Update README

README.md

@@ -2,6 +2,20 @@
 
 This repository contains a Docker Compose setup for running a local AI and automation environment with multiple services.
 
+## Overview
+
+The Local LLM Stack is a comprehensive, Docker-based environment designed to provide a complete ecosystem for working with Large Language Models (LLMs) locally. It integrates several powerful open-source tools that work together to provide document management, workflow automation, vector search, and LLM inference capabilities.
+
+This stack is designed with flexibility in mind, allowing you to use either a locally installed Ollama instance or run Ollama as a containerized service. All components are configured to work together out of the box, with sensible defaults that can be customized to suit your specific needs.
+
+Key features of this stack include:
+- Document processing and management with AnythingLLM
+- AI workflow automation with Flowise
+- Direct LLM interaction through Open WebUI
+- Workflow automation with n8n
+- Vector storage with Qdrant
+- Seamless integration with Ollama for LLM inference
+
 ## Services
 
 ### Flowise
@@ -37,6 +51,13 @@ This repository contains a Docker Compose setup for running a local AI and autom
 - Database used by n8n
 - Port: 5432
 
+### Ollama (Optional)
+- LLM inference engine
+- Port: 11434
+- API endpoint: http://localhost:11434
+- Can be run natively (default) or as a containerized service
+- Used by AnythingLLM and can be used by Flowise
+
 ## Prerequisites
 
 - Docker and Docker Compose installed on your system
@@ -47,8 +68,8 @@ This repository contains a Docker Compose setup for running a local AI and autom
 
 1. Clone this repository:
    ```
-   git clone https://github.com/yourusername/docker-local-ai-llm.git
-   cd docker-local-ai-llm
+   git clone https://github.com/yourusername/local-llm-stack.git
+   cd local-llm-stack
    ```
 
 2. Create a `.env` file based on the provided `.env.sample` file:
@@ -60,7 +81,10 @@ This repository contains a Docker Compose setup for running a local AI and autom
 
 4. Ollama Configuration:
    - By default, the setup is configured to use a locally installed Ollama instance
-   - If you want to run Ollama as a container, uncomment the Ollama service in docker-compose.yml and update the OLLAMA_BASE_PATH and EMBEDDING_BASE_PATH in .env to use http://ollama:11434
+   - If you want to run Ollama as a container, uncomment the following in docker-compose.yml:
+     - The `ollama_storage` volume in the volumes section
+     - The entire `ollama` service definition
+     - Update the OLLAMA_BASE_PATH and EMBEDDING_BASE_PATH in .env to use http://ollama:11434
 
 5. Start the services:
    ```
@@ -101,6 +125,20 @@ AnythingLLM is configured to use:
 - Ollama for LLM capabilities and embeddings
 - The configuration can be adjusted in the .env file
 
+### Ollama Configuration
+
+Ollama can be configured in two ways:
+1. **Native Installation (Default)**: 
+   - Install Ollama directly on your host machine
+   - The services are configured to access Ollama via host.docker.internal
+   - Requires Ollama to be running on your host (`ollama serve`)
+
+2. **Containerized Installation**:
+   - Uncomment the Ollama service in docker-compose.yml
+   - Uncomment the ollama_storage volume
+   - Update the OLLAMA_BASE_PATH and EMBEDDING_BASE_PATH in .env to http://ollama:11434
+   - No need to run Ollama separately on your host
+
 ## Troubleshooting
 
 If you encounter any issues:
@@ -121,6 +159,3 @@ If you encounter any issues:
 
 5. If you're having connection issues between containers and your host machine, check that the `extra_hosts` configuration is correctly set in docker-compose.yml.
 
-## License
-
-[Specify your license here]