{"id":23838073,"url":"https://github.com/hasanghaffari93/llm-apps","last_synced_at":"2026-05-02T18:37:28.787Z","repository":{"id":269607279,"uuid":"907977647","full_name":"hasanghaffari93/llm-apps","owner":"hasanghaffari93","description":"A Streamlit-based chatbot application that leverages LangChain framework to interact with multiple LLM providers.","archived":false,"fork":false,"pushed_at":"2025-02-08T16:33:45.000Z","size":91,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-08T17:26:12.253Z","etag":null,"topics":["chatbot","gpt-4","gpt-4o-mini","langchain","langraph","large-language-models","llama3","openai","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"https://llm-app.streamlit.app","language":"Python","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/hasanghaffari93.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}},"created_at":"2024-12-24T18:58:25.000Z","updated_at":"2025-02-08T16:33:48.000Z","dependencies_parsed_at":"2024-12-30T20:21:53.282Z","dependency_job_id":"f1ad8839-cb6d-4817-8973-95cfbb2a37e7","html_url":"https://github.com/hasanghaffari93/llm-apps","commit_stats":null,"previous_names":["hasanghaffari93/chatbot-app","hasanghaffari93/llm-app-collection","hasanghaffari93/llm-apps"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanghaffari93%2Fllm-apps","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanghaffari93%2Fllm-apps/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanghaffari93%2Fllm-apps/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanghaffari93%2Fllm-apps/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hasanghaffari93","download_url":"https://codeload.github.com/hasanghaffari93/llm-apps/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240122611,"owners_count":19751145,"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":["chatbot","gpt-4","gpt-4o-mini","langchain","langraph","large-language-models","llama3","openai","retrieval-augmented-generation"],"created_at":"2025-01-02T16:26:38.348Z","updated_at":"2026-05-02T18:37:28.781Z","avatar_url":"https://github.com/hasanghaffari93.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM Apps\n\nThis project includes applications leveraging Large Language Models (LLMs) for various tasks such as chatbots, document summarization, and retrieval-augmented generation (RAG). The applications are built using LangChain and LangGraph for the backend processing and Streamlit for the UI.\n\n\n## Features\n### Chatbots\n- Support for multiple LLM providers (e.g. `OpenAI` and `Groq`)\n- Message history with auto-trimming\n- Audio capabilities:\n  - Voice input using OpenAI's `Whisper` for speech-to-text\n  - Text-to-speech responses using OpenAI's `TTS`\n  - Automatic audio playback of responses\n\n### Document Summarization\n- Two summarization techniques:\n  - `Stuff`: For shorter documents that fit within context window\n  - `Map-Reduce`: For longer documents that exceed context limits\n- PDF document support\n\n### Retrieval Augmented Generation (RAG)\n- Agentic RAG: QA with Memory\n  - **Tool-calling**: Tool calling enables the model to decide if a retrieval step is needed. If required, user queries are rewritten based on the chat history (contextualization). If not, the model responds directly without a retrieval step (e.g., in response to a generic greeting).\n  - `FAISS` vector store for efficient similarity search\n  - `OpenAI` embeddings integration\n\n### Technical Features\n- Built with `Streamlit` for interactive UI\n- `LangChain` and `LangGraph` integration for LLM operations\n- Modular architecture with separate pages\n- Simple Authentication via API key or password\n\n\n## Demo App \n\n[![Streamlit](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://llm-app.streamlit.app/)\n\n## Setup\n\n1. Clone the repository:\n\n```sh\ngit clone https://github.com/yourusername/llm-app-collection.git\ncd llm-app-suite\n```\n\n2. Configure API keys in [`.streamlit/secrets.toml`](.streamlit/secrets.toml) file:\n\n```toml\nOPENAI_API_KEY_DEV = \"your-openai-key\"\nGROQ_API_KEY_DEV = \"your-groq-key\"\nPASSWORDS = [\"your-password\"]\n```\n\n3. Create and activate virtual environment:\n\nUbuntu/Linux Terminal\n```sh\npip install virtualenv\nvirtualenv .venv\nsource .venv/bin/activate\n```\n\nWindows PowerShell:\n```sh\npip install virtualenv\nvirtualenv venv\nvenv\\Scripts\\activate.ps1\n```\n\n4. Install dependencies:\n```sh\npip install -r requirements.txt\n```\n\n5. Run the application:\n\n```sh\nstreamlit run app.py\n```\n\n## Resources\n\n- Two ways of text summarization, Stuff and Map-reduce ([link](https://python.langchain.com/docs/tutorials/summarization/))\n- Retrieval Augmented Generation (RAG) using LangChain ([link](https://python.langchain.com/docs/tutorials/qa_chat_history/))","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhasanghaffari93%2Fllm-apps","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhasanghaffari93%2Fllm-apps","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhasanghaffari93%2Fllm-apps/lists"}