Master LLM Apps: Build AI Agents with LangChain & OpenAI
Focused View
3:52:26
01 - Level up LLM applications.mp4
00:39
02 - What you should know.mp4
02:48
01 - Setup and installation.mp4
04:03
02 - Create a chain and interface with LLM.mp4
04:12
03 - Define and structure a prompt.mp4
05:19
04 - Create and invoke a chain (LCEL syntax).mp4
02:54
05 - Work with output parsers.mp4
02:37
01 - Quickstart Installation and setup.mp4
02:28
02 - Create embeddings from text (Faiss).mp4
01:34
03 - Querying the vector store.mp4
01:56
04 - Querying as a retriever.mp4
04:59
01 - RAG Overview and architecture.mp4
02:12
02 - Breaking down the RAG pipeline.mp4
02:50
03 - Project setup.mp4
03:33
04 - Load and split documents into chunks.mp4
05:06
05 - Initialize a vector store (Chroma) and ingest documents.mp4
05:06
06 - Create the chain Prompt + model + parser.mp4
05:39
07 - Create the chain Add context with a retriever.mp4
04:48
08 - Pass data with RunnablePassthrough and query data.mp4
03:27
09 - Challenge Create a custom agent with history.mp4
03:12
10 - Solution Add a chain with chat history.mp4
05:19
11 - Solution Context- and history-aware chatbot.mp4
05:49
01 - Set up the Streamlit application.mp4
04:16
02 - Build the layout with Streamlit components.mp4
05:53
03 - Adding functionality with Streamlit.mp4
04:50
04 - Challenge Deploy your Streamlit app.mp4
03:37
05 - Solution Add app to GitHub.mp4
03:46
06 - Solution Deploy your app.mp4
05:47
01 - Retrieval with query analysis.mp4
01:16
02 - Connect to a data source and create an index.mp4
04:23
03 - Set up query analysis to handle multiple data sources.mp4
05:55
04 - Retrieval with query analysis.mp4
05:07
05 - Challenge Retrieval with multiple data sources.mp4
03:11
06 - Solution Q&A with multiple data sources.mp4
07:13
01 - Getting started with MongoDB Create an account.mp4
01:35
02 - Build and deploy a free cluster.mp4
01:41
03 - Set up the MongoDB environment and connect to the cluster.mp4
06:23
04 - Create a secured database access (user).mp4
03:27
05 - Load sample data and create the vector store.mp4
04:18
06 - Create the Atlas Vector Search index.mp4
04:04
07 - Run vector search queries.mp4
05:33
01 - Create a retrieval chain Define the prompt.mp4
02:51
02 - Create a retrieval chain Define the context.mp4
05:08
03 - Create a retrieval chain Parse and format results.mp4
01:47
04 - Query documents and generate extended responses.mp4
03:33
01 - Using agents to perform actions in chains.mp4
01:36
02 - Define tools.mp4
05:37
03 - Select the perfect prompt.mp4
01:12
04 - Bind tools and create agent.mp4
02:19
05 - Create and run the agent executor.mp4
04:41
06 - Challenge Create a multitask agent.mp4
05:31
07 - Solution Define tools and functions.mp4
06:09
01 - Introducing LangServe Installation and setup.mp4
03:35
02 - Create a server.mp4
00:49
03 - Create the routes and the endpoints.mp4
05:56
04 - Create a runnable to combine a prompt, a model, and output.mp4
03:35
05 - Challenge Deploy a RESTful API.mp4
01:39
06 - Solution Deploy a RESTful API.mp4
02:51
01 - Manage and deploy an app on Render.mp4
01:53
02 - Create a GitHub repository and push your project.mp4
04:21
03 - Deploy a new web service on Render.mp4
04:10
01 - Conclusion.mp4
00:28
More details
Course Overview
Dive into large language model (LLM) application development using LangChain and OpenAI APIs. Learn to build intelligent agents, implement RAG systems, and deploy interactive AI solutions that enhance user experiences through semantic search, Q&A chatbots, and multi-source data handling.
What You'll Learn
- Build LLM-powered applications with LangChain
- Implement retrieval-augmented generation (RAG) pipelines
- Deploy interactive web apps and RESTful APIs
Who This Is For
- Developers looking to integrate LLMs into applications
- AI enthusiasts wanting practical deployment skills
- Technical professionals expanding their AI toolkit
Key Benefits
- Hands-on experience with OpenAI and vector databases
- End-to-end project deployment skills
- Multi-retriever agent development techniques
Curriculum Highlights
- LangChain basics and prompt engineering
- Building RAG systems with MongoDB Atlas
- Deploying Streamlit apps and REST APIs
Focused display
- language english
- Training sessions 62
- duration 3:52:26
- English subtitles has
- Release Date 2025/06/02
