Commit graph

  • 9dcffe3e8e Rename test_main to test_client. It only contains client specific tests Debanjum Singh Solanky 2021-10-02 20:32:53 -0700
  • 7e0d9bafa7 Split test_main into client and search type specific test files Debanjum Singh Solanky 2021-10-02 20:28:33 -0700
  • da33e9e743 Create test directory with model data to reuse for pytest session Debanjum Singh Solanky 2021-10-02 19:46:29 -0700
  • 1832e418e5 Use raw string for regex in orgnode to fix deprecation warning Debanjum Singh Solanky 2021-10-02 17:38:31 -0700
  • f59e321419 Update CLIP model load path Debanjum Singh Solanky 2021-10-02 16:50:06 -0700
  • 31e21a6e4e Update gitignore to ignore src/data and vscode directories Debanjum Singh Solanky 2021-10-02 16:17:33 -0700
  • c47a8cdf16 Allow configuring host, port or unix socket of server via CLI Debanjum Singh Solanky 2021-10-02 16:16:33 -0700
  • 866ccb5cd3 Add all configurables to sample_config. Add test music, ledger data Debanjum Singh Solanky 2021-10-02 16:11:27 -0700
  • e933a5d3d0 Fix badge in readme, post workflow rename Debanjum Singh Solanky 2021-09-30 04:58:18 -0700
  • 0a02dba25f Rename workflow to build from tests Debanjum Singh Solanky 2021-09-30 04:57:32 -0700
  • cedd723721 Add tests badge to readme. Simplify name of tests workflow Debanjum Singh Solanky 2021-09-30 04:51:47 -0700
  • 266a03b03d Test application on Push or PR using Github Actions Debanjum Singh Solanky 2021-09-30 04:36:00 -0700
  • e8b7f06709 Ignore less files. Make gitignore more specific Debanjum Singh Solanky 2021-09-30 04:35:22 -0700
  • 516f28b082 Merge branch 'master' of github.com:debanjum/semantic-search Debanjum Singh Solanky 2021-09-30 04:17:32 -0700
  • c200189385 Test notes search with explicit include, exclude filters Debanjum Singh Solanky 2021-09-30 04:13:40 -0700
  • d2905c4be6 Move tests out to project root. Use absolute import in project Debanjum Singh Solanky 2021-09-30 04:12:14 -0700
  • 58bb420f69 Fix image_metadata argument ordering bug. Add E2E image search test Debanjum Singh Solanky 2021-09-30 03:29:31 -0700
  • d5597442f4 Modularize Code. Wrap Search, Model Config in Classes. Add Tests Debanjum Singh Solanky 2021-09-30 02:04:04 -0700
  • f4dd9cd117 Use type specific model for other search types too. Expose them via SearchModels Debanjum Singh Solanky 2021-09-29 21:09:42 -0700
  • 352d2930ee Use multiple threads to generate model embeddings. Other minor formating Debanjum Singh Solanky 2021-09-29 20:47:58 -0700
  • e22e0b41e3 Wrap asymmetric search model into SearchModels. Test notes search end-to-end Debanjum Singh Solanky 2021-09-29 20:24:27 -0700
  • cde11a2331 Wrap search type enablement status in a search settings class Debanjum Singh Solanky 2021-09-29 19:18:33 -0700
  • 81ce0cacc3 Only allow supported search types to /search, /regenerate APIs Debanjum Singh Solanky 2021-09-29 19:02:55 -0700
  • 5db08c5293 Set query as heading of notes search results in Emacs Org buffer Debanjum Singh Solanky 2021-09-29 13:30:15 -0700
  • 150593c776 Update Readme. Acknowledger PyExifTool and Minor Fixes Debanjum Singh Solanky 2021-09-16 12:39:42 -0700
  • fdb60a8dcf Set Query as Heading of Image Search Results Emacs Buffer Debanjum Singh Solanky 2021-09-16 12:28:05 -0700
  • 169ddcc8c6 Make Using XMP Metadata to Enhance Image Search Optional, Configurable Debanjum Singh Solanky 2021-09-16 12:01:05 -0700
  • a4a23d7a72 Batch encode XMP metadata from images too for image_search Debanjum Singh Solanky 2021-09-16 11:11:36 -0700
  • 3afe054312 Make image batch size to encode configurable via config.yml Debanjum Singh Solanky 2021-09-16 10:51:39 -0700
  • 41c328dae0 Batch encode images to keep memory consumption manageable Debanjum Singh Solanky 2021-09-16 10:15:54 -0700
  • d8abbc0552 Use XMP metadata in images to improve image search Debanjum Singh Solanky 2021-09-15 22:54:03 -0700
  • 0e34c8f493 Allow semantic search on images from Emacs Debanjum Singh Solanky 2021-09-10 01:01:23 -0700
  • 7d5514ecaa Allow user to override inferred search type with other valid options Debanjum Singh Solanky 2021-09-10 00:54:10 -0700
