table2'], credential=DefaultAzureCredential()),
llm=smart_llm
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
Example: describing a table#
agent_executor.run("Desc... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
c13b2a17a9c9-2 | examples=few_shots,
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
agent_executor.run("What was the maximum of value in revenue in dollars in 2022?")
previous
Pandas Dataframe Agent
next
Python Agent
Contents
Some notes
Initialization
Example: describing a table
Exam... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
36011478f118-0 | .ipynb
.pdf
Jira
Jira#
This notebook goes over how to use the Jira tool.
The Jira tool allows agents to interact with a given Jira instance, performing actions such as searching for issues and creating issues, the tool wraps the atlassian-python-api library, for more see: https://atlassian-python-api.readthedocs.io/jir... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
36011478f118-1 | Observation: None
Thought: I now know the final answer
Final Answer: A new issue has been created in project PW with the summary "Make more fried rice" and description "Reminder to make more fried rice".
> Finished chain.
'A new issue has been created in project PW with the summary "Make more fried rice" and descriptio... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
d52f9202dfd2-0 | .ipynb
.pdf
JSON Agent
Contents
Initialization
Example: getting the required POST parameters for a request
JSON Agent#
This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that’s too large to fit in the context window of... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/json.html |
d52f9202dfd2-1 | Thought: I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/json.html |
d52f9202dfd2-2 | Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]
Observation: ['application/json']
Thought: I should look at the application/json key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/json.html |
d52f9202dfd2-3 | Initialization
Example: getting the required POST parameters for a request
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 25, 2023. | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/json.html |
77875496ffb8-0 | .ipynb
.pdf
OpenAPI agents
Contents
1st example: hierarchical planning agent
To start, let’s collect some OpenAPI specs.
How big is this spec?
Let’s see some examples!
Try another API.
2nd example: “json explorer” agent
OpenAPI agents#
We can construct agents to consume arbitrary APIs, here APIs conformant to the Ope... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-1 | !mv openapi.yaml spotify_openapi.yaml
--2023-03-31 15:45:56-- https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercont... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-2 | --2023-03-31 15:45:57-- https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|18... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-3 | You’ll have to set up an application in the Spotify developer console, documented here, to get credentials: CLIENT_ID, CLIENT_SECRET, and REDIRECT_URI.
To get an access tokens (and keep them fresh), you can implement the oauth flows, or you can use spotipy. If you’ve set your Spotify creedentials as environment variabl... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-4 | from langchain.agents.agent_toolkits.openapi import planner
llm = OpenAI(model_name="gpt-4", temperature=0.0)
/Users/jeremywelborn/src/langchain/langchain/llms/openai.py:169: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: `from langchain.chat_mo... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-5 | Thought:I have the plan, now I need to execute the API calls.
Action: api_controller
Action Input: 1. GET /search to search for the album "Kind of Blue"
2. GET /albums/{id}/tracks to get the tracks from the "Kind of Blue" album
3. GET /me to get the current user's information
4. POST /users/{user_id}/playlists to creat... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-6 | Thought:Action: requests_post
Action Input: {"url": "https://api.spotify.com/v1/users/22rhrz4m4kvpxlsb5hezokzwi/playlists", "data": {"name": "Machine Blues"}, "output_instructions": "Extract the id of the created playlist"}
Observation: 7lzoEi44WOISnFYlrAIqyX
Thought:Action: requests_post
Action Input: {"url": "https:/... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-7 | user_query = "give me a song I'd like, make it blues-ey"
spotify_agent.run(user_query)
> Entering new AgentExecutor chain...
Action: api_planner
Action Input: I need to find the right API calls to get a blues song recommendation for the user
Observation: 1. GET /me to get the current user's information
2. GET /recommen... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-8 | Observation: acoustic, afrobeat, alt-rock, alternative, ambient, anime, black-metal, bluegrass, blues, bossanova, brazil, breakbeat, british, cantopop, chicago-house, children, chill, classical, club, comedy, country, dance, dancehall, death-metal, deep-house, detroit-techno, disco, disney, drum-and-bass, dub, dubstep,... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-9 | Observation: [
{
id: '03lXHmokj9qsXspNsPoirR',
name: 'Get Away Jordan'
}
]
Thought:I am finished executing the plan.
Final Answer: The recommended blues song for user Jeremy Welborn (ID: 22rhrz4m4kvpxlsb5hezokzwi) is "Get Away Jordan" with the track ID: 03lXHmokj9qsXspNsPoirR.
