id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
5e622d7788aa-11 | company_values = self.company_values,
conversation_purpose = self.conversation_purpose,
conversation_history="\n".join(self.conversation_history),
conversation_stage = self.current_conversation_stage,
conversation_type=self.conversation_type
)
# A... | https://python.langchain.com/en/latest/use_cases/agents/sales_agent_with_context.html |
5e622d7788aa-12 | '3': "Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.",
'4': "Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen caref... | https://python.langchain.com/en/latest/use_cases/agents/sales_agent_with_context.html |
5e622d7788aa-13 | conversation_type="call",
conversation_stage = conversation_stages.get('1', "Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.")
)
Run the agent#
sales_agent = SalesGPT.from_llm(llm, verbose=False, **config)
#... | https://python.langchain.com/en/latest/use_cases/agents/sales_agent_with_context.html |
5e622d7788aa-14 | sales_agent.step()
Ted Lasso: We have three mattress options: the Comfort Plus, the Support Premier, and the Ultra Luxe. The Comfort Plus is perfect for those who prefer a softer mattress, while the Support Premier is great for those who need more back support. And if you want the ultimate sleeping experience, the Ult... | https://python.langchain.com/en/latest/use_cases/agents/sales_agent_with_context.html |
5e622d7788aa-15 | Run the agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/agents/sales_agent_with_context.html |
33e97e360adc-0 | .ipynb
.pdf
Plug-and-Plai
Contents
Set up environment
Setup LLM
Set up plugins
Tool Retriever
Prompt Template
Output Parser
Set up LLM, stop sequence, and the agent
Use the Agent
Plug-and-Plai#
This notebook builds upon the idea of tool retrieval, but pulls all tools from plugnplai - a directory of AI Plugins.
Set up... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-1 | urls = plugnplai.get_plugins(filter = 'working')
AI_PLUGINS = [AIPlugin.from_url(url + "/.well-known/ai-plugin.json") for url in urls]
Tool Retriever#
We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search ... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-2 | 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.
Attempting to load an OpenAPI 3.... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-3 | 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',
'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',
'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',
'SchoolDigger_API_V2.0.Autocomplete_GetSchools',
'SchoolDigger_API_V2.0.... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-4 | 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',
'SchoolDigger_API_V2.0.Districts_GetDistrict2',
'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',
'SchoolDigger_API_V2.0.Rankings_GetRank_District',
'SchoolDigger_API_V2.0.Schools_GetAllSchools20',
'SchoolDigger_API_V2.0.Schools_GetSchool20']
Prompt Template#
The ... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-5 | template: str
############## NEW ######################
# The list of tools available
tools_getter: Callable
def format(self, **kwargs) -> str:
# Get the intermediate steps (AgentAction, Observation tuples)
# Format them in a particular way
intermediate_steps = kwargs.pop("i... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-6 | if "Final Answer:" in llm_output:
return AgentFinish(
# Return values is generally always a dictionary with a single `output` key
# It is not recommended to try anything else at the moment :)
return_values={"output": llm_output.split("Final Answer:")[-1].strip... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
33e97e360adc-7 | agent_executor.run("what shirts can i buy?")
> Entering new AgentExecutor chain...
Thought: I need to find a product API
Action: Open_AI_Klarna_product_Api.productsUsingGET
Action Input: shirts
Observation:I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materi... | https://python.langchain.com/en/latest/use_cases/agents/custom_agent_with_plugin_retrieval_using_plugnplai.html |
5b2a338c75da-0 | .ipynb
.pdf
Wikibase Agent
Contents
Wikibase Agent
Preliminaries
API keys and other secrats
OpenAI API Key
Wikidata user-agent header
Enable tracing if desired
Tools
Item and Property lookup
Sparql runner
Agent
Wrap the tools
Prompts
Output parser
Specify the LLM model
Agent and agent executor
Run it!
Wikibase Agent#... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-1 | Enable tracing if desired#
#import os
#os.environ["LANGCHAIN_HANDLER"] = "langchain"
#os.environ["LANGCHAIN_SESSION"] = "default" # Make sure this session actually exists.
