id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 59 127 |
|---|---|---|
8b679e615745-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_benchmarking.html |
8b679e615745-1 | 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), **... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_benchmarking.html |
c970e7110d16-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/llm_math.html |
c970e7110d16-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/llm_math.html |
c970e7110d16-2 | next
Evaluating an OpenAPI Chain
Contents
Setting up a chain
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/llm_math.html |
fe807935f65b-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/huggingface_datasets.html |
fe807935f65b-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/huggingface_datasets.html |
fe807935f65b-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/huggingface_datasets.html |
7ceaa4c01233-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
7ceaa4c01233-1 | {'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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
7ceaa4c01233-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/sql_qa_benchmarking_chinook.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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'... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-3 | Real Answer: The Ukrainian Ambassador to the United States is here tonight.
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,... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
5f6ac6e4f46e-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/data_augmented_question_answering.html |
e47d9152bef2-0 | .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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/question_answering.html |
e47d9152bef2-1 | 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 that if we tried to just do exact matc... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/question_answering.html |
e47d9152bef2-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/question_answering.html |
e47d9152bef2-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/question_answering.html |
e47d9152bef2-4 | 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(
... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/question_answering.html |
4e48092ef1df-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-6 | Nike Air Jordan 11 Retro Cherry - White/Varsity Red/Black: https://www.klarna.com/us/shopping/pl/cl337/3202929696/Shoes/Nike-Air-Jordan-11-Retro-Cherry-White-Varsity-Red-Black/?utm_source=openai&ref-site=openai_plugin, Nike Dunk High W - White/Black: https://www.klarna.com/us/shopping/pl/cl337/3201956448/Shoes/Nike-Dun... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-8 | from langchain.prompts import PromptTemplate
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 sam... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-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_... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
4e48092ef1df-26 | '{"task_description": "Find the Dutch word for \'no\'", "learning_language": "Dutch", "native_language": "English", "full_query": "I\'m looking for the Dutch word for \'no\'."}',
'{"task_description": "Explain the meaning of \'hello\' in Japanese", "learning_language": "Japanese", "native_language": "English", "full_q... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/openapi_eval.html |
934dc6a3e200-0 | .ipynb
.pdf
AutoGPT
Contents
Set up tools
Set up memory
Setup model and AutoGPT
Run an example
Chat History Memory
AutoGPT#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT but with LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)
Set up tools#
We’ll set up an AutoGPT wi... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/autogpt.html |
934dc6a3e200-1 | ai_name="Tom",
ai_role="Assistant",
tools=tools,
llm=ChatOpenAI(temperature=0),
memory=vectorstore.as_retriever()
)
# Set verbose to be true
agent.chain.verbose = True
Run an example#
Here we will make it write a weather report for SF
agent.run(["write a weather report for SF today"])
Chat History Memor... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/autogpt.html |
e5f078cfacff-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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi.html |
e5f078cfacff-1 | 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=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations
)
baby_agi({"obje... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi.html |
e5f078cfacff-2 | *****TASK LIST*****
3: Check the current UV index in San Francisco.
4: Check the current air quality in San Francisco.
5: Check the current precipitation levels in San Francisco.
6: Check the current cloud cover in San Francisco.
7: Check the current barometric pressure in San Francisco.
8: Check the current dew point ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi.html |
5e987ffa8a85-0 | .ipynb
.pdf
BabyAGI with Tools
Contents
Install and Import Required Modules
Connect to the Vector Store
Define the Chains
Run the BabyAGI
BabyAGI with Tools#
This notebook builds on top of baby agi, but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. B... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-1 | Task creation chain to select new tasks to add to the list
Task prioritization chain to re-prioritize tasks
Execution Chain to execute the tasks
NOTE: in this notebook, the Execution chain will now be an agent.
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
from langchain import OpenAI, SerpAPIWrapper,... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-2 | llm_chain = LLMChain(llm=llm, prompt=prompt)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)
agent_executor = AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, verbose=True
)
Run the BabyAGI#
Now it’s time to create the BabyAGI controller a... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-3 | 9. Submit the report I now know the final answer
Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather tre... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-4 | Thought: I need to search for current weather conditions in San Francisco
Action: Search
Action Input: Current weather conditions in San FranciscoCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ... I nee... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-5 | 10: Summarize the weather report in a concise manner;
11: Include a summary of the forecasted weather conditions;
12: Include a summary of the current weather conditions;
13: Include a summary of the historical weather patterns;
14: Include a summary of the potential weather-related hazards;
15: Include a summary of th... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
5e987ffa8a85-6 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/baby_agi_with_agent.html |
cb88c78a36e9-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-2 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-3 | 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 = [... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-4 | 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 from the human
]
agent =... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-5 | "criticism": "None",
"speak": "I will use the DuckDuckGo Search command to find the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "DuckDuckGo Search",
"args": {
"query": "winning Boston Marathon times for the past 5 years ending in 2022"
... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-6 | "reasoning": "The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more accurate and comprehensive results.",
"plan": "- Use query_webpage command to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-7 | "file_path": "boston_marathon_winners.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"
}
}
}
{
"thoughts": {
"text": "I have retrieved the winning Boston Marathon ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-8 | }
}
}
{
"thoughts": {
"text": "I have found the winning Boston Marathon times for the past five years ending in 2022. Next, I need to create a table with the year, name, country of origin, and times.",
"reasoning": "Generating a table will help organize the information in a structured format.",
... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-9 | "criticism": "None",
"speak": "I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "process_csv",
"args": {
"csv_file_path": "winning_times.csv",
"instructions": "Re... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-10 | 0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
> Finished chain.
