Commit Graph

  • bff55230ba Reduce the default chunk size in the reasoning pipeline to fit LLM capability trducng 2024-02-03 09:38:50 +07:00
  • 107bc7580e Enable HTML upload trducng 2024-02-02 11:37:57 +07:00
  • 65852b7d71 Add docx + html reader (#139) Duc Nguyen (john) 2024-01-31 19:21:30 +07:00
  • 116919b346 Update docs (#106) ian_Cin 2024-01-30 18:50:17 +07:00
  • cbe40fac99 Show retrieved but non-evidence docs. Support language changing trducng 2024-01-29 11:16:07 +07:00
  • 50b5d936f5 Optionally allow database migration with Alembic trducng 2024-01-28 19:54:15 +07:00
  • 04635b77f6 Make the database table customizable trducng 2024-01-28 07:54:38 +07:00
  • 6ae9634399 Enable .doc file trducng 2024-01-27 23:45:19 +07:00
  • 23c0331bab Enable pptx support trducng 2024-01-27 23:08:06 +07:00
  • 80ec214107 Fix loaders' file_path and other metadata trducng 2024-01-27 22:52:46 +07:00
  • c6637ca56e Relate the retrievers to the indexer trducng 2024-01-27 16:39:40 +07:00
  • 9b586466ff Add the tutorial to mkdocs trducng 2024-01-26 15:40:04 +00:00
  • 22c646e5c4 Add documentation about adding reasoning and indexing pipelines to the application (#138) Duc Nguyen (john) 2024-01-26 22:31:52 +07:00
  • 757aabca4d Add app title, favicon. More natural chat trducng 2024-01-25 22:40:32 +07:00
  • 513e86f490 Add dedicated information panel to the UI (#137) Duc Nguyen (john) 2024-01-25 19:07:53 +07:00
  • ebc61400d8 Provide a developer mode when running ktem (#135) Duc Nguyen (john) 2024-01-23 11:46:59 +07:00
  • 2dd531114f Make ktem official (#134) Duc Nguyen (john) 2024-01-23 10:54:18 +07:00
  • 9c5b707010 Customize application settings (#132) Duc Nguyen (john) 2024-01-21 14:36:07 +07:00
  • 5a9d6f75be Migrate the MVP into kotaemon (#108) Duc Nguyen (john) 2024-01-10 15:28:09 +07:00
  • 230328c62f Best docs Cinnamon will probably ever have (#105) ian_Cin 2023-12-20 11:30:25 +07:00
  • 3fdd97ae3d Deployed c751092 with MkDocs version: 1.5.3 ian 2023-12-15 07:26:59 +07:00
  • 0e30dcbb06 Create Langchain LLM converter to quickly supply it to Langchain's chain (#102) Duc Nguyen (john) 2023-12-11 14:55:56 +07:00
  • da0ac1d69f Change template to private attribute and simplify imports (#101) Duc Nguyen (john) 2023-12-08 18:10:34 +07:00
  • 1f927d3391 Upgrade promptui to conform to Gradio V4 (#98) Duc Nguyen (john) 2023-12-07 15:24:07 +07:00
  • 797df5a69c refractor agents (#100) ian_Cin 2023-12-06 17:06:29 +07:00
  • d9e925eb75 Add UnstructuredReader with support for various legacy files (.doc, .xls) (#99) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-12-05 16:19:13 +07:00
  • 37c744b616 Add file-based document store and vector store (#96) Duc Nguyen (john) 2023-12-04 17:46:00 +07:00
  • 0ce3a8832f Provide type hints for pass-through Langchain and Llama-index objects (#95) Duc Nguyen (john) 2023-12-04 10:59:13 +07:00
  • e34b1e4c6d Refactor the index component and update the MVP insurance accordingly (#90) Duc Nguyen (john) 2023-11-30 18:35:07 +07:00
  • 8e3a1d193f Refactor agents and tools (#91) Nguyen Trung Duc (john) 2023-11-30 09:52:08 +07:00
  • 4256030b4f Adopt pyproject.toml (#89) ian_Cin 2023-11-29 14:58:35 +07:00
  • 8e0779a22d Enforce all IO objects to be subclassed from Document (#88) ian_Cin 2023-11-27 16:35:09 +07:00
  • 2186c5558f Separate rerankers, splitters and extractors (#85) Nguyen Trung Duc (john) 2023-11-27 14:25:54 +07:00
  • 0dede9c82d Subclass chat messages from Document (#86) ian_Cin 2023-11-27 10:38:19 +07:00