Tools#
Three tools are provided for this simple agent:
ItemLookup: for finding the q-number of an item
PropertyLookup: for finding the p-number of ... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-2 | else:
raise ValueError("entity_type must be either 'property' or 'item'")
params = {
"action": "query",
"list": "search",
"srsearch": search,
"srnamespace": srnamespace,
"srlimit": 1,
"srqiprofile": srqiprofile,
"srwhat": 'text',
... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-3 | headers = {
'Accept': 'application/json'
}
if wikidata_user_agent_header is not None:
headers['User-Agent'] = wikidata_user_agent_header
response = requests.get(url, headers=headers, params={'query': query, 'format': 'json'})
if response.status_code != 200:
return "That query fai... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-4 | name = "SparqlQueryRunner",
func=run_sparql,
description="useful for getting results from a wikibase"
)
]
Prompts#
# Set up the base template
template = """
Answer the following questions by running a sparql query against a wikibase where the p and q items are
completely unknown to you. You wil... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-5 | Question: {input}
{agent_scratchpad}"""
# Set up a prompt template
class CustomPromptTemplate(StringPromptTemplate):
# The template to use
template: str
# The list of tools available
tools: List[Tool]
def format(self, **kwargs) -> str:
# Get the intermediate steps (AgentAction, Observat... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-6 | if "Final Answer:" in llm_output:
return AgentFinish(
# Return values is generally always a dictionary with a single `output` key
# It is not recommended to try anything else at the moment :)
return_values={"output": llm_output.split("Final Answer:")[-1].strip... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-7 | # agent_executor.agent.llm_chain.verbose = True
agent_executor.run("How many children did J.S. Bach have?")
> Entering new AgentExecutor chain...
Thought: I need to find the Q number for J.S. Bach.
Action: ItemLookup
Action Input: J.S. Bach
Observation:Q1339I need to find the P number for children.
Action: PropertyLook... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
5b2a338c75da-8 | Action: PropertyLookup
Action Input: Basketball-Reference.com NBA player ID
Observation:P2685Now that I have both the Q-number for Hakeem Olajuwon (Q273256) and the P-number for the Basketball-Reference.com NBA player ID property (P2685), I can run a SPARQL query to get the ID value.
Action: SparqlQueryRunner
Action In... | https://python.langchain.com/en/latest/use_cases/agents/wikibase_agent.html |
7b3a2749cad9-0 | .ipynb
.pdf
Multi-modal outputs: Image & Text
Contents
Multi-modal outputs: Image & Text
Dall-E
StableDiffusion
Multi-modal outputs: Image & Text#
This notebook shows how non-text producing tools can be used to create multi-modal agents.
This example is limited to text and image outputs and uses UUIDs to transfer con... | https://python.langchain.com/en/latest/use_cases/agents/multi_modal_output_agent.html |
7b3a2749cad9-1 | > Finished chain.
def show_output(output):
"""Display the multi-modal output from the agent."""
UUID_PATTERN = re.compile(
r"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{12})"
)
outputs = UUID_PATTERN.split(output)
outputs = [re.sub(r"^\W+", "", el) for el in outp... | https://python.langchain.com/en/latest/use_cases/agents/multi_modal_output_agent.html |
7b3a2749cad9-2 | > Finished chain.
show_output(output)
The UUID of the generated image is
Contents
Multi-modal outputs: Image & Text
Dall-E
StableDiffusion
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/agents/multi_modal_output_agent.html |
d6571d1d9e03-0 | .ipynb
.pdf
Voice Assistant
Voice Assistant#
This chain creates a clone of ChatGPT with a few modifications to make it a voice assistant.
It uses the pyttsx3 and speech_recognition libraries to convert text to speech and speech to text respectively. The prompt template is also changed to make it more suitable for voice... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-1 | {history}
Human: {human_input}
Assistant:"""
prompt = PromptTemplate(
input_variables=["history", "human_input"],
template=template
)
chatgpt_chain = LLMChain(
llm=OpenAI(temperature=0),
prompt=prompt,
verbose=True,
memory=ConversationBufferWindowMemory(k=2),
)
import speech_recognition as s... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-2 | engine.runAndWait()
listen(None)
Calibrating...
Okay, go!
listening now...
Recognizing...
C:\Users\jaden\AppData\Roaming\Python\Python310\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 .auton... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-3 | Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over t... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-4 | Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over t... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-5 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.
Assistant is aware that human ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-6 | Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-7 | Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-li... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-8 | Human: I'd like to learn more about neural networks.
AI: Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are oft... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-9 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.
Assistant is aware that human ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-10 | > Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assis... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-11 | Human: Tell me about a brand new discovered bird species.
