RAG use-case implementation using Llamaindex
Updated Colab notebook with Llama3
Supercharge your RAG pipeline with the following:
- Framework -> Llamaindex
- Loader -> SimpleDirectoryLoader
- Chunking -> Semantic Chunking
- Embeddings -> Gemini Embeddings
- Vector DB -> Llamaindex VectorStoreIndex
- LLM -> Groq Mistral
- Reranking -> Cohere Rerank Model
For index creation follow notebook file rag.ipynb
To run application:
pip install -r requirements.txt
chainlit run app.py