{ "source_file": "0930", "source_platform": "Medium", "author": "Naser Tamimi", "title_listed": "Business Analytics with LangChain and LLMs", "keywords": "", "domain": "大模型算法", "content_type": "深度技术解析", "is_paid_flag": "否", "url": "https://towardsdatascience.com/business-analytics-with-langchain-and-llms-c8e902446073/", "publish_date": "2023-12-19", "corpus_stage": "", "notes": "", "id": "619746617e38", "collected_at": "2026-10-02T05:04:17", "title": "Business Analytics with LangChain and LLMs | Towards Data Science", "body_markdown": "![Revisit consent button](../images/body-df29beacd7496220cc94.svg)\nWe value your privacy\nWe use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking \"Accept All\", you consent to our use of cookies.\nCustomise Reject All Accept All\nCustomise Consent Preferences ![](../images/body-2159bb67f3de8ad870eb.svg)\nWe use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.\nThe cookies that are categorised as \"Necessary\" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more\nNecessaryAlways Active\nNecessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.\n * Cookie\nBCTempID\n * Duration\n10 minutes\n * Description\nNo description available.\n\n\n * Cookie\n__cf_bm\n * Duration\n1 hour\n * Description\nThis cookie, set by Cloudflare, is used to support Cloudflare Bot Management. \n\n\n * Cookie\nAWSALBCORS\n * Duration\n7 days\n * Description\nAmazon Web Services set this cookie for load balancing.\n\n\n * Cookie\n_cfuvid\n * Duration\nsession\n * Description\nCloudflare sets this cookie to track users across sessions to optimize user experience by maintaining session consistency and providing personalized services\n\n\n * Cookie\nli_gc\n * Duration\n6 months\n * Description\nLinkedin set this cookie for storing visitor's consent regarding using cookies for non-essential purposes.\n\n\n * Cookie\n__hssrc\n * Duration\nsession\n * Description\nThis cookie is set by Hubspot whenever it changes the session cookie. The __hssrc cookie set to 1 indicates that the user has restarted the browser, and if the cookie does not exist, it is assumed to be a new session.\n\n\n * Cookie\n__hssc\n * Duration\n1 hour\n * Description\nHubSpot sets this cookie to keep track of sessions and to determine if HubSpot should increment the session number and timestamps in the __hstc cookie.\n\n\n * Cookie\nwpEmojiSettingsSupports\n * Duration\nsession\n * Description\nWordPress sets this cookie when a user interacts with emojis on a WordPress site. It helps determine if the user's browser can display emojis properly.\n\n\n * Cookie\nBCSessionID\n * Duration\n1 year 1 month 4 days\n * Description\nBlueconic sets this cookie as a unique identifier for the BlueConic profile.\n\n\n * Cookie\n_octo\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nlogged_in\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\n__Secure-YEC\n * Duration\npast\n * Description\nYouTube sets this cookie to stores the user's video player preferences using embedded YouTube video\n\n\n * Cookie\n__eoi\n * Duration\n6 months\n * Description\nDescription is currently not available.\n\n\n * Cookie\nAWSALBTGCORS\n * Duration\n7 days\n * Description\nNo description available.\n\n\n * Cookie\nlogin-status-p\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nAWSALBTG\n * Duration\n7 days\n * Description\nNo description available.\n\n\n * Cookie\ncsrf_token\n * Duration\nsession\n * Description\nNo description available.\n\n\n * Cookie\ntoken_v2\n * Duration\n1 day\n * Description\nDescription is currently not available.\n\n\n * Cookie\nD\n * Duration\n1 year\n * Description\nDescription is currently not available.\n\n\n * Cookie\nPHPSESSID\n * Duration\nsession\n * Description\nThis cookie is native to PHP applications. The cookie stores and identifies a user's unique session ID to manage user sessions on the website. The cookie is a session cookie and will be deleted when all the browser windows are closed.\n\n\n * Cookie\nVISITOR_PRIVACY_METADATA\n * Duration\n6 months\n * Description\nYouTube sets this cookie to store the user's cookie consent state for the current domain. \n\n\n * Cookie\ncookietest\n * Duration\nsession\n * Description\nThe cookietest cookie is typically used to determine whether the user's browser accepts cookies, essential for website functionality and user experience.\n\n\n * Cookie\n__Host-airtable-session\n * Duration\n1 year\n * Description\nThis cookie is used to enable us to integrate the services of Airtable.\n\n\n * Cookie\n__Host-airtable-session.sig\n * Duration\n1 year\n * Description\nThis cookie is used to enable us to integrate the services of Airtable.\n\n\n * Cookie\nm\n * Duration\n1 year 1 month 4 days\n * Description\nStripe sets this cookie for fraud prevention purposes. It identifies the device used to access the website, allowing the website to be formatted accordingly.\n\n\n * Cookie\nBIGipServer*\n * Duration\nsession\n * Description\nMarketo sets this cookie to collect information about the user's online activity and build a profile about their interests to provide advertisements relevant to the user. \n\n\n * Cookie\n__cfruid\n * Duration\nsession\n * Description\nCloudflare sets this cookie to identify trusted web traffic.\n\n\n * Cookie\n_GRECAPTCHA\n * Duration\n6 months\n * Description\nGoogle Recaptcha service sets this cookie to identify bots to protect the website against malicious spam attacks.\n\n\n * Cookie\n__Secure-YNID\n * Duration\n6 months\n * Description\nGoogle cookie used to protect user security and prevent fraud, especially during the login process.\n\n\n * Cookie\ncookieyes-consent\n * Duration\n1 year\n * Description\nCookieYes sets this cookie to remember users' consent preferences so that their preferences are respected on subsequent visits to this site. It does not collect or store any personal information about the site visitors.\n\n\nFunctional\nFunctional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.\n * Cookie\nlidc\n * Duration\n1 day\n * Description\nLinkedIn sets the lidc cookie to facilitate data center selection.\n\n\n * Cookie\nbrw\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nbrwConsent\n * Duration\n5 minutes\n * Description\nDescription is currently not available.\n\n\n * Cookie\nWMF-Uniq\n * Duration\n1 year\n * Description\nDescription is currently not available.\n\n\n * Cookie\nloom_anon_comment\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nloom_referral_video\n * Duration\nsession\n * Description\nDescription is currently not available.\n\n\n * Cookie\nVISITOR_INFO1_LIVE\n * Duration\n6 months\n * Description\nA cookie set by YouTube to measure bandwidth that determines whether the user gets the new or old player interface.\n\n\n * Cookie\nyt-remote-connected-devices\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to store the user's video preferences using embedded YouTube videos.\n\n\n * Cookie\nytidb::LAST_RESULT_ENTRY_KEY\n * Duration\nNever Expires\n * Description\nThe cookie ytidb::LAST_RESULT_ENTRY_KEY is used by YouTube to store the last search result entry that was clicked by the user. This information is used to improve the user experience by providing more relevant search results in the future.\n\n\n * Cookie\nyt-remote-device-id\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to store the user's video preferences using embedded YouTube videos.\n\n\n * Cookie\nyt-remote-session-name\n * Duration\nsession\n * Description\nThe yt-remote-session-name cookie is used by YouTube to store the user's video player preferences using embedded YouTube video.\n\n\n * Cookie\nyt-remote-fast-check-period\n * Duration\nsession\n * Description\nThe yt-remote-fast-check-period cookie is used by YouTube to store the user's video player preferences for embedded YouTube videos.\n\n\n * Cookie\nyt-remote-session-app\n * Duration\nsession\n * Description\nThe yt-remote-session-app cookie is used by YouTube to store user preferences and information about the interface of the embedded YouTube video player.\n\n\n * Cookie\nyt-remote-cast-available\n * Duration\nsession\n * Description\nThe yt-remote-cast-available cookie is used to store the user's preferences regarding whether casting is available on their YouTube video player.\n\n\n * Cookie\nyt-remote-cast-installed\n * Duration\nsession\n * Description\nThe yt-remote-cast-installed cookie is used to store the user's video player preferences using embedded YouTube video.