From 1d716d003b78ab28825bfcb1e41ddf465eca0dda Mon Sep 17 00:00:00 2001 From: silentoplayz <50341825+silentoplayz@users.noreply.github.com> Date: Sat, 22 Jun 2024 23:38:15 +0000 Subject: [PATCH 1/4] Update features.mdx --- docs/features.mdx | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/docs/features.mdx b/docs/features.mdx index c5b8817d..8612dfc8 100644 --- a/docs/features.mdx +++ b/docs/features.mdx @@ -46,7 +46,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ”§ **Pipelines Framework**: Seamlessly integrate and customize your Open WebUI experience with our modular plugin framework for enhanced customization and functionality (https://github.com/open-webui/pipelines). Our framework allows for the easy addition of custom logic and integration of Python libraries, from AI agents to home automation APIs. -- πŸ“₯ **Upload Pipeline**: Pipelines can be uploaded directly from the `Admin Panel` > `Settings` > `Pipelines` section, streamlining the pipeline management process. +- πŸ“₯ **Upload Pipeline**: Pipelines can be uploaded directly from the `Admin Panel` > `Settings` > `Pipelines` menu, streamlining the pipeline management process. #### The possibilities with our Pipelines framework knows no bounds and are practically limitless. Start with a few pre-built pipelines to help you get started! @@ -59,7 +59,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - βš–οΈ **User Rate Limiting**: Manage API usage efficiently by controlling the flow of requests sent to LLMs to prevent exceeding rate limits with [Rate Limit](https://github.com/open-webui/pipelines/blob/main/examples/filters/rate_limit_filter_pipeline.py) pipeline. - 🌍 **Real-Time LibreTranslate Translation**: Integrate real-time translations into your LLM interactions using [LibreTranslate](https://github.com/open-webui/pipelines/blob/main/examples/filters/libretranslate_filter_pipeline.py) pipeline, enabling cross-lingual communication. - - Please note that this pipeline requires further setup with LibreTranslate in a Docker container to work. + - Please note that this pipeline requires further setup with LibreTranslate in a Docker container to work. - πŸ›‘οΈ **Toxic Message Filtering**: Our [Detoxify](https://github.com/open-webui/pipelines/blob/main/examples/filters/detoxify_filter_pipeline.py) pipeline automatically filters out toxic messages to maintain a clean and safe chat environment. @@ -97,15 +97,15 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ’Ύ **Persistent Settings**: Benefit from the convenience of saved and persistent settings within Open WebUI, stored in a config.json file for easy access and reuse. -- ❓ **Quick Access to Documentation & Shortcuts**: The question mark button located at the bottom right-hand corner of the main UI screen (available on larger screens like PCs) provides users with easy access to the Open WebUI documentation page and available keyboard shortcuts. +- ❓ **Quick Access to Documentation & Shortcuts**: The question mark button located at the bottom right-hand corner of the main UI screen (available on larger screens like desktop PCs and laptops) provides users with easy access to the Open WebUI documentation page and available keyboard shortcuts. -- πŸ“œ **Changelog & Check for Updates**: Users can access a comprehensive changelog and check for updates in `Settings` > `About` > `See What's New`, which provides a quick overview of the latest features, improvements, and bug fixes, as well as the ability to check for updates. +- πŸ“œ **Changelog & Check for Updates**: Users can access a comprehensive changelog and check for updates in the `Settings` > `About` > `See What's New` menu, which provides a quick overview of the latest features, improvements, and bug fixes, as well as the ability to check for updates. --- ### πŸ’¬ Conversations -- πŸ” **RAG Embedding Support**: Change the Retrieval Augmented Generation (RAG) embedding model directly in `Admin Panel` > `Settings` > `Documents`, enhancing document processing. This feature supports Ollama and OpenAI models. +- πŸ” **RAG Embedding Support**: Change the Retrieval Augmented Generation (RAG) embedding model directly in the `Admin Panel` > `Settings` > `Documents` menu, enhancing document processing. This feature supports Ollama and OpenAI models. - πŸ“œ **Citations in RAG Feature**: The Retrieval