id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
f978e335bd29-6 | 10. Proofread the report for typos and errors I now know the final answer
Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding j... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
b5f66f0521b8-0 | .ipynb
.pdf
Meta-Prompt
Contents
Setup
Specify a task and interact with the agent
Meta-Prompt#
This is a LangChain implementation of Meta-Prompt, by Noah Goodman, for building self-improving agents.
The key idea behind Meta-Prompt is to prompt the agent to reflect on its own performance and modify its own instruction... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-1 | Repeat.
The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it modifies for itself each time. Despite its simplicity, this agent can learn over time and self-impro... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-2 | ####
{chat_history}
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next re... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-3 | chain = initialize_chain(instructions, memory=None)
output = chain.predict(human_input=task)
for j in range(max_iters):
print(f'(Step {j+1}/{max_iters})')
print(f'Assistant: {output}')
print(f'Human: ')
human_input = input()
if any(phrase in hu... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-4 | Human:
You response is not in the form of a poem. Try again!
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: None
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-5 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor tha... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-6 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor tha... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-7 | Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
New Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-8 | AI:
Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.
First, the olives add a salty flavor that be sure to please.
The briny taste be sure to tantalize yer taste buds with ease.
Second, the olives add a bit of texture to the dish.
The crunchy bites be sure to make yer mouth water with a wish... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
b5f66f0521b8-9 | The crunchy bites be sure to make yer mouth water with a wish.
Third, the olives add a bit of color to the plate.
The vibrant green be sure to make yer eyes appreciate.
So, me hearties, ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human: Your response is too... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
2cbc414472a7-0 | .ipynb
.pdf
BabyAGI User Guide
Contents
Install and Import Required Modules
Connect to the Vector Store
Run the BabyAGI
BabyAGI User Guide#
This notebook demonstrates how to implement BabyAGI by Yohei Nakajima. BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.
This guid... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
2cbc414472a7-1 | Now it’s time to create the BabyAGI controller and watch it try to accomplish your objective.
OBJECTIVE = "Write a weather report for SF today"
llm = OpenAI(temperature=0)
# Logging of LLMChains
verbose = False
# If None, will keep on going forever
max_iterations: Optional[int] = 3
baby_agi = BabyAGI.from_llm(
llm=... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
2cbc414472a7-2 | *****NEXT TASK*****
2: Check the current temperature in San Francisco
*****TASK RESULT*****
I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.
*****TASK LIST*****
3: Check the current UV index in San Francisco.
4: Check the current air qua... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
2887fe0f5c2e-0 | .ipynb
.pdf
AutoGPT example finding Winning Marathon Times
Contents
Set up tools
Set up memory
Setup model and AutoGPT
AutoGPT for Querying the Web
AutoGPT example finding Winning Marathon Times#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT
With LangChain primitives (LLMs, PromptTemplates, Vecto... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-1 | finally:
os.chdir(prev_dir)
@tool
def process_csv(
csv_file_path: str, instructions: str, output_path: Optional[str] = None
) -> str:
"""Process a CSV by with pandas in a limited REPL.\
Only use this after writing data to disk as a csv file.\
Any figures must be saved to disk to be viewed by the human... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-2 | script.extract()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
results = "\n".join(chunk for chunk in chunks if chunk)
except Exception as e:
resul... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-3 | def _run(self, url: str, question: str) -> str:
"""Useful for browsing websites and scraping the text information."""
result = browse_web_page.run(url)
docs = [Document(page_content=result, metadata={"source": url})]
web_docs = self.text_splitter.split_documents(docs)
results = [... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-4 | Setup model and AutoGPT#
Model set-up
# !pip install duckduckgo_search
web_search = DuckDuckGoSearchRun()
tools = [
web_search,
WriteFileTool(root_dir="./data"),
ReadFileTool(root_dir="./data"),
process_csv,
query_website_tool,
# HumanInputRun(), # Activate if you want the permit asking for help... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-5 | "plan": "- Use DuckDuckGo Search to find the winning Boston Marathon times\n- Generate a table with the year, name, country of origin, and times\n- Ensure there are no legal complications",
"criticism": "None",
"speak": "I will use the DuckDuckGo Search command to find the winning Boston Marathon times ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-6 | }
}
}
{
"thoughts": {
"text": "I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.",
"reasoning": "The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more a... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-7 | "criticism": "None",
"speak": "I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "write_file",
"args": {
"file_path": "boston_marathon_winners.csv",
"text"... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-8 | "file_path": "winning_boston_marathon_data.csv",
"text": "Year,Name,Country,Time\n2022,Evans Chebet,KEN,2:06:51\n2021,Benson Kipruto,KEN,2:09:51\n2019,Lawrence Cherono,KEN,2:07:57\n2018,Yuki Kawauchi,JPN,2:15:58\n"
}
}
}
{
"thoughts": {
"text": "I have found the winning Boston Marath... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-9 | }
}
}
{
"thoughts": {
"text": "I need to process the CSV file to generate the table with the year, name, country of origin, and winning times.",
"reasoning": "I have already written the data to a file named 'winning_times.csv'. Now, I need to process this CSV file to properly display the data as... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-10 | 3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
Observation: None
Thought:I used the wrong tool to perform the action. I should have used the given data and not interacted with the Python shell. I can now provide the displayed data as the answer si... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-11 | },
"command": {
"name": "process_csv",
"args": {
"csv_file_path": "winning_times.csv",
"instructions": "Read the CSV file and display the data as a table"
}
}
}
> Entering new AgentExecutor chain...
