milvus-io · liyun95 · May 31, 2025 · May 15, 2025 · May 15, 2025 · May 15, 2025
diff --git a/assets/anythingllm_chat.png b/assets/anythingllm_chat.png
diff --git a/assets/anythingllm_config.png b/assets/anythingllm_config.png
diff --git a/assets/anythingllm_dashboard.png b/assets/anythingllm_dashboard.png
diff --git a/assets/anythingllm_milvus.png b/assets/anythingllm_milvus.png
diff --git a/assets/anythingllm_move_to_workspace.png b/assets/anythingllm_move_to_workspace.png
diff --git a/assets/anythingllm_save_and_embed.png b/assets/anythingllm_save_and_embed.png
diff --git a/assets/anythingllm_upload_file.png b/assets/anythingllm_upload_file.png
diff --git a/assets/anythingllm_upload_interface.png b/assets/anythingllm_upload_interface.png
diff --git a/assets/anythingllm_vectordb.png b/assets/anythingllm_vectordb.png
diff --git a/assets/anythingllm_zilliz_cloud.png b/assets/anythingllm_zilliz_cloud.png
diff --git a/assets/multi-language-analyzers-workflow.png b/assets/multi-language-analyzers-workflow.png
diff --git a/assets/phrase-match-workflow.png b/assets/phrase-match-workflow.png
diff --git a/scripts/config.json b/scripts/config.json
@@ -266,9 +266,9 @@
                         "alt_text": "partition-key-level-multi-tenancy"
                     },
                     {
-                        "token": "AFrdwVT8ChT11ibs9lpcuN7onZc",
+                        "token": "ZDYIwC1HwhTrdlbfOgNcOZ4OnWg",
                         "type": "board",
-                        "alt_text": "phrase-match-workflow"
+                        "alt_text": "multi-language-analyzers-workflow"
                     }
                 ]
             }

diff --git a/site/en/Variables.json b/site/en/Variables.json
@@ -1,16 +1,16 @@
 {
-  "milvus_release_version": "2.5.10",
-  "milvus_release_tag": "2.5.10",
+  "milvus_release_version": "2.5.12",
+  "milvus_release_tag": "2.5.12",
   "milvus_deb_name": "milvus_2.2.0-1_amd64",
   "milvus_rpm_name": "milvus-2.2.0-1.el7.x86_64",
   "milvus_python_sdk_version": "2.4.x",
-  "milvus_python_sdk_real_version": "2.5.6",
+  "milvus_python_sdk_real_version": "2.5.10",
   "milvus_node_sdk_version": "2.4.x",
-  "milvus_node_sdk_real_version": "v2.5.8",
+  "milvus_node_sdk_real_version": "v2.5.9",
   "milvus_go_sdk_version": "2.3.x",
   "milvus_go_sdk_real_version": "2.4.0",
   "milvus_java_sdk_version": "2.4.x",
-  "milvus_java_sdk_real_version": "2.5.7",
+  "milvus_java_sdk_real_version": "2.5.9",
   "milvus_csharp_sdk_version": "2.2.x",
   "milvus_csharp_sdk_real_version": "2.2.14", 
   "milvus_restful_sdk_version": "2.4.x",

diff --git a/site/en/getstarted/milvus_lite.md b/site/en/getstarted/milvus_lite.md
@@ -55,7 +55,7 @@ After running the above code snippet, a database file named **milvus_demo.db** w
 ## Examples
 
 Following is a simple demo showing how to use Milvus Lite for text search. There are more comprehensive [examples](https://github.com/milvus-io/bootcamp/tree/master/bootcamp/tutorials) for using Milvus Lite to build applications
-such as [RAG](https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/quickstart/build_RAG_with_milvus.ipynb), [image search](https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/quickstart/image_search_with_milvus.ipynb), and using Milvus Lite in popular RAG framework such as [LangChain](https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/rag_with_milvus_and_langchain.ipynb) and [LlamaIndex](https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/rag_with_milvus_and_llamaindex.ipynb)!
+such as [RAG](https://github.com/milvus-io/bootcamp/blob/master/tutorials/quickstart/build_RAG_with_milvus.ipynb), [image search](https://github.com/milvus-io/bootcamp/blob/master/tutorials/quickstart/image_search_with_milvus.ipynb), and using Milvus Lite in popular RAG framework such as [LangChain](https://github.com/milvus-io/bootcamp/blob/master/integration/rag_with_milvus_and_langchain.ipynb) and [LlamaIndex](https://github.com/milvus-io/bootcamp/blob/master/integration/rag_with_milvus_and_llamaindex.ipynb)!
 
 ```python
 from pymilvus import MilvusClient

diff --git a/site/en/getstarted/quickstart.md b/site/en/getstarted/quickstart.md
@@ -6,8 +6,8 @@ title: Quickstart
 
 # Quickstart with Milvus Lite
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/quickstart/quickstart.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/quickstart/quickstart.ipynb" target="_blank"><img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/></a>
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/tutorials/quickstart/quickstart.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+<a href="https://github.com/milvus-io/bootcamp/blob/master/tutorials/quickstart/quickstart.ipynb" target="_blank"><img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/></a>
 
 Vectors, the output data format of Neural Network models, can effectively encode information and serve a pivotal role in AI applications such as knowledge base, semantic search, Retrieval Augmented Generation (RAG) and more.
 

diff --git a/site/en/getstarted/run-milvus-k8s/install_cluster-helm.md b/site/en/getstarted/run-milvus-k8s/install_cluster-helm.md
@@ -52,7 +52,7 @@ The Milvus Helm Charts repo at `https://github.com/milvus-io/milvus-helm` has be
 helm repo add zilliztech https://zilliztech.github.io/milvus-helm/
 helm repo update
 # upgrade existing helm release
-helm upgrade my-release zilliztech/milvus
+helm upgrade my-release zilliztech/milvus --reset-then-reuse-values
 ```
 
