promptwizard
v1.0.0
Prompt Wizard adalah paket untuk mengevaluasi permintaan khusus menggunakan berbagai metode evaluasi. Ini memungkinkan Anda untuk memberikan petunjuk Anda sendiri atau menghasilkannya secara otomatis dan kemudian mendapatkan hasilnya dalam file JSON.
Untuk menggunakan prompt wizard, Anda perlu menginstal paket dan semua dependensinya menggunakan PIP
pip install promptwizardAtau, klon repositori menggunakan git clone https://github.com/leniolabs/promptwiz.git
Untuk menjalankan prompt wizard, Anda harus mengatur dan menentukan kunci API openai Anda. Anda dapat menghasilkan satu di https://platform.openai.com/account/api-keys. Setelah Anda mendapatkan kunci API, tentukannya menggunakan variabel lingkungan openai_api_key. Perhatikan biaya yang terkait dengan penggunaan API saat menjalankan Eval.
Sebelum menggunakan prompt wizard, Anda harus mendefinisikan variabel lingkungan Anda. Anda memiliki dua opsi yang valid, mintalah OPENAI_API_KEY Anda didefinisikan dalam .env di folder yang benar, atau, jika Anda memutuskan untuk menggunakan azure Anda perlu mendefinisikan OPENAI_API_TYPE Anda sebagai azure dan OPENAI_API_BASE Anda dan OPENAI_API_VERSION dengan benar di .env Anda selain dari OPENAI_API_KEY .
Anda memiliki dua alternatif penggunaan.
Jika Anda ingin menggunakan file YAML:
Pastikan Anda memiliki file YAML dengan petunjuk yang ingin Anda evaluasi. File YAML harus mengikuti struktur yang tepat.
promptwizard YAML_FILE_PATHpromptwizard YAML_FILE_PATH --env_path .env_FILE_PATHTanggapi 'y' ketika ditanya apakah Anda ingin melanjutkan.
output.json di folder yang sama dengan file YAML. Jika Anda memilih metode ELO untuk evaluasi yang cepat, sebaran plot scatter_plot.png juga akan disimpan dalam folder yang sama dengan file YAML. Sejumlah besar file juga akan dihasilkan jika Anda telah ditunjukkan dalam file YAML Anda yang ingin Anda lakukan iterasi.Jika variabel "prompt" tidak didefinisikan dalam file YAML, program akan secara otomatis menghasilkan petunjuk untuk evaluasi.
Jalankan paket yang meneruskan file YAML Anda sebagai parameter:
promptwizard YAML_FILE_PATHTanggapi 'y' ketika ditanya apakah Anda ingin melanjutkan.
output.json di folder yang sama dengan folder YAML. Jika Anda memilih metode ELO untuk evaluasi yang cepat, sebaran plot scatter_plot.png juga akan disimpan dalam folder yang sama dengan file YAML.Anda juga dapat menggunakannya dalam skrip Python Anda:
import promptwizardDan menggunakan berbagai fungsi yang dapat diberikan oleh PromptWizard, seperti misalnya:
# Example of using PromptWizard
from promptwizard import prompt_generation
test_cases = [
{ ' input ' : ' How do you make a classic spaghetti carbonara? ' , ' output ' : ' REPLY ' },
{ ' input ' : " What is John Smith's phone number? " , ' output ' : ' NOT_REPLY ' },
]
description = " Decide whether the question should be answered or not. " # A short description of the type of task for the test cases.
system_gen_prompt = " " " Your job is to generate system prompts for GPT, given a description of the use-case and some test cases.
In your generated prompt, you should describe how the AI should behave in plain English. Include what it will see, and what it's allowed to output. Be creative with prompts to get the best possible results. The AI knows it's an AI -- you don't need to tell it this.
Remember that the prompt should only allow the AI to answer the answer and nothing else. No explanation is necessary.
You will be graded based on the performance of your prompt... but don't cheat! You cannot include specifics about the test cases in your prompt. Any prompts with examples will be disqualified. I repeat, do not include the test cases.
Most importantly, output NOTHING but the prompt. Do not include anything else in your message. " " " # Here you have to indicate to the LLM how your generated prompts should be. This example is useful if you later want to use the equals evaluation method.
