docs

docs/snippets/common.md

@@ -10,3 +10,10 @@ Then select the group you want to add the template to and click the **:material-
 
 ![world editor templates create attribute template 1](/talemate/img/0.26.0/world-editor-templates-create-attribute-template-1.png)
 <!--- --8<-- [end:world-editor-create-group] -->
+
+<!--- --8<-- [start:editor-revision-unwanted-propse-requirement] -->
+!!! note "Unwanted Prose Requirement"
+    Unwanted phrases are defined in the writing style that is currently selected in the [Scene Settings](/talemate/user-guide/world-editor/scene/settings).
+
+    See [Writing Style Templates](/talemate/user-guide/world-editor/templates/writing-style) for more information on how to create a writing style and add unwanted phrases.
+<!--- --8<-- [end:editor-revision-unwanted-propse-requirement] -->

docs/user-guide/agents/editor/settings.md

@@ -1,5 +1,7 @@
 # Settings
 
+## General
+
 ![Editor agent settings](/talemate/img/0.29.0/editor-agent-settings.png)
 
 ##### Fix exposition
@@ -20,12 +22,98 @@ Applies the same rules as above to the user input messages.
 
 Will take the generate message and attempt to add more detail to it.
 
-##### Fix continuity errors
+## Long Term Memory
 
-Will attempt to fix continuity errors in the generated text.
+--8<-- "docs/snippets/tips.md:agent_long_term_memory_settings"
 
-!!! example "Experimental, and doesn't work most of the time"
-    There is something about accurately identifying continuity errors that is currently very 
-    difficult for AI to do. So this feature is very hit and miss. More miss than hit.
+## Revision
 
-    Also takes long to process, so probably leave it turned off.
+![Editor agent revision settings](/talemate/img/0.30.0/editor-revision-settings-dedupe.png)
+
+When :material-typewriter: revision is enabled the editor will analyze and attempt to fix character and narrator messages.
+
+Currently it can detect the following issues:
+
+- Repetition of phrases / concepts
+- Unwanted prose as defined in the writing style
+
+The revision action is split into three parts:
+
+- Find any issues through fuzzy, regex and semantic similarity (embeddings) matching
+- Analyze the issues and plan a fix
+- Apply the fix
+
+This means it comes at a noticable delay IF it finds issues, but the improvements may be worth it.
+
+##### Enable Revision
+
+Check this to enable revision.
+
+##### Revision Method
+
+Which method to use to fix issues. 
+
+- `Dedupe (Fast and dumb)` - this is the default
+- `Rewrite (AI assisted, slower and less dumb, probably)`
+
+When **Dedupe** is active it will be restricting to find repetition and remove it without replacing it with something else, nor understanding the intent or context, so it may sometimes cause disjointed dialogue. This method is much faster as it will never prompt the AI for analysis and fixes.
+
+When **Rewrite** is active, unwanted prose detection will become available and when issues are detected the AI will attempt to rewrite the message to fix the issues.
+
+#### Repetition
+
+##### Repetition Detection Method
+
+How is repetition detected.
+
+- `Fuzzy` - fuzzy matching will match based on character-level similarity, finding text that is approximately the same with small differences (like typos, missing letters, or minor variations). This is faster but less context-aware than semantic matching.
+- `Semantic Similarity` - will match based on the semantic meaning of the text using the Memory Agent's embedding function. (default)
+
+!!! warning "Semantic Similarity"
+    Uses the memory agent's embedding function to compare the text. Will use batching when available, but has the potential to do A LOT of calls to the embedding model.
+
+##### Similarity Threshold
+
+How similar does the text need to be to be considered repetitive. (50 - 100%)
+
+You want to keep this relatively high.
+
+##### Repetition Range
+
+This is the number of **MESSAGES** to consider in the history when checking for repetition.
+
+At its default ot `15` it means the last 15 messages will be considered.
+
+##### Repetition Min. Length
+
+The minimum length of a phrase (in characters) to be considered for repetition. Shorter phrases will be ignored.
+
+### Rewrite Mode
+
+Once switched to rewrite mode some extra settings will become available.
+
+![Editor agent revision settings](/talemate/img/0.30.0/editor-revision-settings.png)
+
+#### Preferences for Rewriting
+
+##### Test parts of setences, split on commas
+
+If active this means that when a sentence doen't produce a hit, if it has one or more commas it will split the sentence on the commas and test each part individually.
+
+##### Minimum issues
+
+The minimum amount of issues that need to be detected to trigger a rewrite.
+
+#### Unwanted Prose
+
+##### Detect Unwanted Prose
+
+Check this to enable unwanted prose detection.
+
+--8<-- "docs/snippets/common.md:editor-revision-unwanted-propse-requirement"
+
+##### Unwanted Prose Threshold
+
+Similarity threshold for unwanted prose detection. (0.4 - 1.0)
+
+You want to keep this relatively high.