 The archived repo is still available for the charts up to 4.0.31. For later releases, use the new repo instead.
@@ -231,7 +231,7 @@ Run the following command to upgrade your running Milvus cluster to the latest v
 
 ```shell
 $ helm repo update
-$ helm upgrade my-release zilliztech/milvus
+$ helm upgrade my-release zilliztech/milvus --reset-then-reuse-values
 ```
 
 ## Uninstall Milvus

diff --git a/site/en/integrations/ETL_using_vectorETL.md b/site/en/integrations/ETL_using_vectorETL.md
@@ -4,10 +4,10 @@ summary: In this tutorial, we'll explore how to efficiently load data into Milvu
 title: Efficient Data Loading into Milvus with VectorETL
 ---
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/ETL_using_vectorETL.ipynb" target="_parent">
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/ETL_using_vectorETL.ipynb" target="_parent">
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/ETL_using_vectorETL.ipynb" target="_blank">
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/ETL_using_vectorETL.ipynb" target="_blank">
     <img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/>
 </a>
 

diff --git a/site/en/integrations/NLWeb_with_milvus.md b/site/en/integrations/NLWeb_with_milvus.md
@@ -0,0 +1,83 @@
+---
+id: NLWeb_with_milvus.md
+summary: Learn how to integrate Microsoft NLWeb with Milvus to build powerful natural language interfaces for websites. This tutorial demonstrates how to leverage Milvus' vector database capabilities for efficient semantic search, embedding storage, and context retrieval in NLWeb applications.
+title: Using NLWeb with Milvus
+---
+
+# Using NLWeb with Milvus
+
+[Microsoft's NLWeb](https://github.com/microsoft/NLWeb) is a proposed framework that enables natural language interfaces for websites, using [Schema.org](https://schema.org/), formats like RSS and the emerging MCP protocol.
+
+[Milvus](https://milvus.io/) is supported as a vector database backend within NLWeb for embedding storage and efficient vector similarity search, enabling powerful context retrieval for natural language processing applications.
+
+> This documentation is primarily based on the official [quick start](https://github.com/microsoft/NLWeb/blob/main/HelloWorld.md) documentation. If you find any outdated or inconsistent content, please prioritize the official documentation and feel free to raise an issue for us.
+
+## Usage
+
+NLWeb can be configured to use Milvus as the retrieval engine. Below is a guide on how to set up and use NLWeb with Milvus.
+
+### Installation
+
+Clone the repo and set up your environment:
+
+```bash
+git clone https://github.com/microsoft/NLWeb
+cd NLWeb
+python -m venv .venv
+source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows
+cd code
+pip install -r requirements.txt
+pip install pymilvus  # Add Milvus Python client
+```
+
+### Configuring Milvus
+
+To use **Milvus**, update your configuration.
+
+
+#### Update config files in `code/config`
+
+Open the `config_retrieval.yaml` file and add the Milvus configuration:
+
+```yaml
+preferred_endpoint: milvus_local
+
+endpoints:
+  milvus_local:
+    database_path: "../data/milvus.db"
+    # Set the collection name to use
+    index_name: nlweb_collection
+    # Specify the database type
+    db_type: milvus
+```
+
+### Loading Data
+
+Once configured, load your content using RSS feeds.
+
+From the `code` directory:
+
+```bash
+python -m tools.db_load https://feeds.libsyn.com/121695/rss Behind-the-Tech
+```
+
+This will ingest the content into your Milvus collection, storing both the text data and vector embeddings.
+
+### Running the Server
+
+To start NLWeb, from the `code` directory, run:
+
+```bash
+python app-file.py
+```
+
+You can now query your content via natural language using either the web UI at http://localhost:8000/ or directly through the MCP-compatible REST API.
+
+## Further Reading
+
+* [Milvus Documentation](https://milvus.io/docs)
+* [NLWeb Source](https://github.com/microsoft/NLWeb)
+* Life of a Chat Query
+* Modifying behavior by changing prompts
+* Modifying control flow
+* Modifying the user interface 
diff --git a/site/en/integrations/apify_milvus_rag.md b/site/en/integrations/apify_milvus_rag.md
@@ -7,7 +7,7 @@ title: "Retrieval-Augmented Generation: Crawling Websites with Apify and Saving
 