# Create 4 prompts.
prompts = prompt_generation.generate_candidate_prompts(system_gen_prompt, test_cases, description)[0]
Jika Anda mau, Anda juga dapat menentukan jumlah iterasi yang ingin Anda lakukan pada petunjuk yang disediakan atau yang akan dihasilkan secara otomatis untuk mendapatkan petunjuk yang mencapai perilaku optimal untuk model bahasa. Di sisi lain, penggunaan fungsi untuk mengulangi petunjuk untuk skrip Python Anda tersedia:
from promptwizard.prompt_generation import iteration
results = iteration.iterations(test_cases, method= ' Elo ' , prompts=old_prompts, number_of_prompts=3)Kami memberi Anda penjelasan tentang struktur yang valid dari file YAML Anda dan batasan tertentu untuk beberapa variabel di dalamnya. Kami menyarankan Anda membacanya dengan cermat sebelum menjalankan evaluasi.
Berikut ini adalah struktur yang harus dimiliki file YAML Anda.
test:
cases: " " " Here, you have to put the test cases you are going to use to evaluate your prompts. If you are going to use the
Elo method to evaluate them, it should be just a list of strings. If you are going to use the methods classification,
equal or includes, it should be a list of tuples with two elements, where the first element is the test case and the
second element is the correct response to the test. Remember that if you decide to use classification, only a boolean
value is allowed as a response. the form of your test cases has to be, in case of selecting the Elo method:
-'Test1'
-'Test2'...
If you choose the methods Classification, Equals, Includes, Semantic Similarity or LogProbs they must be of the form:
-input: 'Test1'
output: 'Answer1'
-input: 'Test2'
output: 'Answer2'
In case the method is Function Calling:
-input: 'Test1'
output1: 'name_function'
output2: 'variable'
-input: 'Test2'
output1: 'name_function'
output2: 'variable'
If you choose Code Generation:
- input: 'Test1'
arguments: (arg1,) in case there is only one argument, (arg1, arg2,...) in case there are more than one argument.
output: res
and finally if you choose JSON Validation:
- input: 'Test1'
output: json_output " " "
description: " " " Here is the description of the type of task that summarizes the test cases. You only have to use this field if
you are going to use the 'Elo' method " " "
method: " " " Here, you select the evaluation method for your prompts. You must choose between 'Elo',
'Classification', 'Equals', 'Includes', 'Function Calling', 'Code Generation' 'JSON Validation', 'Semantic Similarity' and 'LogProbs'. " " "
model:
name: " " " The name of the GPT model you will use to evaluate the prompts. " " "
temperature: " " " The temperature of the GPT model you will use to evaluate the prompts. " " "
max_tokens: " " " The maximum number of tokens you will allow the GPT model to use to generate the response to the test. " " "
functions: " " " This field must only be filled out in case the 'Function Calling' method is intended to be used.
If another method is used, it must not be filled out. The structure is a JSON object. Let's break down the different components:
- Function Name (name): This is the identifier used to refer to this function within the context of your code.
- Function Description (description): A brief description of what the function does.
- Function Parameters (parameters): This section defines the input parameters that the function accepts.
- Type (type): The type of the parameter being defined.
- Properties (properties): This is an object containing properties that the input parameter object should have.
- File Type (file_type): This is a property of the parameter object.
- Enum (enum): An enumeration of allowed values for the 'file_type' property. (optional)
- Description (description): A description of what the 'file_type' property represents.
- Required (required): An array listing the properties that are required within the parameter object. (optional) " " "
function_call: " " " This field must only be filled out in case the 'Function Calling' method is intended to be
used. If another method is used, it must not be filled out. " " "
prompts: " " " You have two options, either provide your list of prompts or generate them following the instructions below. " " "
list: " " " A list of prompts you want to evaluate. If you want to generate them with the prompt generator, don't use this field.
