{"id":31911960,"url":"https://github.com/lbdudc/dsl-xpert","last_synced_at":"2026-04-01T22:05:15.680Z","repository":{"id":239732608,"uuid":"800401263","full_name":"lbdudc/dsl-xpert","owner":"lbdudc","description":"This tool provides a web interface to define domain-specific languages and uses large language models (LLM) to interact with those grammars via chat.","archived":false,"fork":false,"pushed_at":"2025-07-31T10:02:22.000Z","size":4629,"stargazers_count":16,"open_issues_count":0,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-28T00:37:58.296Z","etag":null,"topics":["dsl","huggingface","langium","llm","openai","webllm"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lbdudc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-05-14T09:06:20.000Z","updated_at":"2026-02-16T20:23:05.000Z","dependencies_parsed_at":"2025-03-07T11:24:04.325Z","dependency_job_id":"30da2d73-e963-4141-ab9b-817c97f762b5","html_url":"https://github.com/lbdudc/dsl-xpert","commit_stats":null,"previous_names":["lbdudc/dsl-xpert"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/lbdudc/dsl-xpert","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lbdudc%2Fdsl-xpert","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lbdudc%2Fdsl-xpert/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lbdudc%2Fdsl-xpert/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lbdudc%2Fdsl-xpert/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lbdudc","download_url":"https://codeload.github.com/lbdudc/dsl-xpert/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lbdudc%2Fdsl-xpert/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31292632,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T21:15:39.731Z","status":"ssl_error","status_checked_at":"2026-04-01T21:15:34.046Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dsl","huggingface","langium","llm","openai","webllm"],"created_at":"2025-10-13T17:41:35.644Z","updated_at":"2026-04-01T22:05:15.648Z","avatar_url":"https://github.com/lbdudc.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DSL-Xpert\n\n![GitHub license](https://img.shields.io/badge/license-MIT-blue.svg) ![Node.js Version](https://img.shields.io/badge/node-%3E%3D%2020.2.0-brightgreen.svg) ![GitHub release (latest by date)](https://img.shields.io/github/v/release/lbdudc/dsl-xpert)[![DOI](https://zenodo.org/badge/DOI/10.1145/3652620.3687782.svg)](https://doi.org/10.1145/3652620.3687782)\n\nThis tool provides a web interface to define domain-specific languages and uses large language models (LLM) to interact with those grammars via chat.\n\n![image of the models created](./src/client/public/index_image.png)\n\nIt can validate the generated grammar instances while chatting with the LLM using [Langium](http://langium.org/).\n\n![image of the tool](./src/client/public/form_example.png)\n\nIt has integrations with:\n\n- **OpenAI** models\n- **HuggingFace Inference API**\n- **HuggingFace transformers**: running it locally\n- [WebLLM](https://webllm.mlc.ai/)\n- Connect to any server using **API REST requests**\n\n![image of chat](./src/client/public/chat_example.png)\n\nThen the user can chat with the LLM using the grammar defined.\n\n- [Usage](#usage)\n  - [Docker](#docker)\n  - [Standalone server](#standalone-server)\n  - [HuggingFace custom (only for standalone server)](#huggingface-custom-only-for-standalone-server)\n- [API Routes](#api-routes)\n- [Author](#author)\n- [License](#license)\n\n## Usage\n\nThe project can be run in different ways. The following sections describe how to run the project using Docker or as a standalone server.\n\n### Docker\n\nThe project can be run using Docker. To do so, execute the following commands:\n\nPrerequisites:\n\n- Docker\n- Docker Compose\n\n```sh\ndocker-compose up\n```\n\nThis will start tha application it wil run:\n\n- Web App:  `http://localhost:5555`\n- API: `http://localhost:5555/api`\n\n### Standalone server\n\nThe application also can be run without docker, as a standalone application. To do so, execute the following commands:\n\nPrerequisites:\n\n- NVM\n- Node.js\n- MongoDB\n- Python (optional only if the user wants to use the custom huggingface models)\n\n```sh\n\n# (Optional), check the .nvmrc file\n# for seeing what is the node version\nnvm use\n\nnpm install\nnpm run dev\n```\n\nThis will start:\n\n- Client at `http://localhost:5173`\n- Server at `http://localhost:5173/api`\n\nIt will be necessary to have a MongoDB database running, and set the variable in the `.env` file:\n\n```env\nMONGODB_URI=mongodb://localhost:27017/llm-dsl-builder\n```\n\n### HuggingFace custom (only for standalone server)\n\nWe already have added the HuggingFace Custom Server into the `docker-compose.yml` file, so it will be running by default.\n\nBut in thr standalone version, the user can run the server using the command:\n\n```sh\nnpm run dev:pyserver\n```\n\nThis will start the python server at `ws://localhost:8000/ws`,the client is already configured to interact with this server.\n\n### API Routes\n\nThe API provides the following routes:\n\n- `GET /models`: Get all models\n- `POST /models`: Create a new model\n- `GET /models/:id`: Get a model by id\n- `PUT /models/:id`: Update a model by id\n- `DELETE /models/:id`: Delete a model by id\n\n## Grammars\n\nThe grammars are defined using the Langium syntax. The user can define the grammar in the web interface, and it will be validated using Langium.\n\nExamples can be found in the `/grammars` folder.\n\n## Author\n\n- Victor Lamas\n  - Email: \u003cvictor.lamas@udc.es\u003e\n\n- Daniel Garcia-Gonzalez\n  - Email: \u003cd.garcia2@udc.es\u003e\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flbdudc%2Fdsl-xpert","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flbdudc%2Fdsl-xpert","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flbdudc%2Fdsl-xpert/lists"}