mirror of
https://github.com/kennethreitz/instructor.git
synced 2026-06-05 22:50:18 +00:00
docs: update docs and readme
This commit is contained in:
@@ -1,27 +1,28 @@
|
||||
# Welcome to Instructor - Your Gateway to Structured Outputs with OpenAI
|
||||
# Instructor
|
||||
|
||||
_Pythonic Structured Outputs powered by LLM function calling and tool calling APIs. Designed for simplicity, transparency, and control._
|
||||
_Structured outputs powered by llms. Designed for simplicity, transparency, and control._
|
||||
|
||||
---
|
||||
|
||||
[Star us on Github!](https://www.github.com/jxnl/instructor)
|
||||
|
||||
[](https://twitter.com/jxnlco)
|
||||
[](https://pypi.python.org/pypi/instructor)
|
||||
[](https://jxnl.github.io/instructor)
|
||||
[](https://coveralls.io/github/jxnl/instructor?branch=add-coveralls)
|
||||
[](https://discord.gg/CV8sPM5k5Y)
|
||||
[](https://pypi.python.org/pypi/instructor)
|
||||
|
||||
Dive into the world of Python-based structured extraction, empowered by OpenAI's cutting-edge function calling API. Instructor stands out for its simplicity, transparency, and user-centric design. Whether you're a seasoned developer or just starting out, you'll find Instructor's approach intuitive and its results insightful.
|
||||
Instructor stands out for its simplicity, transparency, and user-centric design. We leverage Pydantic to do the heavy lifting, and we've built a simple, easy-to-use API on top of it by helping you manage [validation context](./concepts/reask_validation.md), retries with [Tenacity](./concepts/retrying.md), and streaming [Lists](./concepts/lists.md) and [Partial](./concepts/partial.md) responses.
|
||||
|
||||
## Ports to other languages
|
||||
Check us out in [Typescript](https://instructor-ai.github.io/instructor-js/) and [Elixir](https://github.com/thmsmlr/instructor_ex/).
|
||||
|
||||
Check out ports to other languages below:
|
||||
Instructor is not limited to the OpenAI API, we have support for many other backends that via patching. Check out more on [patching](./concepts/patching.md).
|
||||
|
||||
- [Typescript / Javascript](https://www.github.com/jxnl/instructor-js)
|
||||
- [Elixir](https://github.com/thmsmlr/instructor_ex/)
|
||||
1. Wrap OpenAI's SDK
|
||||
2. Wrap the create method
|
||||
|
||||
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!
|
||||
Including but not limited to:
|
||||
|
||||
- [Together](./blog/posts/together.md)
|
||||
- [Ollama](./blog/posts/ollama.md)
|
||||
- [AnyScale](./blog/posts/anyscale.md)
|
||||
- [llama-cpp-python](./blog/posts/llama-cpp-python.md)
|
||||
|
||||
## Get Started in Moments
|
||||
|
||||
|
||||
+13
-6
@@ -8,16 +8,23 @@ _Structured outputs powered by llms. Designed for simplicity, transparency, and
|
||||
[](https://discord.gg/CV8sPM5k5Y)
|
||||
[](https://pypi.python.org/pypi/instructor)
|
||||
|
||||
Dive into the world of Python-based structured extraction, by OpenAI's function calling API and Pydantic, the most widely used data validation library for Python. Instructor stands out for its simplicity, transparency, and user-centric design. Whether you're a seasoned developer or just starting out, you'll find Instructor's approach intuitive and steerable.
|
||||
Instructor stands out for its simplicity, transparency, and user-centric design. We leverage Pydantic to do the heavy lifting, and we've built a simple, easy-to-use API on top of it by helping you manage [validation context](./concepts/reask_validation.md), retries with [Tenacity](./concepts/retrying.md), and streaming [Lists](./concepts/lists.md) and [Partial](./concepts/partial.md) responses.
|
||||
|
||||
!!! tip "Support in other languages"
|
||||
Check us out in [Typescript](https://instructor-ai.github.io/instructor-js/) and [Elixir](https://github.com/thmsmlr/instructor_ex/).
|
||||
|
||||
Check out ports to other languages below:
|
||||
!!! tip "Not limited to the OpenAI API"
|
||||
|
||||
- [Typescript / Javascript](https://instructor-ai.github.io/instructor-js/)
|
||||
- [Elixir](https://github.com/thmsmlr/instructor_ex/)
|
||||
Instructor is not limited to the OpenAI API, we have support for many other backends that via patching. Check out more on [patching](./concepts/patching.md).
|
||||
|
||||
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!
|
||||
1. Wrap OpenAI's SDK
|
||||
2. Wrap the create method
|
||||
|
||||
Including but not limited to:
|
||||
|
||||
- [Together](./blog/posts/together.md)
|
||||
- [Ollama](./blog/posts/ollama.md)
|
||||
- [AnyScale](./blog/posts/anyscale.md)
|
||||
- [llama-cpp-python](./blog/posts/llama-cpp-python.md)
|
||||
|
||||
## Usage
|
||||
|
||||
|
||||
+2
-2
@@ -120,10 +120,10 @@ nav:
|
||||
- Introduction:
|
||||
- Welcome To Instructor: 'index.md'
|
||||
- Why use Instructor?: 'why.md'
|
||||
- Prompting Tips: 'concepts/prompting.md'
|
||||
- Help with Instructor: 'help.md'
|
||||
- Installation: 'installation.md'
|
||||
- Contributing: 'contributing.md'
|
||||
- Tips: 'concepts/prompting.md'
|
||||
- Concepts:
|
||||
- Philosophy: 'concepts/philosophy.md'
|
||||
- Models: 'concepts/models.md'
|
||||
@@ -163,7 +163,7 @@ nav:
|
||||
- Image to Ad Copy: 'examples/image_to_ad_copy.md'
|
||||
- Ollama: 'examples/ollama.md'
|
||||
- SQLModel Integration: 'examples/sqlmodel.md'
|
||||
- Hub:
|
||||
- "Hub (new!)":
|
||||
- Introduction: 'hub/index.md'
|
||||
- Single Classification Model: 'hub/single_classification.md'
|
||||
- Multiple Classification Model: 'hub/multiple_classification.md'
|
||||
|
||||
Reference in New Issue
Block a user