Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hwchase17/chat-your-data
https://github.com/hwchase17/chat-your-data
Last synced: 7 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/hwchase17/chat-your-data
- Owner: hwchase17
- License: mit
- Created: 2023-02-06T04:51:25.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2023-11-05T13:11:44.000Z (almost 1 year ago)
- Last Synced: 2024-10-04T06:19:48.783Z (about 1 month ago)
- Language: Python
- Size: 23.7 MB
- Stars: 931
- Watchers: 17
- Forks: 272
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome - hwchase17/chat-your-data - (Python)
- jimsghstars - hwchase17/chat-your-data - (Python)
README
# Chat-Your-Data
Create a ChatGPT like experience over your custom docs using [LangChain](https://github.com/langchain-ai/langchain).
See [this blog post](blogpost.md) for a more detailed explanation.
## Step 0: Install requirements
`pip install -r requirements.txt`
## Step 1: Set your open AI Key
```sh
export OPENAI_API_KEY=
```## Step 2: Ingest your data
Run: `python ingest_data.py`
This builds `vectorstore.pkl` using OpenAI Embeddings and FAISS.
## Query data
Custom prompts are used to ground the answers in the state of the union text file.
## Running the Application
By running `python app.py` from the command line you can easily interact with your ChatGPT over your own data.