# \#api **URL:** https://support.prodi.gy/tag/api/12.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Support python type hints to improve DX](https://support.prodi.gy/t/support-python-type-hints-to-improve-dx/5214)
**Author:** [@nix411](https://support.prodi.gy/u/nix411)\ **Replies:** 8\ **Last updated:** [November 5, 2024, 11:23am UTC](https://support.prodi.gy/t/support-python-type-hints-to-improve-dx/5214 "2024-11-05T11:23:02Z")
Do you support python type hints to improve the developer experience when writing custom scripts? Currently I get no code completion in VS Code when I import various functions from prodigy. --- ## [Are there any health check endpoints for prodigy service.](https://support.prodi.gy/t/are-there-any-health-check-endpoints-for-prodigy-service/1740)
**Author:** [@kapilsahu91](https://support.prodi.gy/u/kapilsahu91)\ **Replies:** 2\ **Last updated:** [September 25, 2024, 12:49pm UTC](https://support.prodi.gy/t/are-there-any-health-check-endpoints-for-prodigy-service/1740 "2024-09-25T12:49:27Z")
Are there any health check endpoints when I’m deploying prodigy services to production? something like http://x.x.x.x:8080/health that would return a 200 OK status if I post to it from any application health monitorin… --- ## [End-to-end nlp project NER](https://support.prodi.gy/t/end-to-end-nlp-project-ner/5050)
**Author:** [@issaga](https://support.prodi.gy/u/issaga)\ **Replies:** 1\ **Last updated:** [December 9, 2021, 2:16am UTC](https://support.prodi.gy/t/end-to-end-nlp-project-ner/5050 "2021-12-09T02:16:25Z")
Hello everybody, I am working on a NER nlp project, we want to have a complete pipeline ie from annotation to model development and stored data in posgresql. And then deployed this model on our web platform, and the use… --- ## [Possible to interface via another app?](https://support.prodi.gy/t/possible-to-interface-via-another-app/4228)
**Author:** [@capaldo](https://support.prodi.gy/u/capaldo)\ **Replies:** 6\ **Last updated:** [May 24, 2021, 9:52pm UTC](https://support.prodi.gy/t/possible-to-interface-via-another-app/4228 "2021-05-24T21:52:30Z")
Hey guys, I'm currently running through the documentation and noticed a lot of hooks to receive information but not many to send. I guess my question is, with the API at present, would I be able to interface with prodig… --- ## [prodigy.serve does not work with custom recipe](https://support.prodi.gy/t/prodigy-serve-does-not-work-with-custom-recipe/2379)
**Author:** [@praveer](https://support.prodi.gy/u/praveer)\ **Replies:** 1\ **Last updated:** [December 29, 2019, 12:42pm UTC](https://support.prodi.gy/t/prodigy-serve-does-not-work-with-custom-recipe/2379 "2019-12-29T12:42:21Z")
I am trying to run a custom recipe from prodigy.serve but it works fine on command line but does not work when triggered from python --- ## [Invalid db component in custom recipe](https://support.prodi.gy/t/invalid-db-component-in-custom-recipe/2337)
**Author:** [@simon.gurcke](https://support.prodi.gy/u/simon.gurcke)\ **Replies:** 1\ **Last updated:** [December 19, 2019, 8:28am UTC](https://support.prodi.gy/t/invalid-db-component-in-custom-recipe/2337 "2019-12-19T08:28:27Z")
I create a Database object as described in the documentation to use a PostgreSQL database in a custom recipe, and I pass it in as the db component in the returned dict. This worked fine in Prodigy 1.8.4 but in 1.9.0 I'm … --- ## [Recipes from entry points in 1.9.0](https://support.prodi.gy/t/recipes-from-entry-points-in-1-9-0/2336)
**Author:** [@simon.gurcke](https://support.prodi.gy/u/simon.gurcke)\ **Replies:** 1\ **Last updated:** [December 19, 2019, 11:37am UTC](https://support.prodi.gy/t/recipes-from-entry-points-in-1-9-0/2336 "2019-12-19T11:37:23Z")
Hi there, I have my recipes and utilities in a prodigy\_utils package with entry points. After upgrading Prodigy to 1.9.0 it can't find my recipes anymore and shows a confusing error message: ✘ Can't find recipe or comma… --- ## [How are answers from active learning used in training](https://support.prodi.gy/t/how-are-answers-from-active-learning-used-in-training/2003)
