{"id":19584719,"url":"https://github.com/oracle-samples/ai-optimizer","last_synced_at":"2025-04-27T11:32:17.460Z","repository":{"id":256813702,"uuid":"853409632","full_name":"oracle-samples/oaim-sandbox","owner":"oracle-samples","description":"GenAI/RAG Sandbox for experimentation using Oracle Database AI Vector Search","archived":false,"fork":false,"pushed_at":"2024-10-18T09:56:15.000Z","size":7007,"stargazers_count":9,"open_issues_count":13,"forks_count":0,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-10-19T14:42:33.135Z","etag":null,"topics":["generative-ai","oracle-database","retreival-augmented-generation"],"latest_commit_sha":null,"homepage":"https://developer.oracle.com/microservices ","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"upl-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/oracle-samples.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-06T15:45:33.000Z","updated_at":"2024-10-17T17:04:39.000Z","dependencies_parsed_at":"2024-10-22T13:13:48.804Z","dependency_job_id":null,"html_url":"https://github.com/oracle-samples/oaim-sandbox","commit_stats":null,"previous_names":["oracle-samples/oaim-sandbox"],"tags_count":0,"template":false,"template_full_name":"oracle/template-repo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle-samples%2Foaim-sandbox","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle-samples%2Foaim-sandbox/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle-samples%2Foaim-sandbox/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle-samples%2Foaim-sandbox/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oracle-samples","download_url":"https://codeload.github.com/oracle-samples/oaim-sandbox/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224069554,"owners_count":17250454,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["generative-ai","oracle-database","retreival-augmented-generation"],"created_at":"2024-11-11T07:49:28.317Z","updated_at":"2025-04-27T11:32:17.453Z","avatar_url":"https://github.com/oracle-samples.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Oracle AI Optimizer and Toolkit\n\n\u003c!-- spell-checker:ignore streamlit, venv, setuptools --\u003e\n\n🚧 The **AI Optimizer** is currently in *Beta*\n\n## Description\n\nThe **Oracle AI Optimizer and Toolkit** (the **AI Optimizer**) 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 **Oracle Database 23ai** AI Vector Search, the Sandbox enables users to enhance existing Large Language Models (LLMs) through RAG.\n\n## AI Optimizer Features\n\n- [Configuring Embedding and Chat Models](https://oracle-samples.github.io/ai-optimizer/client/configuration/model_config)\n- [Splitting and Embedding Documentation](https://oracle-samples.github.io/ai-optimizer/client/tools/split_embed)\n- [Modifying System Prompts (Prompt Engineering)](https://oracle-samples.github.io/ai-optimizer/client/tools/prompt_eng)\n- [Experimenting with **LLM** Parameters](https://oracle-samples.github.io/ai-optimizer/client/chatbot)\n- [Testbed for auto-generated or existing Q\u0026A datasets](https://oracle-samples.github.io/ai-optimizer/client/testbed)\n\n## Getting Started\n\nThe **AI Optimizer** is available to install in your own environment, which may be a developer's desktop, on-premises data center environment, or a cloud provider. It can be run either on bare-metal, within a container, or in a Kubernetes Cluster.\n\nFor more information, including more details on **Setup and Configuration** please visit the [documentation](https://oracle-samples.github.io/ai-optimizer).\n\n### Prerequisites\n\n- Oracle Database 23ai incl. Oracle Database 23ai Free\n- Python 3.11 (for running Bare-Metal)\n- Container Runtime e.g. docker/podman (for running in a Container)\n- Access to an Embedding and Chat Model:\n  - API Keys for Third-Party Models\n  - On-Premises Models\u003csub\u003e\\*\u003c/sub\u003e\n\n\u003csub\u003e\\*Oracle recommends running On-Premises Models on hardware with GPUs. For more information, please review the [Infrastructure](https://oracle-samples.github.io/ai-optimizer/infrastructure) documentation.\u003c/sub\u003e\n\n#### Bare-Metal Installation\n\nTo run the application on bare-metal; download the [source](https://github.com/oracle-samples/ai-optimizer) and from `src/`:\n\n1. Create and activate a Python Virtual Environment:\n\n   ```bash\n   cd src/\n   python3.11 -m venv .venv --copies\n   source .venv/bin/activate\n   pip3.11 install --upgrade pip wheel setuptools\n   ```\n\n1. Install the Python modules:\n\n   ```bash\n   pip3.11 install -e \".[all]\"\n   source .venv/bin/activate\n   ```\n\n1. Start Streamlit:\n\n   ```bash\n   streamlit run launch_client.py --server.port 8501\n   ```\n\n1. Navigate to `http://localhost:8501`.\n\n1. [Configure](https://oracle-samples.github.io/ai-optimizer/client/configuration) the **AI Optimizer**.\n\n#### Container Installation\n\nTo run the application in a container; download the [source](https://github.com/oracle-samples/ai-optimizer):\n\n1. Build the all-in-one image.\n\n   From the `src/` directory, build image:\n\n   ```bash\n   cd src/\n   podman build -t ai-optimizer-aio .\n   ```\n\n1. Start the Container:\n\n   ```bash\n   podman run -p 8501:8501 -it --rm ai-optimizer-aio\n   ```\n\n1. Navigate to `http://localhost:8501`.\n\n1. [Configure](https://oracle-samples.github.io/ai-optimizer/client/configuration/index.html) the **AI Optimizer**.\n\n#### Got OCI?\nThe **AI Optimizer** can be deployed with an Oracle Autonomous Database 23ai using infrastructure as code.  Deploy the **AI Optimizer** in Oracle Cloud Infrastructure using OCI Resource Manager:\n\n[![Deploy to Oracle Cloud][magic_button]][magic_arch_stack]\n\n## Contributing\n\nThis project welcomes contributions from the community. Before submitting a pull request, please [review our contribution guide](./CONTRIBUTING.md).\n\n## Security\n\nPlease consult the [security guide](./SECURITY.md) for our responsible security vulnerability disclosure process.\n\n## License\n\nCopyright (c) 2024 Oracle and/or its affiliates.\nReleased under the Universal Permissive License v1.0 as shown at [https://oss.oracle.com/licenses/upl/](https://oss.oracle.com/licenses/upl/)\n\nSee [LICENSE](./LICENSE.txt) for more details.\n\n\n[magic_button]: https://oci-resourcemanager-plugin.plugins.oci.oraclecloud.com/latest/deploy-to-oracle-cloud.svg\n[magic_arch_stack]: https://cloud.oracle.com/resourcemanager/stacks/create?zipUrl=https://github.com/oracle-samples/ai-optimizer/releases/download/v0.0.1/ai-optimizer-stack.zip","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foracle-samples%2Fai-optimizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foracle-samples%2Fai-optimizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foracle-samples%2Fai-optimizer/lists"}