{"id":18369602,"url":"https://github.com/unstructured-io/irs-manual-demo","last_synced_at":"2026-03-04T03:01:25.493Z","repository":{"id":174024616,"uuid":"625684470","full_name":"Unstructured-IO/irs-manual-demo","owner":"Unstructured-IO","description":null,"archived":false,"fork":false,"pushed_at":"2023-06-09T19:17:25.000Z","size":66913,"stargazers_count":15,"open_issues_count":1,"forks_count":7,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-06-14T14:04:41.837Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Unstructured-IO.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2023-04-09T21:32:13.000Z","updated_at":"2025-05-23T03:05:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"846cdbc9-4e9f-40fd-9434-40299711f427","html_url":"https://github.com/Unstructured-IO/irs-manual-demo","commit_stats":null,"previous_names":["unstructured-io/irs-manual-demo"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Unstructured-IO/irs-manual-demo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Firs-manual-demo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Firs-manual-demo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Firs-manual-demo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Firs-manual-demo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Unstructured-IO","download_url":"https://codeload.github.com/Unstructured-IO/irs-manual-demo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unstructured-IO%2Firs-manual-demo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30070479,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-04T01:03:42.280Z","status":"online","status_checked_at":"2026-03-04T02:00:07.464Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-05T23:29:55.664Z","updated_at":"2026-03-04T03:01:25.486Z","avatar_url":"https://github.com/Unstructured-IO.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Chat with IRS Manuals\n\nThis directory contains an application for chatting with IRS manuals. Once data is available, the chat application only uses self-hosted models and can be run in a disconnected environment. Here's how to get started with the chatbot:\n\n### Installation\n\n```bash\npip install -r requirements.txt\n```\n\n### Environment Variables\n\n**Note there are other options for these connections, but these are the ones referenced in this implementation**\n\n[OpenAI](https://platform.openai.com/docs/api-reference)\n\n[Pinecone](https://docs.pinecone.io/)\n\n```python\nPINECONE_API_KEY\nPINECONE_API_ENV\nOPENAI_API_KEY\nPINECONE_INDEX_NAME\n```\n\n### Download PDFs from IRS website\n\n```bash\npython download_data.py \u003cBase URL\u003e \u003cPage Start\u003e \u003cPage End\u003e \u003cTarget Directory\u003e\n```\n![Download](./gifs/down.gif)\n\n### Run PDFs against unstructured-ingest\n\n```bash\nPYTHONPATH=. ./unstructured/ingest/main.py \\\n  --local-input-path \u003cingest-input-dir\u003e \\\n  --structured-output-dir \u003cingest-output-dir\u003e \\\n  # optional parameter -\u003e this will hit the *NEW* API vs. processing locally\n  --partition-by-api\n  ```\n\n![Download gif](./gifs/process.gif)\n\n\nHere's an example of the structured json output\n\n![JSON](./gifs/sbys.gif)\n\n\n### Seed and utilize vector db\n\n```bash\npython ingest_data.py \u003cpath-to-structured-json-file-directory\u003e\n```\n\n### Run the chat CLI\n\n```bash\npython cli_app.py\n```\n\n![Chat](./gifs/chat.gif)\n\n### Chat with our hosted instance [here](https://huggingface.co/spaces/unstructuredio/irs-manuals)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funstructured-io%2Firs-manual-demo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funstructured-io%2Firs-manual-demo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funstructured-io%2Firs-manual-demo/lists"}