Augmented Generation (RAG) feature allows users to easily track the context of documents fed to LLMs with added citations for reference points. @@ -121,14 +121,14 @@ import { TopBanners } from "@site/src/components/TopBanners"; - 🏷️ **Conversation Tagging**: Effortlessly categorize and locate tagged chats for quick reference and streamlined data collection. -- πŸ‘Ά **Chat Cloning**: Easily clone and save a snapshot of any chat for future reference or continuation. This feature makes it easy to pick up where you left off or share your session with others. To create a copy of your chat, simply click on the `Clone` button in the dropdown menu. Can you keep up with your clones? +- πŸ‘Ά **Chat Cloning**: Easily clone and save a snapshot of any chat for future reference or continuation. This feature makes it easy to pick up where you left off or share your session with others. To create a copy of your chat, simply click on the `Clone` button in the chat's dropdown options. Can you keep up with your clones? - πŸ“œ **Prompt Preset Support**: Instantly access custom preset prompts using the `/` command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Import prompts with ease through [Open WebUI Community](https://openwebui.com/) integration or create your own! - πŸ“… **Prompt Variables Support**: Utilize prompt variables such as `{{CURRENT_DATE}}`, `{{CURRENT_DATETIME}}`, `{{CURRENT_TIME}}`, `{{USER_NAME}}`, and `{{USER_LOCATION}}` can be utilized in the system prompt. - - Please note that the `{{USER_LOCATION}}` prompt variable requires a secure connection over HTTPS. To utilize this particular prompt variable, please ensure that `{{USER_LOCATION}}` is toggled on from `Settings` > `Interface`. + - Please note that the `{{USER_LOCATION}}` prompt variable requires a secure connection over HTTPS. To utilize this particular prompt variable, please ensure that `{{USER_LOCATION}}` is toggled on from the `Settings` > `Interface` menu. -- 🧠 **Memory Feature**: Manually add information you want your LLMs to remember via `Settings` > `Personalization` > `Memory`. Memories can be added, edited, and deleted. +- 🧠 **Memory Feature**: Manually add information you want your LLMs to remember via the `Settings` > `Personalization` > `Memory` menu. Memories can be added, edited, and deleted. --- @@ -151,11 +151,11 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ”„ **Seamless Integration**: Copy any `ollama run {model:tag}` CLI command directly from a model's page on [Ollama library](https://ollama.com/library/) and paste it into the model dropdown to easily select and pull models. -- πŸ—‚οΈ **Create Ollama Modelfile**: To create a model file for Ollama, navagate to the `Admin Panel` > `Settings` > `Models` > `Create a model`. +- πŸ—‚οΈ **Create Ollama Modelfile**: To create a model file for Ollama, navagate to the `Admin Panel` > `Settings` > `Models` > `Create a model` menu. -- ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from Open WebUI from `Admin Settings` > `Settings` > `Model` > `Experimental`. The process has been streamlined with the option to upload from your machine or download GGUF files from Hugging Face. +- ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from Open WebUI from the `Admin Settings` > `Settings` > `Model` > `Experimental` menu. The process has been streamlined with the option to upload from your machine or download GGUF files from Hugging Face. -- βš™οΈ **Default Model Setting**: The default model can be set in `Settings` > `Interface` for mobile devices, or be set easier in a new chat under the model selector dropdown on PCs. +- βš™οΈ **Default Model Setting**: The default model can be set in the `Settings` > `Interface` menu on mobile devices, or can more easily be set in a new chat under the model selector dropdown on desktop PCs and laptops. - πŸ’‘ **LLM Response Insights**: Details of every generated response can be viewed, including external model API insights and comprehensive local model info. @@ -165,7 +165,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - 🍻 **TavernAI Character Card Integration**: Experience enhanced visual storytelling with TavernAI Character Card Integration in our model builder. Users can seamlessly incorporate TavernAI character card PNGs directly into their model files, creating a more immersive and