AI: A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-12 | Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-13 | Human: Tell me a children's story about the importance of honesty and trust.
AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-14 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.
Assistant is aware that human ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-15 | Assistant:
> Finished chain.
You're welcome!
listening now...
Recognizing...
Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?
> Entering new LLMChain chain... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-16 | Human: Wow, Assistant, that was a really good story. Congratulations!
AI: Thank you! I'm glad you enjoyed it.
Human: Thank you.
AI: You're welcome!
Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq t... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-17 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.
Assistant is aware that human ... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-18 | Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-li... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-19 | AI: Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share musi... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
d6571d1d9e03-20 | 521 break
--> 523 buffer = source.stream.read(source.CHUNK)
524 if len(buffer) == 0: break # reached end of the stream
525 frames.append(buffer)
File c:\ProgramData\miniconda3\envs\lang\lib\site-packages\speech_recognition\__init__.py:199, in Microphone.MicrophoneStream.read(self, size)
198 def read(se... | https://python.langchain.com/en/latest/use_cases/chatbots/voice_assistant.html |
99684fe40902-0 | .ipynb
.pdf
Using Hugging Face Datasets
Contents
Setup
Examples
Predictions
Evaluation
Using Hugging Face Datasets#
This example shows how to use Hugging Face datasets to evaluate models. Specifically, we show how to load examples to evaluate models on from Hugging Face’s dataset package.
Setup#
For demonstration pur... | https://python.langchain.com/en/latest/use_cases/evaluation/huggingface_datasets.html |
99684fe40902-1 | 'You will not digest the watermelon seeds',
'The watermelon seeds will be excreted'],
'incorrect_answers': ['You grow watermelons in your stomach',
'You get sick',
'You have bad dreams',
'You die',
'You get indigestion',
'You fall unconscious',
'You digest the watermelon seeds'],
'source': 'https://wond... | https://python.langchain.com/en/latest/use_cases/evaluation/huggingface_datasets.html |
99684fe40902-2 | from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(examples, predictions, question_key="question", answer_key="best_answer", prediction_key="text")
graded_outputs
[{'text': ' INCORRECT'},
{'text': ' INCORRECT'},
{'tex... | https://python.langchain.com/en/latest/use_cases/evaluation/huggingface_datasets.html |
59e9c7097436-0 | .ipynb
.pdf
QA Generation
QA Generation#
This notebook shows how to use the QAGenerationChain to come up with question-answer pairs over a specific document.
This is important because often times you may not have data to evaluate your question-answer system over, so this is a cheap and lightweight way to generate it!
f... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_generation.html |
0d193d0cd997-0 | .ipynb
.pdf
Question Answering Benchmarking: State of the Union Address
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Question Answering Benchmarking: State of the Union Address#
Here we go over how to benchmark performance on a question answering task over ... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_benchmarking_sota.html |
0d193d0cd997-1 | Now we can create a question answering chain.
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=vectorstore.as_retriever(), input_key="question")
Make a prediction#
First, we can make predictions one datapoint at a ... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_benchmarking_sota.html |
0d193d0cd997-2 | for i, prediction in enumerate(predictions):
prediction['grade'] = graded_outputs[i]['text']
from collections import Counter
Counter([pred['grade'] for pred in predictions])
Counter({' CORRECT': 7, ' INCORRECT': 4})
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for ... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_benchmarking_sota.html |
0c59ce9068f4-0 | .ipynb
.pdf
Evaluating an OpenAPI Chain
Contents
Load the API Chain
Optional: Generate Input Questions and Request Ground Truth Queries
Run the API Chain
Evaluate the requests chain
Evaluate the Response Chain
Generating Test Datasets
Evaluating an OpenAPI Chain#
This notebook goes over ways to semantically evaluate ... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-1 | See Generating Test Datasets at the end of this notebook for more details.
# import re
# from langchain.prompts import PromptTemplate
# template = """Below is a service description:
# {spec}
# Imagine you're a new user trying to use {operation} through a search bar. What are 10 different things you want to request?