> Finished chain.
Observation:... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-10 | > Entering new AgentExecutor chain...
Action: api_planner
Action Input: I need to find the right API calls to generate a short piece of advice
Observation: 1. GET /engines to retrieve the list of available engines
2. POST /completions with the selected engine and a prompt for generating a short piece of advice
Thought:... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-11 | Action: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"engine": "davinci", "prompt": "Give me a short piece of advice on how to be more productive."}, "output_instructions": "Extract the text from the first choice"}
Observation: "you must provide a model parameter"
Thought:!! Cou... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-12 | Observation: babbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada
Thought:Action: requests_post
Action Input: {"url": "https://api.openai.com/v1/completions", "data": {"model": "davinci", "prompt": "Give me a short piece of adv... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-13 | Action: api_controller
Action Input: 1. GET /models to retrieve the list of available models
2. Choose a suitable model for generating text (e.g., text-davinci-002)
3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice
> Entering new AgentE... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-14 | Takes awhile to get there!
2nd example: “json explorer” agent#
Here’s an agent that’s not particularly practical, but neat! The agent has access to 2 toolkits. One comprises tools to interact with json: one tool to list the keys of a json object and another tool to get the value for a given key. The other toolkit compr... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-15 | Thought: I should look at the servers key to see what the base url is
Action: json_spec_list_keys
Action Input: data["servers"][0]
Observation: ValueError('Value at path `data["servers"][0]` is not a dict, get the value directly.')
Thought: I should get the value of the servers key
Action: json_spec_get_value
Action In... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-16 | Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-17 | Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-18 | Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]
Observation: ['schema']
Thought: I should look at the schema key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-19 | > Finished chain.
Observation: The required parameters for a POST request to the /completions endpoint are 'model'.
Thought: I now know the parameters needed to make the request.
Action: requests_post
Action Input: { "url": "https://api.openai.com/v1/completions", "data": { "model": "davinci", "prompt": "tell me a joke... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
77875496ffb8-20 | > Finished chain.
'The response of the POST request is {"id":"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv","object":"text_completion","created":1680307139,"model":"davinci","choices":[{"text":" with mummy not there”\\n\\nYou dig deep and come up with,","index":0,"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi.html |
968988b92967-0 | .ipynb
.pdf
Vectorstore Agent
Contents
Create the Vectorstores
Initialize Toolkit and Agent
Examples
Multiple Vectorstores
Examples
Vectorstore Agent#
This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources.
Create the Vectorstores#
from langchai... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
968988b92967-1 | )
vectorstore_info = VectorStoreInfo(
name="state_of_union_address",
description="the most recent state of the Union adress",
vectorstore=state_of_union_store
)
toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)
agent_executor = create_vectorstore_agent(
llm=llm,
toolkit=toolkit,
ve... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
968988b92967-2 | Action Input: What did biden say about ketanji brown jackson
Observation: {"answer": " Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n", "s... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
968988b92967-3 | toolkit=router_toolkit,
verbose=True
)
Examples#
agent_executor.run("What did biden say about ketanji brown jackson is the state of the union address?")
> Entering new AgentExecutor chain...
I need to use the state_of_union_address tool to answer this question.
Action: state_of_union_address
Action Input: What did... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
968988b92967-4 | Thought: I now know the final answer
Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb
> Finished chain.
'Ruff is integrated into nbQA, a tool for running... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
968988b92967-5 | previous
SQL Database Agent
next
Agent Executors
Contents
Create the Vectorstores
Initialize Toolkit and Agent
Examples
Multiple Vectorstores
Examples
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 25, 2023. | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/vectorstore.html |
f10175b72823-0 | .rst
.pdf
Prompt Templates
Prompt Templates#
Note
Conceptual Guide
Language models take text as input - that text is commonly referred to as a prompt.
Typically this is not simply a hardcoded string but rather a combination of a template, some examples, and user input.
LangChain provides several classes and functions t... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates.html |
3d3b3ee5ac17-0 | .rst
.pdf
Output Parsers
Output Parsers#
Note
Conceptual Guide
Language models output text. But many times you may want to get more structured information than just text back. This is where output parsers come in.
Output parsers are classes that help structure language model responses. There are two main methods an out... | https://python.langchain.com/en/latest/modules/prompts/output_parsers.html |
4de0729fb7e2-0 | .ipynb
.pdf
Chat Prompt Template
Chat Prompt Template#
Chat Models takes a list of chat messages as input - this list commonly referred to as a prompt.