engaging user experience. -- 🎲 **Model Playground (Beta)**: Try out models in a sandbox environment with the model playground area (`beta`), which enables users to test and explore model capabilities and settings with ease in a sandbox environment before deployment in a live chat environment. +- 🎲 **Model Playground (Beta)**: Try out models in a sandbox environment with the model playground area (`beta`), which enables users to test and explore model capabilities and parameters with ease in a sandbox environment before deployment in a live chat environment. --- @@ -176,13 +176,13 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ‘πŸ‘Ž **RLHF Annotation**: Enhance the impact of your messages by rating them with either a thumbs up or thumbs down, followed by the option to provide textual feedback, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (`RLHF`). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data. - 🀝 **Community Sharing**: Share your chat sessions with the [Open WebUI Community](https://openwebui.com/) by clicking the `Share to Open WebUI Community` button. This feature allows you to engage with other users and collaborate on the platform. - - To utilize this feature, please sign-in to your Open WebUI Community account. Sharing your chats fosters a vibrant community, encourages knowledge sharing, and facilitates joint problem-solving. Please note that community sharing of chat sessions is an optional feature. Only Admins can toggle this feature on or off via the `Admin Settings` > `Settings` > `General` menu. + - To utilize this feature, please sign-in to your Open WebUI Community account. Sharing your chats fosters a vibrant community, encourages knowledge sharing, and facilitates joint problem-solving. Please note that community sharing of chat sessions is an optional feature. Only Admins can toggle this feature on or off in the `Admin Settings` > `Settings` > `General` menu. --- ### πŸ“š History & Archive -- πŸ“œ **Chat History**: Access and manage your conversation history with ease via the chat navigation sidebar. Toggle off chat history in `Settings` > `Chats` to prevent chat history from being created with new interactions. +- πŸ“œ **Chat History**: Access and manage your conversation history with ease via the chat navigation sidebar. Toggle off chat history in the `Settings` > `Chats` menu to prevent chat history from being created with new interactions. - πŸ”„ **Regeneration History Access**: Easily revisit and explore your entire regeneration history. @@ -205,7 +205,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ—£οΈ **Voice Input Support**: Engage with your model through voice interactions; enjoy the convenience of talking to your model directly. Additionally, explore the option for sending voice input automatically after 3 seconds of silence for a streamlined experience. - Microphone access requires a secure connection over HTTPS for this feature to work. -- 😊 **Emoji Call**: Toggle this feature on from the `Settings` > `Interface`, allowing LLMs to express emotions using emojis during voice calls for a more dynamic interaction. +- 😊 **Emoji Call**: Toggle this feature on from the `Settings` > `Interface` menu, allowing LLMs to express emotions using emojis during voice calls for a more dynamic interaction. - Microphone access requires a secure connection over HTTPS for this feature to work. - πŸŽ™οΈ **Hands-Free Voice Call Feature**: Initiate voice calls without needing to use your hands, making interactions more seamless. From cf199709bdb78fe42c5ddac1cc2241f0040daf7f Mon Sep 17 00:00:00 2001 From: silentoplayz <50341825+silentoplayz@users.noreply.github.com> Date: Sun, 23 Jun 2024 02:14:32 +0000 Subject: [PATCH 2/4] Update images.md Fixes --- docs/tutorial/images.md | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/docs/tutorial/images.md b/docs/tutorial/images.md index 889efec7..60bbc1df 100644 --- a/docs/tutorial/images.md +++ b/docs/tutorial/images.md @@ -5,7 +5,7 @@ title: "Image Generation" # Image Generation -Open WebUI now supports image generation through two backends: **AUTOMATIC1111** and **OpenAI DALLΒ·E**. This guide will help you set up and use both options. +Open WebUI supports image generation through three backends: **AUTOMATIC1111**, **ComfyUI**, and **OpenAI DALLΒ·E**. This guide will help you set up