{"id":695520,"date":"2020-09-30T13:54:51","date_gmt":"2020-09-30T20:54:51","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=695520"},"modified":"2022-04-05T09:21:50","modified_gmt":"2022-04-05T16:21:50","slug":"pythia-ai-assisted-code-completion-system","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/pythia-ai-assisted-code-completion-system\/","title":{"rendered":"Pythia: AI-assisted Code Completion System"},"content":{"rendered":"<p>In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently deployed as part of Intellicode extension in Visual Studio Code IDE. Pythia exploits state-of-the-art large-scale deep learning models trained on code contexts extracted from abstract syntax trees. It is designed to work at a high throughput predicting the best matching code completions on the order of 100 <em>ms<\/em>.<\/p>\n<p>We describe the architecture of the system, perform comparisons to frequency-based approach and invocation-based Markov Chain language model, and discuss challenges serving Pythia models on lightweight client devices.<\/p>\n<p>The offline evaluation results obtained on 2700 Python open source software GitHub repositories show a top-5 accuracy of 92\\%, surpassing the baseline models by 20\\% averaged over classes, for both intra and cross-project settings.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently deployed as part of Intellicode extension in Visual Studio Code IDE. Pythia exploits state-of-the-art large-scale deep learning [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13560,13555],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-695520","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-programming-languages-software-engineering","msr-research-area-search-information-retrieval","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-9-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/1912.00742","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Alexey Svyatkovskiy","user_id":40672,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Alexey Svyatkovskiy"},{"type":"guest","value":"ying-zhao","user_id":770017,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=ying-zhao"},{"type":"user_nicename","value":"Shengyu Fu","user_id":40795,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shengyu Fu"},{"type":"guest","value":"neel-sundaresan","user_id":769174,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=neel-sundaresan"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[599946],"msr_group":[776485],"msr_project":[830764],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":830764,"post_title":"IntelliCode Completions","post_name":"intellicode-completions","post_type":"msr-project","post_date":"2022-03-29 23:46:58","post_modified":"2022-03-30 23:13:03","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/intellicode-completions\/","post_excerpt":"AI-driven code auto-completion in Visual Studio and VSCode The IntelliCode completions project started in 2018 when we tried to improve developer productivity through recommending class members based on user's code context in Visual Studio. The project took off after receiving overwhelming positive feedback from C# developers around the world. We later expanded it to more languages in both Visual Studio and VSCode. Most recently we have shipped IntelliCode whole line completion (opens in new tab)&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/830764"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/695520"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/695520\/revisions"}],"predecessor-version":[{"id":695538,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/695520\/revisions\/695538"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=695520"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=695520"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=695520"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=695520"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=695520"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=695520"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=695520"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=695520"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=695520"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=695520"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=695520"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=695520"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=695520"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=695520"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=695520"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=695520"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}