 # Retrieval-Augmented Generation: Crawling Websites with Apify and Saving Data to Milvus for Question Answering
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/apify_milvus_rag.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/apify_milvus_rag.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
 
 This tutorial explains how to crawl websites using Apify's Website Content Crawler and save the data into Milvus/Zilliz vector database to be later used for question answering.
 

diff --git a/site/en/integrations/build_RAG_from_s3_with_milvus.md b/site/en/integrations/build_RAG_from_s3_with_milvus.md
@@ -4,10 +4,10 @@ summary: This tutorial walks you through the process of building a Retrieval-Aug
 title: "Building a RAG Pipeline: Loading Data from S3 into Milvus"
 ---
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_from_s3_with_milvus.ipynb" target="_parent">
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/build_RAG_from_s3_with_milvus.ipynb" target="_parent">
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_from_s3_with_milvus.ipynb" target="_blank">
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/build_RAG_from_s3_with_milvus.ipynb" target="_blank">
     <img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/>
 </a>
 
@@ -119,7 +119,7 @@ vectorstore = Milvus.from_documents(
     connection_args={
         "uri": "./milvus_demo.db",
     },
-    drop_old=True,  # Drop the old Milvus collection if it exists
+    drop_old=False,  # Drop the old Milvus collection if it exists
 )
 ```
 

diff --git a/site/en/integrations/build_RAG_with_milvus_and_cognee.md b/site/en/integrations/build_RAG_with_milvus_and_cognee.md
@@ -4,10 +4,10 @@ summary: In this tutorial, we will show you how to build a RAG (Retrieval-Augmen
 title: Build RAG with Milvus and Cognee
 ---
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_cognee.ipynb" target="_parent">
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_cognee.ipynb" target="_parent">
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_cognee.ipynb" target="_blank">
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_cognee.ipynb" target="_blank">
     <img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/>
 </a>
 

diff --git a/site/en/integrations/build_RAG_with_milvus_and_crawl4ai.md b/site/en/integrations/build_RAG_with_milvus_and_crawl4ai.md
@@ -6,10 +6,10 @@ title: Building RAG with Milvus and Crawl4AI
 
 # Building RAG with Milvus and Crawl4AI
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_crawl4ai.ipynb" target="_parent">
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_crawl4ai.ipynb" target="_parent">
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_crawl4ai.ipynb" target="_blank">
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_crawl4ai.ipynb" target="_blank">
     <img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/>
 </a>
 

diff --git a/site/en/integrations/build_RAG_with_milvus_and_deepseek.md b/site/en/integrations/build_RAG_with_milvus_and_deepseek.md
@@ -6,8 +6,8 @@ title: Build RAG with Milvus and DeepSeek
 
 # Build RAG with Milvus and DeepSeek
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_deepseek.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_deepseek.ipynb" target="_blank"><img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/></a>
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_deepseek.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_deepseek.ipynb" target="_blank"><img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/></a>
 
 [DeepSeek](https://www.deepseek.com/) enables developers to build and scale AI applications with high-performance language models. It offers efficient inference, flexible APIs, and advanced Mixture-of-Experts (MoE) architectures for robust reasoning and retrieval tasks.  
 

diff --git a/site/en/integrations/build_RAG_with_milvus_and_docling.md b/site/en/integrations/build_RAG_with_milvus_and_docling.md
@@ -4,10 +4,10 @@ summary: In this tutorial, we’ll show you how to build a Retrieval-Augmented G
 title: Build RAG with Milvus and Docling
 ---
 
-<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_docling.ipynb" target="_parent">
+<a href="https://colab.research.google.com/github/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_docling.ipynb" target="_parent">
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-<a href="https://github.com/milvus-io/bootcamp/blob/master/bootcamp/tutorials/integration/build_RAG_with_milvus_and_docling.ipynb" target="_blank">
+<a href="https://github.com/milvus-io/bootcamp/blob/master/integration/build_RAG_with_milvus_and_docling.ipynb" target="_blank">
     <img src="https://img.shields.io/badge/View%20on%20GitHub-555555?style=flat&logo=github&logoColor=white" alt="GitHub Repository"/>
 </a>