information-retrieval, branch HEAD

Playing with nli and smol agents

2026-02-17T20:02:44Z

commit 1507d56ab81f28ecbd24025082ac2ff5c7ad7746 parent eb447c513be89e86ffa878fe0e9239a9978cd1e9 Author: Andrew Laack Date: Tue, 17 Feb 2026 14:02:44 -0600 Playing with nli and smol agents

AI content detection

2026-01-17T22:31:51Z

commit eb447c513be89e86ffa878fe0e9239a9978cd1e9 parent e709ee4038cceeb0574cdfc1e8999502ecb5c960 Author: Andrew Laack Date: Sat, 17 Jan 2026 16:31:51 -0600 AI content detection

Added file summary script

2026-01-13T22:01:19Z

commit e709ee4038cceeb0574cdfc1e8999502ecb5c960 parent 57e642fdae070c5dedd6a3fa4d9e781fe330fbf6 Author: Andrew Laack Date: Tue, 13 Jan 2026 16:01:19 -0600 Added file summary script

Created a better web research tool that uses iterative search and web downloading to find results and summarize context.

2026-01-13T04:44:48Z

commit 57e642fdae070c5dedd6a3fa4d9e781fe330fbf6 parent 8a1d19cbb24d4194399c54c4f2ce31fadaa10b5f Author: Andrew Laack Date: Mon, 12 Jan 2026 22:44:48 -0600 Created a better web research tool that uses iterative search and web downloading to find results and summarize context.

Revision

2026-01-12T23:47:35Z

commit 8a1d19cbb24d4194399c54c4f2ce31fadaa10b5f parent 0e28cdce317175bca9edd6fb04b2513843c319b8 Author: Andrew Laack Date: Mon, 12 Jan 2026 17:47:35 -0600 Revision

Continued updates

2026-01-11T11:02:43Z

commit 0e28cdce317175bca9edd6fb04b2513843c319b8 parent 29672f8c1a72cfaf285b4cb9dc1a0529e19b4c18 Author: Andrew Laack Date: Sun, 11 Jan 2026 05:02:43 -0600 Continued updates

Started working on an LLM based search tool in cpp

2026-01-11T09:56:15Z

commit 29672f8c1a72cfaf285b4cb9dc1a0529e19b4c18 parent ef48935d8f7471ffe8209ed9fcc4d6c0bd9e3ce3 Author: Andrew Laack Date: Sun, 11 Jan 2026 03:56:15 -0600 Started working on an LLM based search tool in cpp

Refactoring

2026-01-11T00:10:47Z

commit ef48935d8f7471ffe8209ed9fcc4d6c0bd9e3ce3 parent 863992bcb89baa8aa852607e1aa6cc07d891c47d Author: Andrew Laack Date: Sat, 10 Jan 2026 18:10:47 -0600 Refactoring

Incremental

2026-01-07T22:42:13Z

commit 863992bcb89baa8aa852607e1aa6cc07d891c47d parent 49cfa7a25d876018bef98fba7b0e516820560740 Author: Andrew Laack Date: Wed, 7 Jan 2026 16:42:13 -0600 Incremental

Updated querying

2026-01-07T06:05:08Z

commit 49cfa7a25d876018bef98fba7b0e516820560740 parent 16e1f7d53b8b85e296cf50efc4a424aea35ceff0 Author: Andrew Laack Date: Wed, 7 Jan 2026 00:05:08 -0600 Updated querying

Add inverse index for titles

2026-01-07T05:51:32Z

commit 16e1f7d53b8b85e296cf50efc4a424aea35ceff0 parent 872a6d92228e10ebdd5076e9314e3c06f1b23699 Author: Andrew Laack Date: Tue, 6 Jan 2026 23:51:32 -0600 Add inverse index for titles

Comment

2026-01-06T19:40:52Z

commit 872a6d92228e10ebdd5076e9314e3c06f1b23699 parent e1c2a8a2d1046eb5cd1f4f7e1a62fe93fcaafd66 Author: Andrew Laack Date: Tue, 6 Jan 2026 13:40:52 -0600 Comment

Improving url indexing, starting with title indexing

2026-01-06T19:39:37Z

commit e1c2a8a2d1046eb5cd1f4f7e1a62fe93fcaafd66 parent 2fd9d19d4eb4a93e01e89647fea0cd40de0850e3 Author: Andrew Laack Date: Tue, 6 Jan 2026 13:39:37 -0600 Improving url indexing, starting with title indexing

Made a bunch of changes to bootstrap tfidf for full text and url search.

