LitChat 🔥 
LitChat is an AI powered tool that employs OpenAI's gpt-3.5-turbo-16k model and llamaindex vector database to interact with a literature corpus. It answers questions and writes reviews based on the literature data it interacts with. It comes with a user-friendly chat interface and the ability to configure custom literature datasets. Users can also provide a flexible literature review template that will be populated by LitChat.
Table of Contents
Features
- GPT-3.5-turbo-16k powered: LitChat uses OpenAI's advanced language model for high quality responses.
- llamaindex integration: Utilises a vector database to query literature for the most relevant context.
- Chat Interface: LitChat offers an intuitive chat interface, making it easy for users to interact with the system.
- Customizable Literature Datasets: LitChat can be configured to use custom literature datasets.
- Literature Review Generation: Provides a flexible template system for literature review generation.
Installation
To get LitChat up and running on your local machine, follow these steps:
- Clone the repository:
git clone https://github.com/yourusername/LitChat.git
- Navigate into the cloned directory:
cd LitChat
- Install the dependencies:
pip install -r requirements.txt
- Add environment variables:
You will need to get your own API keys for OpenAI and llamaindex. Once you have them, add them to a .env file:
echo "OPENAI_API_KEY=your_key_here" >> .env
echo "LLAMAINDEX_API_KEY=your_key_here" >> .env
- Run LitChat:
python main.py
Usage
To interact with LitChat, simply input your question or prompt into the chat interface. If you want to generate a literature review, provide the template in the correct format.
For detailed instructions, please refer to the User Guide.
Contributing
Contributions to LitChat are welcomed! If you found a bug, have an idea for a feature, or think you can improve the code, we'd love to know. Please refer to the Contributing Guide for more information.
License
LitChat is licensed under the MIT license.
Acknowledgements
LitChat would not be possible without the amazing work by the OpenAI and llamaindex teams. This project is not affiliated with OpenAI or llamaindex.
Support
For any issues, please contact LitChat Support.
1 maintainer
Metadata
1 maintainer
Release files for litchat 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| litchat-0.0.1.tar.gz | 2.0 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| litchat-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.0 MB
Release files / litchat-0.0.1.tar.gz
| Download URL | litchat-0.0.1.tar.gz |
|---|---|
| Size | 2.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1446ebc10389b40d1cbefb374d007820f6fba263852b8fe3d151153837361ec9
|
|
BLAKE2b-256 checksum How to use checksums |
836298f17ece909ad11bbcd72a13a2b519a1b747e6f4cd468b587108ad09d87d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-httpx/0.24.1
|
Release files / litchat-0.0.1-py3-none-any.whl
| Download URL | litchat-0.0.1-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
234bcc0f6a0e6d1c8632a1fe98b99f337ac0c5ac072d0dd5f6a5748aa8e4ef90
|
|
BLAKE2b-256 checksum How to use checksums |
edb41639174bffa165af97f338c4e8853e29ede203c2f2f3eb7d0dc37dfc9031
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-httpx/0.24.1
|
Security for litchat 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
