https://github.com/jospin6/askflow
AskFlow is an intelligent chatbot application that leverages advanced AI decision-making to provide accurate responses by either answering directly from its knowledge or performing real-time internet searches using Tavily Search API.
https://github.com/jospin6/askflow
fastapi langchain langgraph streamlit
Last synced: about 2 months ago
JSON representation
AskFlow is an intelligent chatbot application that leverages advanced AI decision-making to provide accurate responses by either answering directly from its knowledge or performing real-time internet searches using Tavily Search API.
- Host: GitHub
- URL: https://github.com/jospin6/askflow
- Owner: Jospin6
- Created: 2025-08-06T22:53:21.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-08-25T08:37:27.000Z (10 months ago)
- Last Synced: 2025-08-25T09:51:42.480Z (10 months ago)
- Topics: fastapi, langchain, langgraph, streamlit
- Language: Python
- Homepage: https://askflow.streamlit.app/
- Size: 123 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# AskFlow - Intelligent Internet-Connected Chatbot
[](https://www.python.org/downloads/)
[](https://www.langchain.com/)
[](https://langchain-ai.github.io/langgraph/)
[](https://fastapi.tiangolo.com/)
[](https://streamlit.io/)
[](https://tavily.com/)
[](https://opensource.org/licenses/MIT)
[](https://render.com/)
[](https://streamlit.io/cloud)
AskFlow is an intelligent chatbot application that leverages advanced AI decision-making to provide accurate responses by either answering directly from its knowledge or performing real-time internet searches using Tavily Search API.

## Features
- **Intelligent Decision Making**: LangGraph-powered agent that decides whether to answer directly or search the web
- **Real-time Internet Access**: Integrated Tavily Search API for up-to-date information
- **Conversational Memory**: Maintains context throughout conversations
- **RESTful API**: FastAPI backend with comprehensive endpoints
- **Modern Web Interface**: Streamlit-based responsive UI
- **Cloud Deployment**: Fully deployed and accessible online
## Live Demos
- **Web Interface**: [AskFlow Streamlit App](https://askflow.streamlit.app/)
## Tech Stack
- **AI Framework**: LangChain, LangGraph
- **Search API**: Tavily Search
- **Backend**: FastAPI, Uvicorn, Pydantic
- **Frontend**: Streamlit
- **LLM Integration**: OpenAI GPT (or your preferred LLM)
- **Deployment**: Render, Streamlit Cloud
- **Environment Management**: Poetry/Pipenv
## How It Works
### Decision Process Flow
1. **User Input**: User submits a question through the interface
2. **Agent Decision**: LangGraph agent analyzes whether to answer directly or search the web
3. **Execution**: Direct answer or web search via Tavily API
4. **Response Delivery**: Formatted response returned to user
## Getting Started
### Prerequisites
- Python 3.10 or higher
- Tavily Search API key
- OpenAI API key (or alternative LLM provider)
- Poetry or Pipenv
### Installation
1. **Clone the repository**
```bash
git clone https://github.com/Jospin6/askflow.git
cd askflow
```
### Run the application locally
```bash
# Start API server
cd api && uvicorn main:app --reload
# Start UI (in separate terminal)
cd ui && streamlit run app.py
```
### 👨💻 Author
Built with ❤️ by Jospin Ndagano