Commit Graph
65 Commits
Author SHA1 Message Date
Brandon Thomas f8e7ae3ced preproduction story finalization 2023-02-14 13:09:22 -05:00
Brandon Thomas a1b8a22225 Download files 2023-02-14 12:47:23 -05:00
Brandon Thomas 0a0105410d Get updated audio status 2023-02-14 05:13:57 -05:00
Brandon Thomas 69a79b76ea seems to work better? 2023-02-14 04:26:53 -05:00
Brandon Thomas 809387958c cleanup 2023-02-14 03:29:46 -05:00
Brandon Thomas 44f7824910 cleanup 2023-02-14 02:59:29 -05:00
Brandon Thomas 1e05dcb7e2 Add sequence order 2023-02-14 02:47:07 -05:00
Brandon Thomas 72bdea7d10 Record inference details 2023-02-14 02:22:00 -05:00
Brandon Thomas c3981e8554 idempotency crate, FakeYou requests to infer work 2023-02-14 02:03:31 -05:00
Brandon Thomas 6b937b7cd0 FakeYou rendering *almost* works 2023-02-14 01:37:26 -05:00
Brandon Thomas 5be10ae87a refactor/organize worker modules 2023-02-13 21:32:46 -05:00
Brandon Thomas 0764711439 pause controls for scraping 2023-02-13 17:12:12 -05:00
Brandon Thomas 969be4726c easier concurrency atomic bools, add controls for pieces 2023-02-13 17:05:22 -05:00
Brandon Thomas 8244bac6e1 tweak timings 2023-02-13 04:52:41 -05:00
Brandon Thomas 1d173a74d5 split into paragraph heuristic 2023-02-13 04:34:24 -05:00
Brandon Thomas 3786a64eb1 text splitting 2023-02-13 03:49:01 -05:00
Brandon Thomas 144df6ffc0 refactor to make llm rendition a part of production flow 2023-02-12 17:52:18 -05:00
Brandon Thomas 85e0ce4b4a Greenlighting stories + production workflow (abstract, but will use) 2023-02-12 15:54:26 -05:00
Brandon Thomas 7efb65ae08 new tables 2023-02-10 21:26:14 -05:00
Brandon Thomas ba3ff9768a WIP - tables for stories 2023-02-10 06:28:55 -05:00
Brandon Thomas b8e37d2e77 mark jobs done 2023-02-10 03:49:45 -05:00
Brandon Thomas 5a1e61b692 add some filters 2023-02-10 01:16:51 -05:00
Brandon Thomas 19b57b9c1d unused module 2023-02-10 00:41:57 -05:00
Brandon Thomas 6c33c31289 skip CNN video content 2023-02-08 05:13:45 -05:00
Brandon Thomas b1bbfe21ec OpenAI API calls 2023-02-08 03:36:41 -05:00
Brandon Thomas 5878224f7e rendition schema 2023-02-07 22:40:35 -05:00
Brandon Thomas 5497b7c0aa small refactor 2023-02-07 18:54:23 -05:00
Brandon Thomas ce17a3e1bf CNN articles, shared extractors 2023-02-07 17:13:07 -05:00
Brandon Thomas b8fe3a0e7d fix pagination bugs 2023-02-07 03:04:04 -05:00
Brandon Thomas 6a86f43a92 scraping appears to work 2023-02-07 02:18:00 -05:00
Brandon Thomas 393bc084d4 scope aichatbot to sqlite 2023-02-06 18:38:33 -05:00
Brandon Thomas 5f35323a5f fixes for windows 2023-02-06 16:14:24 -05:00
Brandon Thomas 30c9f779bd outline remaining work 2023-02-06 05:00:32 -05:00
Brandon Thomas 4f7d03a505 index cnn + techcrunch 2023-02-06 04:56:49 -05:00
Brandon Thomas 5a031b1b80 indexer flow 2023-02-06 04:49:28 -05:00
Brandon Thomas d1b6facd95 worker threads 2023-02-06 04:46:10 -05:00
Brandon Thomas 79984058c0 Save webpage and scraping summary 2023-02-06 03:56:51 -05:00
Brandon Thomas adc52cd01e directory to persist html 2023-02-06 03:32:07 -05:00
Brandon Thomas 8ff2408cbf begin to work on persisting scraping 2023-02-06 02:47:21 -05:00
Brandon Thomas 25b7024655 title, more fields 2023-02-05 17:32:29 -05:00
Brandon Thomas f7b8423623 techcrunch parsing sort of works 2023-02-05 16:29:17 -05:00
Brandon Thomas 0f99360c20 the guardian 2023-02-05 05:54:25 -05:00
Brandon Thomas 665cd83739 techcrunch scraping of RSS feed 2023-02-05 05:12:42 -05:00
Brandon Thomas eefe48f8ca CNN candidate articles via RSS + Sqlite inserts 2023-02-05 05:02:13 -05:00
Brandon Thomas a1c5ef6eb2 add sqlite columns, move database 2023-02-05 03:44:02 -05:00
Brandon Thomas 2f4fe2dabc Web scraping WIP 2023-02-05 03:36:17 -05:00
Brandon Thomas d63a505b8b comments in .gitignore, aichatbot diesel configs 2023-02-05 01:41:08 -05:00
Brandon Thomas a0a5c68086 Project outline 2023-02-04 18:24:45 -05:00
Brandon Thomas ddb106a9af reqwest, ingestion modules (wip) 2023-02-03 23:57:12 -05:00
Brandon Thomas 7c229ba59b fix 2023-02-03 06:00:21 -05:00