Database AI Agents: Complete Guide [NEW]

Learn where to find the course source code by navigating resources, right-clicking the lecture, and using the hyperlink to access the code and PDFs.

Set up your development environment for database ai agents course by installing python and vscode, and create an OpenAI API key, noting costs and $5 credit, following the kinsta guide.

Learn what an AI agent is and how it autonomously uses tools and a large language model to interact with databases, convert natural-language queries to SQL, and achieve goals.

Explore use cases for ai agents, such as customer service bots, personal assistants, scheduling, reminders, data analysis insights, and smart home control, highlighting automation, efficiency, and decision making across domains.

Build your first AI agent using LangChain and the OpenAI model, leveraging an open-source framework to combine external data sources, documents, and your knowledge base for powerful, data-driven agents.

Set up a Python virtual environment, install dependencies from requirements.txt, and configure your OpenAI API key to build and run the first AI agent with LangChain.

Build an interactive console AI agent flow by defining a first_agent and a run_agent loop, processing user questions and returning responses via OpenAI or Lang Chain, with an exit option.

Build your first agent using a GPT-3 powered model wrapped by LangChain, then extend to a CSV agent that can extract and query tabular data with OpenAI.

Paolo checks in with learners, inviting reviews and questions in the discussion board to help guide responses and foster a collaborative learning community.

Leverage CSV agents to interact with CSV tabular data by extracting and analyzing CSV files with an OpenAI model and LangChain, enabling agents to answer queries.

Read a CSV with department, division, gender-based salary over time, using pandas to load data from the data folder, fill missing values with zero, and display five sample rows.

Create a csv agent with LangChain, using the pandas data frame agent, pass the large language model and dataframe, and query for the average salary and row count.

Create and apply prefix and suffix prompts to guide a CSV analysis with a large language model, using pandas options, column names, and cross-method checks to ensure consistent results.

Add a Streamlit-based user interface to preview the dataset, input questions, and run a query against a CSV agent, producing results in markdown output.

Learn to build a csv agent that reads csv data, creates data frames, and uses a large language model with prefix and suffix prompts to extract insights from tabular data.

Create database agents that transform natural language queries into SQL, interact with a SQL database, and return results after converting CSV data into a SQL database using an OpenAI chain.

Create a SQLite database from a CSV file by loading data with pandas, connecting via SQLAlchemy, and writing the dataframe to a table using Lang Chain's SQL database toolkit.

Create a SQL agent using the SQL database toolkit and Lang Chain, connect to a database, and guide the model to generate and run SQL queries for departmental salary insights.

Learn to build a Streamlit UI to test more queries, converting natural language questions into SQL via a SQL agent for interactive database insights.

Build a database agent that uses an OpenAI model and chain to interact with an SQL database, converts CSV to SQL, and runs queries via a Streamlit UI.

Discover how function calling extends agents with tools and predefined functions to query databases and external sources, using an OpenAI API workflow with third-party APIs to deliver secure, structured results.

Define a dummy get current weather function and integrate it with OpenAI's chat API, showing how to pass function parameters, tools, and location data.

Demonstrate a function calling workflow by handling tool calls, invoking get current weather, appending tool responses to messages, and returning a final answer with weather updates.

Set up a database agent with function calling, define sql tools and functions like average salary, female count for division, and overtime pay, then run conversations to trigger right function.

Test database ai agents functions by calling average salary and female count for a division and print results. Copy the code and comment it out to test functions.

Learn to use the OpenAI function calling feature with a SQL database by defining multiple functions, passing them to the model, and handling function responses.

Explore how to leverage OpenAI function calling with SQL databases and use the assistance API to simplify building your own AI agents that follow defined parameters for accurate results.