# Prodigy 1.12.0rc2 release candidate available for download! **URL:** \ **Category:** Uncategorized\ **Tags:** news\ **Created:** [June 28, 2023, 3:18pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636 "2023-06-28T15:18:39Z")\ **Posts on this page:** 6\ **Page:** 1
**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:** [June 28, 2023, 3:18pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/1 "2023-06-28T15:18:39Z")
In the last few weeks we've been collecting your feedback on the `v1.12` alphas (thanks for giving it a spin!) and we've been ironing out all the outstanding issues. We are excited to announce that `v1.12 `release candidate (`v1.12.0rc2`) is now available for download! Like the alphas (and the upcoming `v1.12` stable) this download is available to all `v1.11x `licence holders. As mentioned in our [previous post](https://support.prodi.gy/t/prodigy-1-12-alpha-release-llm-assisted-workflows-prompt-engineering-fully-custom-task-routing-for-multi-annotator-scenarios/6552), for `v1.12 `we have completely refactored Prodigy internals to make the annotation flow **more tractable** and **more customizable.** Adjusting the `Controller` and adding new components such as `Stream` and `Source` let us deliver a number of exciting features. Here are some of the highlights: - **LLM-assisted workflows** ![](https://slabstatic.com/prod/uploads/ox7aj5ff/posts/images/BCLbRsc6FZlTTROCXx44Qtcb.png) Prodigy `v1.12` offers built-in recipes for bootstrapping [NER](https://future.prodi.gy/docs/large-language-models#ner-usage) and [Textcat](https://future.prodi.gy/docs/large-language-models#textcat-usage) annotations with OpenAI gpt-3.5 model. You can easily set up the workflow where the annotators curate label suggestions from the LLM, which is bound to significantly speed up the annotation process. Apart from NER and Textcat, we also provide recipes for [terminology generation](https://future.prodi.gy/docs/recipes/#terms-openai.fetch) which, after curation, can be used as patterns in the PatternMatcher for another type of annotation bootstrapping. See our [docs](https://future.prodi.gy/docs/large-language-models#terms-usage) for example code snippets! The recipes support both **zero-shot** and **few-shot** prompts i.e. they allow you to provide some examples of expected output to steer the model in the right direction. Prodigy provides you with the default prompt template, but of course, custom templates are supported as well. In order to help you make an informed the decision with respect to the optimal prompt for your purpose, Prodigy `v1.12` comes with a couple of prompt engineering recipes. ![](https://slabstatic.com/prod/uploads/ox7aj5ff/posts/images/NFY96cSsqIU_zJMKCZh1PqSd.png) You can choose between **A/B** style evaluation or set up a **tournament** between 3 or more prompts. The [ab.openai.tournament](https://future.prodi.gy/docs/recipes/#ab-openai.tournament) uses an algorithm inspired by [the Glicko ranking system](http://www.glicko.net/glicko/glicko.pdf) to set up the duels and keep track of the best performing candidate. Please check out our LLM [guide](https://future.prodi.gy/docs/large-language-models) for more details. - **The full customization of the annotation flow.** ![](https://slabstatic.com/prod/uploads/ox7aj5ff/posts/images/w_CtKziRAlgDzOVgWpC9_gA3.png) We've exposed two brand new recipe components: the [task router](https://future.prodi.gy/docs/custom-recipes#task_router) and the [session factory](https://future.prodi.gy/docs/custom-recipes#session_factory) that let you control how tasks are distributed across annotators and what should happen when a new annotators joins the server. We have expanded the settings for annotation overlap. Apart from full and zero overlap, you can now set **partial overlap** via new `annotations_per_task` config setting. More importantly though you can implement a **fully custom task router**. For example, you could distribute tasks based on the model score or annotator's expertise. Please check out our [guide](https://future.prodi.gy/docs/task-routing) to task routing for more details and ideas. - **Source-based progress estimation** ![](https://slabstatic.com/prod/uploads/ox7aj5ff/posts/images/KKH30XuGXHXJIRuPtAzTtUWe.png) In Prodigy `v1.12` we have re-implemented the internal representations of the task stream and the input source. The stream is now aware of the underlying source and how much of it has been consumed by the annotators. This allows us to offer more reliable progress tracking for the workflows where the target number of annotations is not known upfront. In the UX, you'll notice 3 different types of progress bar: `target progress` (based on the set target), `source progress` (reflects the progress through the source object) and `progress` (for custom progress estimators). Since