docs/user-guide/agents/memory/embeddings.md

@@ -21,6 +21,12 @@ Sentence transformer model that is decently fast and accurate and will likely be
 
 ### Instructor Models
 
+!!! warning "Support of these likely deprecated"
+    Its become increasingly difficult to install support for these while keeping other dependencies up to date.
+    See [this issue](https://github.com/vegu-ai/talemate/issues/176) for more details.
+
+    Use the `Alibaba-NLP/Gte-Base-En-V1.5` embedding instead, its pretty close in accuracy and much smaller.
+
 Instructor embeddings, coming in three sizes: `base`, `large`, and `xl`. XL is the most accurate but also has the biggest memory footprint and is the slowest. Using `cuda` is recommended for the `xl` and `large` models.
 
 ### OpenAI text-embedding-3-small

docs/user-guide/clients/presets.md

@@ -8,9 +8,9 @@ If you wish to alter the inference parameters sent with the generation requests
 
 ![open settings](/talemate/img/0.26.0/open-settings.png)
 
-Navigate to the :material-tune: **Presets** tab then select the preset you wish to edit.
+Navigate to the :material-tune: **Presets** tab then select the :material-matrix: **Inference** tab.
 
-![selected preset](/talemate/img/0.26.0/inference-presets-1.png)
+![selected preset](/talemate/img/0.30.0/inference-presets-1.png)
 
 !!! warning
     Not all clients support all parameters, and generally it is assumed that the client implementation handles the parameters in a sane way, especially if values are passed for all of them. All presets are used and will be selected depending on the action the agent is performing. If you don't know what these mean, it is recommended to leave them as they are.
@@ -53,3 +53,27 @@ Used mostly for the director when directing the scene flow. Need to be creative
 ### Summarization
 
 Used for summarizing the scene progress into narrative text.
+
+
+## Preset Groups
+
+Initially there is a `Default` group in which the presets are edited, but if you want you can create additional groups to create - for example - model / client specific presets.
+
+To add a new group, type the title in to the **New Group Name** field in the upper right and press `Enter`.
+
+![new group](/talemate/img/0.30.0/inference-presets-custom-group-1.png)
+
+
+The new group will be added and automatically selected for editing.
+
+![new group](/talemate/img/0.30.0/inference-presets-custom-group-2.png)
+
+Once you have adjusted the presets to your liking you can save the group by clicking the :material-content-save: **Save** button.
+
+### Setting the group for the client
+
+In the client listing find the :material-tune: selected preset and click it to expand the meny containing the groups.
+
+![select group](/talemate/img/0.30.0/inference-preset-group-apply.png)
+
+![select group](/talemate/img/0.30.0/inference-preset-group-applied.png)

docs/user-guide/clients/rate-limiting.md

@@ -0,0 +1,19 @@
+# Rate Limiting
+
+You can rate limit a client to N requests per minute.
+
+![Rate limit](/talemate/img/0.30.0/client-ratelimit.png)
+
+Once the limit is hit you will get a popup notification.
+
+![Rate limit popup](/talemate/img/0.30.0/client-ratelimit-popup.png)
+
+Here you can either choose to wait for the rate limit to reset, or to abort the generation.
+
+If you abort the generation, the current stack of actions will be canceled and control will be given back to the user. This is essentially the same as Cancelling the generation through normal means.
+
+If you chose to wait the notification will collapse to the top of the screen with a timer counting down the remaining time.
+
+Clicking the notification will expand it again.
+
+![Rate limit notification](/talemate/img/0.30.0/client-ratelimit-notification.png)