# W... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-2 | dataset
[{'question': 'What iPhone models are available?',
'expected_query': {'max_price': None, 'q': 'iPhone'}},
{'question': 'Are there any budget laptops?',
'expected_query': {'max_price': 300, 'q': 'laptop'}},
{'question': 'Show me the cheapest gaming PC.',
'expected_query': {'max_price': 500, 'q': 'gaming ... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-3 | chain_outputs = []
failed_examples = []
for question in questions:
try:
chain_outputs.append(api_chain(question))
scores["completed"].append(1.0)
except Exception as e:
if raise_error:
raise e
failed_examples.append({'q': question, 'error': e})
scores["complet... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-4 | 'Yes, there are several tablets under $400. These include the Apple iPad 10.2" 32GB (2019), Samsung Galaxy Tab A8 10.5 SM-X200 32GB, Samsung Galaxy Tab A7 Lite 8.7 SM-T220 32GB, Amazon Fire HD 8" 32GB (10th Generation), and Amazon Fire HD 10 32GB.',
'It looks like you are looking for the best headphones. Based on the ... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-5 | "I found several Nike and Adidas shoes in the API response. Here are the links to the products: Nike Dunk Low M - Black/White: https://www.klarna.com/us/shopping/pl/cl337/3200177969/Shoes/Nike-Dunk-Low-M-Black-White/?utm_source=openai&ref-site=openai_plugin, Nike Air Jordan 4 Retro M - Midnight Navy: https://www.klarna... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-6 | Jordan 1 Retro High OG M - True Blue/Cement Grey/White: https://www.klarna.com/us/shopping/pl/cl337/3204655673/Shoes/Nike-Air-Jordan-1-Retro-High-OG-M-True-Blue-Cement-Grey-White/?utm_source=openai&ref-site=openai_plugin, Nike Air Jordan 11 Retro Cherry - White/Varsity Red/Black: https://www.klarna.com/us/shopping/pl/c... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-7 | "I found several skirts that may interest you. Please take a look at the following products: Avenue Plus Size Denim Stretch Skirt, LoveShackFancy Ruffled Mini Skirt - Antique White, Nike Dri-Fit Club Golf Skirt - Active Pink, Skims Soft Lounge Ruched Long Skirt, French Toast Girl's Front Pleated Skirt with Tabs, Alexia... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-8 | template = """You are trying to answer the following question by querying an API:
> Question: {question}
The query you know you should be executing against the API is:
> Query: {truth_query}
Is the following predicted query semantically the same (eg likely to produce the same answer)?
> Predicted Query: {predict_query}... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-9 | ' The original query is asking for laptops with a maximum price of 300. The predicted query is asking for laptops with a minimum price of 0 and a maximum price of 500. This means that the predicted query is likely to return more results than the original query, as it is asking for a wider range of prices. Therefore, th... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-10 | " The original query is asking for the top rated laptops, so the 'size' parameter should be set to 10 to get the top 10 results. The 'min_price' parameter should be set to 0 to get results from all price ranges. The 'max_price' parameter should be set to null to get results from all price ranges. The 'q' parameter shou... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-11 | ' The first part of the query is asking for a Desktop PC, which is the same as the original query. The second part of the query is asking for a size of 10, which is not relevant to the original query. The third part of the query is asking for a minimum price of 0, which is not relevant to the original query. The fourth... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-12 | Evaluate this against the user’s original question.
from langchain.prompts import PromptTemplate
template = """You are trying to answer the following question by querying an API:
> Question: {question}
The API returned a response of:
> API result: {api_response}
Your response to the user: {answer}
Please evaluate the a... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-13 | request_eval_results
[' The original query is asking for all iPhone models, so the "q" parameter is correct. The "max_price" parameter is also correct, as it is set to null, meaning that no maximum price is set. The predicted query adds two additional parameters, "size" and "min_price". The "size" parameter is not nece... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-14 | ' The original query is asking for tablets under $400, so the first two parameters are correct. The predicted query also includes the parameters "size" and "min_price", which are not necessary for the original query. The "size" parameter is not relevant to the question, and the "min_price" parameter is redundant since ... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-15 | ' The original query is asking for a skirt, so the predicted query is asking for the same thing. The predicted query also adds additional parameters such as size and price range, which could help narrow down the results. However, the size parameter is not necessary for the query to be successful, and the price range is... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-16 | " The API response provided a list of laptops with their prices and attributes. The user asked if there were any budget laptops, and the response provided a list of laptops that are all priced under $500. Therefore, the response was accurate and useful in answering the user's question. Final Grade: A",
" The API respo... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-17 | ' The API response provided a list of shoes from both Adidas and Nike, which is exactly what the user asked for. The response also included the product name, price, and attributes for each shoe, which is useful information for the user to make an informed decision. The response also included links to the products, whic... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-18 | parsed_response_results = parse_eval_results(request_eval_results)
# Collect the scores for a final evaluation table
scores['result_synthesizer'].extend(parsed_response_results)
# Print out Score statistics for the evaluation session
header = "{:<20}\t{:<10}\t{:<10}\t{:<10}".format("Metric", "Min", "Mean", "Max")
print... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-19 | 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.