Typically this is not simply a hardcoded list of messages but rather a combination of a template, some examples, and user input.
LangChain provides several classes and ... | https://python.langchain.com/en/latest/modules/prompts/chat_prompt_template.html |
4de0729fb7e2-1 | HumanMessage(content='I love programming.', additional_kwargs={})]
If you wanted to construct the MessagePromptTemplate more directly, you could create a PromptTemplate outside and then pass it in, eg:
prompt=PromptTemplate(
template="You are a helpful assistant that translates {input_language} to {output_language}... | https://python.langchain.com/en/latest/modules/prompts/chat_prompt_template.html |
eb4b2edba405-0 | .rst
.pdf
Example Selectors
Example Selectors#
Note
Conceptual Guide
If you have a large number of examples, you may need to select which ones to include in the prompt. The ExampleSelector is the class responsible for doing so.
The base interface is defined as below:
class BaseExampleSelector(ABC):
"""Interface for... | https://python.langchain.com/en/latest/modules/prompts/example_selectors.html |
c279fcb3b76e-0 | .rst
.pdf
How-To Guides
How-To Guides#
If you’re new to the library, you may want to start with the Quickstart.
The user guide here shows more advanced workflows and how to use the library in different ways.
How to create a custom prompt template
How to create a prompt template that uses few shot examples
How to work w... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/how_to_guides.html |
dbf1783f460a-0 | .md
.pdf
Getting Started
Contents
What is a prompt template?
Create a prompt template
Template formats
Validate template
Serialize prompt template
Pass few shot examples to a prompt template
Select examples for a prompt template
Getting Started#
In this tutorial, we will learn about:
what a prompt template is, and wh... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-1 | no_input_prompt.format()
# -> "Tell me a joke."
# An example prompt with one input variable
one_input_prompt = PromptTemplate(input_variables=["adjective"], template="Tell me a {adjective} joke.")
one_input_prompt.format(adjective="funny")
# -> "Tell me a funny joke."
# An example prompt with multiple input variables
m... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-2 | # -> Tell me a funny joke about chickens.
Currently, PromptTemplate only supports jinja2 and f-string templating format. If there is any other templating format that you would like to use, feel free to open an issue in the Github page.
Validate template#
By default, PromptTemplate will validate the template string by c... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-3 | To generate a prompt with few shot examples, you can use the FewShotPromptTemplate. This class takes in a PromptTemplate and a list of few shot examples. It then formats the prompt template with the few shot examples.
In this example, we’ll create a prompt to generate word antonyms.
from langchain import PromptTemplate... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-4 | input_variables=["input"],
# The example_separator is the string we will use to join the prefix, examples, and suffix together with.
example_separator="\n\n",
)
# We can now generate a prompt using the `format` method.
print(few_shot_prompt.format(input="big"))
# -> Give the antonym of every input
# ->
# -> Wo... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-5 | {"word": "windy", "antonym": "calm"},
]
# We'll use the `LengthBasedExampleSelector` to select the examples.
example_selector = LengthBasedExampleSelector(
# These are the examples is has available to choose from.
examples=examples,
# This is the PromptTemplate being used to format the examples.
exampl... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
dbf1783f460a-6 | long_string = "big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else"
print(dynamic_prompt.format(input=long_string))
# -> Give the antonym of every input
# -> Word: happy
# -> Antonym: sad
# ->
# -> Word: big and huge and massive and large and gigantic and ta... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/getting_started.html |
9288f2fb2fd9-0 | .ipynb
.pdf
How to create a custom prompt template
Contents
Why are custom prompt templates needed?
Creating a Custom Prompt Template
Use the custom prompt template
How to create a custom prompt template#
Let’s suppose we want the LLM to generate English language explanations of a function given its name. To achieve ... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/custom_prompt_template.html |
9288f2fb2fd9-1 | import inspect
def get_source_code(function_name):
# Get the source code of the function
return inspect.getsource(function_name)
Next, we’ll create a custom prompt template that takes in the function name as input, and formats the prompt template to provide the source code of the function.
from langchain.prompt... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/custom_prompt_template.html |
9288f2fb2fd9-2 | prompt = fn_explainer.format(function_name=get_source_code)
print(prompt)
Given the function name and source code, generate an English language explanation of the function.
