![[The AI Show Episode 145]: OpenAI Releases o3 and o4-mini, AI Is Causing “Quiet Layoffs,” Executive Order on Youth AI Education & GPT-4o’s Controversial Update](https://www.marketingaiinstitute.com/hubfs/ep%20145%20cover.png)
_Andy_Dean_Photography_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
![Here’s the Pebble smartwatch reboot in action, and how much tariffs might cost you [Video]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/03/core-2-duo-smartwatch-3.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Apple Reports Q2 FY25 Earnings: $95.4 Billion in Revenue, $24.8 Billion in Net Income [Chart]](https://www.iclarified.com/images/news/97188/97188/97188-640.jpg)
Building a REACT-Style Agent Using Fireworks AI with LangChain that Fetches Data, Generates BigQuery SQL, and Maintains Conversational Memory
In this tutorial, we will explore how to leverage the capabilities of Fireworks AI for building intelligent, tool-enabled agents with LangChain. Starting from installing the langchain-fireworks package and configuring your Fireworks API key, we’ll set up a ChatFireworks LLM instance, powered by the high-performance llama-v3-70b-instruct model, and integrate it with LangChain’s agent framework. Along the […] The post Building a REACT-Style Agent Using Fireworks AI with LangChain that Fetches Data, Generates BigQuery SQL, and Maintains Conversational Memory appeared first on MarkTechPost.
In this tutorial, we will explore how to leverage the capabilities of Fireworks AI for building intelligent, tool-enabled agents with LangChain. Starting from installing the langchain-fireworks package and configuring your Fireworks API key, we’ll set up a ChatFireworks LLM instance, powered by the high-performance llama-v3-70b-instruct model, and integrate it with LangChain’s agent framework. Along the way, we’ll define custom tools such as a URL fetcher for scraping webpage text and an SQL generator for converting plain-language requirements into executable BigQuery queries. By the end, we’ll have a fully functional REACT-style agent that can dynamically invoke tools, maintain conversational memory, and deliver sophisticated, end-to-end workflows powered by Fireworks AI.
!pip install -qU langchain langchain-fireworks requests beautifulsoup4We bootstrap the environment by installing all the required Python packages, including langchain, its Fireworks integration, and common utilities such as requests and beautifulsoup4. This ensures that we have the latest versions of all necessary components to run the rest of the notebook seamlessly.
import requests
from bs4 import BeautifulSoup
from langchain.tools import BaseTool
from langchain.agents import initialize_agent, AgentType
from langchain_fireworks import ChatFireworks
from langchain import LLMChain, PromptTemplate
from langchain.memory import ConversationBufferMemory
import getpass
import osWe bring in all the necessary imports: HTTP clients (requests, BeautifulSoup), the LangChain agent framework (BaseTool, initialize_agent, AgentType), the Fireworks-powered LLM (ChatFireworks), plus prompt and memory utilities (LLMChain, PromptTemplate, ConversationBufferMemory), as well as standard modules for secure input and environment management.
