@ -54,21 +54,65 @@ Most code examples are written in Python, though the concepts can be applied in
- [How to get embeddings from Azure OpenAI](examples/azure/embeddings.ipynb)
- [How to fine-tune GPT-3 with Azure OpenAI](examples/azure/finetuning.ipynb)
## Related resources
## Related OpenAI resources
Beyond the code examples here, you can learn about the [OpenAI API] from the following resources:
- Experiment with [ChatGPT]
- Try out the API in the [OpenAI Playground]
- Try the API in the [OpenAI Playground]
- Read about the API in the [OpenAI Documentation]
- Discuss the API in the [OpenAI Community Forum]
- Look for help in the [OpenAI Help Center]
- Get help in the [OpenAI Help Center]
- Discuss the API in the [OpenAI Community Forum] or [OpenAI Discord channel]
- See example prompts in the [OpenAI Examples]
- Stay up to date with the [OpenAI Blog]
- Stay updated with the [OpenAI Blog]
## Related resources from around the web
People are writing great tools and papers for improving outputs from GPT. Here are some cool ones we've seen:
### Prompting libraries & tools
- [Guidance](https://github.com/microsoft/guidance): A handy looking Python library from Microsoft that uses Handlebars templating to interleave generation, prompting, and logical control.
- [LangChain](https://github.com/hwchase17/langchain): A popular Python/JavaScript library for chaining sequences of language model prompts.
- [FLAML (A Fast Library for Automated Machine Learning & Tuning)](https://microsoft.github.io/FLAML/docs/Getting-Started/): A Python library for automating selection of models, hyperparameters, and other tunable choices.
- [Chainlit](https://docs.chainlit.io/overview): A Python library for making chatbot interfaces.
- [Guardrails.ai](https://shreyar.github.io/guardrails/): A Python library for validating outputs and retrying failures. Still in alpha, so expect sharp edges and bugs.
- [Semantic Kernel](https://devblogs.microsoft.com/semantic-kernel/): A Python/C# library from Microsoft that supports prompt templating, function chaining, vectorized memory, and intelligent planning.
- [Promptify](https://github.com/promptslab/Promptify): A small Python library for using language models to perform NLP tasks.
- [Scale Spellbook](https://scale.com/spellbook): A paid product for building, comparing, and shipping language model apps.
- [PromptPerfect](https://promptperfect.jina.ai/prompts): A paid product for testing and improving prompts.
### Prompting guides
- [promptingguide.ai](https://www.promptingguide.ai/): A prompt engineering guide that demonstrates many techniques.
- [OpenAI Cookbook: Techniques to improve reliability](https://github.com/openai/openai-cookbook/blob/main/techniques_to_improve_reliability.md): A slightly dated (Sep 2022) review of techniques for prompting language models.
- [Lil'Log Prompt Engineering](https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/): An OpenAI researcher's review of the prompt engineering literature (as of March 2023).
- [learnprompting.org](https://learnprompting.org/): An introductory course to prompt engineering.
### Video courses
- [Andrew Ng's DeepLearning.AI](https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/): A short course on prompt engineering for developers.
- [Andrej Karpathy's Let's build GPT](https://www.youtube.com/watch?v=kCc8FmEb1nY): A detailed dive into the machine learning underlying GPT.
- [Prompt Engineering by DAIR.AI](https://www.youtube.com/watch?v=dOxUroR57xs): A one-hour video on various prompt engineering techniques.
### Papers on advanced prompting to improve reasoning
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2022)](https://arxiv.org/abs/2201.11903): Using few-shot prompts to ask models to think step by step improves their reasoning. PaLM's score on math word problems (GSM8K) go from 18% to 57%.
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022)](https://arxiv.org/abs/2203.11171): Taking votes from multiple outputs improves accuracy even more. Voting across 40 outputs raises PaLM's score on math word problems further, from 57% to 74%, and `code-davinci-002`'s from 60% to 78%.
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023)](https://arxiv.org/abs/2305.10601): Searching over trees of step by step reasoning helps even more than voting over chains of thought. It lifts `GPT-4`'s scores on creative writing and crosswords.
- [Language Models are Zero-Shot Reasoners (2022)](https://arxiv.org/abs/2205.11916): Telling instruction-following models to think step by step improves their reasoning. It lifts `text-davinci-002`'s score on math word problems (GSM8K) from 13% to 41%.
- [Large Language Models Are Human-Level Prompt Engineers (2023)](https://arxiv.org/abs/2211.01910): Automated searching over possible prompts found a prompt that lifts scores on math word problems (GSM8K) to 43%, 2 percentage points above the human-written prompt in Language Models are Zero-Shot Reasoners.
- [Faithful Reasoning Using Large Language Models (2022)](https://arxiv.org/abs/2208.14271): Reasoning can be improved by a system that combines: chains of thought generated by alternative selection and inference prompts, a halter model that chooses when to halt selection-inference loops, a value function to search over multiple reasoning paths, and sentence labels that help avoid hallucination.
- [STaR: Bootstrapping Reasoning With Reasoning (2022)](https://arxiv.org/abs/2203.14465): Chain of thought reasoning can be baked into models via fine-tuning. For tasks with an answer key, example chains of thoughts can be generated by language models.
- [ReAct: Synergizing Reasoning and Acting in Language Models (2023)](https://arxiv.org/abs/2210.03629): For tasks with tools or an environment, chain of thought works better you prescriptively alternate between **Re**asoning steps (thinking about what to do) and **Act**ing (getting information from a tool or environment).
- [Reflexion: an autonomous agent with dynamic memory and self-reflection (2023)](https://arxiv.org/abs/2303.11366): Retrying tasks with memory of prior failures improves subsequent performance.
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP (2023)](https://arxiv.org/abs/2212.14024): Models augmented with knowledge via a "retrieve-then-read" can be improved with multi-hop chains of searches.
## Contributing
If there are examples or guides you'd like to see, feel free to suggest them on the [issues page].
If there are examples or guides you'd like to see, feel free to suggest them on the [issues page]. We are also happy to accept high quality pull requests, as long as they fit the scope of the repo.
[chatgpt]: https://chat.openai.com/
[openai api]: https://openai.com/api/
@ -76,7 +120,8 @@ If there are examples or guides you'd like to see, feel free to suggest them on
Ted Sanders
1 year ago
committed by
GitHub