  • 3ac277cc0b Update Elastics store delete() (#84) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-21 15:29:00 +07:00
  • 9a96a9b876 Add Elasticsearch Docstore (#83) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-21 11:59:20 +07:00
  • 8bb7ad91e0 Add Langchain Agent wrapper with OpenAI Function / Self-ask agent support (#82) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-20 16:26:08 +07:00
  • 0a3fc4b228 Correct the use of abstractmethod (#80) Nguyen Trung Duc (john) 2023-11-20 11:18:53 +07:00
  • 98509f886c Update splitters + metadata extractor interface to conform with new LlamaIndex design (#81) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-20 10:09:30 +07:00
  • 98c76c4700 Refactor excel Loader (#79) Nguyen Trung Duc (john) 2023-11-16 11:30:11 +07:00
  • cc1e75b3c6 Add Citation pipeline (#78) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-16 11:24:35 +07:00
  • f8b8d86d4e Move LLM-related components into LLM module (#74) Nguyen Trung Duc (john) 2023-11-15 16:26:53 +07:00
  • 9945afdf6f Add Reranker implementation and integration in Retrieving pipeline (#77) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-15 16:03:51 +07:00
  • b52f312d8e Use new Langchain's dedicated Azure OpenAI embedding class (#76) Nguyen Trung Duc (john) 2023-11-15 14:46:32 +07:00
  • b159897ac6 Combine docstores and vectorstores within a storages component (#72) Nguyen Trung Duc (john) 2023-11-14 17:50:57 +07:00
  • 640962e916 Update retrieving + agent pipeline (#71) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-14 16:40:13 +07:00
  • 693ed39de4 Move prompts into LLMs module (#70) Nguyen Trung Duc (john) 2023-11-14 16:00:10 +07:00
  • 8532138842 Move Document and other interface into base/schema (#69) Nguyen Trung Duc (john) 2023-11-14 11:51:10 +07:00
  • 4704e2c11a Add new OCRReader with PDF+OCR text merging (#66) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-11-13 17:43:02 +07:00
  • d79b3744cb Simplify the BaseComponent inteface (#64) Nguyen Trung Duc (john) 2023-11-13 15:10:18 +07:00
  • 6095526dc7 Add Huggingface embeddings and Cohere embeddings (#63) ian_Cin 2023-11-10 09:38:30 +07:00
  • 9035e25666 Upgrade the declarative pipeline for cleaner interface (#51) Nguyen Trung Duc (john) 2023-10-24 11:12:22 +07:00
  • aab982ddc4 Provide ready binary for Mac and Linux to do sharing tunneling (#49) Nguyen Trung Duc (john) 2023-10-17 17:19:29 +07:00
  • 2b779926c6 Directly caching the python instead of creating virtual env; add option to ignore caching (#45) ian_Cin 2023-10-16 15:27:14 +07:00
  • da6b35f520 Allow persisting the expected output in the code (#46) Nguyen Trung Duc (john) 2023-10-13 10:26:48 +07:00
  • 6e7905cbc0 [AUR-411] Adopt to Example2 project (#28) Nguyen Trung Duc (john) 2023-10-12 15:13:25 +07:00
  • 533fffa6db Enable caching for github actions (#43) ian_Cin 2023-10-12 13:52:19 +07:00
  • 84f1fa8cbd [AUR-395] Adopt Example1 disclaimer pipeline (#42) ian_Cin 2023-10-10 15:42:48 +07:00
  • 79cc60e6a2 [AUR-429] Add MVP pipeline with Ingestion and QA stage (#39) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-10-05 12:31:33 +07:00
  • 2638152054 [Feat] Add support for f-string syntax in PromptTemplate (#38) ian_Cin 2023-10-04 16:40:09 +07:00
  • 56bc41b673 Update Base interface of Index/Retrieval pipeline (#36) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-10-04 14:27:44 +07:00
