{"id":28463812,"url":"https://github.com/bahathabet/rag-openai-agent","last_synced_at":"2026-05-05T09:32:22.951Z","repository":{"id":294887455,"uuid":"988394155","full_name":"bahathabet/rag-openai-agent","owner":"bahathabet","description":"ParmaTIS AI Assistant is a modular, memory-aware chatbot system designed to showcase how modern AI architectures can simulate intelligent internal assistants for organizations. It combines LangChain's Retrieval-Augmented Generation (RAG) capabilities with OpenAI's function-calling Agent SDK, wrapped in a clean Gradio-based UI.","archived":false,"fork":false,"pushed_at":"2025-05-22T14:07:13.000Z","size":20,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-30T17:47:11.326Z","etag":null,"topics":["agentic-ai","agents","claude","gpt","langchain-python","llama","openai-agents-sdk","rag","rag-chatbot"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bahathabet.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-05-22T13:36:02.000Z","updated_at":"2025-06-08T14:43:38.000Z","dependencies_parsed_at":"2025-05-22T15:49:26.123Z","dependency_job_id":null,"html_url":"https://github.com/bahathabet/rag-openai-agent","commit_stats":null,"previous_names":["bahathabet/rag-openai-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bahathabet/rag-openai-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bahathabet%2Frag-openai-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bahathabet%2Frag-openai-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bahathabet%2Frag-openai-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bahathabet%2Frag-openai-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bahathabet","download_url":"https://codeload.github.com/bahathabet/rag-openai-agent/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bahathabet%2Frag-openai-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32643615,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"online","status_checked_at":"2026-05-05T02:00:06.033Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["agentic-ai","agents","claude","gpt","langchain-python","llama","openai-agents-sdk","rag","rag-chatbot"],"created_at":"2025-06-07T05:00:56.718Z","updated_at":"2026-05-05T09:32:22.937Z","avatar_url":"https://github.com/bahathabet.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤖 ParmaTIS AI Assistant\n\nParmaTIS AI Assistant is a modular, memory-aware chatbot system designed to showcase how modern AI architectures can simulate intelligent internal assistants for organizations. It combines LangChain's Retrieval-Augmented Generation (RAG) capabilities with OpenAI's function-calling Agent SDK, wrapped in a clean Gradio-based UI.\n\n---\n## 🧠 What It Does\n\n- ✅ **Convert data** from a knowledge base to vector data store\n- ✅ **Retrieves facts** about ParmaTIS from a vector data store\n- 🧭 **Decides intelligently** when to use retrieval or general reasoning\n- 💬 **Chat UI** built with Gradio for a clean and responsive experience\n- ⚙️ Supports **multiple LLMs** including GPT, LLaMA (localhost), Claude, DeepSeek\n\n---\n\n## 🧠 Project Overview\n\nThis assistant operates on a fictional dataset describing **Parma Tecno Intelligent Services (ParmaTIS)**, an innovative AI company based in Parma, Italy. The assistant answers questions about the company, including:\n\n* Leadership and employees\n* Projects and services\n* Departments and history\n* General knowledge questions\n\n---\n\n## 🏗️ Architecture Summary\n\n* **RAG Agent (LangChain)**: Uses `ConversationalRetrievalChain`, HuggingFace embeddings, and Chroma vector store for searching ParmaTIS documents.\n* **Orchestrator Agent (OpenAI SDK)**: Determines whether to call the RAG agent or respond using general knowledge.\n* **Memory Layers**: Provides 3 memory layers.\n* **Gradio UI**: Interactive frontend that supports real-time communication with history context.\n\n### Memory Layers\n\n* `RAG_memory`: Internal LangChain memory for RAG responses.\n* `chat_memory`: Conversation memory for the orchestrator agent combines also RAG_memory.\n* `history_display`: Maintains full chat history for UI display.\n\n---\n\n## 🚀 Features\n\n* Hybrid architecture (RAG + OpenAI Agents )\n* Multi-agent orchestration with tool calling\n* Company-specific context retrieval\n* Clean, async-friendly Gradio interface\n* Supports multiple models (GPT, Claude, LLaMA, DeepSeek, etc.)\n\n---\n\n## 🔧 Setup Instructions\n\n### 1. Clone the repository\n\n```bash\ngit clone https://github.com/bahathabet/rag-openai-agent.git\ncd rag-openai-agent\n```\n\n### 2. Install dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n### 3. Set up environment variables\n\nCreate a `.env` file with the following:\n\n```env\nOPENAI_API_KEY=your_key_here\nANTHROPIC_API_KEY=...\nDEEPSEEK_API_KEY=...\n...\n```\n\n---\n\n## 💬 Example Prompts\n\n* \"Who is the CEO of ParmaTIS?\"\n* \"What projects are currently ongoing?\"\n* \"Tell me about the AI department.\"\n* \"What is the capital of France?\" *(general knowledge)*\n\n---\n\n## 📦 Built With\n\n* [LangChain](https://www.langchain.com/)\n* [OpenAI Agent SDK](https://platform.openai.com/)\n* [Gradio](https://www.gradio.app/)\n* [ChromaDB](https://www.trychroma.com/)\n* [HuggingFace Embeddings](https://huggingface.co/)\n\n---\n\n## 📌 Notes\n\n* This is a **demo project** using **synthetic data** for ParmaTIS.\n* Extendable with additional tools: calendar, Gmail, PDF parsing, and more.\n* Easily adaptable to real enterprise use cases.\n\n---\n## 🧠 How to Install and Run Ollama Locally\nfrom here:\nhttps://github.com/bahathabet/agentic-search/blob/master/README.md\n---\n\n## 📜 License\n\nMIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbahathabet%2Frag-openai-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbahathabet%2Frag-openai-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbahathabet%2Frag-openai-agent/lists"}