**Author:** [@Superscope](https://support.prodi.gy/u/Superscope)\ **Replies:** 2\ **Last updated:** [September 13, 2019, 1:10pm UTC](https://support.prodi.gy/t/how-are-answers-from-active-learning-used-in-training/2003 "2019-09-13T13:10:15Z")
I have what I think is a basic question (if this has been addressed on the forum pls point, poking around I couldn't find an answer). The annotations from active learning have a label and an answer. What role does the a… --- ## [Problems starting recipes programatically](https://support.prodi.gy/t/problems-starting-recipes-programatically/1994)
**Author:** [@edward](https://support.prodi.gy/u/edward)\ **Replies:** 1\ **Last updated:** [September 9, 2019, 3:45pm UTC](https://support.prodi.gy/t/problems-starting-recipes-programatically/1994 "2019-09-09T15:45:33Z")
Hi, I'm trying to integrate Prodigy into a Python-based automated workflow. I want to start a task like this: from prodigy import recipes output=recipes.ner.make\_gold( dataset='ner-dataset', spacy\_model=Pa… --- ## [Dynamically add to stream during update](https://support.prodi.gy/t/dynamically-add-to-stream-during-update/1963)
**Author:** [@kabir](https://support.prodi.gy/u/kabir)\ **Replies:** 5\ **Last updated:** [September 1, 2019, 6:34pm UTC](https://support.prodi.gy/t/dynamically-add-to-stream-during-update/1963 "2019-09-01T18:34:22Z")
I'd like to build a workflow that dynamically fetches data during the update callback and adds new tasks to the stream. Is there a way to do that from a custom recipe? It seems that the stream is only called once and th… --- ## [Model Architecture textcat.train-batch](https://support.prodi.gy/t/model-architecture-textcat-train-batch/1932)
**Author:** [@Superscope](https://support.prodi.gy/u/Superscope)\ **Replies:** 2\ **Last updated:** [August 26, 2019, 2:32pm UTC](https://support.prodi.gy/t/model-architecture-textcat-train-batch/1932 "2019-08-26T14:32:08Z")
I was wondering what the exact architecture of the CNN underlying the textcat.train-batch is? I have seen it described as a 'simple cnn' and I assume its the same one being used by spacy's textcat component. Thanks --- ## [/get\_questions in classification task not returning id?](https://support.prodi.gy/t/get-questions-in-classification-task-not-returning-id/1924)
**Author:** [@arnaudsj](https://support.prodi.gy/u/arnaudsj)\ **Replies:** 3\ **Last updated:** [August 23, 2019, 9:35am UTC](https://support.prodi.gy/t/get-questions-in-classification-task-not-returning-id/1924 "2019-08-23T09:35:40Z")
Hi, I am trying to run an active learning annotation classification task(textcat.teach) via the prodigy api, but contrary to what the documentation states in Prodigy's excellent README.html, I don't see an id field in t… --- ## [Can't import DB from prodigy](https://support.prodi.gy/t/cant-import-db-from-prodigy/1854)
**Author:** [@aslitoj](https://support.prodi.gy/u/aslitoj)\ **Replies:** 2\ **Last updated:** [August 5, 2019, 9:51am UTC](https://support.prodi.gy/t/cant-import-db-from-prodigy/1854 "2019-08-05T09:51:50Z")
Hello, I m very new to the prodigy and was following the very first step for an annotation task, and I used ner.manual in order to label the multi words in the pattern that I'm looking for. But at some point when I try … --- ## [End session request](https://support.prodi.gy/t/end-session-request/1865)
**Author:** [@atilla](https://support.prodi.gy/u/atilla)\ **Replies:** 4\ **Last updated:** [August 4, 2019, 2:55pm UTC](https://support.prodi.gy/t/end-session-request/1865 "2019-08-04T14:55:48Z")
I'm trying to end a session with a POST request: url = "http://localhost:8080/end\_session" import requests params = {'session\_id':"2019-08-03\_20-36-12"} r = requests.post(url=url, params=params) print(r.json()) yet ge… --- ## [Starting Prodigy server on a remote machine ('--no-browser --port=XXXX)](https://support.prodi.gy/t/starting-prodigy-server-on-a-remote-machine-no-browser-port-xxxx/1688)
**Author:** [@Andrey](https://support.prodi.gy/u/Andrey)\ **Replies:** 2\ **Last updated:** [June 21, 2019, 12:12pm UTC](https://support.prodi.gy/t/starting-prodigy-server-on-a-remote-machine-no-browser-port-xxxx/1688 "2019-06-21T12:12:21Z")
I’m using a remote high spec linux server for training spacy models and prodigy. Is there any possibility to start the prodigy server remotely, similar to jupyter notebook with ‘–no-browser --port=XXXX’ option? --- ## [question about function add\_labels\_options](https://support.prodi.gy/t/question-about-function-add-labels-options/1621)
