{"id":22656543,"url":"https://github.com/intervenehq/parser","last_synced_at":"2025-08-06T08:32:25.482Z","repository":{"id":199532966,"uuid":"700476261","full_name":"intervenehq/parser","owner":"intervenehq","description":"Open source NLA. Hosted service in private beta, signup now! Alternative to Zapier NLA","archived":false,"fork":false,"pushed_at":"2023-11-20T14:15:48.000Z","size":43005,"stargazers_count":24,"open_issues_count":2,"forks_count":7,"subscribers_count":0,"default_branch":"main","last_synced_at":"2023-11-20T15:34:56.065Z","etag":null,"topics":["agents","gpt","llm","openapi","rag"],"latest_commit_sha":null,"homepage":"https://tryintervene.com","language":"TypeScript","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/intervenehq.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}},"created_at":"2023-10-04T17:04:17.000Z","updated_at":"2023-11-17T05:01:34.000Z","dependencies_parsed_at":"2023-11-20T15:44:52.804Z","dependency_job_id":null,"html_url":"https://github.com/intervenehq/parser","commit_stats":null,"previous_names":["tryintervene/parser","intervenehq/parser"],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intervenehq%2Fparser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intervenehq%2Fparser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intervenehq%2Fparser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intervenehq%2Fparser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intervenehq","download_url":"https://codeload.github.com/intervenehq/parser/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228871543,"owners_count":17984456,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["agents","gpt","llm","openapi","rag"],"created_at":"2024-12-09T10:15:02.755Z","updated_at":"2024-12-09T10:15:03.513Z","avatar_url":"https://github.com/intervenehq.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Intervene Parser\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/tryintervene/parser/main/public/images/logo.jpg\" alt=\"Intervene Parser Logo\" width=\"200\" height=\"200\"\u003e\n  \u003cbr /\u003e\n  \u003cbr /\u003e\n  \u003ca href=\"https://discord.gg/tsgtfUEvWk\"\u003e\n   \u003cimg src=\"https://dcbadge.vercel.app/api/server/tsgtfUEvWk?compact=true\u0026style=flat\" alt=\"Discord\"/\u003e\n  \u003c/a\u003e\n\n[Introduction](#introduction) |\n[How to use](#usage) |\n[FAQs](#faqs) |\n[Contact](mailto:me@sudhanshug.com)\n\n\u003c/p\u003e\n\n\u003e Launching a drop-in replacement to Zapier NLA by Nov 7th! Please contact me [me@sudhanshug.com](mailto:me@sudhanshug.com) if you have any questions.\n\n## Introduction\n\n_Open source Natural Language Actions (NLA)_\n\nTranslate natural language into API calls.\n\n\u003cbr/\u003e\n\n### Here is a web based demo to try it out:\nhttps://tryintervene.github.io/parser-demo/\n\n\u003cbr /\u003e\n\nHere's a quick demo video:\n\nhttps://github.com/tryintervene/parser/assets/9914480/b91eb0d2-64c5-4231-8989-1c27a105c3be\n\nHere's a sample output:\n\n```bash\n{\n    \"provider\": \"\u003cAPI provider name\u003e\",\n    \"method\": \"\u003cHttp Method\u003e\",\n    \"path\": \"\u003cAPI endpoint to call\u003e\",\n    \"bodyParams\": \"\u003ceval'able function to return body params\u003e\",\n    \"queryParams\": \"\u003ceval'able function to return query params\u003e\",\n    \"pathParams\": \"\u003ceval'able function to return path params\u003e\",\n    \"requestContentType\": \"application/x-www-form-urlencoded\",\n    \"responseContentType\": \"application/json\",\n    \"responseSchema\": \"\u003cschema of the Response\u003e\"\n  }\n```\n\n## Usage\n\nYou can install the parser by running:\n\n```bash\nnpm install @intervene/parser\n```\n\n\u003e Note: The project is under active development and has not reached v0 yet. Proceed with caution and report any issues you may notice.\n\n## FAQs\n\n### This looks cool, but what about prod?\n\nYou can use the library as is in production but proceed with caution as it is under active development.\n\nIf you're interested in a hosted solution, please [fill out this quick form](https://tally.so/r/wzMJ8a), and I will get back to you in no time!\n\n### Can it run with GPT 3.5?\n\nYou can use GPT 3.5 (or equivalent) which will make this a lot faster, cheaper but less accurate. You can go this route for simpler API calls that need to extract data from the user prompt. You can use the `--trivial` flag to do this\n\nHowever, the code can be optimized to use the less capable models for selective tasks. Open to PRs :)\n\n### What about other LLMs?\n\nThis project works only with OpenAI models for now. I will be exploring other LLMs as well. Let me know [which one you want by opening an issue here](https://github.com/tryintervene/parser/issues/new?title=Request%20to%20integrate%20LLM:%20[LLM]\u0026body=Hi,%20can%20you%20please%20add%20the%20following%20LLM%20to%20the%20parser:%20) or feel free to open a PR!\n\n### Umm I don't like JavaScript. What about python?\n\nBefore porting it to Python or Golang (or both), I want to determine if there are any real-world use cases for this technology. Please try out the CLI, share your thoughts, and I will promptly port it to other languages based on the feedback.\n\nI chose to start with a statically typed language due to the nature of the project. I could have used Golang, but I aimed for simplicity, hence the choice of TypeScript.\n\n### I want to contribute\n\nAwesome! PRs and issues are welcome!\n\n## Credits\n\nCredits to [LangChain](https://github.com/langchain-ai/langchain) and [LlamaIndex](https://github.com/run-llama/llama_index) for the inspiration for some of the techniques used in the project.\n\nSpecial credits to [@rohanmayya](https://github.com/rohanmayya) for helping lay the foundation for this project.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintervenehq%2Fparser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintervenehq%2Fparser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintervenehq%2Fparser/lists"}