added langChain RAG notebook that uses NIM + embedding model from HF + FAISS VDB (#186)

* added notebook that showcases copilot application suing NIM, embedding model and FAISS VDB. All these tools are integrated using Langchain plugins. The notebook also has a Gradio-based UI to interact with the application
---------

Co-authored-by: Mitesh Patel <[email protected]>
Co-authored-by: Jay Rodge <[email protected]>

Author: patelmiteshn

community/llm_video_series/data/.DS_Store

@@ -11,7 +11,7 @@ The system utilizes LlamaIndex for efficient indexing and retrieval of informati
 - **Multi-format Document Processing**: Handles text files, PDFs, PowerPoint presentations, and images.
 - **Advanced Text Extraction**: Extracts text from PDFs and PowerPoint slides, including tables and embedded images.
 - **Image Analysis**: Uses a VLM (NeVA) to describe images and Google's DePlot for processing graphs/charts on NIM microservices.
-- **Vector Store Indexing**: Creates a searchable index of processed documents using Milvus vector store.
+- **Vector Store Indexing**: Creates a searchable index of processed documents using Milvus vector store. This folder is auto generated on execution.
 - **Interactive Chat Interface**: Allows users to query the processed information through a chat-like interface.
 
 ## Setup
@@ -106,4 +106,4 @@ Contributions to this project are welcome! Please follow these steps:
 1. Fork the NVIDIA/GenerativeAIExamples repository.
 2. Create a new branch for your feature or bug fix.
 3. Make your changes in the community/multimodal_rag/ directory.
-4. Submit a pull request to the main repository.
+4. Submit a pull request to the main repository.

community/llm_video_series/data/imgs/offline.png

@@ -1,4 +1,4 @@
-pymupdf==1.22.5
+pymupdf==1.24.10
 streamlit==1.38.0
 python-pptx==1.0.2
 Pillow==10.4.0