**Author:** [@Kasra](https://support.prodi.gy/u/Kasra)\ **Replies:** 3\ **Last updated:** [June 7, 2019, 8:47am UTC](https://support.prodi.gy/t/question-about-function-add-labels-options/1621 "2019-06-07T08:47:40Z")
Hello, I am trying to add the recipe textcat.manual to a previous prodigy version. The reason is that at the moment I am not ready to switch to the newest spacy version so I cannot upgrade to the latest prodigy version … --- ## [Why is there no active learning for manual/gold standard annotations?](https://support.prodi.gy/t/why-is-there-no-active-learning-for-manual-gold-standard-annotations/1507)
**Author:** [@ldorigo](https://support.prodi.gy/u/ldorigo)\ **Replies:** 2\ **Last updated:** [May 10, 2019, 7:38pm UTC](https://support.prodi.gy/t/why-is-there-no-active-learning-for-manual-gold-standard-annotations/1507 "2019-05-10T19:38:36Z")
Hi there, Apologies in case this was brought up before or in the documentation, I haven’t found a good answer. From what I understand (and I might be wrong, I haven’t studied the details behind the active learning stra… --- ## [Including own active learning function / active learning outputs](https://support.prodi.gy/t/including-own-active-learning-function-active-learning-outputs/1498)
**Author:** [@krstp](https://support.prodi.gy/u/krstp)\ **Replies:** 6\ **Last updated:** [May 10, 2019, 3:09pm UTC](https://support.prodi.gy/t/including-own-active-learning-function-active-learning-outputs/1498 "2019-05-10T15:09:54Z")
Dear Prodigy, Two questions: I would like to add my own active learning function and/or external 3rd party supported active learning library. Is it possible to include those within prodigy instead of build-in Prodigy… --- ## [using prodigy.serve for textcat.batch-train](https://support.prodi.gy/t/using-prodigy-serve-for-textcat-batch-train/1405)
**Author:** [@Ati](https://support.prodi.gy/u/Ati)\ **Replies:** 13\ **Last updated:** [May 6, 2019, 9:35pm UTC](https://support.prodi.gy/t/using-prodigy-serve-for-textcat-batch-train/1405 "2019-05-06T21:35:47Z")
I get the following error when using prodigy.serve to call textcat.batch-train recipe: File “/usr/local/lib/python3.6/site-packages/prodigy/init.py”, line 23, in serve controller.config.update(config) AttributeError: … --- ## [On\_exit not called](https://support.prodi.gy/t/on-exit-not-called/1396)
**Author:** [@akshitasood63](https://support.prodi.gy/u/akshitasood63)\ **Replies:** 2\ **Last updated:** [April 16, 2019, 10:18am UTC](https://support.prodi.gy/t/on-exit-not-called/1396 "2019-04-16T10:18:09Z")
Hi @ines @honnibal , Whenever I exit prodigy, my on\_exit function is not called, whereas on\_load gets called whenever I start prodigy. The way I exit is by killing each of the individual process running on different po… --- ## [Text Classifier model architecture](https://support.prodi.gy/t/text-classifier-model-architecture/114)
**Author:** [@jan](https://support.prodi.gy/u/jan)\ **Replies:** 7\ **Last updated:** [January 17, 2019, 12:09pm UTC](https://support.prodi.gy/t/text-classifier-model-architecture/114 "2019-01-17T12:09:15Z")
Is there a place in the docs where the architecture of the text classifier is laid out ? i looked at the spacy/\_ml.py implementation, but it seems i first have to learn to read thinc code before i can understand what’s g… --- ## [Custom Recipe - Stream Parameters](https://support.prodi.gy/t/custom-recipe-stream-parameters/953)
**Author:** [@landon](https://support.prodi.gy/u/landon)\ **Replies:** 3\ **Last updated:** [November 13, 2018, 6:13pm UTC](https://support.prodi.gy/t/custom-recipe-stream-parameters/953 "2018-11-13T18:13:42Z")
I wrote a custom recipe. I implemented both stream() and update() to both interface with an external API to GET messages, and POST annotations, respectively. Naively, I would implement my GET messages endpoint to get th… --- ## [How will merge\_spans treat Negative examples (no annotations)](https://support.prodi.gy/t/how-will-merge-spans-treat-negative-examples-no-annotations/924)
**Author:** [@manganc](https://support.prodi.gy/u/manganc)\ **Replies:** 4\ **Last updated:** [November 8, 2018, 4:34pm UTC](https://support.prodi.gy/t/how-will-merge-spans-treat-negative-examples-no-annotations/924 "2018-11-08T16:34:05Z")
Hi guys, I followed this article: Merging annotations from different datasets to deal with the following scenario: Trained Dataset A w/ Label A off training data TD-A Trained Dataset B w/ Label B off training data TD-… --- ## [Asynchronous stream](https://support.prodi.gy/t/asynchronous-stream/773)
