オープンAIクックブック

このリポジトリは、OpenAI API を使用して一般的なタスクを実行するためのサンプルコードとサンプルプロンプトを共有します。

これらの例を自分で試すには、OpenAI アカウントが必要です。無料のアカウントを作成して開始してください。

ほとんどのコード例は Python で記述されていますが、概念はどの言語でも適用できます。

クックブックのレシピがすべての可能な食事やテクニックを網羅しているわけではないのと同じように、これらの例は考えられるすべてのユースケースや方法を網羅しているわけではありません。それらを出発点として使用して、詳しく説明し、発見し、発明します。

関連リソース

ここでのコード例以外にも、次のリソースから OpenAI API について学ぶことができます。

• OpenAI プレイグラウンドで GPT-3 をお試しください
• APIについては、OpenAIのドキュメントを参照してください。
• OpenAIコミュニティフォーラムでAPIについて話し合う
• OpenAI ヘルプセンターでヘルプを探す
• プロンプトの例については、「OpenAI の例」を参照してください。

機能別に整理された例

大規模な言語モデルのしくみ

大規模な言語モデルは、テキストをテキストにマップする関数です。テキストの入力文字列を指定すると、大規模な言語モデルは次に来るテキストを予測しようとします。

大規模な言語モデルの魔法は、膨大な量のテキストでこの予測エラーを最小限に抑えるようにトレーニングすることで、モデルがこれらの予測に役立つ概念を学習することです。たとえば、次のような概念を学びます。

• 綴り方
• 文法の仕組み
• 言い換える方法
• 質問に答える方法
• 会話の持ち方
• 多くの言語で書く方法
• コーディング方法
• 等。

これらの機能はどれも明示的にプログラムされていません-それらはすべてトレーニングの結果として現れます。

GPT-3の機能は、生産性アプリ、教育アプリ、ゲームなど、何百もの異なるソフトウェア製品に電力を供給しています。

大規模な言語モデルを制御する方法

大規模な言語モデルへのすべての入力の中で、最も影響力のあるのはテキスト プロンプトです。

大規模な言語モデルでは、いくつかの方法で出力を生成するように求めることができます。

• 指示:モデルに必要なものを伝えます
• 完了:モデルが必要なものの始まりを完了するように誘導します
• デモンストレーション: 次のいずれかを使用して、必要なものをモデルに示します。
  • プロンプトのいくつかの例
  • トレーニングデータセットの微調整における数百または数千の例

それぞれの例を以下に示します。

指示プロンプト

命令に従うモデル(たとえば、またはで始まるモデル)は、指示に従うように特別に設計されています。プロンプトの上部(または下部、またはその両方)に指示を書くと、モデルは指示に従ってから停止するために最善を尽くします。指示は詳細にすることができるので、あなたが望む出力を明示的に詳述する段落を書くことを恐れないでください。

text-davinci-003

text-

指示プロンプトの例:

Extract the name of the author from the quotation below.

“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.”
― Ted Chiang, Exhalation

Output:
Ted Chiang

Completion prompt example
Completion-style prompts take advantage of how large language models try to write text they think is most likely to come next. To steer the model, try beginning a pattern or sentence that will be completed by the output you want to see. Relative to direct instructions, this mode of steering large language models can take more care and experimentation. In addition, the models won't necessarily know where to stop, so you will often need stop sequences or post-processing to cut off text generated beyond the desired output.
Example completion prompt:
“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.”
― Ted Chiang, Exhalation

The author of this quote is

Output:
 Ted Chiang

Demonstration prompt example (few-shot learning)
Similar to completion-style prompts, demonstrations can show the model what you want it to do. This approach is sometimes called few-shot learning, as the model learns from a few examples provided in the prompt.
Example demonstration prompt:
Quote:
“When the reasoning mind is forced to confront the impossible again and again, it has no choice but to adapt.”
― N.K. Jemisin, The Fifth Season
Author: N.K. Jemisin

Quote:
“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.”
― Ted Chiang, Exhalation
Author:

Output:
 Ted Chiang

Fine-tuned prompt example
With enough training examples, you can fine-tune a custom model. In this case, instructions become unnecessary, as the model can learn the task from the training data provided. However, it can be helpful to include separator sequences (e.g., 
->
 or 
###
 or any string that doesn't commonly appear in your inputs) to tell the model when the prompt has ended and the output should begin. Without separator sequences, there is a risk that the model continues elaborating on the input text rather than starting on the answer you want to see.