2026-01-06T03:05:35Z

commit 2fd9d19d4eb4a93e01e89647fea0cd40de0850e3 parent 7067745bb56e6e07eabb2574447937fbc0ec3779 Author: Andrew Laack Date: Mon, 5 Jan 2026 21:05:35 -0600 Made a bunch of changes to bootstrap tfidf for full text and url search.

Started making this better. No sqlite, better code, all that. Still needs some refactoring though....

2026-01-03T08:18:03Z

commit 7067745bb56e6e07eabb2574447937fbc0ec3779 parent 0547119084bf9b2df319d703a9e30f116e940c66 Author: Andrew Laack Date: Sat, 3 Jan 2026 02:18:03 -0600 Started making this better. No sqlite, better code, all that. Still needs some refactoring though....

Leaving as is; starting fresh with postgres

2026-01-03T04:26:39Z

commit 0547119084bf9b2df319d703a9e30f116e940c66 parent 3fd57e78245f76e883bf38fd86c4b40be798b05a Author: Andrew Laack Date: Fri, 2 Jan 2026 22:26:39 -0600 Leaving as is; starting fresh with postgres

Added language detection to pipeline and queries. improved spider prioritization.

2026-01-02T05:24:40Z

commit 3fd57e78245f76e883bf38fd86c4b40be798b05a parent 677346e211c3c9544f3708ab117f2f61e2b27f01 Author: Andrew Laack Date: Thu, 1 Jan 2026 23:24:40 -0600 Added language detection to pipeline and queries. improved spider prioritization.

Sent my first queriesgit status!

2026-01-01T23:48:23Z

commit 677346e211c3c9544f3708ab117f2f61e2b27f01 parent 6c374cfe6d87c097ed0f3fe655d4b5ce0cc68837 Author: Andrew Laack Date: Thu, 1 Jan 2026 17:48:23 -0600 Sent my first queriesgit status!

Respect robots.txt

2026-01-01T22:56:57Z

commit 6c374cfe6d87c097ed0f3fe655d4b5ce0cc68837 parent 6654bdb0e73dbb6f1328cd341aed8f23936dcb96 Author: Andrew Laack Date: Thu, 1 Jan 2026 16:56:57 -0600 Respect robots.txt

Improved link tracking

2026-01-01T22:33:02Z

commit 6654bdb0e73dbb6f1328cd341aed8f23936dcb96 parent 7844a7045ce08b808a43213e2f2a24588b3109cd Author: Andrew Laack Date: Thu, 1 Jan 2026 16:33:02 -0600 Improved link tracking

Reworked spider to queue links

2026-01-01T21:56:18Z

commit 7844a7045ce08b808a43213e2f2a24588b3109cd parent 26aaac222ee693bd1d6ec1306ec135468ddb3deb Author: Andrew Laack Date: Thu, 1 Jan 2026 15:56:18 -0600 Reworked spider to queue links

Added tf calculation for indexing.

2026-01-01T10:36:31Z

commit 26aaac222ee693bd1d6ec1306ec135468ddb3deb parent 75a4065b8167979b8484560b5f623a023ba647c4 Author: Andrew Laack Date: Thu, 1 Jan 2026 04:36:31 -0600 Added tf calculation for indexing.

Updated todo

2025-12-31T23:45:00Z

commit 75a4065b8167979b8484560b5f623a023ba647c4 parent edd197026c4213a9b7479de73a77d0f3944df0cf Author: Andrew Laack Date: Wed, 31 Dec 2025 17:45:00 -0600 Updated todo

Continued working, created todo, setup idf, played with language detection, setup project.

2025-12-31T23:44:39Z

commit edd197026c4213a9b7479de73a77d0f3944df0cf parent 01a14abfa7d688731f7220f16dde22042bb068eb Author: Andrew Laack Date: Wed, 31 Dec 2025 17:44:39 -0600 Continued working, created todo, setup idf, played with language detection, setup project.

Setup larger idf

2025-12-31T08:21:06Z

commit 01a14abfa7d688731f7220f16dde22042bb068eb parent 1b5bb8f087a72d206aa5b50669676e519509a755 Author: Andrew Laack Date: Wed, 31 Dec 2025 02:21:06 -0600 Setup larger idf

Improved crawling

2025-12-31T06:18:13Z

commit 1b5bb8f087a72d206aa5b50669676e519509a755 parent 6d3b8448a30a10843c1f3d016516729060da39ad Author: Andrew Laack Date: Wed, 31 Dec 2025 00:18:13 -0600 Improved crawling

Implemented tf-idf and created a basic spider

2025-12-30T23:17:12Z

commit 6d3b8448a30a10843c1f3d016516729060da39ad Author: Andrew Laack Date: Tue, 30 Dec 2025 17:17:12 -0600 Implemented tf-idf and created a basic spider