**Author:** [@alejandro.mesa](https://support.prodi.gy/u/alejandro.mesa)\ **Replies:** 3\ **Last updated:** [October 15, 2018, 11:50am UTC](https://support.prodi.gy/t/asynchronous-stream/773 "2018-10-15T11:50:03Z")
Hello, The stream for our recipe is composed of text elements that are loaded asynchronously every hour and for several days. For this reason, when we first run prodigy with our custom recipe, we’re able to label the ta… --- ## [Understanding high level flow of Prodigy for text classification](https://support.prodi.gy/t/understanding-high-level-flow-of-prodigy-for-text-classification/849)
**Author:** [@DataVakra](https://support.prodi.gy/u/DataVakra)\ **Replies:** 1\ **Last updated:** [September 28, 2018, 10:59am UTC](https://support.prodi.gy/t/understanding-high-level-flow-of-prodigy-for-text-classification/849 "2018-09-28T10:59:31Z")
Hello guys, Some background on what i am trying to do I am creating a custom recipe for sentence categorization to categorize for e.g. “Does the sentence imply the user blaming his employer?” and want to use the new s… --- ## [Getting previous answers on\_load](https://support.prodi.gy/t/getting-previous-answers-on-load/769)
**Author:** [@log0ymxm](https://support.prodi.gy/u/log0ymxm)\ **Replies:** 2\ **Last updated:** [August 21, 2018, 6:23pm UTC](https://support.prodi.gy/t/getting-previous-answers-on-load/769 "2018-08-21T18:23:57Z")
I’m working with a custom recipe that has a model update. I’d like to train the model with the on\_load function but it seems the docs for this have a mistake. For the basic example: def on\_load(controller): session… --- ## [Prodigy single span data incompatible with NER model which expects all data to be present?](https://support.prodi.gy/t/prodigy-single-span-data-incompatible-with-ner-model-which-expects-all-data-to-be-present/762)
**Author:** [@plusepsilon](https://support.prodi.gy/u/plusepsilon)\ **Replies:** 3\ **Last updated:** [August 17, 2018, 6:26pm UTC](https://support.prodi.gy/t/prodigy-single-span-data-incompatible-with-ner-model-which-expects-all-data-to-be-present/762 "2018-08-17T18:26:58Z")
Prodigy data requires single spans for NER annotation (labeling one entity at a time). But I think the NER model requires all of the entities labeled at training time. Please correct me if I am wrong. What we noticed is… --- ## [What does the "id" field in the "tokens" mean?](https://support.prodi.gy/t/what-does-the-id-field-in-the-tokens-mean/721)
**Author:** [@Zainpann](https://support.prodi.gy/u/Zainpann)\ **Replies:** 3\ **Last updated:** [August 1, 2018, 1:54pm UTC](https://support.prodi.gy/t/what-does-the-id-field-in-the-tokens-mean/721 "2018-08-01T13:54:09Z")
{ "text":"Tabdeli Yhi Log Laskengy", "\_input\_hash":-915958241, "\_task\_hash":694961601, "tokens":\[ {"text":"Tabdeli","start":0,"end":7,"id":0}, {"text":"Yhi","start":8,"end":11,"id":1}, … --- ## [Prodigy Version 1.5.1 vs 1.4.2](https://support.prodi.gy/t/prodigy-version-1-5-1-vs-1-4-2/690)
**Author:** [@claudio84destri](https://support.prodi.gy/u/claudio84destri)\ **Replies:** 3\ **Last updated:** [July 21, 2018, 10:06am UTC](https://support.prodi.gy/t/prodigy-version-1-5-1-vs-1-4-2/690 "2018-07-21T10:06:51Z")
Dears, it appears there a difference between version 1.4.2 and 1.5.1 with regard to annotations displayed. In version 1.5.1 it seems that after a web browser refresh there is a new annotation, and it is possible that s… --- ## [Opaque error from malformed prodigy.json](https://support.prodi.gy/t/opaque-error-from-malformed-prodigy-json/670)
**Author:** [@andy](https://support.prodi.gy/u/andy)\ **Replies:** 2\ **Last updated:** [July 4, 2018, 1:21pm UTC](https://support.prodi.gy/t/opaque-error-from-malformed-prodigy-json/670 "2018-07-04T13:21:49Z")
I commented out a line in my prodigy.json file with a #, and Prodigy really didn’t like that. I got the following error and it took me a while to figure out what the problem was. Is there a way of making problems with th… [Next page](https://support.prodi.gy/tag/api/12.md?match_all_tags=true&page=1&tags%5B%5D=api)