\n\n\n * Cookie\ncp_session\n * Duration\n3 months\n * Description\nCodepen sets this cookie for Help systems found in the website.\n\n\n * Cookie\nloid\n * Duration\n1 year 1 month 4 days\n * Description\nThis cookie is set by the Reddit. The cookie enables the sharing of content from the website onto the social media platform.\n\n\nAnalytics\nAnalytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.\n * Cookie\n__hstc\n * Duration\n6 months\n * Description\nHubspot set this main cookie for tracking visitors. It contains the domain, initial timestamp (first visit), last timestamp (last visit), current timestamp (this visit), and session number (increments for each subsequent session).\n\n\n * Cookie\nhubspotutk\n * Duration\n6 months\n * Description\nHubSpot sets this cookie to keep track of the visitors to the website. This cookie is passed to HubSpot on form submission and used when deduplicating contacts.\n\n\n * Cookie\n_ga\n * Duration\n1 year 1 month 4 days\n * Description\nGoogle Analytics sets this cookie to calculate visitor, session and campaign data and track site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognise unique visitors.\n\n\n * Cookie\n_ga_*\n * Duration\n1 year 1 month 4 days\n * Description\nGoogle Analytics sets this cookie to store and count page views.\n\n\n * Cookie\n__Host-psifi.analyticsTrace\n * Duration\n6 hours\n * Description\nDescription is currently not available.\n\n\n * Cookie\n__Host-psifi.analyticsTraceV2\n * Duration\n6 hours\n * Description\nDescription is currently not available.\n\n\n * Cookie\n_gh_sess\n * Duration\nsession\n * Description\nGitHub sets this cookie for temporary application and framework state between pages like what step the user is on in a multiple step form.\n\n\n * Cookie\nYSC\n * Duration\nsession\n * Description\nYSC cookie is set by Youtube and is used to track the views of embedded videos on Youtube pages.\n\n\n * Cookie\najs_anonymous_id\n * Duration\n1 year\n * Description\nThis cookie is set by Segment to count the number of people who visit a certain site by tracking if they have visited before.\n\n\n * Cookie\nvuid\n * Duration\n1 year 1 month 4 days\n * Description\nVimeo installs this cookie to collect tracking information by setting a unique ID to embed videos on the website. \n\n\nPerformance\nPerformance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.\n * Cookie\nAWSALB\n * Duration\n7 days\n * Description\nAWSALB is an application load balancer cookie set by Amazon Web Services to map the session to the target.\n\n\n * Cookie\nacq\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nacq.sig\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nptc\n * Duration\n2 years\n * Description\nNo description available.\n\n\nAdvertisement\nAdvertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.\n * Cookie\nmuc_ads\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to collect user behaviour and interaction data to optimize the website.\n\n\n * Cookie\nguest_id_marketing\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor.\n\n\n * Cookie\nguest_id_ads\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor.\n\n\n * Cookie\npersonalization_id\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to integrate and share features for social media and also store information about how the user uses the website, for tracking and targeting.\n\n\n * Cookie\nguest_id\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor. It registers if a user is signed in to the Twitter platform and collects information about ad preferences.\n\n\n * Cookie\nbcookie\n * Duration\n1 year\n * Description\nLinkedIn sets this cookie from LinkedIn share buttons and ad tags to recognize browser IDs.\n\n\n * Cookie\n__Secure-ROLLOUT_TOKEN\n * Duration\n6 months\n * Description\nYouTube sets this cookie to manage feature rollout and experimentation. It helps Google control which new features or interface changes are shown to users as part of testing and staged rollouts, ensuring consistent experience for a given user during an experiment.\n\n\n * Cookie\nyt.innertube::nextId\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to register a unique ID to store data on what videos from YouTube the user has seen.\n\n\n * Cookie\nyt.innertube::requests\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to register a unique ID to store data on what videos from YouTube the user has seen.\n\n\n * Cookie\nsession_tracker\n * Duration\nsession\n * Description\nThis cookie is set by the Reddit. This cookie is used to identify trusted web traffic. It also helps in adverstising on the website.\n\n\n * Cookie\nedgebucket\n * Duration\nsession\n * Description\nReddit sets this cookie to save the information about a log-on Reddit user, for the purpose of advertisement recommendations and updating the content.\n\n\n * Cookie\ndid\n * Duration\n1 year\n * Description\nArbor sets this cookie to show targeted ads to site visitors.This cookie expires after 2 months or 1 year.\n\n\nUncategorised\nOther uncategorised cookies are those that are being analysed and have not been classified into a category as yet.\nNo cookies to display.\nReject All Save My Preferences Accept All\nToggle Search[](https://towardsdatascience.com/)Toggle Mobile Navigation\n[](https://towardsdatascience.com/)\nPublish AI, ML & data-science insights to a global community of data professionals.\nSign in[Submit an Article](https://write.insightmediagroup.io)\n[Latest](https://towardsdatascience.com/latest/)[Editor's Picks](https://towardsdatascience.com/tag/editors-pick/)[Newsletter](https://towardsdatascience.com/tag/the-variable/)[ShipAI](https://towardsdatascience.com/shipai/)\n* * *\n[Write For TDS](https://towardsdatascience.com/submissions/)\n[LinkedIn](https://www.linkedin.com/company/towards-data-science/)[X](https://x.com/TDataScience)Toggle Search\n[Artificial Intelligence](https://towardsdatascience.com/category/artificial-intelligence/)\n# Business Analytics with LangChain and LLMs\nA step-by-step tutorial on querying SQL databases with human language\n[Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\nDecember 19, 20238 min read\n### GENERATIVE AI\n![Image by the author \\(generated via Midjourney\\)](../images/000.png)\nImage by the author (generated via Midjourney)\nMany businesses have a lot of proprietary data stored in their databases. If there's a virtual agent that understands human language and can query these databases, it opens up big opportunities for these businesses. Think of customer service chatbots, they're a common example. These agents can take customer requests, ask the database for information, and give the customer what they need.\nThe benefit of such agents is not limited to external customer interactions. Many business owners or people in companies, even in tech companies, might not know SQL or similar languages, but they still need to ask the database for information. That's where frameworks like LangChain come in. Such frameworks make it easy to create these helpful agents/applications. Agents that can talk to humans and at the same time, talk to databases, APIs, and more.\nLearn this step by step with the interactive [AI Engineer](https://roadmap.sh/ai-engineer), [AI and Data Scientist](https://roadmap.sh/ai-data-scientist), [Computer Science](https://roadmap.sh/computer-science), [Prompt Engineering](https://roadmap.sh/prompt-engineering) and [Machine Learning](https://roadmap.sh/machine-learning) roadmaps.\n## LLM-backed Applications\nLangChain is an open-source framework for building interactive applications using Large Language Models (LLMs). It's a tool that helps LLMs connect with other sources of information and lets them talk to the world around them. One important concept in such frameworks is the Chain. Let's take a look at this concept.\n### What are Chains?\nChains are advanced tools in this framework that combine LLMs with other tools to perform more complicated tasks. Specifically, chains are interfaces that use a sequence of LLMs along with other tools, such as SQL databases, API calls, bash operators, or math calculators, to complete a complex job. An example could be our application receiving input from a user and passing it to our LLM model; then, the LLM calls an API. The API responds to the LLM, and the LLM takes the response to perform another task, and so on. As you can see, it is a chain of inputs and outputs where, in many parts of this sequence, we have LLM models handling the situation.