{"id":13780941,"url":"https://github.com/intelligentnode/IntelliServer","last_synced_at":"2025-05-11T14:34:20.312Z","repository":{"id":192254913,"uuid":"683831957","full_name":"intelligentnode/IntelliServer","owner":"intelligentnode","description":"AI models as scalable microservices, enabling evaluation of LLMs and offering end-to-end functions such as chatbot, semantic search, image generation and beyond.","archived":false,"fork":false,"pushed_at":"2025-03-10T08:04:42.000Z","size":3026,"stargazers_count":27,"open_issues_count":2,"forks_count":3,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-30T02:38:30.629Z","etag":null,"topics":["ai","chatbot","claude","cohere","docker","gpt4","image-generation","llama3","llm","microservice","nodejs","openai","replicate","semantic-search","stable-diffusion"],"latest_commit_sha":null,"homepage":"https://intelli-server.vercel.app","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/intelligentnode.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-08-27T20:48:56.000Z","updated_at":"2025-03-09T02:41:19.000Z","dependencies_parsed_at":"2024-01-18T09:56:45.745Z","dependency_job_id":"2c7b0c27-5360-4f53-8cbd-ffcb560ef018","html_url":"https://github.com/intelligentnode/IntelliServer","commit_stats":null,"previous_names":["intelligentnode/intelliserver"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligentnode%2FIntelliServer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligentnode%2FIntelliServer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligentnode%2FIntelliServer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligentnode%2FIntelliServer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intelligentnode","download_url":"https://codeload.github.com/intelligentnode/IntelliServer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253501665,"owners_count":21918317,"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":["ai","chatbot","claude","cohere","docker","gpt4","image-generation","llama3","llm","microservice","nodejs","openai","replicate","semantic-search","stable-diffusion"],"created_at":"2024-08-03T18:01:21.348Z","updated_at":"2025-05-11T14:34:20.292Z","avatar_url":"https://github.com/intelligentnode.png","language":"JavaScript","funding_links":[],"categories":["LLM Deployment","LLM Applications"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"images/server-header.png\" width=\"600em\"\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://discord.gg/VYgCh2p3Ww\" alt=\"discord\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Discord-Community-light?style=flat-square\" /\u003e\n\u003c/a\u003e\n\n\n\u003ca href=\"https://hub.docker.com/r/intellinode/intelliserver\" alt=\"docker image\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/docker/pulls/intellinode/intelliserver?style=flat-square\" /\u003e\n\u003c/a\u003e\n\n\n\u003ca href=\"https://github.com/Hannibal046/Awesome-LLM\" target=\"_blank\"\u003e\n     \u003cimg src=\"https://awesome.re/mentioned-badge.svg\" alt=\"Mentioned in Awesome LLM\"\u003e\n\u003c/a\u003e\n\n\u003c/p\u003e\n\n# IntelliServer\nAI models as private microservice - ChatGPT, Cohere, Llama, Stability, Hugging inference and more.\n\nIntelliserver is a microservice providing unified access to multiple AI models, allowing you to easily integrate cutting-edge AI into your project.\n\n[![Run in Postman](https://run.pstmn.io/button.svg)](https://god.gw.postman.com/run-collection/29770592-caa8dae9-7eea-46a6-b64c-ada5c07be9f4?action=collection%2Ffork\u0026source=rip_markdown\u0026collection-url=entityId%3D29770592-caa8dae9-7eea-46a6-b64c-ada5c07be9f4%26entityType%3Dcollection%26workspaceId%3D0b88b327-c88a-4050-a084-cd4486f86b68#?env%5Bintelliserver-showcase%5D=W3sia2V5IjoidXJsIiwidmFsdWUiOiIiLCJlbmFibGVkIjp0cnVlLCJ0eXBlIjoiZGVmYXVsdCIsInNlc3Npb25WYWx1ZSI6IiIsInNlc3Npb25JbmRleCI6MH1d)\n\n## Core Services\n\n- **Chatbot**: chatbot functionalities using popular models like ChatGPT, Llama, and AWS Sagemaker models.