Commit Graph

14 Commits

Author SHA1 Message Date
Josako
2ca006d82c Added excluded element classes to HTML parsing to allow for more complex document parsing
Added chunking to conversion of HTML to markdown in case of large files
2024-08-22 16:41:13 +02:00
Josako
926a4e8cc2 - Add support for environment in communication with portkey 2024-08-19 12:06:10 +02:00
Josako
64cf8df3a9 - Improvements to enable deployment in the cloud, mainly changing file access to Minio
- Improvements on RAG logging, and some debugging in that area
2024-08-01 17:35:54 +02:00
Josako
88ca04136d Portkey Integration 2024-07-18 07:08:42 +02:00
Josako
908a2eaf7e - Improve annotation algorithm for Youtube (and others)
- Patch Pytube
- improve OS deletion of files and writing of files
- Start working on Claude
- Improve template management
2024-07-16 14:21:49 +02:00
Josako
ea0127b4b8 Improve algorithms for HTML and PDF processing 2024-07-08 15:20:45 +02:00
Josako
8e1dac0233 Youtube added - further checking required 2024-07-04 08:11:31 +02:00
Josako
cc9f6c95aa Started to work on interaction views. However, need a quick check in because of a python upgrade systemwide that breaks code. 2024-06-21 09:52:06 +02:00
Josako
b77e1ab321 Variables for rag_context and fallback algorithms added to Tenant and parts of the implementation. 2024-06-13 15:23:35 +02:00
Josako
24a3747b99 Include history to improve query if required. 2024-06-13 10:35:15 +02:00
Josako
be311c440b Improving chat functionality significantly throughout the application. 2024-06-12 11:07:18 +02:00
Josako
27b6de8734 Removing DocumentLanguage, as both System Context and User Context are to be defined on DocumentVersion level.
Finetuning of embedding workers.
2024-06-06 15:26:49 +02:00
Josako
61e1372dc8 Improvements to Document Interface and correcting embedding workers 2024-06-04 14:59:38 +02:00
Josako
fcc0caeb09 Optimizing admin interface for user domain, completing security views 2024-06-03 09:37:59 +02:00