\n## Getting Our Hands Dirty\nNow it's time to get our hands dirty and start coding a simple LLM-backed application. For this application, we are going to make a simple Q&A agent that takes our question and queries a SQL database to find the answer for us.\n## Set Up A PostgreSQL Sample Database\nWe use [DVD Rental Sample Database](https://www.postgresqltutorial.com/postgresql-getting-started/postgresql-sample-database/) from postgresqltutorial.com ([License Information](https://dev.mysql.com/doc/sakila/en/sakila-license.html)). To install the database on your local system, you need to have PostgreSQL installed. Simply type `_psql_`in your terminal and see if it runs.\nThen you should follow the instructions [here](https://www.postgresqltutorial.com/postgresql-getting-started/load-postgresql-sample-database/). Here I walk through the database installation with you quickly.\nIn your terminal launch PostgreSQL via:\nbash\n\n```\npsql -U \n```\n\nYou must substitute the `` with your actual username. Then the system asks you about your password. Enter your password and you get into your Postgres database.\nFirst, we should create a database to load all the tables.\ntext\n\n```\npostgres=# CREATE DATABASE dvdrental;\n```\n\nAfter creating the database, you can check it by typing `_list_`command, You should see your dvdrental database in the returned list. Then simply exit Postgres (via`q`).\nNow we need to download the tables and data. You can download everything as a tar file here: [Download DVD Rental Sample Database](https://www.postgresqltutorial.com/wp-content/uploads/2019/05/dvdrental.zip)\nGo to the folder that you downloaded the tar file and using pg_restore, we can load the tables into our Postgres Database.\nbash\n\n```\npg_restore -U postgres -d dvdrental dvdrental.tar\n```\n\nBefore going further, let's check if the tables are loaded. Launch Postgres via `psql -U ` and enter your password.\nThen type the following commands to list tables inside the dvdrental database.\ntext\n\n```\npostgres=# c dvdrental\ndvdrental=# dt\n```\n\nYou must see a list of tables like this:\ntext\n\n```\n List of relations\n Schema | Name | Type | Owner\n--------+---------------+-------+----------\n public | actor | table | postgres\n public | address | table | postgres\n public | category | table | postgres\n public | city | table | postgres\n public | country | table | postgres\n public | customer | table | postgres\n public | film | table | postgres\n public | film_actor | table | postgres\n public | film_category | table | postgres\n public | inventory | table | postgres\n public | language | table | postgres\n public | payment | table | postgres\n public | rental | table | postgres\n public | staff | table | postgres\n public | store | table | postgres\n```\n\n## Set Up .env File\nAfter building the sample database, we need to create a `.env` file. We use this file to store our secrets and keys as well as environmental variables. Of course, we can put all that information in our code, but we must follow best engineering practices even for small projects. An accidental git push can expose our API keys and secrets to the public. Here is our `.env` file:\nplaintext\n\n```\nOPENAI_API_KEY = 'YOUR-OPENAI-API-KEY'\nPSQL_HOST = 'localhost'\nPSQL_PORT = 'YOUR-POSTGRES-PORT'\nPSQL_USERNAME = 'YOUR-POSTGRES-USERNAME'\nPSQL_PASSWORD = 'YOUR-POSTGRES-PASSWORD'\nPSQL_DB = 'dvdrental'\n```\n\nAs you see, you need to get your own OpenAI API key for this test. You can follow the instructions [here](https://medium.com/@rithin_9167/how-to-obtain-openai-api-key-30df0b8bd114) to obtain an API key from Open AI.\n## Creating a LangChain Application\nAfter saving your .env file in your project folder, we can start the actual code. First, we import the required libraries into our Python code.\nbash\n\n```\npip install langchain langchain-experimental openai psycopg2\n```\n\nFor this tutorial, I recommend using a Jupyter Notebook to test it step by step.\nWe need to import the required libraries at the beginning.\npython\n\n```\nfrom os import environ\nfrom dotenv import load_dotenv\n\nfrom langchain.chat_models import ChatOpenAI\nfrom langchain.utilities import SQLDatabase\nfrom langchain_experimental.sql import SQLDatabaseChain\n\nload_dotenv()\n```\n\nUsing load_dotenv(), we load the environment variables that we defined in the `.env` file. Now, safely we can access them in the code.\nFor our chain, we need a language model with chat capabilities. For simplicity, we chose gpt-3.5-turbo from OpenAI which is accessible through the API. You can use any other public or private models.\npython\n\n```\n# Instantiating Our LLM\n\nOPENAI_API_KEY = environ.get(\"OPENAI_API_KEY\")\nllm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0, openai_api_key=OPENAI_API_KEY)\n```\n\nIn addition to a model, we need a SQL Database connection. That connection enables our chain to query against the database and get the results back. As mentioned before, we use a PostgreSQL Database, but according to LangChain, any SQL engine with a JDBC connection should be easy to use (e.g. MySQL, Presto, Databricks).\npython\n\n```\n# Database Setup\n\nPSQL_HOST = environ.get(\"PSQL_HOST\")\nPSQL_PORT = environ.get(\"PSQL_PORT\")\nPSQL_USERNAME = environ.get(\"PSQL_USERNAME\")\nPSQL_PASSWORD = environ.get(\"PSQL_PASSWORD\")\nPSQL_DB = environ.get(\"PSQL_DB\")\npsql_uri = f\"postgresql+psycopg2://{PSQL_USERNAME}:{PSQL_PASSWORD}@{PSQL_HOST}:{PSQL_PORT}/{PSQL_DB}\"\n\ndb = SQLDatabase.from_uri(psql_uri, sample_rows_in_table_info=3)\ndb.get_usable_table_names()\n```\n\nIn case you are wondering about `sample_rows_in_table_info` parameter that we used in our SQL database connection, Rajkumar et. al showed in their paper () that including a few sample rows from the table increases the performance of the model in creating mode affecting querying the data. In LangChain, simply you can set `sample_rows_in_table_info` and determine the number of sample rows from each table that will be appended to each table description.\nTo test the SQL database connection, I printed the list of available tables using `db.get_usable_table_names()`. It should return the following list of tables for you too.\ntext\n\n```\n['actor',\n 'address',\n 'category',\n 'city',\n 'country',\n 'customer',\n 'film',\n 'film_actor',\n 'film_category',\n 'inventory',\n 'language',\n 'payment',\n 'rental',\n 'staff',\n 'store']\n```\n\nThe next step is the most important one. With our LLM model and a SQL database connection, now we should be able to instantiate our chain. Before showing the instantiation, let's get a little bit more sense about a chain.\nNow, we are using an SQL chain from LangChain to get a human question, convert it to an SQL query, run it on the database, and retrieve the results.\npython\n\n```\n# Definining Our SQL Dabatabe Chain\n\ndb_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n```\n\nFinally, we use the `run()` method to pass our input/question to the chain and get the final response back.\npython\n\n```\n# Define a Function To Run the Chain with Our Query\n\ndef query(input: str) -> str:\n response = db_chain.run(input)\n return response\n```\n\nNow it is time to test our code. We start with a simple query that requires querying a single table.\npython\n\n```\n# Example 1:\n\nquery(\"What is the average length of films released in 2006\")\n```\n\nThe chain gets our human-style query and converts it into an SQL query first. Then using the SQL DB connection, it runs the SQL query on the database. The returned response provides context for the LLM and along with the human original query, triggers a response. In this case, you can see the final response:\ntext\n\n```\n> Entering new SQLDatabaseChain chain...\nWhat is the average length of films released in 2006\nSQLQuery:SELECT AVG(length) FROM film WHERE release_year = 2006\nSQLResult: [(Decimal('115.2720000000000000'),)]\nAnswer:The average length of films released in 2006 is 115.272 minutes.\n> Finished chain.\n'The average length of films released in 2006 is 115.272 minutes.'\n```\n\nFirst, since the `verbose=True` (where we defined the db_chain) we get more information about the constructed SQL query and the returned SQL results. If you turn off the verbose, you only see the final results (highlighted with the boldface). The final answer shows correctly that the average length of films released in 2006 is 115.272 minutes (you can verify it with your own SQL query on Postgres).