RAG Powered AI App | Adding MongoDB along with PDFs, URLs, SQL, Postgres as a Knowledge Base| Part15

RAG Powered AI App | Adding MongoDB along with PDFs, URLs, SQL, Postgres as a Knowledge Base| Part15

🆓 Welcome back to the RAG Powered AI Agent tutorial series! In Part 15, we take a crucial step towards making our LLM agent smarter by integrating semi-structured data from a NoSQL Database known as MongoDB.

🔗 Code Repository: https://github.com/vardhmanandroid2015/rag_powered_ai_qa

🧠 You'll learn how to
🔧/📦 Setup MongoDB with Docker that includes creating volume, copying data to container specific directory
🔧/📦 Convert List of tuples into JSON format with Python code that can be loaded to MongoDB with MongoIport utility
🔧/📦 Load data to Mongodb with MongoImport utility
🔧/📦 Basic commands like Count Documents from collection, Access Documents with find from collection within Mongo Shell
🔧/📦 Connect to MongoDB using Python (pymongo) and Extract documents to ensure python can interact with MongoDB

Now we have setup our knowledge base in MongoDB so we are all set to integrate MongoDB data source to our RAG Application to increase its coverage for Semi structured flexible data in the form of JSON too.

🔍 Stay tuned for Part 16 where we will be Adding new data source with MongoDB!

Whether you're a developer, ML enthusiast, or researcher building with LLMs powered with RAG AI application, or you're building a chatbot, search assistant, document intelligence, enterprise Q&A systems or custom AI workflow, this tutorial shows you how to enhance your app with live web knowledge!

# Commands Used in the Video
## Create Docker volume to persist data
```
docker volume create mongodb_data
```
## Create Docker container for mongodb
```
docker run -d --net=host --name mongodb -e MONGODB_USERNAME=rag_app_user -e MONGODB_PASSWORD=rag_app_pwd_@123 -e MONGODB_DATABASE=rag_app_db -e ALLOW_EMPTY_PASSWORD=yes -v mongodb_data:/bitnami/mongodb bitnami/mongodb:latest
```
## Copy file with knowledge base data to container directory /tmp
```
docker cp /mongodb_data/mongo_init/system_design_faqs.json mongodb:/tmp/system_design_faqs.json
```
## Load data to collection name system_design_faqs on mongodb
```
docker exec -it mongodb mongoimport --db rag_app_db --collection system_design_faqs --file /tmp/system_design_faqs.json --username rag_app_user --password rag_app_pwd_@123 --authenticationDatabase rag_app_db --drop --verbose
```
## Basic commands
```
show collections;
db.system_design_faqs.countDocuments();
db.system_design_faqs.find().limit(5);
```

Part 1 (Theory & Concepts) 👉 https://youtu.be/E2YsOkIsihQ
Part 2 (Env Setup) 👉 https://youtu.be/DO_crG2LdOo
Part 3 (PDF to Vector DB) 👉 https://youtu.be/CJ9C00nj4X4
Part 4 (Console RAG Code) 👉 https://youtu.be/bXo7Few4gbU
Part 5 (Streamlit vs Gradio) 👉 https://youtu.be/KmRl1gjJq68
Part 6 (Console App to Interactive Web App) 👉 https://www.youtube.com/watch?v=w_2ojb7YnKQ
Part 7 (Upload PDF & Ask Question From Loaded PDF) 👉 https://www.youtube.com/watch?v=hrVfMRO2a_Q
Part 8 (Summarization & Suggestion for 5 Questions) 👉 https://www.youtube.com/watch?v=jIMNOjAO2CE
Part 9 (Fixing Vector Similarity Limitations with RERANK Models) 👉 https://www.youtube.com/watch?v=ZvKs6X97IOk
Part 10 (RERANK Model Integration with Pinecone To Fine-Tuning RAG Retrieval Quality) 👉 https://www.youtube.com/watch?v=4EXzPbCdJYg
Part 11 (Extract data from Web Search (URL) for RAG powered AI app ) 👉 https://www.youtube.com/watch?v=NVaFQlmUEks
Part 12 (Integrate Knowledge from Relational DB along with PDF & URL data ) 👉 https://www.youtube.com/watch?v=uQkEWrSEV8Y
Part 13 (POSTGRESQL - Setup & Load 733 Questions/Answers for 50 Topics of System Design) 👉 https://www.youtube.com/watch?v=2wOFrdjF_VA
Part 14 (Integrate PostgreSQL Database as LLM Knowledge Base for system design concepts) 👉 https://www.youtube.com/watch?v=vsRen4HVGhg

#mongodb #pinecone #Ai #rag #AI #GeminiAI #LangChain #Pinecone #RAG #Gradio #PDFProcessing #WebScraping #PythonAI #tutorials #postgresql #mongodbatlas #gradio

Видео RAG Powered AI App | Adding MongoDB along with PDFs, URLs, SQL, Postgres as a Knowledge Base| Part15 канала Abhishek Jain