Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ccomkhj/agentic-rag-chatbot-with-streamlit

implementing an agentic approach to Retrieval Augmented Generation (RAG) using Gemini AI and Streamlit

https://github.com/ccomkhj/agentic-rag-chatbot-with-streamlit

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

implementing an agentic approach to Retrieval Augmented Generation (RAG) using Gemini AI and Streamlit

Basic Info
  • Host: GitHub
  • Owner: ccomkhj
  • Language: Python
  • Default Branch: main
  • Size: 185 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme

README.md

Agentic RAG Chatbot with Gemini AI and Streamlit

Front Page Screenshot

A demo showcasing an agentic approach to Retrieval Augmented Generation (RAG) with Gemini AI and Streamlit.

Features

  • Interactive chat UI with Streamlit
  • Gemini AI integration (API + LangChain)
  • Document processing & semantic retrieval
  • Multi-format support (pdf, docx, txt, csv, xlsx, html, md)
  • Session state management
  • Temperature control

Quick Setup

bash git clone https://github.com/ccomkhj/llm-chatbot-demo.git cd llm-chatbot-demo python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt

Add API Key

  1. Get a Gemini API key from Google AI Studio
  2. Create credentials.yaml in the project root:

yaml API_KEY: "your_gemini_api_key_here" AGENT_MODEL_NAME: "gemini-2.5-flash-preview-04-17" # or another Gemini model

Running the App

bash streamlit run main.py

  1. Upload Documents (sidebar): Add files for the chatbot to reference
  2. Process the documents to enable RAG capabilities
  3. Chat with the model using the input at the bottom

Agentic RAG Architecture

Core Components:

  • Document Processor: Handles file ingestion and vectorization
  • LLM Interface: Connects to Gemini AI via direct API or LangChain
  • Chat Interface: Provides the conversational UI

Key Capabilities:

  • Document understanding and semantic retrieval
  • Context integration with conversation history
  • Automatic switching between RAG and direct LLM access
  • Temperature-controlled response generation

Extension Possibilities:

  • External tool integration
  • Multi-step reasoning chains
  • Self-reflection mechanisms

Owner

  • Name: Huijo
  • Login: ccomkhj
  • Kind: user
  • Location: Germany
  • Company: @hexafarms

Self Learner

GitHub Events

Total
  • Push event: 1
Last Year
  • Push event: 1

Dependencies

requirements.txt pypi
  • bs4 >=0.0.1
  • faiss-cpu >=1.7.4
  • google-cloud-aiplatform >=1.55.0
  • langchain >=0.1.0
  • langchain-community >=0.0.13
  • langchain-google-vertexai >=0.1.0
  • openpyxl >=3.1.2
  • pdf2image >=1.16.3
  • pydantic >=2.0.0
  • pylint >=3.0.0
  • pytesseract >=0.3.10
  • python-docx >=1.0.1
  • python-dotenv >=1.0.0
  • python-magic >=0.4.27
  • streamlit >=1.29.0
  • unstructured >=0.11.0