Example fine-tuned prompt (for a model that has been custom trained on similar prompt-completion pairs):
“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.”
― Ted Chiang, Exhalation

###



Output:
 Ted Chiang

More prompt advice
For more prompt examples, visit OpenAI Examples.
In general, the input prompt is the best lever for improving model outputs. You can try tricks like:

• Give more explicit instructions. E.g., if you want the output to be a comma separated list, ask it to return a comma separated list. If you want it to say "I don't know" when it doesn't know the answer, tell it 'Say "I don't know" if you do not know the answer.'
• Supply better examples. If you're demonstrating examples in your prompt, make sure that your examples are diverse and high quality.
• Ask the model to answer as if it was an expert. Explicitly asking the model to produce high quality output or output as if it was written by an expert can induce the model to give higher quality answers that it thinks an expert would write. E.g., "The following answer is correct, high-quality, and written by an expert."
• Prompt the model to write down the series of steps explaining its reasoning. E.g., prepend your answer with something like "Let's think step by step." Prompting the model to give an explanation of its reasoning before its final answer can increase the likelihood that its final answer is consistent and correct.

Text Capabilities

1. Write text

Large language models are excellent at writing text. They can assist with:

• Blog posts
• Email copy
• Ad copy
• Website copy
• Product descriptions
• Memos
• Storytelling
• Brainstorming
• Question generation
• etc.

An example prompt for an instruction-following model:

Write an email to a colleague named Jill congratulating her on her promotion. The tone should be warm yet professional. Mention how you admire the work she's been putting in.  Include a joke about how her pet lizard Max enjoys eating grasshoppers. Mention how you're looking forward to the team off-site next week.

Output:
Dear Jill,

Congratulations on your promotion! I've been admiring the great work you've been putting in and I'm really happy for your success. Max the lizard must be thrilled too - I bet he's looking forward to feasting on even more grasshoppers!

I'm really looking forward to next week's team off-site. It's going to be great to catch up with everyone and brainstorm some new ideas.

Best,

[Your Name]

In general, writing can work with any style of prompt. Experiment to see what works best for your use case.

text-davinci-003

davinci

2. Explain text

One capability of large language models is distilling information from a piece of text. This can include:

• Answering questions about a piece of text, e.g.:
  • Querying a knowledge base to help people look up things they don't know
  • Querying an unfamiliar document to understand what it contains
  • Querying a document with structured questions in order to extract tags, classes, entities, etc.
• Summarizing text, e.g.:
  • Summarizing long documents
  • Summarizing back-and-forth emails or message threads
  • Summarizing detailed meeting notes with key points and next steps
• Classifying text, e.g.:
  • Classifying customer feedback messages by topic or type
  • Classifying documents by topic or type
  • Classifying the tone or sentiment of text
• Extracting entities, e.g.:
  • Extracting contact information from a customer message
  • Extracting names of people or companies or products from a document
  • Extracting things mentioned in customer reviews or feedback

Answering questions about a piece of text

Example prompt for answering questions about a piece of text:

Using the following text, answer the following question. If the answer is not contained within the text, say "I don't know."

Text:
"""
Oklo Mine (sometimes Oklo Reactor or Oklo Mines), located in Oklo, Gabon on the west coast of Central Africa, is believed to be the only natural nuclear fission reactor. Oklo consists of 16 sites at which self-sustaining nuclear fission reactions are thought to have taken place approximately 1.7 billion years ago, and ran for hundreds of thousands of years. It is estimated to have averaged under 100 kW of thermal power during that time.
"""

Question: How many natural fission reactors have ever been discovered?

Answer:

Output:
 One

If the text you wish to ask about is longer than the token limit (~4,000 tokens for 
text-davinci-003
 and ~2,000 tokens for earlier models), we recommend splitting the text into smaller pieces, ranking them by relevance, and then asking the most-relevant-looking pieces.

Summarization
An example prompt for summarization:
Summarize the following text.

Text:
"""
Two independent experiments reported their results this morning at CERN, Europe's high-energy physics laboratory near Geneva in Switzerland. Both show convincing evidence of a new boson particle weighing around 125 gigaelectronvolts, which so far fits predictions of the Higgs previously made by theoretical physicists.

"As a layman I would say: 'I think we have it'. Would you agree?" Rolf-Dieter Heuer, CERN's director-general, asked the packed auditorium. The physicists assembled there burst into applause.
"""

Summary:

Output:
CERN has announced the discovery of a new particle, the Higgs boson. This particle has been predicted by theoretical physicists and is a major step forward in our understanding of the universe.