# List the paths in the OpenAPI Spec
paths = sorted(spec.paths.keys())
paths
['/v1/public/openai/explain-phrase',
'/v1/public/openai/explain-task',
'/v1/public/openai/transla... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-20 | additional_context?: string,
/* Full text of the user's question. */
full_query?: string,
}) => any;
# Compress the service definition to avoid leaking too much input structure to the sample data
template = """In 20 words or less, what does this service accomplish?
{spec}
Function: It's designed to """
prompt = Promp... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-21 | "I'm looking for the Dutch word for 'no'.",
"Can you explain the meaning of 'hello' in Japanese?",
"I need help understanding the Russian word for 'thank you'.",
"Can you tell me how to say 'goodbye' in Chinese?",
"I'm trying to learn the Arabic word for 'please'."]
# Define the generation chain to get hypotheses
a... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-22 | '{"task_description": "Help with pronunciation of \'yes\' in Portuguese", "learning_language": "Portuguese", "native_language": "English", "full_query": "Can you help me with the pronunciation of \'yes\' in Portuguese?"}',
'{"task_description": "Find the Dutch word for \'no\'", "learning_language": "Dutch", "native_la... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-23 | ground_truth = []
for query, request_arg in list(zip(queries, request_args)):
feedback = input(f"Query: {query}\nRequest: {request_arg}\nRequested changes: ")
if feedback == 'n' or feedback == 'none' or not feedback:
ground_truth.append(request_arg)
continue
resolved = correction_chain.run(r... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-24 | Query: Can you help me with the pronunciation of 'yes' in Portuguese?
Request: {"task_description": "Help with pronunciation of 'yes' in Portuguese", "learning_language": "Portuguese", "native_language": "English", "full_query": "Can you help me with the pronunciation of 'yes' in Portuguese?"}
Requested changes:
Query... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-25 | Requested changes:
Query: I'm trying to learn the Arabic word for 'please'.
Request: {"task_description": "Learn the Arabic word for 'please'", "learning_language": "Arabic", "native_language": "English", "full_query": "I'm trying to learn the Arabic word for 'please'."}
Requested changes:
Now you can use the ground_... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
0c59ce9068f4-26 | '{"task_description": "Explain the meaning of \'hello\' in Japanese", "learning_language": "Japanese", "native_language": "English", "full_query": "Can you explain the meaning of \'hello\' in Japanese?"}',
'{"task_description": "understanding the Russian word for \'thank you\'", "learning_language": "Russian", "native... | https://python.langchain.com/en/latest/use_cases/evaluation/openapi_eval.html |
1f0d5b362384-0 | .ipynb
.pdf
LLM Math
Contents
Setting up a chain
LLM Math#
Evaluating chains that know how to do math.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("llm-math")
Downloading and prepar... | https://python.langchain.com/en/latest/use_cases/evaluation/llm_math.html |
1f0d5b362384-1 | sum(correct) / len(correct)
1.0
for i, example in enumerate(dataset):
print("input: ", example["question"])
print("expected output :", example["answer"])
print("prediction: ", numeric_output[i])
input: 5
expected output : 5.0
prediction: 5.0
input: 5 + 3
expected output : 8.0
prediction: 8.0
input: 2^3... | https://python.langchain.com/en/latest/use_cases/evaluation/llm_math.html |
1f0d5b362384-2 | next
Evaluating an OpenAPI Chain
Contents
Setting up a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/evaluation/llm_math.html |
109ae1d3b643-0 | .ipynb
.pdf
Agent VectorDB Question Answering Benchmarking
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Agent VectorDB Question Answering Benchmarking#
Here we go over how to benchmark performance on a question answering task using an agent to route between... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_vectordb_sota_pg.html |
109ae1d3b643-1 | dataset[-1]
{'question': 'What is the purpose of YC?',
'answer': 'The purpose of YC is to cause startups to be founded that would not otherwise have existed.',
'steps': [{'tool': 'Paul Graham QA System', 'tool_input': None},
{'tool': None, 'tool_input': 'What is the purpose of YC?'}]}
Setting up a chain#
Now we nee... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_vectordb_sota_pg.html |
109ae1d3b643-2 | from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
tools = [
Tool(
name = "State of Union QA System",