Thought: Since the data is already loaded in a pandas dataframe, ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
2887fe0f5c2e-12 | "reasoning": "I have completed the required actions and obtained the desired data. The task is complete.",
"plan": "- Use the finish command",
"criticism": "None",
"speak": "I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete."
},
"comman... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
ac5ab922eafa-0 | .ipynb
.pdf
Question Answering Benchmarking: Paul Graham Essay
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Question Answering Benchmarking: Paul Graham Essay#
Here we go over how to benchmark performance on a question answering task over a Paul Graham essa... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_benchmarking_pg.html |
ac5ab922eafa-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_pg.html |
ac5ab922eafa-2 | from collections import Counter
Counter([pred['grade'] for pred in predictions])
Counter({' CORRECT': 12, ' INCORRECT': 10})
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for pred in predictions if pred['grade'] == " INCORRECT"]
incorrect[0]
{'question': 'What did the a... | https://python.langchain.com/en/latest/use_cases/evaluation/qa_benchmarking_pg.html |
9f7c1b371b2b-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 |
9f7c1b371b2b-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 |
5b52e1efeaf5-0 | .ipynb
.pdf
SQL Question Answering Benchmarking: Chinook
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
SQL Question Answering Benchmarking: Chinook#
Here we go over how to benchmark performance on a question answering task over a SQL database.
It is highly r... | https://python.langchain.com/en/latest/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
5b52e1efeaf5-1 | {'question': 'How many employees are there?', 'answer': '8'}
Setting up a chain#
This uses the example Chinook database.
To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository.
Note that here we load a simple c... | https://python.langchain.com/en/latest/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
5b52e1efeaf5-2 | llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(predicted_dataset, predictions, question_key="question", prediction_key="result")
We can add in the graded output to the predictions dict and then get a count of the grades.
for i, prediction in enumerate(predictions... | https://python.langchain.com/en/latest/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
ff1b33b6ae76-0 | .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 |
ff1b33b6ae76-1 | 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 |
ff1b33b6ae76-2 | 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 |
ff1b33b6ae76-3 | context_examples = [
{
"question": "How old am I?",
"context": "I am 30 years old. I live in New York and take the train to work everyday.",
},
{
"question": 'Who won the NFC championship game in 2023?"',
"context": "NFC Championship Game 2023: Philadelphia Eagles 31, San Fra... | https://python.langchain.com/en/latest/use_cases/evaluation/question_answering.html |
ff1b33b6ae76-4 | predictions[i]['id'] = str(i)
predictions[i]['prediction_text'] = predictions[i]['text']
for p in predictions:
del p['text']
new_examples = examples.copy()
for eg in new_examples:
del eg ['question']
del eg['answer']
from evaluate import load
squad_metric = load("squad")
results = squad_metric.compute(
... | https://python.langchain.com/en/latest/use_cases/evaluation/question_answering.html |
b0e5a2af4753-0 | .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 |
d8f1606b10c3-0 | .ipynb
.pdf
Data Augmented Question Answering
Contents
Setup
Examples
Evaluate
Evaluate with Other Metrics
Data Augmented Question Answering#
This notebook uses some generic prompts/language models to evaluate an question answering system that uses other sources of data besides what is in the model. For example, this... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-1 | "answer": "Nothing"
}
]
# Generated examples
from langchain.evaluation.qa import QAGenerateChain
example_gen_chain = QAGenerateChain.from_llm(OpenAI())
new_examples = example_gen_chain.apply_and_parse([{"doc": t} for t in texts[:5]])
new_examples
[{'query': 'According to the document, what did Vladimir Putin miscal... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-2 | eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(examples, predictions)
for i, eg in enumerate(examples):
print(f"Example {i}:")
print("Question: " + predictions[i]['query'])
print("Real Answer: " + predictions[i]['answer'])
print("Predicted Answer: " + predictions[i]['result'... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-3 | Predicted Answer: I don't know.