and use either of these options. ## AUTOMATIC1111 @@ -25,8 +25,9 @@ Open WebUI supports image generation through the **AUTOMATIC1111** [API](https:/ ### Configuring Open WebUI -1. In Open WebUI, navigate to **Settings > Images**. -2. In the API URL field, enter the address where AUTOMATIC1111's API is accessible: +1. In Open WebUI, navigate to the **Admin Panel** > **Settings** > **Images** menu. +2. Set the `Image Generation Engine` field to `Default (Automatic1111)`. +3. In the API URL field, enter the address where AUTOMATIC1111's API is accessible: ``` http://:7860/ ``` @@ -54,10 +55,11 @@ ComfyUI provides an alternative interface for managing and interacting with imag ### Configuring Open WebUI -1. In Open WebUI, navigate to **Settings > Images**. -2. In the API URL field, enter the address where ComfyUI's API is accessible: +1. In Open WebUI, navigate to the **Admin Panel** > **Settings** > **Images** menu. +2. Set the `Image Generation Engine` field to `ComfyUI`. +3. In the API URL field, enter the address where ComfyUI's API is accessible: ``` - http://:7860/ + http://:8188/ ``` Set the environment variable `COMFYUI_BASE_URL` to this address to ensure proper integration. @@ -71,8 +73,8 @@ Open WebUI also supports image generation through the **OpenAI DALLΒ·E APIs**. T ### Configuring Open WebUI -1. In Open WebUI, navigate to **Settings > Images**. -2. Select **OpenAI** as your image generation backend. +1. In Open WebUI, navigate to the **Admin Panel** > **Settings** > **Images** menu. +2. Set the `Image Generation Engine` field to `Open AI (Dall-E)`. 3. Enter your OpenAI API key. 4. Choose the DALLΒ·E model you wish to use. Note that image size options will depend on the selected model: - **DALLΒ·E 2**: Supports `256x256`, `512x512`, or `1024x1024` images. @@ -83,4 +85,4 @@ Open WebUI also supports image generation through the **OpenAI DALLΒ·E APIs**. T ![Image Generation Tutorial](/img/tutorial_image_generation.png) 1. First, use a text generation model to write a prompt for image generation. -2. After the response has finished, you can click the Picture icon to generate an image. \ No newline at end of file +2. After the response has finished, you can click the Picture icon to generate an image. From 38359c686192063684da2b8dd14622705550263e Mon Sep 17 00:00:00 2001 From: silentoplayz <50341825+silentoplayz@users.noreply.github.com> Date: Sun, 23 Jun 2024 03:25:29 +0000 Subject: [PATCH 3/4] Update rag.md Revamp --- docs/tutorial/rag.md | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) diff --git a/docs/tutorial/rag.md b/docs/tutorial/rag.md index 54bd80ab..979f0c38 100644 --- a/docs/tutorial/rag.md +++ b/docs/tutorial/rag.md @@ -5,27 +5,40 @@ title: "Retrieval Augmented Generation (RAG)" # Retrieval Augmented Generation (RAG) -Retrieval Augmented Generation (RAG) allows context from other diverse sources to be included in chats. Text from different sources is combined with the RAG template and prefixed to the user's prompt. +Retrieval Augmented Generation (RAG) is a a cutting-edge technology that enhances the conversational capabilities of chatbots by incorporating context from diverse sources. It works by retrieving relevant information from a wide range of sources such as local and remote documents, web content, and even multimedia sources like YouTube videos. The retrieved text is then combined with a predefined RAG template and prefixed to the user's prompt, providing a more informed and contextually relevant response. -## Including external sources in chats -Activate RAG by starting the prompt with a `#` symbol. A list of sources will appear. +One of the key advantages of RAG is its ability to access and integrate information from a variety of sources, making it an ideal solution for complex conversational scenarios. For instance, when a user asks a question related to a specific document or webpage, RAG can retrieve and incorporate the relevant information from that source into the chat response. RAG can also retrieve and incorporate information from multimedia sources like YouTube videos. By analyzing the transcripts or captions of these videos, RAG can extract relevant information and incorporate it into the chat response. -Once selected, a document icon appears at the top of the prompt, indicating successful retrieval. +## Local and