Classification
The best approach for classifying text depends on whether the classes are known in advance or not.
If your classes are known in advance, classification is best done with a fine-tuned model, as demonstrated in Fine-tuned_classification.ipynb.
If your classes are not known in advance (e.g., they are set by a user or generated on the fly), you can try zero-shot classification by either giving an instruction containing the classes or even by using embeddings to see which class label (or other classified texts) are most similar to the text (Zero-shot_classification.ipynb).
Entity extraction
An example prompt for entity extraction:
From the text below, extract the following entities in the following format:
Companies: <comma-separated list of companies mentioned>
People & titles: <comma-separated list of people mentioned (with their titles or roles appended in parentheses)>

Text:
"""
In March 1981, United States v. AT&T came to trial under Assistant Attorney General William Baxter. AT&T chairman Charles L. Brown thought the company would be gutted. He realized that AT&T would lose and, in December 1981, resumed negotiations with the Justice Department. Reaching an agreement less than a month later, Brown agreed to divestiture—the best and only realistic alternative. AT&T's decision allowed it to retain its research and manufacturing arms. The decree, titled the Modification of Final Judgment, was an adjustment of the Consent Decree of 14 January 1956. Judge Harold H. Greene was given the authority over the modified decree....

In 1982, the U.S. government announced that AT&T would cease to exist as a monopolistic entity. On 1 January 1984, it was split into seven smaller regional companies, Bell South, Bell Atlantic, NYNEX, American Information Technologies, Southwestern Bell, US West, and Pacific Telesis, to handle regional phone services in the U.S. AT&T retains control of its long distance services, but was no longer protected from competition.
"""

Output:
Companies: United States v. AT&T, AT&T, Justice Department, Bell South, Bell Atlantic, NYNEX, American Information Technologies, Southwestern Bell, US West, Pacific Telesis
People & titles: William Baxter (Assistant Attorney General), Charles L. Brown (AT&T chairman), Harold H. Greene (Judge)

3. Edit text
In addition to the completion API endpoint, OpenAI now offers an edit API endpoint (blog post). In contrast to completions, which only take a single text input, edits take two text inputs: the instruction and the text to be modified.
An example edit prompt:
Instruction input:
Fix the OCR errors

Text input:
Therewassomehostilityntheenergybehindthe researchreportedinPerceptrons....Part of ourdrivecame,aswequiteplainlyacknoweldgednourbook,fromhe facthatfundingndresearchnergywerebeingdissipatedon. . .misleadingttemptsouseconnectionistmethodsnpracticalappli-cations.

Output:
There was some hostility in the energy behind the research reported in Perceptrons....Part of our drive came, as we quite plainly acknowledged in our book, from the fact that funding and research energy were being dissipated on...misleading attempts to use connectionist methods in practical applications.

Translation
Translation is another emergent capability of large language models. In 2021, GPT-3 was used to set a new state-of-the-art record in unsupervised translation on the WMT14 English-French benchmark.
Example translation prompt using the edits endpoint:
Instruction input:
translation into French

Text input:
That's life.

Output:
C'est la vie.

Example translation prompt using the completions endpoint:
Translate the following text from English to French.

English: That's life.
French:

Output:
 C'est la vie.

Tips for translation:

• Performance is best in the most common languages
• We've seen better performance when the instruction is given in the final language (so if translating into French, give the instruction

  Traduire le texte de l'anglais au français.

  rather than

  Translate the following text from English to French.

  )
• Backtranslation (as described here) can also increase performance
• Text with colons and heavy punctuation can trip up the instruction-following models, especially if the instruction is using colons (e.g.,

  English: {english text} French:

  )
• The edits endpoint has been seen to sometimes repeat the text input alongside the translation

When it comes to translation, large language models particularly shine at combining other instructions alongside translation. For example, you can ask GPT-3 to translate Slovenian to English but keep all LaTeX typesetting commands unchanged. The following notebook details how we translated a Slovenian math book into English:

Translation of a Slovenian math book into English

4. Compare text

The OpenAI API embeddings endpoint can be used to measure similarity between pieces of text (blog post). By leveraging GPT-3's understanding of text, these embeddings achieved state-of-the-art results on benchmarks in both unsupervised learning and transfer learning settings.

Embeddings can be used for semantic search, recommendations, cluster analysis, near-duplicate detection, and more.

Semantic search

Embeddings can be used for search either by themselves or as a feature in a larger system.

The simplest way to use embeddings for search is as follows:

• Before the search (precompute):
  • Split your text corpus into chunks smaller than the token limit (e.g., <8,000 tokens)
  • Embed each chunk
  • Store those embeddings in your own database or in a vector search provider like Pinecone or Weaviate
• At the time of the search (live compute):
  • Embed the search query
  • Find the closest embeddings in your database
  • Return the top results, ranked by cosine similarity

An example of how to use embeddings for search is shown in Semantic_text_search_using_embeddings.ipynb.

In more advanced search systems, the cosine similarity of embeddings can be used as one feature among many in ranking search results.

Recommendations

Recommendations are quite similar to search, except that instead of a free-form text query, the inputs are items in a set.

An example of how to use embeddings for recommendations is shown in Recommendation_using_embeddings.ipynb.

Similar to search, these cosine similarity scores can either be used on their own to rank items or as features in larger ranking algorithms.

