Cheney Zhang
Workflows by Cheney Zhang
Paul Graham essay search & chat with Milvus vector database
## Paul Graham Essay Search & Chat with Milvus Vector Database ### How It Works This workflow creates a RAG (Retrieval-Augmented Generation) system using [Milvus](https://milvus.io/) vector database to search Paul Graham essays: 1. **Scrape & Load**: Fetches [Paul Graham essays](https://paulgraham.com/articles.html), extracts text, and stores them as vector embeddings in Milvus 2. **Chat Interface**: Enables semantic search and AI-powered conversations about the essays ### Set Up Steps 1. Set up Milvus server following the [official installation guide](https://milvus.io/docs/install_standalone-docker.md), then create a collection 2. Execute the workflow to scrape essays and load them into your Milvus collection 3. Chat with the AI agent using the Milvus tool to query and discuss essay content
Create a Paul Graham essay Q&A system with OpenAI and Milvus vector database
### Create a Paul Graham Essay Q&A System with OpenAI and Milvus Vector Database #### How It Works This workflow creates a question-answering system based on Paul Graham essays. It has two main steps: 1. **Data Collection & Processing**: - Scrapes [Paul Graham essays](http://www.paulgraham.com/articles.html) - Extracts text content - Loads them into a [Milvus](https://milvus.io/) vector store 2. **Chat Interaction**: - Provides a question-answering interface using the stored vector embeddings - Utilizes [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings) for semantic search #### Set Up Steps 1. Set up a Milvus server following the [official guide](https://milvus.io/docs/install_standalone-docker.md) 2. Create a collection named "my_collection" 3. Run the workflow to scrape and load Paul Graham essays 4. Start chatting with the QA system The workflow handles the entire process from fetching essays, extracting content, generating embeddings via OpenAI, storing vectors in Milvus, and providing retrieval for question answering.
Create a RAG system with Paul Essays, Milvus, and OpenAI for cited answers
### Create a RAG System with Paul Essays, Milvus, and OpenAI for Cited Answers This workflow automates the process of creating a document-based AI retrieval system using [Milvus](https://milvus.io/), an open-source vector database. It consists of two main steps: 1. Data collection/processing 2. Retrieval/response generation The system scrapes [Paul Graham essays](https://paulgraham.com/articles.html), processes them, and loads them into a Milvus vector store. When users ask questions, it retrieves relevant information and generates responses with citations. ### Step 1: Data Collection and Processing 1. Set up a Milvus server using the [official guide](https://milvus.io/docs/install_standalone-docker.md) 2. Create a collection named "my_collection" 3. Execute the workflow to scrape Paul Graham essays: - Fetch essay lists - Extract names - Split content into manageable items - Limit results (if needed) - Fetch texts - Extract content - Load everything into Milvus Vector Store This step uses [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings) for vectorization. ### Step 2: Retrieval and Response Generation When a chat message is received, the system: * Sets chunks to send to the model * Retrieves relevant information from the Milvus Vector Store * Prepares chunks * Answers the query based on those chunks * Composes citations * Generates a comprehensive response This process uses OpenAI embeddings and models to ensure accurate and relevant answers with proper citations. For more information on vector databases and similarity search, visit [Milvus documentation](https://milvus.io/docs).