\n- **LLM Evaluation**: evaluate different AI models to choose the optimal solution for your requirements.\n- **Semantic Search**: leverage context-aware semantic search capabilities across text documents.\n- **Image Generation**: generate quality images based on described contexts using diffusion image models.\n- **Chat Context**: get the relevant messages for the chatbot conversation.\n- **Parsers**: convert documents to text such as PDF and word.\n- **OCR**: extract text from images using AWS or Google vision.\n\n## Installation\n\n### Repository Setup\nInstructions to run the microservice from GitHub repo:\n\n**npm**\n```bash\ncd intelliserver\nnpm install\nnpm start\n```\n\n**docker**\n\n```bash\n# docker run\ndocker build -t intelliserver:latest .\ndocker run -p 80:80 intelliserver:latest\n\n# or docker compose run\ndocker-compose up\n```\n\n### Release (Docker Hub)\nTo pull the release image from docker hub:\n```bash\ndocker pull intellinode/intelliserver:latest\n```\nRun IntelliServer\n```bash\n# run with custom keys\nAPI_KEY=\u003cYOUR_API_KEY\u003e\nADMIN_KEY=\u003cYOUR_ADMIN_KEY\u003e\ndocker run -p 80:80 -e API_KEY=$API_KEY -e ADMIN_KEY=$ADMIN_KEY intellinode/intelliserver:latest\n\n# or run with the default key - only for testing\ndocker run -p 80:80 intellinode/intelliserver:latest\n```\n\n-----\n**Mac M-series processors**\n\nFor Mac M-series users, pull the arm64 version:\n```bash\ndocker pull intellinode/intelliserver:arm64\n```\n\n## API and Admin Keys\n- **API_KEY**: Set this key to protect your server endpoints. Clients must include this key in their requests.\n- **ADMIN_KEY**: Required for administrative operations, such as changing the API key.\n\nSet these keys via environment variables when starting the container, or define them in a `.env` file in the repo root:\n```python\nAPI_KEY=your-api-key\nADMIN_KEY=your-admin-key\n```\n\n## Testing\n\nTo test Intelliserver, you can find the endpoints collection in the [postman repository](https://github.com/intelligentnode/IntelliServer/tree/main/postman).\n\nOr access the swagger interactive docs: `localhost/api-docs/`\n\nTo customize the default keys and settings, create a `.env` file inside intelliserver cloned repo with the following values:\n```\n# api keys\nAPI_KEY=\u003ckey\u003e\nADMIN_KEY=\u003ckey\u003e\n\n# models keys - if not added, the user should send the key in the API call\nOPENAI_API_KEY=\u003ckey\u003e\nAZURE_OPENAI_API_KEY=\u003ckey\u003e\nCOHERE_API_KEY=\u003ckey\u003e\nGOOGLE_API_KEY=\u003ckey\u003e\nSTABILITY_API_KEY=\u003ckey\u003e\nHUGGING_API_KEY=\u003ckey\u003e\nREPLICATE_API_KEY=\u003ckey\u003e\n```\n\n## Key Benefits\n\n- **Unified Access:** Intelliserver provides a unified API for accessing different AI models. This allows for seamless switching between models using the same endpoint format.\n\n- **Scalability:** Intelliserver utilizes microservices architecture, allowing the AI middleware to run as an independent service with dedicated resources.\n\n- **Model Evaluation:** Intelliserver's design allows for seamless evaluation and comparison of different AI models using unified service. This facilitates data-driven decision when selecting the optimal model for specific use cases.\n\n## License\nIntelliserver is released under the [MIT License](https://github.com/intelligentnode/IntelliServer/blob/main/LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintelligentnode%2FIntelliServer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintelligentnode%2FIntelliServer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintelligentnode%2FIntelliServer/lists"}