https://github.com/balnarendrasapa/doc-chatbot
Streamlit chatbot app that can answer questions based on a pdf. see the readme for more information
https://github.com/balnarendrasapa/doc-chatbot
all-minilm-l6-v2 chatbot embeddings falcon-7b langchain openai openai-api rag streamlit transformers
Last synced: 4 months ago
JSON representation
Streamlit chatbot app that can answer questions based on a pdf. see the readme for more information
- Host: GitHub
- URL: https://github.com/balnarendrasapa/doc-chatbot
- Owner: balnarendrasapa
- License: mit
- Created: 2023-10-31T15:06:27.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2023-12-24T00:08:35.000Z (almost 2 years ago)
- Last Synced: 2023-12-24T22:47:24.373Z (almost 2 years ago)
- Topics: all-minilm-l6-v2, chatbot, embeddings, falcon-7b, langchain, openai, openai-api, rag, streamlit, transformers
- Language: Python
- Homepage:
- Size: 33.2 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ChatBot with documents
- Provide a pdf to this chatbot and ask a question. It answers the question based on the pdf.
- A javascript restful api is also implemented. go [here](https://github.com/balnarendrasapa/doc-chatbot-backend)
## Running the app - Method 1
- Intialize a virtual environment. run `python -m venv .venv`
- activate the virtual environment
- Windows - run `.venv/Scripts/activate`
- Linux - run `source .venv/bin/activate`
- Install dependencies from requirements.txt. run `pip install -r requirements.txt` (takes about ~6 minutes)
- Run the streamlit app. run `streamlit run app.py`
- Open `localhost:8501` in browser
## Running the app - Method 2
- Install docker from official website and make sure the docker is running
- run `cd other`
- run `docker-compose up` (takes about ~6 minutes)
- Open `localhost:8501` in browser