Remote RAG Integration -### Local sources +Local documents must first be uploaded via the Documents section of the Workspace area to access them using the `#` symbol before a query. Click on the formatted URL in the that appears above the chatbox. Once selected, a document icon appears above `Send a message`, indicating successful retrieval. -Local documents must first be uploaded via the Documents section. - -### Sourcing from the Web +## Web Search for RAG -Remote sources are achieved with `#` followed by the target URL. Open WebUI fetches and parses the URL. +For web content integration, start a query in a chat with `#`, followed by the target URL. Click on the formatted URL in the box that appears above the chatbox. Once selected, a document icon appears above `Send a message`, indicating successful retrieval. Open WebUI fetches and parses information from the URL if it can. -> **Tip:** Webpages often include extraneous information such as navigation and footer. Link to a raw or reader-friendly version of the page for better results. +> **Tip:** Webpages often contain extraneous information such as navigation and footer. For better results, link to a raw or reader-friendly version of the page. -## Document parsing +## RAG Template Customization -A variety of parsers extract content from local and remote documents. For more, see the [`get_loader`](https://github.com/open-webui/open-webui/blob/2fa94956f4e500bf5c42263124c758d8613ee05e/backend/apps/rag/main.py#L328) function. +Customize the RAG template from the `Admin Panel` > `Settings` > `Documents` menu. + +## RAG Embedding Support + +Change the RAG embedding model directly in the `Admin Panel` > `Settings` > `Documents` menu. This feature supports Ollama and OpenAI models, enabling you to enhance document processing according to your requirements. + +## Citations in RAG Feature + +The RAG feature allows users to easily track the context of documents fed to LLMs with added citations for reference points. This ensures transparency and accountability in the use of external sources within your chats. -## RAG Template Customisation +## Enhanced RAG Pipeline -Modify the RAG template by accessing the 'settings' icon housed within the 'Documents' section. +The togglable hybrid search sub-feature for our RAG embedding feature enhances RAG functionality via `BM25`, with re-ranking powered by `CrossEncoder`, and configurable relevance score thresholds. This provides a more precise and tailored RAG experience for your specific use case. + +## YouTube RAG Pipeline + +The dedicated RAG pipeline for summarizing YouTube videos via video URLs enables smooth interaction with video transcriptions directly. This innovative feature allows you to incorporate video content into your chats, further enriching your conversation experience. + +## Document Parsing + +A variety of parsers extract content from local and remote documents. For more, see the [`get_loader`](https://github.com/open-webui/open-webui/blob/2fa94956f4e500bf5c42263124c758d8613ee05e/backend/apps/rag/main.py#L328) function. From c8735fc287b5bd765b486b10d642a139df00f6da Mon Sep 17 00:00:00 2001 From: silentoplayz <50341825+silentoplayz@users.noreply.github.com> Date: Sun, 23 Jun 2024 01:40:54 -0400 Subject: [PATCH 4/4] Update features.mdx A few fixes --- docs/features.mdx | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/features.mdx b/docs/features.mdx index 8612dfc8..085c6406 100644 --- a/docs/features.mdx +++ b/docs/features.mdx @@ -20,7 +20,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - βœ’οΈπŸ”’ **Full Markdown and LaTeX Support**: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction. -- 🧩 **Model Builder**: Easily create Ollama models directly from Open WebUI. Create and add custom characters/agents, customize chat elements, and import models effortlessly through [Open WebUI Community](https://openwebui.com/) integration. +- 🧩 **Model Builder**: Easily create Ollama models directly from Open WebUI. Create and add custom characters and agents, customize chat elements, and import models effortlessly through [Open WebUI Community](https://openwebui.com/) integration. - πŸ“š **Local and Remote RAG Integration**: Dive into the future of chat interactions and explore your documents with our cutting-edge Retrieval Augmented Generation (RAG) technology