Function Name: get_source_code
Source Code:
def get_source_code(function_name):
# Get the source code of the fu... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/custom_prompt_template.html |
ab4263d92dd0-0 | .ipynb
.pdf
How to serialize prompts
Contents
PromptTemplate
Loading from YAML
Loading from JSON
Loading Template from a File
FewShotPromptTemplate
Examples
Loading from YAML
Loading from JSON
Examples in the Config
Example Prompt from a File
How to serialize prompts#
It is often preferrable to store prompts not as p... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/prompt_serialization.html |
ab4263d92dd0-1 | prompt = load_prompt("simple_prompt.yaml")
print(prompt.format(adjective="funny", content="chickens"))
Tell me a funny joke about chickens.
Loading from JSON#
This shows an example of loading a PromptTemplate from JSON.
!cat simple_prompt.json
{
"_type": "prompt",
"input_variables": ["adjective", "content"],
... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/prompt_serialization.html |
ab4263d92dd0-2 | output: sad
- input: tall
output: short
Loading from YAML#
This shows an example of loading a few shot example from YAML.
!cat few_shot_prompt.yaml
_type: few_shot
input_variables:
["adjective"]
prefix:
Write antonyms for the following words.
example_prompt:
_type: prompt
input_variables:
["i... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/prompt_serialization.html |
ab4263d92dd0-3 | !cat few_shot_prompt.json
{
"_type": "few_shot",
"input_variables": ["adjective"],
"prefix": "Write antonyms for the following words.",
"example_prompt": {
"_type": "prompt",
"input_variables": ["input", "output"],
"template": "Input: {input}\nOutput: {output}"
},
"exampl... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/prompt_serialization.html |
ab4263d92dd0-4 | Output: short
Input: funny
Output:
Example Prompt from a File#
This shows an example of loading the PromptTemplate that is used to format the examples from a separate file. Note that the key changes from example_prompt to example_prompt_path.
!cat example_prompt.json
{
"_type": "prompt",
"input_variables": ["in... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/prompt_serialization.html |
77e1d05beda2-0 | .ipynb
.pdf
How to work with partial Prompt Templates
Contents
Partial With Strings
Partial With Functions
How to work with partial Prompt Templates#
A prompt template is a class with a .format method which takes in a key-value map and returns a string (a prompt) to pass to the language model. Like other methods, it ... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/partial.html |
77e1d05beda2-1 | print(prompt.format(bar="baz"))
foobaz
Partial With Functions#
The other common use is to partial with a function. The use case for this is when you have a variable you know that you always want to fetch in a common way. A prime example of this is with date or time. Imagine you have a prompt which you always want to ha... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/partial.html |
77e1d05beda2-2 | Contents
Partial With Strings
Partial With Functions
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 25, 2023. | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/partial.html |
3c8d7e4f998c-0 | .ipynb
.pdf
How to create a prompt template that uses few shot examples
Contents
Use Case
Using an example set
Create the example set
Create a formatter for the few shot examples
Feed examples and formatter to FewShotPromptTemplate
Using an example selector
Feed examples into ExampleSelector
Feed example selector int... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
3c8d7e4f998c-1 | "answer":
"""
Are follow up questions needed here: Yes.
Follow up: Who was the founder of craigslist?
Intermediate answer: Craigslist was founded by Craig Newmark.
Follow up: When was Craig Newmark born?
Intermediate answer: Craig Newmark was born on December 6, 1952.
So the final answer is: December 6, 1952
"""
},
... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
3c8d7e4f998c-2 | print(example_prompt.format(**examples[0]))
Question: Who lived longer, Muhammad Ali or Alan Turing?
Are follow up questions needed here: Yes.
Follow up: How old was Muhammad Ali when he died?
Intermediate answer: Muhammad Ali was 74 years old when he died.
Follow up: How old was Alan Turing when he died?
Intermediate ... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
3c8d7e4f998c-3 | Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The mother of George Washington was Mary Ball Washington.
Follow up: Who was the father of Mary Ball Washington?
Intermediate answer: The father of Mary Ball Washington was Joseph Ball.
So the final answer... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
3c8d7e4f998c-4 | # This is the list of examples available to select from.
examples,
# This is the embedding class used to produce embeddings which are used to measure semantic similarity.
OpenAIEmbeddings(),
# This is the VectorStore class that is used to store the embeddings and do a similarity search over.
Chroma,... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
3c8d7e4f998c-5 | suffix="Question: {input}",
input_variables=["input"]
)
print(prompt.format(input="Who was the father of Mary Ball Washington?"))
Question: Who was the maternal grandfather of George Washington?
Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The m... | https://python.langchain.com/en/latest/modules/prompts/prompt_templates/examples/few_shot_examples.html |
7f6b30f6958b-0 | .ipynb
.pdf
NGram Overlap ExampleSelector
NGram Overlap ExampleSelector#
The NGramOverlapExampleSelector selects and orders examples based on which examples are most similar to the input, according to an ngram overlap score. The ngram overlap score is a float between 0.0 and 1.0, inclusive.
The selector allows for a th... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/ngram_overlap.html |
7f6b30f6958b-1 | {"input": "Spot can run.", "output": "Spot puede correr."},
]
example_prompt = PromptTemplate(
input_variables=["input", "output"],
template="Input: {input}\nOutput: {output}",
)
example_selector = NGramOverlapExampleSelector(
# These are the examples it has available to choose from.
examples=examples, ... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/ngram_overlap.html |
7f6b30f6958b-2 | Output: Ver correr a Spot.
Input: My dog barks.
Output: Mi perro ladra.
Input: Spot can run fast.
Output:
# You can add examples to NGramOverlapExampleSelector as well.
new_example = {"input": "Spot plays fetch.", "output": "Spot juega a buscar."}
example_selector.add_example(new_example)
print(dynamic_prompt.format(se... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/ngram_overlap.html |
7f6b30f6958b-3 | Input: Spot plays fetch.
Output: Spot juega a buscar.
Input: Spot can play fetch.
Output:
# Setting threshold greater than 1.0
example_selector.threshold=1.0+1e-9
print(dynamic_prompt.format(sentence="Spot can play fetch."))
Give the Spanish translation of every input
Input: Spot can play fetch.
Output:
previous
Maxima... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/ngram_overlap.html |
b3862d1e86d8-0 | .ipynb
.pdf
LengthBased ExampleSelector
LengthBased ExampleSelector#
This ExampleSelector selects which examples to use based on length. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while ... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/length_based.html |
b3862d1e86d8-1 | # it is provided as a default value if none is specified.
# get_text_length: Callable[[str], int] = lambda x: len(re.split("\n| ", x))
)
dynamic_prompt = FewShotPromptTemplate(
# We provide an ExampleSelector instead of examples.
example_selector=example_selector,
example_prompt=example_prompt,
pref... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/length_based.html |
b3862d1e86d8-2 | Input: sunny
Output: gloomy
Input: windy
Output: calm
Input: big
Output: small
Input: enthusiastic
Output:
previous
How to create a custom example selector
next
Maximal Marginal Relevance ExampleSelector
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 25, 2023. | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/length_based.html |
48bec9e45eaf-0 | .ipynb
.pdf
Similarity ExampleSelector
Similarity ExampleSelector#
The SemanticSimilarityExampleSelector selects examples based on which examples are most similar to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.
from langchain.prompts.exam... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/similarity.html |
48bec9e45eaf-1 | example_prompt=example_prompt,
prefix="Give the antonym of every input",
suffix="Input: {adjective}\nOutput:",
input_variables=["adjective"],
)
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
# Input is a feeling, so should select the happy/sad example
pr... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/similarity.html |
7b6a7ef29c78-0 | .md
.pdf
How to create a custom example selector
Contents
Implement custom example selector
Use custom example selector
How to create a custom example selector#
In this tutorial, we’ll create a custom example selector that selects every alternate example from a given list of examples.
An ExampleSelector must implemen... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/custom_example_selector.html |
7b6a7ef29c78-1 | # Add new example to the set of examples
example_selector.add_example({"foo": "4"})
example_selector.examples
# -> [{'foo': '1'}, {'foo': '2'}, {'foo': '3'}, {'foo': '4'}]
# Select examples
example_selector.select_examples({"foo": "foo"})
# -> array([{'foo': '1'}, {'foo': '4'}], dtype=object)
previous
Example Selectors... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/custom_example_selector.html |
05909e3a2d74-0 | .ipynb
.pdf
Maximal Marginal Relevance ExampleSelector
Maximal Marginal Relevance ExampleSelector#
The MaxMarginalRelevanceExampleSelector selects examples based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddin... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/mmr.html |
05909e3a2d74-1 | k=2
)
mmr_prompt = FewShotPromptTemplate(
# We provide an ExampleSelector instead of examples.
example_selector=example_selector,
example_prompt=example_prompt,
prefix="Give the antonym of every input",
suffix="Input: {adjective}\nOutput:",
input_variables=["adjective"],
)
# Input is a feeling,... | https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/mmr.html |
b5af1bcea04b-0 | .ipynb
.pdf
Output Parsers
Output Parsers#
Language models output text. But many times you may want to get more structured information than just text back. This is where output parsers come in.
