shamoon
fd543f2bff
Fix: 3.1.0 llm suggestions remove existing metadata from prompt, dont drop name suggestions ( #13866 )
2026-08-30 21:25:26 -07:00
shamoon
14b6a41b88
Fix: 3.1 llm suggestions request a flat list we change later ( #13860 )
2026-08-30 07:44:45 -07:00
shamoon
00d9bf474a
Fix: always pass a non-empty api key for OpenAI-like servers ( #13838 )
2026-08-28 09:55:13 -07:00
shamoon
262183e848
Enhancement (beta): support LLM timeout config ( #13002 )
2026-06-18 08:35:11 -07:00
shamoon
bcf5d2cffc
Chore: set tool_required to opena-like llm calls ( #13025 )
2026-06-17 06:24:38 -07:00
shamoon
52222d23d3
Fix (beta): dont use tool calling with ollama ( #12896 )
2026-06-01 12:12:23 -07:00
shamoon
f6c865bf47
Enhancement: AI LLM chunk size and context window config ( #12891 )
2026-06-01 17:56:21 +00:00
Trenton H and Claude Sonnet 4.6
bb860a5834
Fix: Improvements for security around the AI ( #12895 )
...
* Fix: Validate and limit chat question input in ChatStreamingView
Add max_length=4000 to ChatStreamingSerializer.q and replace the bare
request.data["q"] read with proper serializer.is_valid(raise_exception=True)
so oversized or missing questions are rejected with HTTP 400 before
reaching the LLM.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
* Fix: Add defensive prompt framing to mark document content as untrusted
* Also adds a system prompt which is treated higher that this is untrusted stuff
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-06-01 10:03:27 -07:00
shamoon
01d8fad622
Security: fixes for v3 beta ( #12838 )
2026-05-26 16:46:23 +00:00
shamoon
cc918bae5f
Fix: pass allow parallel tool calls in LLM client ( #12718 )
2026-05-05 16:57:47 -07:00
shamoon
69cb4d06c6
Enhancement (dev): Use OpenAI-like backend ( #12668 )
2026-04-28 10:06:59 -07:00
shamoon
4d4f30b5f8
Security: validate outbound llm URLs and block internal endpoints
2026-03-16 22:58:16 -07:00
Trenton H
f5c0c21922
Chore: Lazy imports of the heavy AI modules ( #12275 )
2026-03-07 12:53:22 -08:00
Sebastian Steinbeißer
3b5ffbf9fa
Chore(mypy): Annotate None returns for typing improvements ( #11213 )
2026-02-02 08:44:12 -08:00
shamoon
94a5af66eb
Fix default llama3.1
2026-01-14 15:36:01 -08:00
shamoon
948c664dcf
Correct get_tool_calls_from_response signature
2026-01-14 14:55:03 -08:00
shamoon
e940764fe0
Feature: Paperless AI ( #10319 )
2026-01-13 16:24:42 +00:00
shamoon
Trenton HandClaude Sonnet 4.6
Sebastian Steinbeißer