{
... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-11 | Action Input: df.head()
Observation: Year Name Country Time
0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
cb88c78a36e9-12 | "command": {
"name": "finish",
"args": {
"response": "I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete."
}
}
}
'I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.'
Contents
... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/marathon_times.html |
3b6255c1a6c7-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-1 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-2 | ####
{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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-3 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-4 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-5 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-6 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-7 | 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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-8 | Human: Provide a systematic argument for why we should always eat pasta with olives.
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 ... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
3b6255c1a6c7-9 | Second, the olives add a bit of texture to the dish.
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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/autonomous_agents/meta_prompt.html |
dcd511091652-0 | .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... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/question_answering/semantic-search-over-chat.html |
dcd511091652-1 | 3. Ingest chat embeddings#
We load the messages in the text file, chunk and upload to ActiveLoop Vector store.
with open("messages.txt") as f:
state_of_the_union = f.read()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
pages = text_splitter.split_text(state_of_the_union)
text_splitter = Re... | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/question_answering/semantic-search-over-chat.html |
d4f836f4fac3-0 | .md
.pdf
YouTube
Contents
⛓️Official LangChain YouTube channel⛓️
Introduction to LangChain with Harrison Chase, creator of LangChain
Videos (sorted by views)
YouTube#
This is a collection of LangChain videos on YouTube.
⛓️Official LangChain YouTube channel⛓️#
Introduction to LangChain with Harrison Chase, creator of ... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
d4f836f4fac3-1 | Run BabyAGI with Langchain Agents (with Python Code) by 1littlecoder
How to Use Langchain With Zapier | Write and Send Email with GPT-3 | OpenAI API Tutorial by StarMorph AI
Use Your Locally Stored Files To Get Response From GPT - OpenAI | Langchain | Python by Shweta Lodha
Langchain JS | How to Use GPT-3, GPT-4 to Ref... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
d4f836f4fac3-2 | LangChain. Crear aplicaciones Python impulsadas por GPT by Jesús Conde
Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial by Rachel Woods
BabyAGI + GPT-4 Langchain Agent with Internet Access by tylerwhatsgood
Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI by Arnoldas Kemekl... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
d4f836f4fac3-3 | ⛓️ Build your own custom LLM application with Bubble.io & Langchain (No Code & Beginner friendly) by No Code Blackbox
⛓️ Simple App to Question Your Docs: Leveraging Streamlit, Hugging Face Spaces, LangChain, and Claude! by Chris Alexiuk
⛓️ LANGCHAIN AI- ConstitutionalChainAI + Databutton AI ASSISTANT Web App by Avra
⛓... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
d4f836f4fac3-4 | ⛓️ Summarizing and Querying Multiple Papers with LangChain by Automata Learning Lab
⛓️ Using Langchain (and Replit) through Tana, ask Google/Wikipedia/Wolfram Alpha to fill out a table by Stian Håklev
⛓️ Langchain PDF App (GUI) | Create a ChatGPT For Your PDF in Python by Alejandro AO - Software & Ai
⛓️ Auto-GPT with L... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
d4f836f4fac3-5 | Videos (sorted by views)
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/youtube.html |
3116a252bb86-0 | .ipynb
.pdf
Model Comparison
Model Comparison#
Constructing your language model application will likely involved choosing between many different options of prompts, models, and even chains to use. When doing so, you will want to compare these different options on different inputs in an easy, flexible, and intuitive way... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/model_laboratory.html |
3116a252bb86-1 | pink
prompt = PromptTemplate(template="What is the capital of {state}?", input_variables=["state"])
model_lab_with_prompt = ModelLaboratory.from_llms(llms, prompt=prompt)
model_lab_with_prompt.compare("New York")
Input:
New York
OpenAI
Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p'... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/model_laboratory.html |
3116a252bb86-2 | names = [str(open_ai_llm), str(cohere_llm)]
model_lab = ModelLaboratory(chains, names=names)
model_lab.compare("What is the hometown of the reigning men's U.S. Open champion?")
Input:
What is the hometown of the reigning men's U.S. Open champion?
OpenAI
Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tok... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/model_laboratory.html |
3116a252bb86-3 | So the final answer is:
Carlos Alcaraz
previous
Tracing
next
YouTube
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/model_laboratory.html |
ac052675d58d-0 | .md
.pdf
Tracing
Contents
Tracing Walkthrough
Changing Sessions
Tracing#
By enabling tracing in your LangChain runs, you’ll be able to more effectively visualize, step through, and debug your chains and agents.
First, you should install tracing and set up your environment properly.
You can use either a locally hosted... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/tracing.html |
ac052675d58d-1 | Changing Sessions#
To initially record traces to a session other than "default", you can set the LANGCHAIN_SESSION environment variable to the name of the session you want to record to:
import os
os.environ["LANGCHAIN_TRACING"] = "true"
os.environ["LANGCHAIN_SESSION"] = "my_session" # Make sure this session actually ex... | rtdocs_stable/api.python.langchain.com/en/stable/additional_resources/tracing.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.