paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-05-23 12:58:18 -05:00
Code Issues Packages Projects Releases Wiki Activity

Just some docs

Browse Source 
[ci skip]
This commit is contained in:
shamoon 2025-04-25 00:29:23 -07:00
parent 1df52fd4c1
commit 88ac3098ef
No known key found for this signature in database
2 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/configuration.md
View File

@ -1716,6 +1716,18 @@ suggestions. This setting is required to be set to true in order to use the AI f
Defaults to false.
#### [`PAPERLESS_LLM_EMBEDDING_BACKEND=<str>`](#PAPERLESS_LLM_EMBEDDING_BACKEND) {#PAPERLESS_LLM_EMBEDDING_BACKEND}
: The embedding backend to use for RAG. This can be either "openai" or "local".
Defaults to "local".
#### [`PAPERLESS_LLM_EMBEDDING_MODEL=<str>`](#PAPERLESS_LLM_EMBEDDING_MODEL) {#PAPERLESS_LLM_EMBEDDING_MODEL}
: The model to use for the embedding backend for RAG. This can be either "text-embedding-3-small" or any of the models supported by the current embedding backend.
Defaults to None.
#### [`PAPERLESS_AI_BACKEND=<str>`](#PAPERLESS_AI_BACKEND) {#PAPERLESS_AI_BACKEND}
: The AI backend to use. This can be either "openai" or "ollama". If set to "ollama", the AI

8
docs/usage.md
View File

@ -265,6 +265,14 @@ for details.
Paperless-ngx can suggest tags, correspondents, document types and storage paths for documents based on the content of the document. This is done using a machine learning model that is trained on the documents in your database. The suggestions are shown in the document detail page and can be accepted or rejected by the user.
## AI Features
Paperless-ngx includes several features that use AI to enhance the document management experience. These features are optional and can be enabled or disabled in the settings. If you are using the AI features, you may want to also enable the "LLM index" feature, which supports Retrieval-Augmented Generation (RAG) which significantly improves the quality of the AI features. The LLM index feature is not enabled by default and requires additional configuration.
### Document Chat
Paperless-ngx can use an AI LLM model to answer questions about a document or across multiple documents. <<add more details here>>
### AI-Enhanced Suggestions
If enabled, Paperless-ngx can use an AI LLM model to suggest document titles, dates, tags, correspondents and document types for documents. This feature will always be "opt-in" and does not disable the existing suggestion system. Currently, both remote (via the OpenAI API) and local (via Ollama) models are supported, see [configuration](configuration.md#ai) for details.