Commit Graph

294 Commits

Author SHA1 Message Date
cfa9ef4726 fix: lowercase remote-user header in authelia auto-login procedure
Ensure the remote-user header is lowercased to fix case-sensitivity issues in the authelia auto-login process, improving compatibility.
2025-06-02 20:53:39 +08:00
560c6e8ff1 Claude: control cache TTL with config 2025-05-23 21:40:40 +03:00
157315cd68 Add Vertex AI express mode support (#3977)
* Add Vertex AI express mode support
Split Google AI Studio and Vertex AI

* Add support for Vertex AI, including updating default models and related settings, modifying frontend HTML to include Vertex AI options, and adjusting request processing logic in the backend API.

* Log API name in the console

* Merge sysprompt toggles back

* Use Gemma tokenizers for Vertex and LearnLM

* AI Studio parity updates

* Add link to express mode doc. Also technically it's not a form

* Split title

* Use array includes

* Add support for Google Vertex AI in image captioning feature

* Specify caption API name, add to compression list

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-05-22 20:10:53 +03:00
db2971c82d Remove Pygmalion instruct template (duplicate of Metharme)
ST already applies user sequence as stop string, so Pygmalion's <|user|> stop_sequence is meaningless.
2025-05-01 03:24:28 -05:00
8dc7aa0c20 Add post_history field to default prompts 2025-04-30 21:07:06 +03:00
775ae0f557 TC sysprompt: Add Post-History Instructions control
Closes #3920
2025-04-28 00:14:57 +03:00
61c7f53d22 Move endpoint version to conifg. Refactor ugli model lists 2025-04-27 14:56:51 +03:00
76aa17e08f Merge pull request #3911 from cloak1505/staging
Normalize instruct names behavior and repair Lightning 1.1's system prompt
2025-04-26 00:10:01 +03:00
321efa354a Update index.json 2025-04-25 15:35:44 -05:00
82c86c9ce6 Clean Lightning 1.1 2025-04-25 14:57:42 -05:00
cf7edd99a7 trivial: remove extraneous \n after sop token 2025-04-26 00:08:02 +09:00
2151ae7aaa Normalize instruct "names_behavior" to "force" for those that don't require "none" or "always 2025-04-25 09:40:49 -05:00
81fec97f54 Repair Lightning 1.1's system prompt 2025-04-25 09:22:10 -05:00
2d366117dd chat preset: GLM-4 2025-04-25 15:22:51 +09:00
13099c43a9 add char-archive to whitelistImportDomains 2025-04-19 12:30:14 -06:00
897632b583 fix: system prompt not the same as user prompt for L3/4 2025-04-13 15:12:09 +01:00
6f05c087b9 chore: update index 2025-04-13 14:26:20 +01:00
fc9b2173c0 fix: add <|begin_of_text|> to story string 2025-04-13 14:14:43 +01:00
61ca7775d2 fix: start/end header tags 2025-04-13 14:09:54 +01:00
f95077ac9f chore: add llama 4 chat templates 2025-04-13 14:04:52 +01:00
0e2290dacf Enable disk cache by default 2025-03-19 22:45:26 +02:00
694df8ca55 Merge branch 'staging' into disk-cache 2025-03-19 22:40:11 +02:00
c92ca8dbfb Merge branch 'staging' into integrity 2025-03-18 01:51:07 +02:00
271c93a504 Rename DeepSeek template, add Blank reasoning template 2025-03-18 00:32:31 +02:00
62342b35e2 Reasoning template 2025-03-16 15:01:31 +02:00
400d29e97e Add chat integrity check to saveChat 2025-03-16 02:24:20 +02:00
684ee98168 Add config, increase cache TTL, use async file reads 2025-03-15 19:43:26 +02:00
070de9df2d (CC) Move continue nudge at the end of completion (#3611)
* Move continue nudge at the end of completion
Closes #3607

* Move continue message together with nudge
2025-03-09 18:17:02 +02:00
28bad6479c Use human-readable memory cache capacity in config 2025-03-05 00:45:34 +02:00
3d813e4ef6 Move shallow toggle to config.yaml 2025-03-04 23:32:42 +02:00
7d568dd4e0 Generic generate methods (#3566)
* sendOpenAIRequest/getTextGenGenerationData methods are improved, now it can use custom API, instead of active ones

* Added missing model param

* Removed unnecessary variable

* active_oai_settings -> settings

* settings -> textgenerationwebui_settings

* Better presetToSettings names, simpler settings name in getTextGenGenerationData,

* Removed unused jailbreak_system

* Reverted most core changes, new custom-request.js file

* Forced stream to false, removed duplicate method, exported settingsToUpdate

* Rewrite typedefs to define props one by one

* Added extractData param for simplicity

* Fixed typehints

* Fixed typehints (again)

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-03-03 10:30:20 +02:00
1d995fb92d Rewrite to only consider Docker 2025-03-01 20:22:33 +02:00
58fe54954a Update whitelist entry in config.yaml to use gateway.docker.internal 2025-02-28 00:21:35 +02:00
0bc4396427 Resolve hostnames from whitelist 2025-02-27 23:14:57 +02:00
e7fcd0072b Refactor server startup 2025-02-26 14:46:54 +00:00
a73dfa7586 Merge branch 'staging' into immutable-config 2025-02-22 20:15:13 +02:00
a2ecb81378 Move minLogLevel to logging section 2025-02-22 13:58:08 +02:00
b12cd9fe05 Merge branch 'staging' into feature/access-log-middleware 2025-02-22 13:49:36 +02:00
30f97e0e64 Merge branch 'release' into staging 2025-02-22 12:41:18 +02:00
938c8a9a36 Add /default do-not-edit notice 2025-02-22 12:41:09 +02:00
db500188d8 feat(middleware): add separate access log middleware with config option 2025-02-21 20:32:23 +08:00
eb31d7baa2 Merge branch 'staging' into immutable-config 2025-02-20 21:54:41 +02:00
3f5b63bba0 Feature: Add configurable X-Real-IP header support for rate limiting (#3504)
* fix: correct client IP detection behind reverse proxy

* Revert "fix: correct client IP detection behind reverse proxy"

This reverts commit 7207506240.

* feat: support X-Real-IP header for reverse proxy setups

* feat: add option to use x-real-ip for rate limiting behind reverse proxy

* docs: update rate limiting configuration comments for X-Real-IP usage

* refactor: extract getIpAddress function to reduce code duplication

* revert(whitelist): rate limit settings shouldn't affect whitelist
2025-02-20 21:11:44 +02:00
7ea2c5f8cf Move cookie secret to data root. Make config.yaml immutable 2025-02-20 20:16:44 +02:00
362470da18 Plugins: Add auto-update functionality (#3487)
* Plugins: Add auto-update functionality

* Check if directory is a git repo

* Display message if any plugins were loaded
2025-02-16 20:55:53 +02:00
96d6a6df07 Merge pull request #3478 from Dakraid/feature/set-listen-ip
Feature: Allow user to configure an address to listen to
2025-02-15 00:02:15 +02:00
b029ae98dc Fix default config for IPv6 2025-02-14 20:06:45 +01:00
f5bfbce0ad Group listenAddress for config 2025-02-14 20:04:23 +01:00
2445b6d9dc Split up listen address configuration between IPv4 and IPv6 2025-02-14 19:58:59 +01:00
ad8f0f564f Use IP Regex package, update default 2025-02-14 19:06:07 +01:00