  • 3bdeeb1e19 Autoload main semantic-search function Debanjum Singh Solanky 2021-09-09 22:10:37 -0700
  • f4bde75249 Decouple results shown to user and text the model is trained on Debanjum Singh Solanky 2021-08-29 05:47:43 -0700
  • 7ee3007070 Get ID, QUERY, TYPE, CATEGORY properties from org property drawer when present Debanjum Singh Solanky 2021-08-29 04:33:24 -0700
  • 0263d4d068 Enable semantic search for songs in org-music Debanjum Singh Solanky 2021-08-29 03:07:36 -0700
  • fd7888f3d4 Resolve relative file paths to config YAML file in cli.py Debanjum Singh Solanky 2021-08-29 03:03:37 -0700
  • fc531a1915 Resolve relative file paths to model embeddings in all search types Debanjum Singh Solanky 2021-08-28 22:26:12 -0700
  • 74faa34bee Update sample config to add minimal config for ledger, image search Debanjum Singh Solanky 2021-08-22 21:54:49 -0700
  • 8dec58b12a Update Readme to state can now query beancount transactions, images Debanjum Singh Solanky 2021-08-22 21:50:27 -0700
  • 4daeddbbda Enable Semantic Search on Images Debanjum Singh Solanky 2021-08-22 21:00:54 -0700
  • fd217fe8b7 Enable Semantic Search for Beancount transactions Debanjum Singh Solanky 2021-08-22 03:16:57 -0700
  • 97263b8209 Move CLI into a separate module. Move CLI tests into a separate file Debanjum Singh Solanky 2021-08-21 19:21:38 -0700
  • 78a1f4ebb4 Use YAML file to allow user to configure application. Add tests Debanjum Singh Solanky 2021-08-21 18:47:55 -0700
  • bafc86d583 Add helpers to merge dictionaries and get keys deep inside a dictionary Debanjum Singh Solanky 2021-08-21 15:32:23 -0700
  • eddbc67358 Document how to install latest version in Readme Debanjum Singh Solanky 2021-08-17 18:27:10 -0700
  • 252266b62a Pass type of item via regenerate API. Default type query param to None Debanjum Singh Solanky 2021-08-17 04:36:48 -0700
  • ff7207a6bd Extract commandline arguments into separate testable method Debanjum Singh Solanky 2021-08-17 04:00:45 -0700
  • a3a1100be9 Arrange modules in standardized ordering Debanjum Singh Solanky 2021-08-17 03:59:58 -0700
  • 569e30b1c8 Create a few basic tests Debanjum Singh Solanky 2021-08-17 03:27:16 -0700
  • af9660f28e Move application files under src directory. Update Readmes Debanjum Singh Solanky 2021-08-17 01:25:12 -0700
  • c35c6fb0b3 Reuse asymmetric.setup & input validation from asymmetric & org_to_jsonl Debanjum Singh Solanky 2021-08-16 23:58:24 -0700
  • 02a84df37a Update state vars after regeneration. Minimize time app in inconsistent state Debanjum Singh Solanky 2021-08-16 23:47:33 -0700
  • 0509854e14 Replace README.md with README.org. Can be used as notes for testing Debanjum Singh Solanky 2021-08-16 20:00:05 -0700
  • 79aff85fcb Update Readme. No separate SETUP step required. Simpler RUN step Debanjum Singh Solanky 2021-08-16 19:18:48 -0700
  • 95bf26a7f2 Set verbosity commandline parameters default value to 0 Debanjum Singh Solanky 2021-08-16 19:16:29 -0700
  • 04a9a6d62f Expose API endpoint to (re-)generate embeddings from latest notes Debanjum Singh Solanky 2021-08-16 18:52:38 -0700
  • 1c00c33e73 Improve debug output from org_to_jsonl.py script Debanjum Singh Solanky 2021-08-16 18:50:29 -0700
  • 2a57156428 Fix org_to_jsonl. Use passed args not global variables in methods. Fix orgnode import Debanjum Singh Solanky 2021-08-16 17:37:44 -0700
  • 66238004d8 Use verbosity level instead of bool across application Debanjum Singh Solanky 2021-08-16 17:15:41 -0700
  • adbf157deb Remove usage of the closure to search_notes as it's not required Debanjum Singh Solanky 2021-08-16 16:52:48 -0700
  • 649e5d1327 Allow reuse of get_absolute_path, is_none_or_empty methods Debanjum Singh Solanky 2021-08-16 16:33:43 -0700
  • 9703afb814 Rename search_types to search_type to standardize to singular naming Debanjum Singh Solanky 2021-08-16 16:04:45 -0700
  • 19d6678eb1 Allow importing org-to-jsonl as module for reuse Debanjum Singh Solanky 2021-08-16 15:59:13 -0700
