All in one LLM

This is a LLM based application. It has LLama-v2 LLM used. One can utilize one of the two facilities.

Simple LLM : You can ask questions, and the application will provide relevant answers based on the information it has.
Customzied RAG : RAG is a technique that combines information retrieval with language generation, allowing for more precise and informative responses to user queries. One has to upload pdf files to utilize its power and just query through to have results from those PDFs

git clone <repository_url>

pip install -r requirements.txt

Replace <your_replicate_api_token> in the customizable_llm_rag.py and simple_llm.py files with your actual Replicate API token.

Once you've completed the setup, you can start the application by running:

python app.py

This will start the Flask server, and you can access the application via your web browser at http://localhost:5000.

This project is licensed under the MIT License.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
llm		llm
static		static
templates		templates
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
__init__.py		__init__.py
app.py		app.py
config.py		config.py
requirements.txt		requirements.txt

Provide feedback