\nThe second question is a little bit more complicated and requires joining three tables.\npython\n\n```\n# Example 2:\n\nquery(\"Which actor played in movies with total longer duration? And how much was the duration?\")\n```\n\nThe question asks about the actor who played in movies that their total length is more than any other actors. This question requires joining three tables: actor, film_actor, and film. Here is the chain response:\ntext\n\n```\n> Entering new SQLDatabaseChain chain...\nWhich actor played in movies with total longer duration? And how much was the duration?\nSQLQuery:SELECT a.first_name, a.last_name, SUM(f.length) AS total_duration\nFROM actor a\nJOIN film_actor fa ON a.actor_id = fa.actor_id\nJOIN film f ON fa.film_id = f.film_id\nGROUP BY a.actor_id\nORDER BY total_duration DESC\nLIMIT 1;\nSQLResult: [('Mary', 'Keitel', 4962)]\nAnswer:Mary Keitel played in movies with a total duration of 4962 minutes.\n> Finished chain.\n'Mary Keitel played in movies with a total duration of 4962 minutes.'\n```\n\nAs you see, our super-simple LangChain application did a good job of understanding the relationships between these tables and constructing the SQL query.\n## Summary\nIn this article, we introduced a powerful open-source tool called LangChain that enables us to build LLM-based applications.\nThen we used SQLDatabaseChain to build an application that queries a SQL database based on user questions and returns the results.\nThis simple Q&A application can be expanded into a more complex business analytics assistant that anyone inside a business can use daily to get the latest insights from the proprietary data.\n## Register Now to Continue Reading\n### Unlock Towards Data Science with a Free Account\nAll articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more.\nRegister for freeSign in to your account\n* * *\n![](../images/body-909ce5c2500185af5a85.jpeg)\nWritten By\n## [Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\n[See all from Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\n[Artificial Intelligence](https://towardsdatascience.com/tag/artificial-intelligence/)[ChatGPT](https://towardsdatascience.com/tag/chatgpt/)[Data Science](https://towardsdatascience.com/tag/data-science/)[Machine Learning](https://towardsdatascience.com/tag/machine-learning/)[Technology](https://towardsdatascience.com/tag/technology/)\nShare This Article\n * [](https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&title=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n * [](https://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&title=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n * [](https://x.com/share?url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&text=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n\n\nTowards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program.\n[Write for TDS](https://towardsdatascience.com/submissions/)\n## Related Articles\n * [![](../images/001.jpeg)](https://towardsdatascience.com/the-future-of-data-catalogs-868ffbe7354d/)\n## [The Future of Data Catalogs](https://towardsdatascience.com/the-future-of-data-catalogs-868ffbe7354d/)\n[Data Science](https://towardsdatascience.com/category/data-science/)\nLet's visit a website just to \"browse the metadata,\" said no one ever\n[Prukalpa Sankar](https://towardsdatascience.com/author/prukalpa/)\nMay 10, 20226 min read\n * [![](../images/002.jpg)](https://towardsdatascience.com/4-resources-to-get-you-started-with-quantum-computing-eb7afe3e9747/)\n## [4 Resources to Get You Started With Quantum Computing](https://towardsdatascience.com/4-resources-to-get-you-started-with-quantum-computing-eb7afe3e9747/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nThere's no better time to start than now.\n[Sara A. Metwalli](https://towardsdatascience.com/author/saraametwalli/)\nDecember 7, 20204 min read\n * [![](../images/003.png)](https://towardsdatascience.com/understand-the-machine-learning-blackbox-with-ml-interpreter-7b0f9a2d8e9f/)\n## [Understand the machine learning Blackbox with ML interpreter](https://towardsdatascience.com/understand-the-machine-learning-blackbox-with-ml-interpreter-7b0f9a2d8e9f/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nThere are dangers in having models running the world and making decisions from hiring to criminal justice\n[Hannah Yan Han](https://towardsdatascience.com/author/yanhann10/)\nMarch 23, 20207 min read\n * [![](../images/004.png)](https://towardsdatascience.com/why-regularization-isnt-enough-a-better-way-to-train-neural-networks-with-two-objectives/)\n## [Why Regularization Isn’t Enough: A Better Way to Train Neural Networks with Two Objectives](https://towardsdatascience.com/why-regularization-isnt-enough-a-better-way-to-train-neural-networks-with-two-objectives/)\n[Deep Learning](https://towardsdatascience.com/category/artificial-intelligence/deep-learning/)\nWhy splitting your objectives and your model might be the key to better performance and clearer trade-offs in deep learning.\n[Mehdi Yazdani](https://towardsdatascience.com/author/myjahromi/)\nMay 27, 202525 min read\n * [![](../images/005.jpg)](https://towardsdatascience.com/how-to-select-an-initial-model-for-your-data-science-problem-77f7b811bd0/)\n## [How to Select an Initial Model for your Data Science Problem](https://towardsdatascience.com/how-to-select-an-initial-model-for-your-data-science-problem-77f7b811bd0/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nSave yourself some time and headaches and start simple.\n[Zachary Warnes](https://towardsdatascience.com/author/zjwarnes/)\nJuly 22, 20214 min read\n * [![](../images/006.png)](https://towardsdatascience.com/retrieving-openstreetmap-data-in-python-1777a4be45bb/)\n## [Retrieving OpenStreetMap data in Python](https://towardsdatascience.com/retrieving-openstreetmap-data-in-python-1777a4be45bb/)\n[Programming](https://towardsdatascience.com/category/programming/)\nA guide on how to access the OpenStreetMap database with Python using Google Colab.\n[Abdishakur](https://towardsdatascience.com/author/shakasom/)\nDecember 9, 20194 min read\n * [![](../images/007.png)](https://towardsdatascience.com/pca-whitening-vs-zca-whitening-a-numpy-2d-visual-518b32033edf/)\n## [PCA-whitening vs ZCA-whitening : a numpy 2d visual](https://towardsdatascience.com/pca-whitening-vs-zca-whitening-a-numpy-2d-visual-518b32033edf/)\n[Data Science](https://towardsdatascience.com/category/data-science/)\nThe process of whitening data consists in a transformation such that the transformed data has identity matrix as covariance matrix. This...\n[Yoann Mocquin](https://towardsdatascience.com/author/mocquin/)\nAugust 14, 20226 min read\n * [![](../images/008.png)](https://towardsdatascience.com/part-3-building-a-deep-q-network-to-play-gridworld-learning-instability-and-target-networks-fb399cb42616/)\n## [Part 3- Building a deep Q-network to play Gridworld - Learning Instability and Target Networks](https://towardsdatascience.com/part-3-building-a-deep-q-network-to-play-gridworld-learning-instability-and-target-networks-fb399cb42616/)\n[Deep Learning](https://towardsdatascience.com/category/artificial-intelligence/deep-learning/)\nIn this article let's understand what is Learning instability which is a common problem with Deep Reinforcement Learning agents. We will...\n[NandaKishore Joshi](https://towardsdatascience.com/author/nandakishorej8/)\nDecember 5, 20216 min read\n * [![](../images/009.jpg)](https://towardsdatascience.com/sentiment-analysis-using-logistic-regression-and-naive-bayes-16b806eb4c4b/)\n## [Sentiment Analysis using Logistic Regression and Naive Bayes](https://towardsdatascience.com/sentiment-analysis-using-logistic-regression-and-naive-bayes-16b806eb4c4b/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nLets compare which algorithm is better for classifying the tweets based on their sentiments.\n[Atharva Mashalkar](https://towardsdatascience.com/author/atharva-mashalkar/)\nNovember 28, 202013 min read\n\n\n * [YouTube](https://www.youtube.com/c/TowardsDataScience)\n * [X](https://x.com/TDataScience)\n * [LinkedIn](https://www.linkedin.com/company/towards-data-science/)\n * [Threads](https://www.threads.net/@towardsdatascience)\n * [Bluesky](https://bsky.app/profile/towardsdatascience.com)\n\n\n[](https://towardsdatascience.com/)\nYour home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.