Predicted Grade: INCORRECT
Example 4:
Question: How many countries were part of the coalition formed to confront Putin?
Real Answer: 27 members of the European Union, France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzer... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-4 | Predicted Grade: CORRECT
Evaluate with Other Metrics#
In addition to predicting whether the answer is correct or incorrect using a language model, we can also use other metrics to get a more nuanced view on the quality of the answers. To do so, we can use the Critique library, which allows for simple calculation of va... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-5 | for k, v in metrics.items()
}
Finally, we can print out the results. We can see that overall the scores are higher when the output is semantically correct, and also when the output closely matches with the gold-standard answer.
for i, eg in enumerate(examples):
score_string = ", ".join([f"{k}={v['examples'][i]['val... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-6 | Example 2:
Question: According to the document, what did Vladimir Putin miscalculate?
Real Answer: He miscalculated that he could roll into Ukraine and the world would roll over.
Predicted Answer: Putin miscalculated that the world would roll over when he rolled into Ukraine.
Predicted Scores: rouge=0.5185, chrf=0.695... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
d8f1606b10c3-7 | Question: What action is the U.S. Department of Justice taking to target Russian oligarchs?
Real Answer: The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and joining with European allies to find and seize their yachts, luxury apartments, and private jets.
P... | https://python.langchain.com/en/latest/use_cases/evaluation/data_augmented_question_answering.html |
c8c2dc4205f0-0 | .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 |
c8c2dc4205f0-1 | 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 |
c8c2dc4205f0-2 | 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 |
c8c2dc4205f0-3 | '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 |
c8c2dc4205f0-4 | 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 |
f0672ab75009-0 | .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 |
f0672ab75009-1 | 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 |
f0672ab75009-2 | 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 |
a9f87a034200-0 | .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 |
a9f87a034200-1 | 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 |
a9f87a034200-2 | 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 |
a9f87a034200-3 | 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 |
a9f87a034200-4 | '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 |
a9f87a034200-5 | "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 |
a9f87a034200-6 | 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 |
a9f87a034200-7 | "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 |
a9f87a034200-8 | 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 |
a9f87a034200-9 | ' 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 |
a9f87a034200-10 | " 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 |
a9f87a034200-11 | ' 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 |
a9f87a034200-12 | 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 |
a9f87a034200-13 | 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 |
a9f87a034200-14 | ' 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 |
a9f87a034200-15 | ' 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 |
a9f87a034200-16 | " 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 |
a9f87a034200-17 | ' 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 |
a9f87a034200-18 | 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 |
a9f87a034200-19 | 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 |
a9f87a034200-20 | 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 |
a9f87a034200-21 | "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 |
a9f87a034200-22 | '{"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 |
a9f87a034200-23 | 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 |
a9f87a034200-24 | 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 |
a9f87a034200-25 | 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 |
a9f87a034200-26 | '{"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 |
0a2cd3c4a537-0 | .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 |
0a2cd3c4a537-1 | 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 |
0a2cd3c4a537-2 | > 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 |
0a2cd3c4a537-3 | }
> 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 |
0a2cd3c4a537-4 | )
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 |
0a2cd3c4a537-5 | )
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 |
0a2cd3c4a537-6 | 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 |
2c6780f1e3b7-0 | .ipynb
.pdf
Benchmarking Template
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Benchmarking Template#
This is an example notebook that can be used to create a benchmarking notebook for a task of your choice. Evaluation is really hard, and so we greatly welc... | https://python.langchain.com/en/latest/use_cases/evaluation/benchmarking_template.html |
2c6780f1e3b7-1 | # Othertimes you may want to write a for loop to catch errors
Evaluate performance#
Any guide to evaluating performance in a more systematic manner goes here.
previous
Agent VectorDB Question Answering Benchmarking
next
Data Augmented Question Answering
Contents
Loading the data
Setting up a chain
Make a prediction... | https://python.langchain.com/en/latest/use_cases/evaluation/benchmarking_template.html |
52177689ee8d-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 |
52177689ee8d-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 |
52177689ee8d-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 |
06b23ebbafa8-0 | .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 |
06b23ebbafa8-1 | '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 |
06b23ebbafa8-2 | 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 |
c6e8a7ce0a5b-0 | .ipynb
.pdf
Question answering over a group chat messages
Contents
1. Install required packages
2. Add API keys
2. Create sample data
3. Ingest chat embeddings
4. Ask questions
Question answering over a group chat messages#
In this tutorial, we are going to use Langchain + Deep Lake with GPT4 to semantically search a... | https://python.langchain.com/en/latest/use_cases/question_answering/semantic-search-over-chat.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.