Output parsers are classes that help structure language model responses. There are two main methods an output parser must impl... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/getting_started.html |
b5af1bcea04b-1 | punchline: str = Field(description="answer to resolve the joke")
# You can add custom validation logic easily with Pydantic.
@validator('setup')
def question_ends_with_question_mark(cls, field):
if field[-1] != '?':
raise ValueError("Badly formed question!")
return field
# S... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/getting_started.html |
1bda4ae2be2a-0 | .ipynb
.pdf
RetryOutputParser
RetryOutputParser#
While in some cases it is possible to fix any parsing mistakes by only looking at the output, in other cases it can’t. An example of this is when the output is not just in the incorrect format, but is partially complete. Consider the below example.
from langchain.prompts... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/retry.html |
1bda4ae2be2a-1 | 23 json_object = json.loads(json_str)
---> 24 return self.pydantic_object.parse_obj(json_object)
26 except (json.JSONDecodeError, ValidationError) as e:
File ~/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/pydantic/main.py:527, in pydantic.main.BaseModel.parse_obj()
File ~/.pyenv/version... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/retry.html |
1bda4ae2be2a-2 | fix_parser.parse(bad_response)
Action(action='search', action_input='')
Instead, we can use the RetryOutputParser, which passes in the prompt (as well as the original output) to try again to get a better response.
from langchain.output_parsers import RetryWithErrorOutputParser
retry_parser = RetryWithErrorOutputParser.... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/retry.html |
3a463b0f687c-0 | .ipynb
.pdf
PydanticOutputParser
PydanticOutputParser#
This output parser allows users to specify an arbitrary JSON schema and query LLMs for JSON outputs that conform to that schema.
Keep in mind that large language models are leaky abstractions! You’ll have to use an LLM with sufficient capacity to generate well-form... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/pydantic.html |
3a463b0f687c-1 | prompt = PromptTemplate(
template="Answer the user query.\n{format_instructions}\n{query}\n",
input_variables=["query"],
partial_variables={"format_instructions": parser.get_format_instructions()}
)
_input = prompt.format_prompt(query=joke_query)
output = model(_input.to_string())
parser.parse(output)
Joke(... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/pydantic.html |
c8aa8a2d2fbe-0 | .ipynb
.pdf
OutputFixingParser
OutputFixingParser#
This output parser wraps another output parser and tries to fix any mmistakes
The Pydantic guardrail simply tries to parse the LLM response. If it does not parse correctly, then it errors.
But we can do other things besides throw errors. Specifically, we can pass the m... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/output_fixing_parser.html |
c8aa8a2d2fbe-1 | 24 return self.pydantic_object.parse_obj(json_object)
File ~/.pyenv/versions/3.9.1/lib/python3.9/json/__init__.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
343 if (cls is None and object_hook is None and
344 parse_int is None and parse_float is N... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/output_fixing_parser.html |
c8aa8a2d2fbe-2 | Cell In[6], line 1
----> 1 parser.parse(misformatted)
File ~/workplace/langchain/langchain/output_parsers/pydantic.py:29, in PydanticOutputParser.parse(self, text)
27 name = self.pydantic_object.__name__
28 msg = f"Failed to parse {name} from completion {text}. Got: {e}"
---> 29 raise OutputParserException(ms... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/output_fixing_parser.html |
851ba990e298-0 | .ipynb
.pdf
Structured Output Parser
Structured Output Parser#
While the Pydantic/JSON parser is more powerful, we initially experimented data structures having text fields only.
from langchain.output_parsers import StructuredOutputParser, ResponseSchema
from langchain.prompts import PromptTemplate, ChatPromptTemplate,... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/structured.html |
851ba990e298-1 | ],
input_variables=["question"],
partial_variables={"format_instructions": format_instructions}
)
_input = prompt.format_prompt(question="what's the capital of france")
output = chat_model(_input.to_messages())
output_parser.parse(output.content)
{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Pari... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/structured.html |
b6b28c526660-0 | .ipynb
.pdf
CommaSeparatedListOutputParser
CommaSeparatedListOutputParser#
Here’s another parser strictly less powerful than Pydantic/JSON parsing.
from langchain.output_parsers import CommaSeparatedListOutputParser
from langchain.prompts import PromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate
from langch... | https://python.langchain.com/en/latest/modules/prompts/output_parsers/examples/comma_separated.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.