ai-rag-pdf

Architechture

Demo

Tools Used

• PyPDFLoader - Lanchain library for loading pdf data
• FAISS - Vector Storage and simliarity search through Langchain
• Titan Text v1 - Creating text embeddings
• Bedrock - LangChain module for integrating with AWS Bedrock for LLM interactions.
• Streamlit - Framework for building interactive web applications (particularly in data science)
• Docker - Containerization platform used for running the application locally.
• Claude-v2 - Large language model used

Imporant to note

• Chunking size mattered a lot here, apparenlty 300-500 is recommended for resumes to give it more context

Local Testing

To test the application locally, follow these steps:

1. Clone the repo:

git clone https://github.com/mfkimbell/ai-rag-hr.git

2. Pull the Docker Image:

   docker pull mfkimbell/ai-rag-doc:latest

3. Run the Docker Container:

   docker run --env-file .env -p 8501:8501 mfkimbell/ai-rag-doc:latest

   Ensure that you have a .env file with the necessary environment variables.

AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY AWS_DEFAULT_REGION

3. Access Webapp

   http://0.0.0.0:8501/ or http://localhost:8501/