✋ feat: Stop Sequences for Conversations & Presets (#2536)

* feat: `stop` conversation parameter

* feat: Tag primitive

* feat: dynamic tags

* refactor: update tag styling

* feat: add stop sequences to OpenAI settings

* fix(Presentation): prevent `SidePanel` re-renders that flicker side panel

* refactor: use stop placeholder

* feat: type and schema update for `stop` and `TPreset` in generation param related types

* refactor: pass conversation to dynamic settings

* refactor(OpenAIClient): remove default handling for `modelOptions.stop`

* docs: fix Google AI Setup formatting

* feat: current_model

* docs: WIP update

* fix(ChatRoute): prevent default preset override before `hasSetConversation.current` becomes true by including latest conversation state as template

* docs: update docs with more info on `stop`

* chore: bump config_version

* refactor: CURRENT_MODEL handling

docs/install/configuration/ai_endpoints.md

@@ -260,8 +260,9 @@ Some of the endpoints are marked as **Known,** which means they might have speci
 
 - API is strict with unrecognized parameters and errors are not descriptive (usually "no body")
 
-    - The use of [`dropParams`](./custom_config.md#dropparams) to drop "stop", "user", "frequency_penalty", "presence_penalty" params is required.
-
+    - The use of [`dropParams`](./custom_config.md#dropparams) to drop "user", "frequency_penalty", "presence_penalty" params is required.
+    - `stop` is no longer included as a default parameter, so there is no longer a need to include it in [`dropParams`](./custom_config.md#dropparams), unless you would like to completely prevent users from configuring this field.
+    
 - Allows fetching the models list, but be careful not to use embedding models for chat.
 
 ```yaml
@@ -289,6 +290,8 @@ Some of the endpoints are marked as **Known,** which means they might have speci
 - **Known:** icon provided.
 - **Known issue:** fetching list of models is not supported. See [Pull Request 2728](https://github.com/ollama/ollama/pull/2728).
 - Download models with ollama run command. See [Ollama Library](https://ollama.com/library)
+- It's recommend to use the value "current_model" for the `titleModel` to avoid loading more than 1 model per conversation.
+    - Doing so will dynamically use the current conversation model for the title generation.
 - The example includes a top 5 popular model list from the Ollama Library, which was last updated on March 1, 2024, for your convenience.
 
 ```yaml
@@ -306,16 +309,18 @@ Some of the endpoints are marked as **Known,** which means they might have speci
           ]
         fetch: false # fetching list of models is not supported
       titleConvo: true
-      titleModel: "llama2"
+      titleModel: "current_model"
       summarize: false
-      summaryModel: "llama2"
+      summaryModel: "current_model"
       forcePrompt: false
       modelDisplayLabel: "Ollama"
 ```
 
 !!! tip "Ollama -> llama3"
     
-    To prevent the behavior where llama3 does not stop generating, add this `addParams` block to the config:
+    Note: Once `stop` was removed from the [default parameters](./custom_config.md#default-parameters), the issue highlighted below should no longer exist.
+
+    However, in case you experience the behavior where `llama3` does not stop generating, add this `addParams` block to the config:
     
     ```yaml
     - name: "Ollama"
@@ -327,9 +332,9 @@ Some of the endpoints are marked as **Known,** which means they might have speci
           ]
         fetch: false # fetching list of models is not supported
       titleConvo: true
-      titleModel: "llama3"
+      titleModel: "current_model"
       summarize: false
-      summaryModel: "llama3"
+      summaryModel: "current_model"
       forcePrompt: false
       modelDisplayLabel: "Ollama"
       addParams:
@@ -341,6 +346,31 @@ Some of the endpoints are marked as **Known,** which means they might have speci
             ]
     ```
 
+    If you are only using `llama3` with **Ollama**, it's fine to set the `stop` parameter at the config level via `addParams`.
+
+    However, if you are using multiple models, it's now recommended to add stop sequences from the frontend via conversation parameters and presets.
+
+    For example, we can omit `addParams`:
+
+    ```yaml
+    - name: "Ollama"
+      apiKey: "ollama"
+      baseURL: "http://host.docker.internal:11434/v1/" 
+      models:
+        default: [
+          "llama3:latest",
+          "mistral"
+          ]
+        fetch: false # fetching list of models is not supported
+      titleConvo: true
+      titleModel: "current_model"
+      modelDisplayLabel: "Ollama"
+    ```
+
+    And use these settings (best to also save it):
+
+    ![image](https://github.com/danny-avila/LibreChat/assets/110412045/57460b8c-308a-4d21-9dfe-f48a2ac85099)
+
 ## Openrouter
 > OpenRouter API key: [openrouter.ai/keys](https://openrouter.ai/keys)
 
@@ -348,7 +378,7 @@ Some of the endpoints are marked as **Known,** which means they might have speci
 
 - **Known:** icon provided, fetching list of models is recommended as API token rates and pricing used for token credit balances when models are fetched.
 
-- It's recommended, and for some models required, to use [`dropParams`](./custom_config.md#dropparams) to drop the `stop` parameter as Openrouter models use a variety of stop tokens.
+- `stop` is no longer included as a default parameter, so there is no longer a need to include it in [`dropParams`](./custom_config.md#dropparams), unless you would like to completely prevent users from configuring this field.
 
 - **Known issue:** you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
 

docs/install/configuration/ai_setup.md

@@ -159,7 +159,8 @@ For your convenience, these are the latest models as of 4/15/24 that can be used
 GOOGLE_MODELS=gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision
 ```
 