func=chain_sota.run,
description="useful for when you need to answer questions about the most recent state of the union address. Input should be a ful... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_vectordb_sota_pg.html |
109ae1d3b643-3 | 'output': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'}
Next, we can use a language model to score them programatically
from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evalu... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_vectordb_sota_pg.html |
109ae1d3b643-4 | Benchmarking Template
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/evaluation/agent_vectordb_sota_pg.html |
ac2d771a094d-0 | .ipynb
.pdf
Agent Benchmarking: Search + Calculator
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Agent Benchmarking: Search + Calculator#
Here we go over how to benchmark performance of an agent on tasks where it has access to a calculator and a search tool... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_benchmarking.html |
ac2d771a094d-1 | predictions = []
predicted_dataset = []
error_dataset = []
for data in dataset:
new_data = {"input": data["question"], "answer": data["answer"]}
try:
predictions.append(agent(new_data))
predicted_dataset.append(new_data)
except Exception as e:
predictions.append({"output": str(e), **... | https://python.langchain.com/en/latest/use_cases/evaluation/agent_benchmarking.html |
943f569a4350-0 | .ipynb
.pdf
Generic Agent Evaluation
Contents
Setup
Testing the Agent
Evaluating the Agent
Generic Agent Evaluation#
Good evaluation is key for quickly iterating on your agent’s prompts and tools. Here we provide an example of how to use the TrajectoryEvalChain to evaluate your agent.
Setup#
Let’s start by defining o... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-1 | memory_key="chat_history", return_messages=True, output_key="output"
)
llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo")
agent = initialize_agent(
tools,
llm,
agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,
verbose=True,
memory=memory,
return_intermediate_steps=True, # This is n... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-2 | > Entering new AgentExecutor chain...
{
"action": "Calculator",
"action_input": "The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-3 | }
> Entering new LLMMathChain chain...
The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-4 | )
print("Score from 1 to 5: ", evaluation["score"])
print("Reasoning: ", evaluation["reasoning"])
Score from 1 to 5: 1
Reasoning: First, let's evaluate the final answer. The final answer is incorrect because it uses the volume of golf balls instead of ping pong balls. The answer is not helpful.
Second, does the model... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-5 | )
print("Score from 1 to 5: ", evaluation["score"])
print("Reasoning: ", evaluation["reasoning"])
Score from 1 to 5: 3
Reasoning: i. Is the final answer helpful?
Yes, the final answer is helpful as it provides an approximate number of Eiffel Towers needed to cover the US from coast to coast.
ii. Does the AI language ... | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
943f569a4350-6 | Setup
Testing the Agent
Evaluating the Agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/evaluation/generic_agent_evaluation.html |
cf420ff1c6b5-0 | .ipynb
.pdf
Question Answering
Contents
Setup
Examples
Predictions
Evaluation
Customize Prompt
Evaluation without Ground Truth
Comparing to other evaluation metrics
Question Answering#
This notebook covers how to evaluate generic question answering problems. This is a situation where you have an example containing a ... | https://python.langchain.com/en/latest/use_cases/evaluation/question_answering.html |
cf420ff1c6b5-1 | predictions = chain.apply(examples)
predictions
[{'text': ' 11 tennis balls'},
{'text': ' No, this sentence is not plausible. Joao Moutinho is a professional soccer player, not an American football player, so it is not likely that he would be catching a screen pass in the NFC championship.'}]
Evaluation#
We can see th... | https://python.langchain.com/en/latest/use_cases/evaluation/question_answering.html |
cf420ff1c6b5-2 | Real Answer: No
Predicted Answer: No, this sentence is not plausible. Joao Moutinho is a professional soccer player, not an American football player, so it is not likely that he would be catching a screen pass in the NFC championship.
Predicted Grade: CORRECT
Customize Prompt#
You can also customize the prompt that i... | https://python.langchain.com/en/latest/use_cases/evaluation/question_answering.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.