the semantics of these new progress bars is different, we recommend reading our [docs on progress](https://future.prodi.gy/docs/api-components#controller-get-progress) which explain that in detail. We have also improved the loaders and provided a refactored [get\_stream](https://future.prodi.gy/docs/api-components#stream.get_stream) utility that resolves the source type and initializes the [Stream](https://future.prodi.gy/docs/api-components#stream) accordingly. We also added support for `Parquet` input files as well as a new section on the docs about [deploying Prodigy](https://future.prodi.gy/docs/deployment). These are the highlights,`v1.12`also comes with a number of smaller features, bug fixes and DX improvements. And it supports python 3.11. Please check out the full `v1.12rc2` [changelog](https://future.prodi.gy/docs/changelog#v1.12.0rc1) for details. As always, we are looking forward to any feedback you might have! To install: ```python pip install --pre prodigy -f https://XXXX-XXXX-XXXX-XXXX@download.prodi.gy ``` ---
**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:** [June 28, 2023, 3:19pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/2 "2023-06-28T15:19:12Z")
---
**Author:** ![Andrey](https://avatars.discourse-cdn.com/v4/letter/a/73ab20/32.png) [@Andrey](https://support.prodi.gy/u/Andrey)\ **Post date:** [July 5, 2023, 6:06pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/3 "2023-07-05T18:06:11Z")
Hi @magdaaniol, thank you for sharing and the comments. I am wondering if there is a way to use other LLMs locally instead of the online OpenAI ones? Of course, at the expense of their accuracy. The reason I am asking is that I am working with sensitive data that sits within a secure research environment without internet access. Using this fantastic approach as `ner.openai.correct` will significantly boos the annotation performance. Perhaps some of the advanced Hugging Face models can be used instead to give a similar experience. Thank you. ---
**Author:** ![ryanwesslen](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ryanwesslen/32/2969_2.png) [@ryanwesslen](https://support.prodi.gy/u/ryanwesslen)\ **Post date:** [July 5, 2023, 6:41pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/4 "2023-07-05T18:41:13Z")
---
**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:** [July 5, 2023, 7:18pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/5 "2023-07-05T19:18:57Z")
Hi Andrey, You can definitely achieve similar results with a custom ner correct recipe and the new `spacy-llm` [library](https://github.com/explosion/spacy-llm). `spacy-llm` let's you integrate an LLM (hosted or local) as a spaCy component. It will take care of prompt generation and parsing and store the LLM annotation results on the Doc object just like any other spaCy pipeline. To use a LLM with spaCy you’ll need to start by creating a configuration file that tells `spacy-llm` how to construct a prompt for your task. Please see `spacy-llm` docs for [details](https://github.com/explosion/spacy-llm), but for NER it could look like this: ```python [nlp] lang = "en" pipeline = ["llm"] [components] [components.llm] factory = "llm" [components.llm.task] @llm_tasks = "spacy.NER.v2" labels = ["PERSON", "ORGANISATION", "LOCATION"] [components.llm.backend] @llm_backends = "spacy.Dolly_HF.v1" # For better performance, use databricks/dolly-v2-12b instead model = "databricks/dolly-v2-3b" ``` Then, from your custom recipe you could assemble the nlp pipeline like so: ```python from spacy_llm.util import assemble # Assemble a spaCy pipeline from the config nlp = assemble("config.cfg") # Use this pipeline as you would normally doc = nlp("I know of a great pizza recipe with anchovis.") print(doc.ents) # (pizza, anchovis) ``` Once you have processed your examples with the LLM loaded pipeline, you can use it as input to [ner\_manual](https://prodi.gy/docs/api-interfaces#ner_manual) interface for annotators to correct the LLM annotations just like it's done with `openai.ner.correct.` In the very near future we are going to release Prodigy built-in `spacy-llm` recipes, but for now the same results can be achieved with a just a little bit custom scripting thanks to `spacy-llm`. Let us know how it goes and if you need any assistance! ---
**Author:** ![Andrey](https://avatars.discourse-cdn.com/v4/letter/a/73ab20/32.png) [@Andrey](https://support.prodi.gy/u/Andrey)\ **Post date:** [July 5, 2023, 7:29pm UTC](https://support.prodi.gy/t/prodigy-1-12-0rc2-release-candidate-available-for-download/6636/6 "2023-07-05T19:29:25Z")
Amazing! Thank you so much @magdaaniol for your quick response. I will double check the suggested `spacy-llm` library. We are training and developing custom Llama-based models and it will be great to see them integrated with Prodigy. Thank you!