Merge branch 'master' into 59-streaming-support-for-n8n-pipeline

Signed-off-by: owndev <69784886+owndev@users.noreply.github.com>

Author: owndev

README.md

@@ -27,18 +27,17 @@
 
 ## Prerequisites 🔗
 
-> [!WARNING]
+> [!IMPORTANT]
 > To use these functions, ensure the following requirements are met:
-
-1. **An Active Open WebUI Instance**: You must have [Open WebUI](https://github.com/open-webui/open-webui) installed and running.
-
-2. **Required AI Services (if applicable)**: Some pipelines require external AI services, such as [Azure AI](https://ai.azure.com/).
-
-3. **Admin Access**: To install functions in Open WebUI, you must have administrator privileges.
+>
+> 1. **An Active Open WebUI Instance**: You must have [Open WebUI](https://github.com/open-webui/open-webui) installed and running.
+> 2. **Required AI Services (if applicable)**: Some pipelines require external AI services, such as [Azure AI](https://ai.azure.com/).
+> 3. **Admin Access**: To install functions in Open WebUI, you must have administrator privileges.
 
 ## Installation 🚀
 
-To install and configure functions in Open WebUI, follow these steps:
+> [!TIP]
+> Follow these steps to install and configure functions in Open WebUI:
 
 1. **Ensure Admin Access**:
 
@@ -66,6 +65,9 @@ To install and configure functions in Open WebUI, follow these steps:
 
 ## Security Features 🛡️
 
+> [!WARNING]
+> **API Key Security**: Always use encryption for sensitive information like API keys!
+
 ### API Key Encryption
 
 The functions include a built-in encryption mechanism for sensitive information:
@@ -75,21 +77,18 @@ The functions include a built-in encryption mechanism for sensitive information:
 - **Transparent Usage**: The encryption/decryption happens automatically when values are accessed.
 - **No Configuration Required**: Works out-of-the-box when [WEBUI_SECRET_KEY](https://docs.openwebui.com/getting-started/env-configuration/#webui_secret_key) is set.
 
-**To enable encryption:**
-
-> [!CAUTION]
-> **WEBUI_SECRET_KEY is required for encryption to work!**
+> [!IMPORTANT]
+> **To enable encryption**, set the `WEBUI_SECRET_KEY` environment variable:
 >
 > ```bash
 > # Set this in your Open WebUI environment or .env file
 > WEBUI_SECRET_KEY="your-secure-random-string"
 > ```
->
-> Without this key, API keys and sensitive data will **not** be encrypted.
 
 ## Pipelines 🧩
 
-Pipelines are processing functions that extend Open WebUI with **custom AI models**, **external integrations**, and **data manipulation logic**.
+> [!NOTE]
+> Pipelines are processing functions that extend Open WebUI with **custom AI models**, **external integrations**, and **data manipulation logic**.
 
 ### **1. [Azure AI Foundry Pipeline](./pipelines/azure/azure_ai_foundry.py)**
 
@@ -101,6 +100,8 @@ Pipelines are processing functions that extend Open WebUI with **custom AI model
 - Enables interaction with **Azure OpenAI** and other **Azure AI** models.
 - Supports Azure Search integration for enhanced document retrieval.
 - Supports multiple Azure AI models selection via the `AZURE_AI_MODEL` environment variable (e.g. `gpt-4o;gpt-4o-mini`).
+- Customizable pipeline display with configurable prefix via `AZURE_AI_PIPELINE_PREFIX`.
+- Azure AI Search / RAG integration with enhanced collapsible citation display (Azure OpenAI only).
 - Filters valid parameters to ensure clean requests.
 - Handles both streaming and non-streaming responses.
 - Provides configurable error handling and timeouts.
@@ -148,14 +149,19 @@ Pipelines are processing functions that extend Open WebUI with **custom AI model
 - **Configurable Parameters**: Environment variables for image optimization (quality, max dimensions, format conversion).
 - Grounding with Google search with [google_search_tool.py filter](./filters/google_search_tool.py)
 - Native tool calling support
+- Configurable API version support
 
 🔗 [Google Gemini Pipeline in Open WebUI](https://openwebui.com/f/owndev/google_gemini)
 
 🔗 [Learn More About Google Gemini](https://ai.google.dev/gemini-api/docs?hl=de)
 
+> [!NOTE]
+> **For LiteLLM Users**: To use Google Gemini models through LiteLLM, configure LiteLLM directly in Open WebUI's Admin Panel → Settings → Connections → OpenAI section instead of using this pipeline. For more information about LiteLLM, visit the [official LiteLLM GitHub repository](https://github.com/BerriAI/litellm).
+
 ## Filters 🔍
 
-Filters allow for **preprocessing and postprocessing** of data within Open WebUI.
+> [!NOTE]
+> Filters allow for **preprocessing and postprocessing** of data within Open WebUI.
 