\nSubscribe to Our Newsletter[Write For TDS](https://towardsdatascience.com/submissions/)•[About](https://towardsdatascience.com/about-towards-data-science-d691af11cc2f/)•[Advertise](https://contact.towardsdatascience.com/advertise-with-towards-data-science)•[Privacy Policy](https://towardsdatascience.com/privacy-policy/)•[Terms of Use](https://towardsdatascience.com/website-terms-of-use/)\n© Insight Media Group, LLC 2026•[The New Stack](https://thenewstack.io)•[roadmap.sh](https://roadmap.sh)•[Creator Network](https://insightmediagroup.io/creator-network)\n#### Recommended Articles \nClose\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607686/image?etag=1782161464448&width=500&height=500) How Relevance Models Foreshadowed Transformers for NLP ](https://towardsdatascience.com/how-relevance-models-foreshadowed-transformers-for-nlp/ \"How Relevance Models Foreshadowed Transformers for NLP\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607639/image?etag=1781250125848&width=500&height=500) Javascript Fatigue: HTMX Is All You Need to Build ChatGPT — Part 1 ](https://towardsdatascience.com/javascript-fatigue-you-dont-need-js-to-build-chatgpt/ \"Javascript Fatigue: HTMX Is All You Need to Build ChatGPT — Part 1\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607930/image?etag=1782124566054&width=500&height=500) The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs ](https://towardsdatascience.com/subset-sum-problem-solved-in-linear-time-for-dense-enough-inputs/ \"The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/3660/image?etag=1780176246070&width=500&height=500) Does Your Company Have a Data Strategy? ](https://towardsdatascience.com/does-your-company-have-a-data-strategy-e8944dbec4ae/ \"Does Your Company Have a Data Strategy?\")\n\n\n", "metadata": { "title": "Business Analytics with LangChain and LLMs | Towards Data Science", "description": "A step-by-step tutorial on querying SQL databases with human language", "keywords": null, "author": "Naser Tamimi", "og:locale": "en_US", "og:type": "article", "og:title": "Business Analytics with LangChain and LLMs", "og:description": "A step-by-step tutorial on querying SQL databases with human language", "og:url": "https://towardsdatascience.com/business-analytics-with-langchain-and-llms-c8e902446073/", "og:site_name": "Towards Data Science", "og:image": "https://assets.insightmediagroup.io/media/wp-content/uploads/2023/12/12uCoZdVRfrdZkz8Ak-GttA.png", "og:image:width": "1024", "og:image:height": "1024", "og:image:type": "image/png", "twitter:card": "summary_large_image", "twitter:site": "@TDataScience", "twitter:creator": "@TDataScience", "twitter:label1": "Written by", "twitter:data1": "Naser Tamimi", "twitter:label2": "Est. reading time", "twitter:data2": "8 min read", "article:published_time": "2023-12-19T15:15:44.000Z", "article:modified_time": "2023-12-19T15:15:44.000Z", "article:author": "https://towardsdatascience.com/author/tamimi-naser/" }, "paywall": { "listed_paid": false, "detected": false, "marker": "", "public_only": false, "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙" }, "crawl": { "success": true, "status_code": 202, "error": "" }, "code_blocks": [ { "language": "txt", "file": "attachments/619746617e38/code/block_000.txt", "chars": 19 }, { "language": "txt", "file": "attachments/619746617e38/code/block_001.txt", "chars": 38 }, { "language": "txt", "file": "attachments/619746617e38/code/block_002.txt", "chars": 50 }, { "language": "txt", "file": "attachments/619746617e38/code/block_003.txt", "chars": 38 }, { "language": "txt", "file": "attachments/619746617e38/code/block_004.txt", "chars": 761 }, { "language": "txt", "file": "attachments/619746617e38/code/block_005.txt", "chars": 200 }, { "language": "txt", "file": "attachments/619746617e38/code/block_006.txt", "chars": 61 }, { "language": "txt", "file": "attachments/619746617e38/code/block_007.txt", "chars": 215 }, { "language": "txt", "file": "attachments/619746617e38/code/block_008.txt", "chars": 163 }, { "language": "txt", "file": "attachments/619746617e38/code/block_009.txt", "chars": 411 }, { "language": "txt", "file": "attachments/619746617e38/code/block_010.txt", "chars": 181 }, { "language": "txt", "file": "attachments/619746617e38/code/block_011.txt", "chars": 97 }, { "language": "txt", "file": "attachments/619746617e38/code/block_012.txt", "chars": 138 }, { "language": "txt", "file": "attachments/619746617e38/code/block_013.txt", "chars": 76 }, { "language": "txt", "file": "attachments/619746617e38/code/block_014.txt", "chars": 363 }, { "language": "txt", "file": "attachments/619746617e38/code/block_015.txt", "chars": 111 }, { "language": "txt", "file": "attachments/619746617e38/code/block_016.txt", "chars": 561 } ], "images": [ { "status": "http_404", "url": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607686/image?etag=1782161464448&width=500&height=500", "src": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607686/image?etag=1782161464448&width=500&height=500", "alt": "", "downloaded": false, "discovery": "saved_markdown", "retried_at": "2026-10-20T17:36:14Z" }, { "status": "http_404", "url": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607639/image?etag=1781250125848&width=500&height=500", "src": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607639/image?etag=1781250125848&width=500&height=500", "alt": "", "downloaded": false, "discovery": "saved_markdown", "retried_at": "2026-10-20T17:36:14Z" }, { "status": "http_404", "url": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607930/image?etag=1782124566054&width=500&height=500", "src": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607930/image?etag=1782124566054&width=500&height=500", "alt": "", "downloaded": false, "discovery": "saved_markdown", "retried_at": "2026-10-20T17:36:14Z" }, { "status": "http_404", "url": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/3660/image?etag=1780176246070&width=500&height=500", "src": "https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/3660/image?etag=1780176246070&width=500&height=500", "alt": "", "downloaded": false, "discovery": "saved_markdown", "retried_at": "2026-10-20T17:36:14Z" } ], "audio": [], "videos": [ { "url": "https://www.youtube.com/c/TowardsDataScience", "kind": "channel_reference", "status": "reference_only" } ], "links": [ { "type": "internal", "href": "https://towardsdatascience.com/" }, { "type": "internal", "href": "https://towardsdatascience.com/latest/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/editors-pick/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/the-variable/" }, { "type": "internal", "href": "https://towardsdatascience.com/shipai/" }, { "type": "internal", "href": "https://towardsdatascience.com/submissions/" }, { "type": "internal", "href": "https://towardsdatascience.com/category/artificial-intelligence/" }, { "type": "internal", "href": "https://towardsdatascience.com/author/tamimi-naser/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/artificial-intelligence/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/chatgpt/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/data-science/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/machine-learning/" }, { "type": "internal", "href": "https://towardsdatascience.com/tag/technology/" }, { "type": "internal", "href": "https://towardsdatascience.com/the-future-of-data-catalogs-868ffbe7354d/" }, { "type": "internal", "href": "https://towardsdatascience.com/category/data-science/" }, { "type": "internal", "href": "https://towardsdatascience.com/author/prukalpa/" }, { "type": "internal", "href": "https://towardsdatascience.com/4-resources-to-get-you-started-with-quantum-computing-eb7afe3e9747/" }, { "type": "internal", "href": "https://towardsdatascience.com/category/artificial-intelligence/machine-learning/" }, { "type": "internal", "href": "https://towardsdatascience.com/author/saraametwalli/" }, { "type": "internal", "href": "https://towardsdatascience.com/understand-the-machine-learning-blackbox-with-ml-interpreter-7b0f9a2d8e9f/" }, { "type": "external", "href": "https://write.insightmediagroup.io" }, { "type": "external", "href": "https://www.linkedin.com/company/towards-data-science/" }, { "type": "external", "href": "https://x.com/TDataScience" }, { "type": "external", "href": "https://roadmap.sh/ai-engineer" }, { "type": "external", "href": "https://roadmap.sh/ai-data-scientist" }, { "type": "external", "href": "https://roadmap.sh/computer-science" }, { "type": "external", "href": "https://roadmap.sh/prompt-engineering" }, { "type": "external", "href": "https://roadmap.sh/machine-learning" }, { "type": "external", "href": "https://www.postgresqltutorial.com/postgresql-getting-started/postgresql-sample-database/" }, { "type": "external", "href": "https://dev.mysql.com/doc/sakila/en/sakila-license.html" }, { "type": "external", "href": "https://www.postgresqltutorial.com/postgresql-getting-started/load-postgresql-sample-database/" }, { "type": "external", "href": "https://www.postgresqltutorial.com/wp-content/uploads/2019/05/dvdrental.zip" }, { "type": "external", "href": "https://medium.com/@rithin_9167/how-to-obtain-openai-api-key-30df0b8bd114" }, { "type": "external", "href": "https://arxiv.org/abs/2204.00498" }, { "type": "external", "href": "https://www.facebook.com/sharer/sharer.php?title=Business+Analytics+with+LangChain+and+LLMs&u=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F" }, { "type": "external", "href": "https://www.linkedin.com/shareArticle?mini=true&title=Business+Analytics+with+LangChain+and+LLMs&url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F" }, { "type": "external", "href": "https://x.com/share?text=Business+Analytics+with+LangChain+and+LLMs&url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F" }, { "type": "external", "href": "https://www.youtube.com/c/TowardsDataScience" }, { "type": "external", "href": "https://www.threads.net/@towardsdatascience" }, { "type": "external", "href": "https://bsky.app/profile/towardsdatascience.com" } ], "repair_version": 2, "repaired_at": "2026-10-20T17:23:07Z", "source_url": "https://towardsdatascience.com/business-analytics-with-langchain-and-llms-c8e902446073/", "delivery_status": "unverified", "discovery_status": "http_403", "missing_reason": "源页面未重新核验:http_403；已按保留正文补采图片", "repair_error": "", "actual_video_files": [], "expected_saved_body_images": 4, "image_discovery": "saved_markdown", "source_body_markdown": "![Revisit consent button](https://cdn-cookieyes.com/assets/images/revisit.svg)\nWe value your privacy\nWe use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking \"Accept All\", you consent to our use of cookies.\nCustomise Reject All Accept All\nCustomise Consent Preferences ![](https://cdn-cookieyes.com/assets/images/close.svg)\nWe use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.\nThe cookies that are categorised as \"Necessary\" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more\nNecessaryAlways Active\nNecessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.\n * Cookie\nBCTempID\n * Duration\n10 minutes\n * Description\nNo description available.\n\n\n * Cookie\n__cf_bm\n * Duration\n1 hour\n * Description\nThis cookie, set by Cloudflare, is used to support Cloudflare Bot Management. \n\n\n * Cookie\nAWSALBCORS\n * Duration\n7 days\n * Description\nAmazon Web Services set this cookie for load balancing.\n\n\n * Cookie\n_cfuvid\n * Duration\nsession\n * Description\nCloudflare sets this cookie to track users across sessions to optimize user experience by maintaining session consistency and providing personalized services\n\n\n * Cookie\nli_gc\n * Duration\n6 months\n * Description\nLinkedin set this cookie for storing visitor's consent regarding using cookies for non-essential purposes.\n\n\n * Cookie\n__hssrc\n * Duration\nsession\n * Description\nThis cookie is set by Hubspot whenever it changes the session cookie. The __hssrc cookie set to 1 indicates that the user has restarted the browser, and if the cookie does not exist, it is assumed to be a new session.\n\n\n * Cookie\n__hssc\n * Duration\n1 hour\n * Description\nHubSpot sets this cookie to keep track of sessions and to determine if HubSpot should increment the session number and timestamps in the __hstc cookie.\n\n\n * Cookie\nwpEmojiSettingsSupports\n * Duration\nsession\n * Description\nWordPress sets this cookie when a user interacts with emojis on a WordPress site. It helps determine if the user's browser can display emojis properly.\n\n\n * Cookie\nBCSessionID\n * Duration\n1 year 1 month 4 days\n * Description\nBlueconic sets this cookie as a unique identifier for the BlueConic profile.\n\n\n * Cookie\n_octo\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nlogged_in\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\n__Secure-YEC\n * Duration\npast\n * Description\nYouTube sets this cookie to stores the user's video player preferences using embedded YouTube video\n\n\n * Cookie\n__eoi\n * Duration\n6 months\n * Description\nDescription is currently not available.\n\n\n * Cookie\nAWSALBTGCORS\n * Duration\n7 days\n * Description\nNo description available.\n\n\n * Cookie\nlogin-status-p\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nAWSALBTG\n * Duration\n7 days\n * Description\nNo description available.\n\n\n * Cookie\ncsrf_token\n * Duration\nsession\n * Description\nNo description available.\n\n\n * Cookie\ntoken_v2\n * Duration\n1 day\n * Description\nDescription is currently not available.\n\n\n * Cookie\nD\n * Duration\n1 year\n * Description\nDescription is currently not available.\n\n\n * Cookie\nPHPSESSID\n * Duration\nsession\n * Description\nThis cookie is native to PHP applications. The cookie stores and identifies a user's unique session ID to manage user sessions on the website. The cookie is a session cookie and will be deleted when all the browser windows are closed.\n\n\n * Cookie\nVISITOR_PRIVACY_METADATA\n * Duration\n6 months\n * Description\nYouTube sets this cookie to store the user's cookie consent state for the current domain. \n\n\n * Cookie\ncookietest\n * Duration\nsession\n * Description\nThe cookietest cookie is typically used to determine whether the user's browser accepts cookies, essential for website functionality and user experience.\n\n\n * Cookie\n__Host-airtable-session\n * Duration\n1 year\n * Description\nThis cookie is used to enable us to integrate the services of Airtable.\n\n\n * Cookie\n__Host-airtable-session.sig\n * Duration\n1 year\n * Description\nThis cookie is used to enable us to integrate the services of Airtable.\n\n\n * Cookie\nm\n * Duration\n1 year 1 month 4 days\n * Description\nStripe sets this cookie for fraud prevention purposes. It identifies the device used to access the website, allowing the website to be formatted accordingly.\n\n\n * Cookie\nBIGipServer*\n * Duration\nsession\n * Description\nMarketo sets this cookie to collect information about the user's online activity and build a profile about their interests to provide advertisements relevant to the user. \n\n\n * Cookie\n__cfruid\n * Duration\nsession\n * Description\nCloudflare sets this cookie to identify trusted web traffic.\n\n\n * Cookie\n_GRECAPTCHA\n * Duration\n6 months\n * Description\nGoogle Recaptcha service sets this cookie to identify bots to protect the website against malicious spam attacks.\n\n\n * Cookie\n__Secure-YNID\n * Duration\n6 months\n * Description\nGoogle cookie used to protect user security and prevent fraud, especially during the login process.\n\n\n * Cookie\ncookieyes-consent\n * Duration\n1 year\n * Description\nCookieYes sets this cookie to remember users' consent preferences so that their preferences are respected on subsequent visits to this site. It does not collect or store any personal information about the site visitors.\n\n\nFunctional\nFunctional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.\n * Cookie\nlidc\n * Duration\n1 day\n * Description\nLinkedIn sets the lidc cookie to facilitate data center selection.\n\n\n * Cookie\nbrw\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nbrwConsent\n * Duration\n5 minutes\n * Description\nDescription is currently not available.\n\n\n * Cookie\nWMF-Uniq\n * Duration\n1 year\n * Description\nDescription is currently not available.\n\n\n * Cookie\nloom_anon_comment\n * Duration\n1 year\n * Description\nNo description available.\n\n\n * Cookie\nloom_referral_video\n * Duration\nsession\n * Description\nDescription is currently not available.\n\n\n * Cookie\nVISITOR_INFO1_LIVE\n * Duration\n6 months\n * Description\nA cookie set by YouTube to measure bandwidth that determines whether the user gets the new or old player interface.\n\n\n * Cookie\nyt-remote-connected-devices\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to store the user's video preferences using embedded YouTube videos.