Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/instructor-ai/instructor-rb
Structured outputs for LLMs
https://github.com/instructor-ai/instructor-rb
artificial-intelligence artificial-intelligence-projects chatgpt chatgpt-api function-calling large-language-models llm openai openai-api openai-assistant-api structured-data
Last synced: about 2 months ago
JSON representation
Structured outputs for LLMs
- Host: GitHub
- URL: https://github.com/instructor-ai/instructor-rb
- Owner: instructor-ai
- License: mit
- Created: 2024-01-19T02:02:24.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-06-12T13:42:57.000Z (7 months ago)
- Last Synced: 2024-07-24T21:58:04.931Z (6 months ago)
- Topics: artificial-intelligence, artificial-intelligence-projects, chatgpt, chatgpt-api, function-calling, large-language-models, llm, openai, openai-api, openai-assistant-api, structured-data
- Language: Ruby
- Homepage: https://useinstructor.com/
- Size: 377 KB
- Stars: 47
- Watchers: 6
- Forks: 2
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: docs/contributing.md
- License: LICENSE
Awesome Lists containing this project
README
# instructor-rb
_Structured extraction in Ruby, powered by llms, designed for simplicity, transparency, and control._
---
[](https://twitter.com/jxnlco)
[](https://twitter.com/sbayona)
[](https://jxnl.github.io/instructor-rb)
[](https://github.com/instructor-ai/instructor-rb/issues)
[](https://discord.gg/CV8sPM5k5Y)
Instructor-rb is a Ruby library that makes it a breeze to work with structured outputs from large language models (LLMs). Built on top of [EasyTalk](https://github.com/sergiobayona/easy_talk), it provides a simple, transparent, and user-friendly API to manage validation, retries, and streaming responses. Get ready to supercharge your LLM workflows!
# Getting Started
1. Install Instructor-rb at the command prompt if you haven't yet:
```bash
$ gem install instructor-rb
```
2. In your Ruby project, require the gem:
```ruby
require 'instructor'
```
3. At the beginning of your script, initialize and patch the client:
For the OpenAI client:
```ruby
client = Instructor.from_openai(OpenAI::Client)
```
For the Anthropic client:
```ruby
client = Instructor.from_anthropic(Anthropic::Client)
```
## Usage
export your API key:
```bash
export OPENAI_API_KEY=sk-...
```
or for Anthropic:
```bash
export ANTHROPIC_API_KEY=sk-...
```
Then use Instructor by defining your schema in Ruby using the `define_schema` block and [EasyTalk](https://github.com/sergiobayona/easy_talk)'s schema definition syntax. Here's an example in:
```ruby
require 'instructor'
class UserDetail
include EasyTalk::Model
define_schema do
property :name, String
property :age, Integer
end
end
client = Instructor.from_openai(OpenAI::Client).new
user = client.chat(
parameters: {
model: 'gpt-3.5-turbo',
messages: [{ role: 'user', content: 'Extract Jason is 25 years old' }]
},
response_model: UserDetail
)
user.name
# => "Jason"
user.age
# => 25
```
> ℹ️ **Tip:** Support in other languages
Check out ports to other languages below:
- [Python](https://www.github.com/jxnl/instructor)
- [TS/JS](https://github.com/instructor-ai/instructor-js/)
- [Ruby](https://github.com/instructor-ai/instructor-rb)
- [Elixir](https://github.com/thmsmlr/instructor_ex/)
If you want to port Instructor to another language, please reach out to us on [Twitter](https://twitter.com/jxnlco) we'd love to help you get started!
## Why use Instructor?
1. **OpenAI Integration** — Integrates seamlessly with OpenAI's API, facilitating efficient data management and manipulation.
2. **Customizable** — It offers significant flexibility. Users can tailor validation processes and define unique error messages.
3. **Tested and Trusted** — Its reliability is proven by extensive real-world application.
[Installing Instructor](installation.md) is a breeze.
## Contributing
If you want to help out, checkout some of the issues marked as `good-first-issue` or `help-wanted`. Found [here](https://github.com/instructor-ai/instructor-js/labels/good%20first%20issue). They could be anything from code improvements, a guest blog post, or a new cook book.
Checkout the [contribution guide]() for details on how to set things up, testing, changesets and guidelines.
## License
This project is licensed under the terms of the MIT License.
## TODO
- [ ] Add patch
- [ ] Mode.FUNCTIONS
- [ ] Mode.TOOLS
- [ ] Mode.MD_JSON
- [ ] Mode.JSON
- [ ] Add response_model
- [ ] Support async
- [ ] Support stream=True, Partial[T] and iterable[T]
- [ ] Support Streaming
- [ ] Optional/Maybe types
- [ ] Add Tutorials, include in docs
- [ ] Text Classification
- [ ] Search Queries
- [ ] Query Decomposition
- [ ] Citations
- [ ] Knowledge Graph
- [ ] Self Critique
- [ ] Image Extracting Tables
- [ ] Moderation
- [ ] Entity Resolution
- [ ] Action Item and Dependency Mapping
- [ ] Logging for Distillation / Finetuning
- [ ] Add `llm_validator`