Commit graph

15 commits

Author SHA1 Message Date
Abdullah 3li
aa00822169 feat: Add Docling support as ETL_SERVICE option
- Added DOCLING as third ETL_SERVICE option (alongside UNSTRUCTURED/LLAMACLOUD)
- Implemented add_received_file_document_using_docling function
- Added Docling processing logic in documents_routes.py
- Enhanced chunking with configurable overlap support
- Added comprehensive document processing service
- Supports both CPU and GPU processing with user selection

Addresses #161 - Add Docling Support as an ETL_SERVICE
Follows same pattern as LlamaCloud integration (PR #123)
2025-07-20 11:42:55 +03:00
DESKTOP-RTLN3BA\$punk
5045b7433a refactor: Move utility services to a dedicated 'services' module
- Updated import paths for LLM, connector, query, and streaming services to reflect their new location in the 'services' module.
- Removed obsolete utility service files that have been migrated.
2025-07-06 17:51:24 -07:00
DESKTOP-RTLN3BA\$punk
d8f2c5f7cf fix: generate content hash based on search space id as well.
- Allows Reindexing in selperate seatch spaces.
2025-06-10 13:56:23 -07:00
DESKTOP-RTLN3BA\$punk
a85f7920a9 feat: added configurable LLM's 2025-06-09 15:50:15 -07:00
DESKTOP-RTLN3BA\$punk
deea3fa544 chore: remove VERSION file and clean up unused imports across multiple files 2025-06-03 01:33:21 -07:00
DESKTOP-RTLN3BA\$punk
0365febc8c fix for content hashing 2025-05-30 19:30:56 -07:00
DESKTOP-RTLN3BA\$punk
73751c0eb1 feat: Removed Hard Dependency on Unstructured.io
- Added Llamaparse Support :)
2025-05-30 19:17:19 -07:00
DESKTOP-RTLN3BA\$punk
5411bac8e0 feat: Added content based hashing to prevent duplicates and fix resync issues 2025-05-28 23:52:00 -07:00
DESKTOP-RTLN3BA\$punk
4c8b03ce2b feat: Code Block Syntax Highlighting & Copy Func 2025-05-19 23:19:20 -07:00
ritikprajapat21
16867b4bed Changes updated 2025-05-12 09:37:37 +05:30
ritikprajapat21
ccd12d3ad2 Fix #33: Refactored code 2025-05-10 17:11:51 +05:30
DESKTOP-RTLN3BA\$punk
1586a0bd78 chore: Added direct handling for markdown files.
- Fixed podcast imports.
2025-05-07 22:04:57 -07:00
DESKTOP-RTLN3BA\$punk
22da221ad5 feat: Shifted to RecursiveChunker and CodeChunker
- Codebase Q/A should be lot better now.
2025-04-29 23:02:07 -07:00
DESKTOP-RTLN3BA\$punk
b43272a115 feat(youtube): integrate YouTube video processing connector
- Added support for processing YouTube videos, including transcript extraction and document creation.
- Implemented a new background task for adding YouTube video documents.
- Enhanced the connector service to search for YouTube videos and return relevant results.
- Updated frontend components to include YouTube video options in the dashboard and connector sources.
- Added necessary dependencies for YouTube transcript API.
2025-04-11 15:05:17 -07:00
DESKTOP-RTLN3BA\$punk
da23012970 feat: SurfSense v0.0.6 init 2025-03-14 18:53:14 -07:00