\n\n\n * Cookie\nytidb::LAST_RESULT_ENTRY_KEY\n * Duration\nNever Expires\n * Description\nThe cookie ytidb::LAST_RESULT_ENTRY_KEY is used by YouTube to store the last search result entry that was clicked by the user. This information is used to improve the user experience by providing more relevant search results in the future.\n\n\n * Cookie\nyt-remote-device-id\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to store the user's video preferences using embedded YouTube videos.\n\n\n * Cookie\nyt-remote-session-name\n * Duration\nsession\n * Description\nThe yt-remote-session-name cookie is used by YouTube to store the user's video player preferences using embedded YouTube video.\n\n\n * Cookie\nyt-remote-fast-check-period\n * Duration\nsession\n * Description\nThe yt-remote-fast-check-period cookie is used by YouTube to store the user's video player preferences for embedded YouTube videos.\n\n\n * Cookie\nyt-remote-session-app\n * Duration\nsession\n * Description\nThe yt-remote-session-app cookie is used by YouTube to store user preferences and information about the interface of the embedded YouTube video player.\n\n\n * Cookie\nyt-remote-cast-available\n * Duration\nsession\n * Description\nThe yt-remote-cast-available cookie is used to store the user's preferences regarding whether casting is available on their YouTube video player.\n\n\n * Cookie\nyt-remote-cast-installed\n * Duration\nsession\n * Description\nThe yt-remote-cast-installed cookie is used to store the user's video player preferences using embedded YouTube video.\n\n\n * Cookie\ncp_session\n * Duration\n3 months\n * Description\nCodepen sets this cookie for Help systems found in the website.\n\n\n * Cookie\nloid\n * Duration\n1 year 1 month 4 days\n * Description\nThis cookie is set by the Reddit. The cookie enables the sharing of content from the website onto the social media platform.\n\n\nAnalytics\nAnalytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.\n * Cookie\n__hstc\n * Duration\n6 months\n * Description\nHubspot set this main cookie for tracking visitors. It contains the domain, initial timestamp (first visit), last timestamp (last visit), current timestamp (this visit), and session number (increments for each subsequent session).\n\n\n * Cookie\nhubspotutk\n * Duration\n6 months\n * Description\nHubSpot sets this cookie to keep track of the visitors to the website. This cookie is passed to HubSpot on form submission and used when deduplicating contacts.\n\n\n * Cookie\n_ga\n * Duration\n1 year 1 month 4 days\n * Description\nGoogle Analytics sets this cookie to calculate visitor, session and campaign data and track site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognise unique visitors.\n\n\n * Cookie\n_ga_*\n * Duration\n1 year 1 month 4 days\n * Description\nGoogle Analytics sets this cookie to store and count page views.\n\n\n * Cookie\n__Host-psifi.analyticsTrace\n * Duration\n6 hours\n * Description\nDescription is currently not available.\n\n\n * Cookie\n__Host-psifi.analyticsTraceV2\n * Duration\n6 hours\n * Description\nDescription is currently not available.\n\n\n * Cookie\n_gh_sess\n * Duration\nsession\n * Description\nGitHub sets this cookie for temporary application and framework state between pages like what step the user is on in a multiple step form.\n\n\n * Cookie\nYSC\n * Duration\nsession\n * Description\nYSC cookie is set by Youtube and is used to track the views of embedded videos on Youtube pages.\n\n\n * Cookie\najs_anonymous_id\n * Duration\n1 year\n * Description\nThis cookie is set by Segment to count the number of people who visit a certain site by tracking if they have visited before.\n\n\n * Cookie\nvuid\n * Duration\n1 year 1 month 4 days\n * Description\nVimeo installs this cookie to collect tracking information by setting a unique ID to embed videos on the website. \n\n\nPerformance\nPerformance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.\n * Cookie\nAWSALB\n * Duration\n7 days\n * Description\nAWSALB is an application load balancer cookie set by Amazon Web Services to map the session to the target.\n\n\n * Cookie\nacq\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nacq.sig\n * Duration\npast\n * Description\nDescription is currently not available.\n\n\n * Cookie\nptc\n * Duration\n2 years\n * Description\nNo description available.\n\n\nAdvertisement\nAdvertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.\n * Cookie\nmuc_ads\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to collect user behaviour and interaction data to optimize the website.\n\n\n * Cookie\nguest_id_marketing\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor.\n\n\n * Cookie\nguest_id_ads\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor.\n\n\n * Cookie\npersonalization_id\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to integrate and share features for social media and also store information about how the user uses the website, for tracking and targeting.\n\n\n * Cookie\nguest_id\n * Duration\n1 year 1 month 4 days\n * Description\nTwitter sets this cookie to identify and track the website visitor. It registers if a user is signed in to the Twitter platform and collects information about ad preferences.\n\n\n * Cookie\nbcookie\n * Duration\n1 year\n * Description\nLinkedIn sets this cookie from LinkedIn share buttons and ad tags to recognize browser IDs.\n\n\n * Cookie\n__Secure-ROLLOUT_TOKEN\n * Duration\n6 months\n * Description\nYouTube sets this cookie to manage feature rollout and experimentation. It helps Google control which new features or interface changes are shown to users as part of testing and staged rollouts, ensuring consistent experience for a given user during an experiment.\n\n\n * Cookie\nyt.innertube::nextId\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to register a unique ID to store data on what videos from YouTube the user has seen.\n\n\n * Cookie\nyt.innertube::requests\n * Duration\nNever Expires\n * Description\nYouTube sets this cookie to register a unique ID to store data on what videos from YouTube the user has seen.\n\n\n * Cookie\nsession_tracker\n * Duration\nsession\n * Description\nThis cookie is set by the Reddit. This cookie is used to identify trusted web traffic. It also helps in adverstising on the website.\n\n\n * Cookie\nedgebucket\n * Duration\nsession\n * Description\nReddit sets this cookie to save the information about a log-on Reddit user, for the purpose of advertisement recommendations and updating the content.\n\n\n * Cookie\ndid\n * Duration\n1 year\n * Description\nArbor sets this cookie to show targeted ads to site visitors.This cookie expires after 2 months or 1 year.\n\n\nUncategorised\nOther uncategorised cookies are those that are being analysed and have not been classified into a category as yet.\nNo cookies to display.\nReject All Save My Preferences Accept All\nToggle Search[](https://towardsdatascience.com/)Toggle Mobile Navigation\n[](https://towardsdatascience.com/)\nPublish AI, ML & data-science insights to a global community of data professionals.\nSign in[Submit an Article](https://write.insightmediagroup.io)\n[Latest](https://towardsdatascience.com/latest/)[Editor's Picks](https://towardsdatascience.com/tag/editors-pick/)[Newsletter](https://towardsdatascience.com/tag/the-variable/)[ShipAI](https://towardsdatascience.com/shipai/)\n* * *\n[Write For TDS](https://towardsdatascience.com/submissions/)\n[LinkedIn](https://www.linkedin.com/company/towards-data-science/)[X](https://x.com/TDataScience)Toggle Search\n[Artificial Intelligence](https://towardsdatascience.com/category/artificial-intelligence/)\n# Business Analytics with LangChain and LLMs\nA step-by-step tutorial on querying SQL databases with human language\n[Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\nDecember 19, 20238 min read\n### GENERATIVE AI\n![Image by the author \\(generated via Midjourney\\)](https://assets.insightmediagroup.io/media/wp-content/uploads/2023/12/12uCoZdVRfrdZkz8Ak-GttA.png)\nImage by the author (generated via Midjourney)\nMany businesses have a lot of proprietary data stored in their databases. If there's a virtual agent that understands human language and can query these databases, it opens up big opportunities for these businesses. Think of customer service chatbots, they're a common example. These agents can take customer requests, ask the database for information, and give the customer what they need.