within your chats. Documents can be loaded into the workspace area, after which they can be accessed using the `#` symbol before a query, or by starting the prompt with `#`, followed by a URL for web content integration. @@ -139,7 +139,7 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ“š **Knowledge Support for Models**: The ability to attach functions and documents directly to models from the models workspace enhances the information available to each model. -- πŸ—‚οΈ **Model Presets**: Create and manage model presets for both the Ollama/OpenAI API. +- πŸ—‚οΈ **Model Presets**: Create and manage model presets for both the Ollama and OpenAI API. - 🏷️ **Model Tagging**: The models workspace enables users to organize their models using tagging. @@ -155,17 +155,17 @@ import { TopBanners } from "@site/src/components/TopBanners"; - ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from Open WebUI from the `Admin Settings` > `Settings` > `Model` > `Experimental` menu. The process has been streamlined with the option to upload from your machine or download GGUF files from Hugging Face. -- βš™οΈ **Default Model Setting**: The default model can be set in the `Settings` > `Interface` menu on mobile devices, or can more easily be set in a new chat under the model selector dropdown on desktop PCs and laptops. +- βš™οΈ **Default Model Setting**: The default model preference for new chats can be set in the `Settings` > `Interface` menu on mobile devices, or can more easily be set in a new chat under the model selector dropdown on desktop PCs and laptops. - πŸ’‘ **LLM Response Insights**: Details of every generated response can be viewed, including external model API insights and comprehensive local model info. - πŸ“₯πŸ—‘οΈ **Download/Delete Models**: Models can be downloaded or deleted directly from Open WebUI with ease. -- πŸ”„ **Update All Ollama Models**: A convenient button allows users to update locally installed models in one operation, streamlining model management. +- πŸ”„ **Update All Ollama Models**: A convenient button allows users to update all their locally installed models in one operation, streamlining model management. - 🍻 **TavernAI Character Card Integration**: Experience enhanced visual storytelling with TavernAI Character Card Integration in our model builder. Users can seamlessly incorporate TavernAI character card PNGs directly into their model files, creating a more immersive and engaging user experience. -- 🎲 **Model Playground (Beta)**: Try out models in a sandbox environment with the model playground area (`beta`), which enables users to test and explore model capabilities and parameters with ease in a sandbox environment before deployment in a live chat environment. +- 🎲 **Model Playground (Beta)**: Try out models with the model playground area (`beta`), which enables users to test and explore model capabilities and parameters with ease in a sandbox environment before deployment in a live chat environment. --- @@ -184,13 +184,13 @@ import { TopBanners } from "@site/src/components/TopBanners"; - πŸ“œ **Chat History**: Access and manage your conversation history with ease via the chat navigation sidebar. Toggle off chat history in the `Settings` > `Chats` menu to prevent chat history from being created with new interactions. -- πŸ”„ **Regeneration History Access**: Easily revisit and explore your entire regeneration history. +- πŸ”„ **Regeneration History Access**: Easily revisit and explore your entire LLM response regeneration history. - πŸ“¬ **Archive Chats**: Effortlessly store away completed conversations you've had with models for future reference or interaction, maintaining a tidy and clutter-free chat interface. - πŸ—ƒοΈ **Archive All Chats**: This feature allows you to quickly archive all of your chats at once. -- πŸ“¦ **Export All Archived Chats as JSON**: This features enables users to easily export all their archived chats in a single JSON file, which can be used for backup or transfer purposes. +- πŸ“¦ **Export All Archived Chats as JSON**: This feature enables users to easily export all their archived chats in a single JSON file, which can be used for backup or transfer purposes. - πŸ“„ **Download Chats as JSON/PDF/TXT**: Easily download your chats individually in your preffered format of `.json`, `.pdf`, or `.txt` format.