khanh.pndc/nextcloud-docs
1
0
Fork 0
mirror of https://github.com/nextcloud/documentation.git synced 2026-01-03 02:09:45 +07:00
Code Issues Packages Projects Releases Wiki Activity

Admin AI docs: Add references for supported languages

Browse Source 
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
This commit is contained in:
Marcel Klehr
2024-09-10 13:35:11 +02:00
parent 2f785aeaec
commit dde43e86ff
3 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
admin_manual/ai/app_context_chat.rst
View File

@@ -100,6 +100,7 @@ Known Limitations
-----------------
* Language models are likely to generate false information and should thus only be used in situations that are not critical. It's recommended to only use AI at the beginning of a creation process and not at the end, so that outputs of AI serve as a draft for example and not as final product. Always check the output of language models before using it.
* Context Chat is not integrated into the Chat UI of assistant app, at the moment, but has it's own interface in the assistant modal
* Make sure to test this app for whether it meets your use-case's quality requirements
* Customer support is available upon request, however we can't solve false or problematic output, most performance issues, or other problems caused by the underlying model. Support is thus limited only to bugs directly caused by the implementation of the app (connectors, API, front-end, AppAPI)
* Nextcloud usernames can be only 56 characters long. This is a limitation of the vector database we use (Chroma DB) and will be fixed soon.

14
admin_manual/ai/app_llm2.rst
View File

@@ -11,8 +11,22 @@ This app uses `ctransformers <https://github.com/marella/ctransformers>`_ under
* `Llama3 8b Instruct <https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF>`_ (reasonable quality; fast; good acclaim; multilingual output may not be optimal)
* `Llama3 70B Instruct <https://huggingface.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF>`_ (good quality; good acclaim; good multilingual output)
Multilinguality
---------------
This app supports input and output in languages other than English if the underlying model supports the language.
Llama 3.1 `supports the following languages: <https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct#multilingual-benchmarks>`_
* English
* Portuguese
* Spanish
* Italian
* German
* French
* Hindi
* Thai
Requirements
------------

2
admin_manual/ai/app_stt_whisper2.rst
View File

@@ -13,6 +13,8 @@ This app uses `faster-whisper <https://github.com/SYSTRAN/faster-whisper>`_ unde
* OpenAI Whisper large-v2 or v3 (multilingual)
* OpenAI Whisper medium.en (English only)
Whisper large v3 supports about ~100 languages and shows outstanding performance in ~10 of them. FOr more details see the `OpenAI Whisper paper <https://cdn.openai.com/papers/whisper.pdf>`_
Requirements
------------