Please provide a minimum number of 4 prompts. Your prompts must be listed as follows:
- 'Prompt1'
- 'Prompt2'... " " "
generation:
number: " " " The number of prompts you are going to evaluate. You need to provide this key value only if you are going to generate the prompts. Indicate the quantity of prompts you want to generate. Please provide a minimum number of 4 prompts. If you do not define this key by default, 4 prompts will be created. " " "
constraints: " " " If you are going to generate prompts, this optional feature allows you to add special characteristics to the prompts that will be generated. For example, if you want prompts with a maximum length of 50 characters, simply complete with 'Generate prompts with a maximum length of 50 characters'. If you don't want to use it, you don't need to have this key defined. " " "
description: " " " Here is the description of the type of task that summarizes the test cases. If you use the 'Elo' method you mustn't use this field. " " "
best_prompts: " " " The number of prompts you want to iterate over and on which you want to highlight the final results. the value must be between 2 and the number of prompts you provide (or generate) minus one. If you do not define this value the default value will be 2. " " "
model:
name: " " " The name of the GPT model you will use to generate the prompts. " " "
temperature: " " " The temperature of the GPT model you will use to generate the prompts. " " "
max_tokens: " " " The maximum number of tokens you will allow the GPT model to use to generate your prompts. " " "
iterations:
number: " " " The number of iterations you want to perform on the best prompts obtained in your initial testing to arrive at
prompts with better final results. If you don't want to try alternatives combining your best prompts just put 0. " " "
best_percentage: " " " Number between 0 and 100 indicating that iterations should be stopped if all 'best_prompts' equaled or exceeded the indicated accuracy. If this value is not defined, it will default to 100. " " "
model:
name: " " " The name of the GPT model you will use to generate the prompts. " " "
temperature: " " " The temperature of the GPT model you will use to generate the prompts. " " "
max_tokens: " " " The maximum number of tokens you will allow the GPT model to use to generate your prompts. " " "
You can not define these variables for ' model ' in case you want to keep the same variables that were used in ' generation ' , in case the ' generation ' field has not been used it will take the following default values:
name: ' gpt-4
temperature: 0.6
max_tokens: 300"""
timeout: """Timeout set for an API request. This time limit indicates how long the client should wait to receive a response before the request expires."""
n_retries: """Number of attempts that will be automatically made to resend an API request in case the initial request fails."""Dalam hal file YAML yang ingin Anda evaluasi memiliki kesalahan dalam strukturnya, jangan khawatir. Sebelum dinilai oleh Insinyur Prompt, file Anda akan divalidasi, dan Anda akan menerima pemberitahuan yang menunjukkan di mana Anda perlu melakukan koreksi untuk itu agar dapat dievaluasi dengan sukses.
Ingatlah bahwa ketika Anda menghasilkan petunjuk Anda, Anda dapat menggunakan kunci constraints untuk secara eksplisit meminta agar petunjuk yang akan Anda hasilkan memiliki karakteristik khusus, misalnya, 'menghasilkan petunjuk dengan panjang yang tidak melebihi 20 kata'.
Jika Anda ingin tahu berapa biaya untuk menjalankan evaluasi Anda, cukup masukkan:
promptwizard YAML_FILE_PATHDan cukup jawab 'n' ketika ditanya apakah Anda ingin melanjutkan.
Jika tidak, tanggapi 'Y' dan jalankan evaluasi Anda dan Anda akan menerima perkiraan biaya, bersama dengan biaya akhir yang sebenarnya di akhir. Dalam file JSON terakhir, selain melihat petunjuk teratas dengan hasil terbaik, Anda juga akan memiliki informasi yang sama tentang biaya dan jumlah token yang dikonsumsi secara efektif untuk GPT-3.5-Turbo dan GPT-4.
Atau, Anda dapat melakukan hal berikut dalam skrip Python Anda:
from promptwizard.approximate_cost import cost
print(cost.approximate_cost(test_cases, method, prompts_value))Dan Anda akan melihat perkiraan biaya untuk evaluasi Anda yang mungkin.
Jika Anda ingin melihat contoh penggunaan, kami menyediakan notebook Colab berikut untuk Anda menjelajahi berbagai cara Anda dapat menggunakan promptWizard. (https://colab.research.google.com/drive/1iw2y43923vecohkpuhogenwy1y81rw8i?usp=sharing)
PromptWizard dibuat dengan cinta oleh Leniolab dan komunitas kontributor yang berkembang. Kami membangun pengalaman digital dengan ide -ide Anda. Hubungi! Juga, jika Anda memiliki pertanyaan atau umpan balik tentang PromptWizard, jangan ragu untuk menghubungi kami di [email protected]. Kami ingin mendengar dari Anda!
