# Prodigy 1.13.0 is out! 🎉

**URL:** <https://support.prodi.gy/t/prodigy-1-13-0-is-out/6737>\
**Category:** Uncategorized\
**Tags:** news\
**Created:** [August 15, 2023, 10:44am UTC](https://support.prodi.gy/t/prodigy-1-13-0-is-out/6737 "2023-08-15T10:44:38Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![magdaaniol](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/magdaaniol/32/2787_2.png) [@magdaaniol](https://support.prodi.gy/u/magdaaniol)\
**Post date:** [August 15, 2023, 10:44am UTC](https://support.prodi.gy/t/prodigy-1-13-0-is-out/6737/1 "2023-08-15T10:44:38Z")

</div>

Hey everyone!

We have just released Prodigy `v1.13.0` which comes with a set of **new recipes** for **LLM-assisted workflows** via [`spacy-llm`](https://github.com/explosion/spacy-llm) that offers **multi-LLM backends** as well as **improved prompts** for **NER** , **textcat** and **spancat** annotation! ✨

[![](https://img.youtube.com/vi/zEu-ZJz0NOo/maxresdefault.jpg "PRODIGY v1.13: SPACY-LLM support, more LLM backends, better prompts and local model support!") ](https://www.youtube.com/watch?v=zEu-ZJz0NOo)

The new [spacy-llm recipes](https://prodi.gy/docs/large-language-models#getting-started-spacy-llm) are an improved version of our existing OpenAI recipes which we'll be slowly phasing out.

There are several advantages to the new spacy-llm workflows that we'd like to highlight:

- you can now choose from **various LLM providers** or even use a **locally running model** eliminating the need to send your data to a third party. A full list of supported models can be found on [`spacy-llm` docs](https://spacy.io/usage/large-language-models#models):  
 ![image](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/4/4753a1ecee4470e9e1f738e1b0c0f201150bda38.png)
- we have provided workflows for **NER,**  **textcat** and **spancat** annotations but in custom recipes you can benefit from all [`spacy-llm` tasks](https://spacy.io/usage/large-language-models#tasks). The tasks and prompts are under active development from spaCy team so all the upgrades to `spacy-llm` can be expected to be directly transferable to your Prodigy workflows.  
 ![image](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/7/7a20cbcebadb8b2c7166f683f3a9f5104c5aaf78.png)
- you are now able to improve your prompts by adding **examples** and **label definitions** for your task
- you can also configure the **cache** to help reduce costs
- all these settings (and [more](https://github.com/explosion/spacy-llm)!) are configurable using [spaCy config system](https://spacy.io/api/data-formats#config) which makes it easy to keep your environment reproducible and well organized:  
 ![image](https://us1.discourse-cdn.com/flex020/uploads/prodigy/original/2X/f/fc9f65725ddfc0c64885ceb845a78ea6ee4b3da2.jpeg)

We have updated our [Large Language Models docs](https://prodi.gy/docs/large-language-models), where you find all details and a ton of examples.  
As always, we are looking forward to your feedback 🙂

To install:

```python
pip install --upgrade prodigy -f https://XXXX-XXXX-XXXX-XXXX@download.prodi.gy

```

---

<div class="post-metadata">

**Author:** ![magdaaniol](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/magdaaniol/32/2787_2.png) [@magdaaniol](https://support.prodi.gy/u/magdaaniol)\
**Post date:** [August 15, 2023, 10:45am UTC](https://support.prodi.gy/t/prodigy-1-13-0-is-out/6737/2 "2023-08-15T10:45:04Z")

</div>



---

<div class="post-metadata">

**Author:** ![magdaaniol](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/magdaaniol/32/2787_2.png) [@magdaaniol](https://support.prodi.gy/u/magdaaniol)\
**Post date:** [August 23, 2023, 4:52pm UTC](https://support.prodi.gy/t/prodigy-1-13-0-is-out/6737/3 "2023-08-23T16:52:04Z")

</div>