Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dataprofessor/langchain-blog-outline-generator
Blog outline generator app built using Langchain and Streamlit.
https://github.com/dataprofessor/langchain-blog-outline-generator
langchain langchain-python large-language-models llm streamlit
Last synced: 3 months ago
JSON representation
Blog outline generator app built using Langchain and Streamlit.
- Host: GitHub
- URL: https://github.com/dataprofessor/langchain-blog-outline-generator
- Owner: dataprofessor
- Created: 2023-05-17T12:19:58.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-06-24T05:16:52.000Z (7 months ago)
- Last Synced: 2024-06-24T06:29:13.447Z (7 months ago)
- Topics: langchain, langchain-python, large-language-models, llm, streamlit
- Language: Python
- Homepage: https://langchain-outline-generator.streamlit.app/
- Size: 309 KB
- Stars: 12
- Watchers: 2
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# π¦π Langchain - Blog Outline Generator App
Blog Outline Generator App built using Langchain and Streamlit.
## Overview of the App
1. Accept user provided prompt as an input using Streamlit's `st.text_input()`
2. Create the final prompt by usingΒ `PromptTemplate()` to combine the **"topic"** and the **prompt instructions**.
3. The above prompt (from step 3) serves as an input to the OpenAI LLM model for generating a response (the blog outline)## Demo App
[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://langchain-outline-generator.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.