Search

More Filters

Show More
Add Listing
Go Back

agentic chatbot

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository implements a supervisor-based multi-agent AI chatbot that classifies user queries and routes them to specialized agents for task-specific handling. It is designed to answer questions across several domains including Turkish Resmi Gazete documents, news and general knowledge, travel planning, and user-uploaded documents via retrieval-augmented generation. The system is built in Python using LangChain and LangGraph for orchestration, Google Gemini as the LLM, ChromaDB as the vector store, and Streamlit for the user interface. The project includes data processing and embedding generation scripts, configuration files, and Docker support for local or containerized deployment. Users interact through a Streamlit UI, can upload documents for document QA, request travel plans that can be exported to PDF, and view source context for RAG responses.

Links

App URL
https://github.com/ogulcanakca/agentic-chatbot
Github Repository
https://github.com/ogulcanakca/agentic-chatbot/blob/main/README.md

Categorization

App Details

Features
Supervisor routing that classifies incoming queries into categories and triggers the corresponding agent. Resmi Gazete RAG agent that retrieves and uses Turkish official gazette documents via a ChromaDB vector database. News and general knowledge agent that leverages web search tools and Wikipedia for current events and definitions. Agentic RAG for user uploaded documents supporting PDF, TXT, DOCX and similar formats. Travel planning subsystem implemented as its own LangGraph workflow with subagents for destination research, dates and budget, and a coordinator that can output a PDF plan. Fallback agent for out-of-scope queries. Supporting modules include embedding generation, LLM management, external API tools, data fetchers, and scripts to build and update the vector store. Streamlit UI and Docker compose files are included.
Use Cases
The project bundles multiple retrieval and agent capabilities into a single conversational interface so users can ask domain specific questions, query official gazette content, consult recent news or general knowledge, upload documents for direct question answering, and request structured travel plans. The supervisor architecture routes queries to the most suitable specialist, improving relevance and allowing complex sub-workflows such as travel planning to run independently. RAG using ChromaDB and multilingual embeddings provides citationable context and transparency by exposing the context used for Resmi Gazete answers. Included scripts automate data fetching, processing and embedding generation, and Docker support simplifies deployment. The README notes a current deficiency in persistent agent memory and that API keys must be set in an environment file.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*