Introduction
Level up LLM applications
()
What you should know
()
1. LangChain Basics: Intro to Building LLM-Powered Apps
Setup and installation
()
Create a chain and interface with LLM
()
Define and structure a prompt
()
Create and invoke a chain (LCEL syntax)
()
Work with output parsers
()
2. Adding Similarity Search and Context
Quickstart: Installation and setup
()
Create embeddings from text (Faiss)
()
Querying the vector store
()
Querying as a retriever
()
3. Leveraging LLMs with LangChain and RAG
RAG: Overview and architecture
()
Breaking down the RAG pipeline
()
Project setup
()
Load and split documents into chunks
()
Initialize a vector store (Chroma) and ingest documents
()
Create the chain: Prompt + model + parser
()
Create the chain: Add context with a retriever
()
Pass data with RunnablePassthrough and query data
()
Challenge: Create a custom agent with history
()
Solution: Add a chain with chat history
()
Solution: Context- and history-aware chatbot
()
4. Create an Interactive Web App (Streamlit)
Set up the Streamlit application
()
Build the layout with Streamlit components
()
Adding functionality with Streamlit
()
Challenge: Deploy your Streamlit app
()
Solution: Add app to GitHub
()
Solution: Deploy your app
()
5. Build a Q&A Agent with Multiple Data Sources and Query Analysis
Retrieval with query analysis
()
Connect to a data source and create an index
()
Set up query analysis to handle multiple data sources
()
Retrieval with query analysis
()
Challenge: Retrieval with multiple data sources
()
Solution: Q&A with multiple data sources
()
6. Perform Semantic Search Using MongoDB Atlas Vector Search and OpenAI
Getting started with MongoDB: Create an account
()
Build and deploy a free cluster
()
Set up the MongoDB environment and connect to the cluster
()
Create a secured database access (user)
()
Load sample data and create the vector store
()
Create the Atlas Vector Search index
()
Run vector search queries
()
7. Interact with a NoSQL Database (MongoDB)
Create a retrieval chain: Define the prompt
()
Create a retrieval chain: Define the context
()
Create a retrieval chain: Parse and format results
()
Query documents and generate extended responses
()
8. LLM Fine-Tuning with the OpenAI Tools and Functions
Using agents to perform actions in chains
()
Define tools
()
Select the perfect prompt
()
Bind tools and create agent
()
Create and run the agent executor
()
Challenge: Create a multitask agent
()
Solution: Define tools and functions
()
9. Deploy Chains as a RESTful API with LangServe
Introducing LangServe: Installation and setup
()
Create a server
()
Create the routes and the endpoints
()
Create a runnable to combine a prompt, a model, and output
()
Challenge: Deploy a RESTful API
()
Solution: Deploy a RESTful API
()
10. Finish Line: Deploy to the Cloud and Share with the World
Manage and deploy an app on Render
()
Create a GitHub repository and push your project
()
Deploy a new web service on Render
()