Customizing Embeddings

Although OpenAI's embedding model weights cannot be fine-tuned, you can still use training data to customize embeddings to your application.

In the following notebook, we provide an example method for customizing your embeddings using training data. The idea of the method is to train a custom matrix to multiply embedding vectors by in order to get new customized embeddings. With good training data, this custom matrix will highlight the features relevant to your training labels and suppress the rest. You can equivalently consider the matrix multiplication as (a) a modification of the embeddings or (b) a modification of the distance function used to measure the distances between embeddings.

• Customizing_embeddings.ipynb

Code Capabilities

Large language models aren't only great at text - they can be great at code too. OpenAI's specialized code model is called Codex.

Codex powers more than 70 products, including:

• GitHub Copilot (autocompletes code in VS Code and other IDEs)
• Pygma (turns Figma designs into code)
• Replit (has an 'Explain code' button and other features)
• Warp (a smart terminal with AI command search)
• Machinet (writes Java unit test templates)

Note that unlike instruction-following text models (e.g.,

text-davinci-003

1. Write code

An example prompt for writing code with

code-davinci-002

SQL tables (and columns):
* Customers(customer_id, signup_date)
* Streaming(customer_id, video_id, watch_date, watch_minutes)

A well-written SQL query that lists customers who signed up during March 2020 and watched more than 50 hours of video in their first 30 days:
```

Output:
SELECT c.customer_id
FROM Customers c
JOIN Streaming s
ON c.customer_id = s.customer_id
WHERE c.signup_date BETWEEN '2020-03-01' AND '2020-03-31'
AND s.watch_date BETWEEN c.signup_date AND DATE_ADD(c.signup_date, INTERVAL 30 DAY)
GROUP BY c.customer_id
HAVING SUM(s.watch_minutes) > 50 * 60
code-davinci-002
 is able to make inferences from variable names; for example, it infers that 
watch_minutes
 has units of minutes and therefore needs to be converted by a factor of 60 before being compared with 50 hours.

2. Explain code
Code explanation can be applied to many use cases:

• Generating in-code documentation (e.g., Python docstrings, git commit messages)
• Generating out-of-code documentation (e.g., man pages)
• In an interactive code exploration tool
• Communicating program results back to users via a natural language interface

An example prompt for explaining code with

code-davinci-002

A SQL query:
```
SELECT c.customer_id
FROM Customers c
JOIN Streaming s
ON c.customer_id = s.customer_id
WHERE c.signup_date BETWEEN '2020-03-01' AND '2020-03-31'
AND s.watch_date BETWEEN c.signup_date AND DATE_ADD(c.signup_date, INTERVAL 30 DAY)
GROUP BY c.customer_id
HAVING SUM(s.watch_minutes) > 50 * 60
```

Questions:
1. What does the SQL query do?
2. Why might someone be interested in this time period?
3. Why might a company be interested in this SQL query?

Answers:

Output:
1. The SQL query finds all customers who signed up in March 2020 and watched more than 50 hours of content in the first 30 days after signing up.
2. The time period is interesting because it is the first month of the COVID-19 pandemic.
3. A company might be interested in this SQL query because it can help them understand how the pandemic has affected their business.

3. Edit code
OpenAI's edit endpoint is particularly useful for editing code.
Example text input to 
code-davinci-edit-001
:

def tribonacci(n):
    if n == 0:
        return 0
    elif n == 1:
        return 1
    elif n == 2:
        return 1
    elif n == 3:
        return 2
    else:
        return tribonacci(n-1) + tribonacci(n-2) + tribonacci(n-3)
Example instruction inputs:
Add a docstring

Add typing

Improve the runtime

Add a test

Translate to JavaScript (or Rust or Lisp or any language you like)

Example output after improving the runtime and translating to JavaScript:
function tribonacci(n) {
  let a = 0;
  let b = 1;
  let c = 1;
  for (let i = 0; i < n; i++) {
    [a, b, c] = [b, c, a + b + c];
  }
  return a;
}
As you can see, 
code-davinci-edit-001
 was able to successfully reduce the function's runtime from exponential down to linear, as well as convert from Python to JavaScript.

4. Compare code
The OpenAI API also features code search embeddings, which can measure the relevance of a section of code to a text query, or the similarity between two sections of code.
OpenAI code search embeddings significantly improved the state-of-the-art on the CodeSearchNet evaluation suite, scoring 93.5% versus the previous record of 77.4%.
Read more about OpenAI's code embeddings in the blog post announcement or documentation.
Code embeddings can be useful for use cases such as:

• Code search
• Codebase clustering & analysis

An example of code search is shown in Code_search.ipynb.

We haven't written an example of code clustering, but the idea is the same as the text clustering in Clustering.ipynb.