  • 5f8221f77e Remove unused verbose argument to collate_results method Debanjum Singh Solanky 2021-08-16 13:54:41 -0700
  • 85bf15628d Use better cmdline argument names. Drop unneeded no-compress argument Debanjum Singh Solanky 2021-08-16 13:44:42 -0700
  • d9f60c00bf Warn if any input files to org-to-json are potentially non org-mode files Debanjum Singh Solanky 2021-08-16 13:26:49 -0700
  • 3aa0c30fee Use absolute file path to open files in org-to-jsonl.py, asymmetric.py Debanjum Singh Solanky 2021-08-16 13:22:46 -0700
  • e773611558 Remove unused jsonl_file argument from convert_org_entries_to_jsonl Debanjum Singh Solanky 2021-08-16 13:05:35 -0700
  • 8b29e272d3 Standardize interface, better default args for org-to-json.py script Debanjum Singh Solanky 2021-08-16 11:17:42 -0700
  • 7547e90745 Minor doc updates after merging emacs package with main repository Debanjum Singh Solanky 2021-08-16 01:42:50 -0700
  • ec157ea0ff Add Emacs interface to semantic-search directly to main repository Debanjum Singh Solanky 2021-08-16 01:27:46 -0700
  • dcf7b2d04f Remove requirements.txt for now as virtualenv setup doesn't work Debanjum Singh Solanky 2021-08-16 00:15:10 -0700
  • 3b81fafa3e Use updated path to MiniLM bi-encoder model on hugging-face Debanjum Singh Solanky 2021-08-15 23:57:22 -0700
  • 4839153086 Acknowledge ML models used for search. Simplify path used in commands Debanjum Singh Solanky 2021-08-15 23:56:18 -0700
  • c58c1d96aa Change default install directory to current, fix open file code Debanjum Singh Solanky 2021-08-15 23:01:55 -0700
  • ae15e429b5 Reduce indentation from 4 to 2 in Readme.md. Debanjum Singh Solanky 2021-08-15 22:56:36 -0700
  • 636b6195cc Add Readme, License. Update .gitignore Debanjum Singh Solanky 2021-08-15 22:52:37 -0700
  • 354c541b62 Add org processor to generate compressed jsonl from org-mode files Debanjum Singh Solanky 2021-08-15 22:49:09 -0700
  • b74cb9a104 Move install.py to new utils dir as it's for cmdline ease of use only Debanjum Singh Solanky 2021-08-15 19:10:30 -0700
  • ec92f3e146 Move different search types into search_types directory Debanjum Singh Solanky 2021-08-15 19:09:50 -0700
  • 4d681c86ec Update requirements.txt for users wanting to use pip install Debanjum Singh Solanky 2021-08-15 18:45:37 -0700
  • d75df54385 Create API interface for Semantic Search Debanjum Singh Solanky 2021-08-15 17:50:08 -0700
  • e3088c8cf8 Create environment.yml to install prerequisites for app via conda Debanjum Singh Solanky 2021-08-15 17:17:37 -0700
  • 660e6c3937 Add explicit filters to asymmetric search Debanjum Singh Solanky 2021-08-15 17:12:04 -0700
  • 91a2c598fe Resolve paths to absolute paths once. Use pathlib glob directly Debanjum Singh Solanky 2021-08-09 00:29:51 -0700
  • ca0a22f4dd Search for images similar to query image provided by the user Debanjum Singh Solanky 2021-08-08 23:11:15 -0700
  • 00d0065c5b Allow user to search images via text queries Debanjum Singh Solanky 2021-08-08 22:17:19 -0700
  • 181cab89d2 Ignore Title Notes i.e notes with just headings from compute Debanjum Singh Solanky 2021-08-04 18:29:22 -0700
  • d6d7b9d6a8 Make installed script executable. Minor clean-up of duplicate code Debanjum Singh Solanky 2021-08-02 00:41:52 -0700
  • 2eb029a7b0 Create script to install semantic-search as a program Debanjum Singh Solanky 2021-08-02 00:29:09 -0700
  • 13d5100ce6 Rename script similarity to symmetric Debanjum Singh Solanky 2021-07-31 20:37:07 -0700
  • ad7e90bec3 Modularize script, provide cmdline control, improve results rendering Debanjum Singh Solanky 2021-07-31 03:02:43 -0700
  • eb03f57917 Save, Load Embeddings to/from file to speed up script load time Debanjum Singh Solanky 2021-07-31 02:58:34 -0700
  • 0914f284bb Re-rank using cross encoder to get even more relevant results Debanjum Singh Solanky 2021-07-31 02:56:45 -0700
  • 9864a2b551 Retrieve most relevant entries for a query using MSMarco based bi-encoder Debanjum Singh Solanky 2021-07-31 00:20:37 -0700
  • 0ef5495701 Use Sentence Transformers to Encode, Query Schedule.org Headings debanjum 2021-04-04 04:53:03 -0700