https://github.com/dataprofessor/langchain-quickstart

Build your first LLM powered app with Langchain and Streamlit.
https://github.com/dataprofessor/langchain-quickstart

langchain langchain-python large-language-models llm streamlit

Last synced: 1 day ago
JSON representation

Build your first LLM powered app with Langchain and Streamlit.

• Host: GitHub
• URL: https://github.com/dataprofessor/langchain-quickstart
• Owner: dataprofessor
• Created: 2023-05-20T06:06:31.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2024-06-24T05:16:07.000Z (5 months ago)
• Last Synced: 2024-08-13T07:07:27.410Z (3 months ago)
• Topics: langchain, langchain-python, large-language-models, llm, streamlit
• Language: Python
• Homepage: https://langchain-quickstart.streamlit.app/
• Size: 228 KB
• Stars: 62
• Watchers: 2
• Forks: 133
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• jimsghstars - dataprofessor/langchain-quickstart - Build your first LLM powered app with Langchain and Streamlit. (Python)

README

        
# 🦜🔗 Langchain - Quickstart App

Build your first LLM powered app with Langchain and Streamlit.

## Overview of the App



- Accepts input text (*e.g.* `What are the three key pieces of advice for learning how to code?`) as prompt input using Streamlit's `st.text_area()`, then assign this to the `text` variable.

- LLM model is called via `llm()` and it is applied on the prompt input `text` to generate a response via `llm(text)`

## Demo App

[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://langchain-quickstart.streamlit.app/)

## Get an OpenAI API key

You can get your own OpenAI API key by following the following instructions:

1. Go to https://platform.openai.com/account/api-keys.

2. Click on the `+ Create new secret key` button.

3. Next, enter an identifier name (optional) and click on the `Create secret key` button.

## Try out the app

Once the app is loaded, go ahead and enter your OpenAI API key and type a question in the text box and wait for a generated response.