From 72d9611aee73448d0476325fb77bed0b117abc2e Mon Sep 17 00:00:00 2001 From: John Lathouwers Date: Thu, 12 Sep 2024 14:32:21 +0000 Subject: [PATCH] Getting Started --- README.md | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 67 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 617dcec..58f29b3 100644 --- a/README.md +++ b/README.md @@ -6,11 +6,75 @@ The **Oracle AI Microservices Sandbox** provides a streamlined environment where developers and data scientists can explore the potential of Generative Artificial Intelligence (GenAI) combined with Retrieval-Augmented Generation (RAG) capabilities. By integrating the **Oracle Database** for Vector Storage, the Sandbox enables users to enhance existing Large Language Models (LLMs) through RAG. This method significantly improves the performance and accuracy of AI models, helping to avoid common issues such as knowledge cutoff and hallucinations. -## Documentation +## Getting Started -⚠️ Thank you for your patience as we work on updating the documentation. Please check back soon for the latest updates. +The **Oracle AI Microservices Sandbox** is available to install in your own environment, which may be an developer's desktop, on-premises data center environment, or a cloud provider. It can be run either on a bare-metal, within a container, or in a Kubernetes Cluster. -For more information, including how to **Get Started** please visit the [documentation](https://oracle-samples.github.io/oaim-sandbox) +For more information, including additional information on **Setup and Configuration** please visit the [documentation](https://oracle-samples.github.io/oaim-sandbox) + +### Prerequisites + +- Oracle Database 23ai incl. Oracle Database 23ai Free +- Python 3.11 (for running Bare-Metal) +- Container Runtime e.g. docker/podman (for running in a Container) +- Access to an Embedding and Chat Model: + - API Keys for Third-Party Chat Model + - On-Premises Chat Model + +#### Bare-Metal Installation + +To run the application on bare-metal; download the [source](https://github.com/oracle-samples/oaim-sandbox) and from the top-level directory: + +1. Create and activate a Python Virtual Environment: + + ```bash + python3.11 -m venv .venv + source .venv/bin/activate + pip3 install --upgrade pip wheel + ``` + +1. Install the Python modules: + + ```bash + pip3 install -r app/requirements.txt + ``` + +1. Start Streamlit: + + ```bash + cd app/src + streamlit run oaim-sandbox.py --server.port 8501 + ``` + +1. Navigate to `http://localhost:8501`. + +1. [Configure](configuration) the Sandbox. + +1. Complete the [Walkthrough](walkthrough/) to get familiar with the Sandbox. + +#### Container Installation + +To run the application in a container; download the [source](https://github.com/oracle-samples/oaim-sandbox) and from the top-level directory: + +1. Build the image. + + From the `app/` directory, build Image: + + ```bash + podman build -t oaim-sandbox . + ``` + +1. Start the Container: + + ```bash + podman run -p 8501:8501 -it --rm oaim-sandbox + ``` + +1. Navigate to `http://localhost:8501`. + +1. [Configure](configuration) the Sandbox. + +1. Complete the [Walkthrough](walkthrough/) to get familiar with the Sandbox. ## Contributing