|
1 | | -<a href="https://cookbook.openai.com" target="_blank"> |
2 | | - <picture> |
3 | | - <source media="(prefers-color-scheme: dark)" srcset="/images/openai-cookbook-white.png" style="max-width: 100%; width: 400px; margin-bottom: 20px"> |
4 | | - <img alt="OpenAI Cookbook Logo" src="/images/openai-cookbook.png" width="400px"> |
5 | | - </picture> |
6 | | -</a> |
| 1 | +# OpenAI Cookbook |
7 | 2 |
|
8 | | -<h3></h3> |
9 | | - |
10 | | -> ✨ Navigate at [cookbook.openai.com](https://cookbook.openai.com) |
| 3 | +## What is the OpenAI Cookbook? |
11 | 4 |
|
12 | | -Example code and guides for accomplishing common tasks with the [OpenAI API](https://platform.openai.com/docs/introduction). To run these examples, you'll need an OpenAI account and associated API key ([create a free account here](https://platform.openai.com/signup)). Set an environment variable called `OPENAI_API_KEY` with your API key. Alternatively, in most IDEs such as Visual Studio Code, you can create an `.env` file at the root of your repo containing `OPENAI_API_KEY=<your API key>`, which will be picked up by the notebooks. |
| 5 | +The OpenAI Cookbook is a community-driven collection of examples and guides for building with OpenAI's API. Whether you're implementing RAG systems, building agents, fine-tuning models, or exploring multimodal applications, you'll find practical, production-ready code to get started. |
13 | 6 |
|
14 | | -Most code examples are written in Python, though the concepts can be applied in any language. |
| 7 | +This resource is designed for developers, researchers, and anyone looking to understand how to leverage modern language models in real-world applications. |
15 | 8 |
|
16 | | -For other useful tools, guides and courses, check out these [related resources from around the web](https://cookbook.openai.com/related_resources). |
| 9 | +## OpenAI API Overview |
| 10 | + |
| 11 | +OpenAI's platform provides powerful tools for building AI applications: |
| 12 | + |
| 13 | +- **Language Models**: `gpt-4o` and `gpt-4o-mini` deliver strong performance across reasoning, coding, and creative tasks |
| 14 | +- **Multimodal Capabilities**: Process and generate text, images, and audio in unified workflows |
| 15 | +- **Responses API**: Simplified, stateful API for multi-turn conversations with built-in tool orchestration |
| 16 | +- **Function Calling**: Connect models to external tools, APIs, and databases |
| 17 | +- **Structured Outputs**: Generate guaranteed JSON responses using `response_format` |
| 18 | +- **Embeddings**: Build semantic search and RAG systems with `text-embedding-3-small` and `text-embedding-3-large` |
| 19 | +- **Image Generation**: Create images with the DALL-E API |
| 20 | +- **Voice & Audio**: Real-time audio processing with `gpt-4o-audio-preview` and the Realtime API |
| 21 | + |
| 22 | +## Getting Started |
| 23 | + |
| 24 | +### 1. Create an OpenAI Account |
| 25 | + |
| 26 | +Sign up at [platform.openai.com/signup](https://platform.openai.com/signup) to get API access. Free-tier accounts can explore the API with usage limits. |
| 27 | + |
| 28 | +### 2. Get Your API Key |
| 29 | + |
| 30 | +Navigate to [platform.openai.com/api-keys](https://platform.openai.com/api-keys) and create a new API key. Keep it secure—treat it like a password. |
| 31 | + |
| 32 | +### 3. Set Up Your Environment |
| 33 | + |
| 34 | +**Option A: Environment Variable** |
| 35 | + |
| 36 | +```bash |
| 37 | +# macOS/Linux |
| 38 | +export OPENAI_API_KEY='your-api-key-here' |
| 39 | + |
| 40 | +# Windows (Command Prompt) |
| 41 | +set OPENAI_API_KEY=your-api-key-here |
| 42 | + |