 ### **1. [Time Token Tracker](./filters/time_token_tracker.py)**
 
@@ -194,16 +200,19 @@ Look here for [Google Gemini Integration](./docs/google-gemini-integration.md).
 
 ## Contribute 💪
 
-We accept different types of contributions, including some that don't require you to write a single line of code.
-For detailed instructions on how to get started with our project, see [about contributing to Open-WebUI-Functions](https://own.dev/github-owndev-open-webui-functions-contributing).
+> [!TIP]
+> We welcome contributions of all kinds! You don't need to write code to contribute.
+>
+> For detailed instructions on how to get started with our project, see [about contributing to Open-WebUI-Functions](./.github/CONTRIBUTING.md).
 
 ## License 📜
 
 This project is licensed under the [Apache License 2.0](./LICENSE) - see the [LICENSE](./LICENSE) file for details. 📄
 
 ## Support 💬
 
-If you have any questions, suggestions, or need assistance, please open an [issue](../../issues/new/choose) to connect with us! 🤝
+> [!NOTE]
+> If you have any questions, suggestions, or need assistance, please open an [issue](../../issues/new/choose) to connect with us! 🤝
 
 ## Star History 💫
 
@@ -217,4 +226,4 @@ If you have any questions, suggestions, or need assistance, please open an [issu
 
 ---
 
-Created by [owndev](https://own.dev/github) - Let's make Open WebUI even more amazing together! 💪
+Created by [owndev](https://github.com/owndev) - Let's make Open WebUI even more amazing together! 💪

docs/google-gemini-integration.md

@@ -2,11 +2,11 @@
 
 This integration enables **Open WebUI** to interact with **Google Gemini** models via the official Google Generative AI API (using API Keys) or through Google Cloud Vertex AI (leveraging Google Cloud's infrastructure and authentication). It provides a robust and customizable pipeline to access text and multimodal generation capabilities from Google’s latest AI models.
 
-🔗 [Learn More About Google AI](https://own.dev/ai-google-dev)
+🔗 [Learn More About Google AI](https://ai.google.dev/)
 
 ## Pipeline
 
-- 🧩 [Google Gemini Pipeline](https://own.dev/github-owndev-open-webui-functions-google-gemini)
+- 🧩 [Google Gemini Pipeline](../pipelines/google/google_gemini.py)
 
 ## Features
 
@@ -52,7 +52,10 @@ This integration enables **Open WebUI** to interact with **Google Gemini** model
 - **Grounding with Google search**  
   Improve the accuracy and recency of Gemini responses with Google search grounding.
 
-- **Native tool calling support**
+- **Ability to forward User Headers and change gemini base url**  
+  Forward user information headers (like Name, Id, Email and Role) to Google API or LiteLLM for better context and analytics. Also, change the base URL for the Google Generative AI API if needed.
+
+- **Native tool calling support**  
   Leverage Google genai native function calling to orchestrate the use of tools
 
 ## Environment Variables
@@ -95,6 +98,23 @@ GOOGLE_IMAGE_ENABLE_OPTIMIZATION=true
 # Default: 0.5
 GOOGLE_IMAGE_PNG_THRESHOLD_MB=0.5
 
+# Maximum number of images (history + current message) sent per request
+# Default: 5
+GOOGLE_IMAGE_HISTORY_MAX_REFERENCES=5
+
+# Add inline labels like [Image 1] before each image to allow references in follow-up prompts
+# Default: true
+GOOGLE_IMAGE_ADD_LABELS=true
+
+# Deduplicate identical images from history (hash-based) to reduce payload size
+# Default: true
+GOOGLE_IMAGE_DEDUP_HISTORY=true
+
+# Boolean: When true (default) history images come before current message images.
+# When false, current message images are placed first.
+# Default: true
+GOOGLE_IMAGE_HISTORY_FIRST=true
+
 # Enable fallback to data URL when image upload fails
 # Default: true
 GOOGLE_IMAGE_UPLOAD_FALLBACK=true
@@ -111,7 +131,7 @@ GOOGLE_API_KEY="your-google-api-key"
 ```
 
 > [!TIP]
-> You can obtain your API key from the [Google AI Studio](https://own.dev/aistudio-google-com) dashboard after signing up.
+> You can obtain your API key from the [Google AI Studio](https://aistudio.google.com/) dashboard after signing up.
 
 ### Connection Method: Google Cloud Vertex AI