The project uses a trustworthy language model from Cleanlab (TLM) that prvides a confidence score and reasoning on the generated output. It also uses LlamaParse to parse complex documents into LLM ready clean markdown format.
Before you start, grab your API keys for LlamaParse and TLM
Setup Environment:
- Paste your API keys by creating a
.env - Refer
.env.examplefile
Install Dependencies: Ensure you have Python 3.11 or later installed.
pip install llama-index-llms-cleanlab llama-index llama-index-embeddings-huggingfaceRunning the app:
streamlit run app.pyGet a FREE Data Science eBook 📖 with 150+ essential lessons in Data Science when you subscribe to our newsletter! Stay in the loop with the latest tutorials, insights, and exclusive resources. Subscribe now!
Contributions are welcome! Please fork the repository and submit a pull request with your improvements.