-Notes:
+**Notes:**
+
 - A gemini-pro model or `gemini-pro-vision` are required in your list for attaching images.
 - Using LibreChat, PaLM2 and Codey models can only be accessed through Vertex AI, not the Generative Language API.
     - Only models that support the `generateContent` method can be used natively with LibreChat + the Gen AI API.

docs/install/configuration/azure_openai.md

@@ -92,7 +92,7 @@ To properly integrate Azure OpenAI with LibreChat, specific fields must be accur
 
 These settings apply globally to all Azure models and groups within the endpoint. Here are the available fields:
 
-1. **titleModel** (String, Optional): Specifies the model to use for generating conversation titles. If not provided, the default model is set as `gpt-3.5-turbo`, which will result in no titles if lacking this model.
+1. **titleModel** (String, Optional): Specifies the model to use for generating conversation titles. If not provided, the default model is set as `gpt-3.5-turbo`, which will result in no titles if lacking this model. You can also set this to dynamically use the current model by setting it to `current_model`.
 
 2. **plugins** (Boolean, Optional): Enables the use of plugins through Azure. Set to `true` to activate Plugins endpoint support through your Azure config. Default: `false`.
 
@@ -398,8 +398,11 @@ endpoints:
     titleModel: "gpt-3.5-turbo"
 ```
 
-**Note**: "gpt-3.5-turbo" is the default value, so you can omit it if you want to use this exact model and have it configured. If not configured and `titleConvo` is set to `true`, the titling process will result in an error and no title will be generated.
+**Note**: "gpt-3.5-turbo" is the default value, so you can omit it if you want to use this exact model and have it configured. If not configured and `titleConvo` is set to `true`, the titling process will result in an error and no title will be generated. You can also set this to dynamically use the current model by setting it to `current_model`.
 
+```yaml
+    titleModel: "current_model"
+```
 
 ### Using GPT-4 Vision with Azure
 

docs/install/configuration/custom_config.md

@@ -24,7 +24,9 @@ Stay tuned for ongoing enhancements to customize your LibreChat instance!
 
 ## Compatible Endpoints
 
-Any API designed to be compatible with OpenAI's should be supported, but here is a list of **[known compatible endpoints](./ai_endpoints.md) including example setups.**
+Any API designed to be compatible with OpenAI's should be supported
+
+Here is a list of **[known compatible endpoints](./ai_endpoints.md) including example setups.**
 
 ## Setup
 
@@ -665,6 +667,7 @@ endpoints:
   - Type: String
   - Example: `titleModel: "mistral-tiny"`
   - **Note**: Defaults to "gpt-3.5-turbo" if omitted. May cause issues if "gpt-3.5-turbo" is not available.
+  - **Note**: You can also dynamically use the current conversation model by setting it to "current_model".
 
 ### **summarize**: 
 
@@ -752,11 +755,6 @@ Custom endpoints share logic with the OpenAI endpoint, and thus have default par
   "top_p": 1,
   "presence_penalty": 0,
   "frequency_penalty": 0,
-  "stop": [
-    "||>",
-    "\nUser:",
-    "<|diff_marker|>",
-  ],
   "user": "LibreChat_User_ID",
   "stream": true,
   "messages": [
@@ -773,7 +771,6 @@ Custom endpoints share logic with the OpenAI endpoint, and thus have default par
 - `top_p`: Defaults to `1` if not provided via preset,
 - `presence_penalty`: Defaults to `0` if not provided via preset,
 - `frequency_penalty`: Defaults to `0` if not provided via preset,
-- `stop`: Sequences where the AI will stop generating further tokens. By default, uses the start token (`||>`), the user label (`\nUser:`), and end token (`<|diff_marker|>`). Up to 4 sequences can be provided to the [OpenAI API](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stop)
 - `user`: A unique identifier representing your end-user, which can help OpenAI to [monitor and detect abuse](https://platform.openai.com/docs/api-reference/chat/create#chat-create-user).
 - `stream`: If set, partial message deltas will be sent, like in ChatGPT. Otherwise, generation will only be available when completed.
 - `messages`: [OpenAI format for messages](https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages); the `name` field is added to messages with `system` and `assistant` roles when a custom name is specified via preset.