| 43 | +# Windows (PowerShell) |
| 44 | +$env:OPENAI_API_KEY='your-api-key-here' |
| 45 | +``` |
| 46 | + |
| 47 | +**Option B: .env File (Recommended)** |
| 48 | + |
| 49 | +Create a `.env` file in your project root: |
| 50 | + |
| 51 | +``` |
| 52 | +OPENAI_API_KEY=your-api-key-here |
| 53 | +``` |
| 54 | + |
| 55 | +Most notebooks and Python applications will automatically load this file. |
| 56 | + |
| 57 | +### 4. Install the SDK |
| 58 | + |
| 59 | +```bash |
| 60 | +# Python |
| 61 | +pip install openai |
| 62 | + |
| 63 | +# Node.js |
| 64 | +npm install openai |
| 65 | +``` |
| 66 | + |
| 67 | +### 5. Run the Examples |
| 68 | + |
| 69 | +Most examples are Jupyter notebooks. Install Jupyter if you haven't already: |
| 70 | + |
| 71 | +```bash |
| 72 | +pip install jupyter |
| 73 | +jupyter notebook |
| 74 | +``` |
| 75 | + |
| 76 | +Then open any `.ipynb` file from the `examples/` directory and run the cells. |
| 77 | + |
| 78 | +## What's in the Cookbook |
| 79 | + |
| 80 | +The cookbook is organized into focused examples covering common use cases: |
| 81 | + |
| 82 | +- **[Function Calling](examples/function_calling/)**: Connect models to external tools, APIs, and databases |
| 83 | +- **[Embeddings & RAG](examples/rag/)**: Build retrieval-augmented generation systems over your own data |
| 84 | +- **[Agents](examples/agents/)**: Create autonomous agents that plan, reason, and execute tasks |
| 85 | +- **[Vision](examples/vision/)**: Work with image inputs for analysis and understanding |
| 86 | +- **[Audio](examples/audio/)**: Build applications for transcription, speech recognition, and audio processing |
| 87 | +- **[Image Generation](examples/image_generation/)**: Create images using the DALL·E API |
| 88 | +- **[Structured Outputs](examples/structured_outputs/)**: Produce guaranteed JSON using `response_format` |
| 89 | +- **[Batch Processing](examples/batch/)**: Run large-scale inference jobs efficiently |
| 90 | +- **[Prompt Engineering](examples/prompt_engineering/)**: Learn effective prompt design techniques |
| 91 | +- **[Evaluation & Reasoning](examples/reasoning/)**: Evaluate model performance and test reasoning quality |
| 92 | +- **[Data ETL](examples/data_etl/)**: Prepare and transform data for downstream tasks |
| 93 | +- **[Python Examples](examples/python/)**: How to use the Python SDK in real applications |
| 94 | +- **[JavaScript Examples](examples/javascript/)**: Examples demonstrating the Node.js SDK |
| 95 | +- **[Assistants](examples/assistants/)**: Build assistants with persistent threads and tool use |
| 96 | + |
| 97 | +Browse the full collection at [cookbook.openai.com](https://cookbook.openai.com) or explore the [examples directory](examples/) directly. |
| 98 | + |
| 99 | +## Resources |
| 100 | + |
| 101 | +- **[OpenAI Platform Documentation](https://platform.openai.com/docs)**: Official API reference and guides |
| 102 | +- **[OpenAI API Reference](https://platform.openai.com/docs/api-reference)**: Complete endpoint documentation |
| 103 | +- **[Community Forum](https://community.openai.com)**: Get help and share what you're building |
| 104 | +- **[Related Resources](https://cookbook.openai.com/related_resources)**: Curated tools, guides, and courses from the community |
| 105 | + |
| 106 | +## Contributing |
| 107 | + |
| 108 | +We welcome contributions! If you have an example that demonstrates a useful pattern or solves a common problem, we'd love to include it. |
| 109 | + |
| 110 | +Check out [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to submit examples. |
17 | 111 |
|
18 | 112 | ## License |
19 | 113 |
|
|
0 commit comments