  • 49ed3f6994 [AUR-405] Auto-generate markdown documentation from pipeline (#33) Nguyen Trung Duc (john) 2023-10-04 10:54:24 +07:00
  • 6ab1854532 feat: Add chain-of-thought (#37) Nguyen Trung Duc (john) 2023-10-04 02:16:33 +07:00
  • f80a4ea883 [AUR-425] Fix the cookiecutter command (#35) Nguyen Trung Duc (john) 2023-10-03 12:13:10 +07:00
  • 205955b8a3 [AUR-387, AUR-425] Add start-project to CLI (#29) cin-jacky 2023-10-03 13:55:34 +09:00
  • d83c22aa4e [AUR-395, AUR-415] Adopt Example1 Injury pipeline; add .flow() for enabling bottom-up pipeline execution (#32) ian_Cin 2023-10-02 16:24:56 +07:00
  • 3cceec63ef [AUR-431] Add ReAct Agent (#34) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-10-02 11:29:12 +07:00
  • 91048770fa [AUR-431, AUR-435] Add Agent Interface and ReWOO Agent implementation (#31) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-10-01 11:53:08 +07:00
  • f9fc02a32a [AUR-363, AUR-433, AUR-434] Add Base Tool interface with Wikipedia/Google tools (#30) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-09-29 10:18:49 +07:00
  • 317323c0e5 [AUR-424] Setup CLI interface (#25) cin-jacky 2023-09-27 16:44:38 +09:00
  • 6c3d614973 [AUR-432] Add layout-aware table parsing PDF reader (#27) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-09-26 15:52:44 +07:00
  • 6207f4332a [AUR-430] Add test case for Chroma VectoStore save/load (#26) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-09-26 10:58:41 +07:00
  • 4f189dc931 [AUR-408] Export logs to Excel (#23) Nguyen Trung Duc (john) 2023-09-25 17:20:03 +07:00
  • 08b6e5d3fb [AUR-390] Add prompt template and prompt component (#24) ian_Cin 2023-09-25 14:38:22 +07:00
  • c6dd01e820 [AUR-338, AUR-406, AUR-407] Export pipeline to config for PromptUI. Construct PromptUI dynamically based on config. (#16) Nguyen Trung Duc (john) 2023-09-21 14:27:23 +07:00
  • c329c4c03f [AUR-362] Add In-memory vector store (#22) cin-jacky 2023-09-20 17:51:50 +09:00
  • b794051653 [AUR-421] base output post-processor that works using regex. (#20) ian_Cin 2023-09-19 19:54:44 +07:00
  • 2a3a23ecd7 [AUR-420] Provide document store base interface and an in-memory version (#21) Nguyen Trung Duc (john) 2023-09-19 14:49:23 +07:00
  • 620b2b03ca [AUR-392, AUR-413, AUR-414] Define base vector store, and make use of ChromaVectorStore from llama_index. Indexing and retrieving vectors with vector store (#18) Nguyen Trung Duc (john) 2023-09-14 14:18:20 +07:00
  • c339912312 [AUR-389] Add base interface and embedding model (#17) Nguyen Trung Duc (john) 2023-09-14 14:08:58 +07:00
  • 1061192731 [AUR-418] Add member public keys to git-secret: John, Ian, Tadashi, Jacky ian_Cin 2023-09-06 17:19:22 +07:00
  • f4596aa720 Fix import trducng 2023-09-04 10:30:53 +07:00
  • 21350153d4 [AUR-391, AUR-393] Add Document and DocumentReader base (#6) Tuan Anh Nguyen Dang (Tadashi_Cin) 2023-08-31 11:24:12 +07:00
  • 4211315a54 [AUR-396] Scaffold prompt engineering code base section (#5) Nguyen Trung Duc (john) 2023-08-30 14:31:21 +07:00
  • 5241edbc46 [AUR-361] Setup pre-commit, pytest, GitHub actions, ssh-secret (#3) ian_Cin 2023-08-30 07:22:01 +07:00
  • c3c25db48c [AUR-385, AUR-388] Declare BaseComponent and decide LLM call interface (#2) Nguyen Trung Duc (john) 2023-08-29 15:47:12 +07:00
  • e9d1d5c118 [AUR-401] Disable Haystack telemetry with monkey patching (#1) Nguyen Trung Duc (john) 2023-08-22 10:02:46 +07:00
  • 043209fda7 Initiate repository v0.0.0 trducng 2023-08-16 14:56:48 +07:00