\nThe benefit of such agents is not limited to external customer interactions. Many business owners or people in companies, even in tech companies, might not know SQL or similar languages, but they still need to ask the database for information. That's where frameworks like LangChain come in. Such frameworks make it easy to create these helpful agents/applications. Agents that can talk to humans and at the same time, talk to databases, APIs, and more.\nLearn this step by step with the interactive [AI Engineer](https://roadmap.sh/ai-engineer), [AI and Data Scientist](https://roadmap.sh/ai-data-scientist), [Computer Science](https://roadmap.sh/computer-science), [Prompt Engineering](https://roadmap.sh/prompt-engineering) and [Machine Learning](https://roadmap.sh/machine-learning) roadmaps.\n## LLM-backed Applications\nLangChain is an open-source framework for building interactive applications using Large Language Models (LLMs). It's a tool that helps LLMs connect with other sources of information and lets them talk to the world around them. One important concept in such frameworks is the Chain. Let's take a look at this concept.\n### What are Chains?\nChains are advanced tools in this framework that combine LLMs with other tools to perform more complicated tasks. Specifically, chains are interfaces that use a sequence of LLMs along with other tools, such as SQL databases, API calls, bash operators, or math calculators, to complete a complex job. An example could be our application receiving input from a user and passing it to our LLM model; then, the LLM calls an API. The API responds to the LLM, and the LLM takes the response to perform another task, and so on. As you can see, it is a chain of inputs and outputs where, in many parts of this sequence, we have LLM models handling the situation.\n## Getting Our Hands Dirty\nNow it's time to get our hands dirty and start coding a simple LLM-backed application. For this application, we are going to make a simple Q&A agent that takes our question and queries a SQL database to find the answer for us.\n## Set Up A PostgreSQL Sample Database\nWe use [DVD Rental Sample Database](https://www.postgresqltutorial.com/postgresql-getting-started/postgresql-sample-database/) from postgresqltutorial.com ([License Information](https://dev.mysql.com/doc/sakila/en/sakila-license.html)). To install the database on your local system, you need to have PostgreSQL installed. Simply type `_psql_`in your terminal and see if it runs.\nThen you should follow the instructions [here](https://www.postgresqltutorial.com/postgresql-getting-started/load-postgresql-sample-database/). Here I walk through the database installation with you quickly.\nIn your terminal launch PostgreSQL via:\nbash\n\n```\npsql -U \n```\n\nYou must substitute the `` with your actual username. Then the system asks you about your password. Enter your password and you get into your Postgres database.\nFirst, we should create a database to load all the tables.\ntext\n\n```\npostgres=# CREATE DATABASE dvdrental;\n```\n\nAfter creating the database, you can check it by typing `_list_`command, You should see your dvdrental database in the returned list. Then simply exit Postgres (via`q`).\nNow we need to download the tables and data. You can download everything as a tar file here: [Download DVD Rental Sample Database](https://www.postgresqltutorial.com/wp-content/uploads/2019/05/dvdrental.zip)\nGo to the folder that you downloaded the tar file and using pg_restore, we can load the tables into our Postgres Database.\nbash\n\n```\npg_restore -U postgres -d dvdrental dvdrental.tar\n```\n\nBefore going further, let's check if the tables are loaded. Launch Postgres via `psql -U ` and enter your password.\nThen type the following commands to list tables inside the dvdrental database.\ntext\n\n```\npostgres=# c dvdrental\ndvdrental=# dt\n```\n\nYou must see a list of tables like this:\ntext\n\n```\n List of relations\n Schema | Name | Type | Owner\n--------+---------------+-------+----------\n public | actor | table | postgres\n public | address | table | postgres\n public | category | table | postgres\n public | city | table | postgres\n public | country | table | postgres\n public | customer | table | postgres\n public | film | table | postgres\n public | film_actor | table | postgres\n public | film_category | table | postgres\n public | inventory | table | postgres\n public | language | table | postgres\n public | payment | table | postgres\n public | rental | table | postgres\n public | staff | table | postgres\n public | store | table | postgres\n```\n\n## Set Up .env File\nAfter building the sample database, we need to create a `.env` file. We use this file to store our secrets and keys as well as environmental variables. Of course, we can put all that information in our code, but we must follow best engineering practices even for small projects. An accidental git push can expose our API keys and secrets to the public. Here is our `.env` file:\nplaintext\n\n```\nOPENAI_API_KEY = 'YOUR-OPENAI-API-KEY'\nPSQL_HOST = 'localhost'\nPSQL_PORT = 'YOUR-POSTGRES-PORT'\nPSQL_USERNAME = 'YOUR-POSTGRES-USERNAME'\nPSQL_PASSWORD = 'YOUR-POSTGRES-PASSWORD'\nPSQL_DB = 'dvdrental'\n```\n\nAs you see, you need to get your own OpenAI API key for this test. You can follow the instructions [here](https://medium.com/@rithin_9167/how-to-obtain-openai-api-key-30df0b8bd114) to obtain an API key from Open AI.\n## Creating a LangChain Application\nAfter saving your .env file in your project folder, we can start the actual code. First, we import the required libraries into our Python code.\nbash\n\n```\npip install langchain langchain-experimental openai psycopg2\n```\n\nFor this tutorial, I recommend using a Jupyter Notebook to test it step by step.\nWe need to import the required libraries at the beginning.\npython\n\n```\nfrom os import environ\nfrom dotenv import load_dotenv\n\nfrom langchain.chat_models import ChatOpenAI\nfrom langchain.utilities import SQLDatabase\nfrom langchain_experimental.sql import SQLDatabaseChain\n\nload_dotenv()\n```\n\nUsing load_dotenv(), we load the environment variables that we defined in the `.env` file. Now, safely we can access them in the code.\nFor our chain, we need a language model with chat capabilities. For simplicity, we chose gpt-3.5-turbo from OpenAI which is accessible through the API. You can use any other public or private models.\npython\n\n```\n# Instantiating Our LLM\n\nOPENAI_API_KEY = environ.get(\"OPENAI_API_KEY\")\nllm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0, openai_api_key=OPENAI_API_KEY)\n```\n\nIn addition to a model, we need a SQL Database connection. That connection enables our chain to query against the database and get the results back. As mentioned before, we use a PostgreSQL Database, but according to LangChain, any SQL engine with a JDBC connection should be easy to use (e.g. MySQL, Presto, Databricks).\npython\n\n```\n# Database Setup\n\nPSQL_HOST = environ.get(\"PSQL_HOST\")\nPSQL_PORT = environ.get(\"PSQL_PORT\")\nPSQL_USERNAME = environ.get(\"PSQL_USERNAME\")\nPSQL_PASSWORD = environ.get(\"PSQL_PASSWORD\")\nPSQL_DB = environ.get(\"PSQL_DB\")\npsql_uri = f\"postgresql+psycopg2://{PSQL_USERNAME}:{PSQL_PASSWORD}@{PSQL_HOST}:{PSQL_PORT}/{PSQL_DB}\"\n\ndb = SQLDatabase.from_uri(psql_uri, sample_rows_in_table_info=3)\ndb.get_usable_table_names()\n```\n\nIn case you are wondering about `sample_rows_in_table_info` parameter that we used in our SQL database connection, Rajkumar et. al showed in their paper () that including a few sample rows from the table increases the performance of the model in creating mode affecting querying the data. In LangChain, simply you can set `sample_rows_in_table_info` and determine the number of sample rows from each table that will be appended to each table description.\nTo test the SQL database connection, I printed the list of available tables using `db.get_usable_table_names()`. It should return the following list of tables for you too.\ntext\n\n```\n['actor',\n 'address',\n 'category',\n 'city',\n 'country',\n 'customer',\n 'film',\n 'film_actor',\n 'film_category',\n 'inventory',\n 'language',\n 'payment',\n 'rental',\n 'staff',\n 'store']\n```\n\nThe next step is the most important one. With our LLM model and a SQL database connection, now we should be able to instantiate our chain. Before showing the instantiation, let's get a little bit more sense about a chain.\nNow, we are using an SQL chain from LangChain to get a human question, convert it to an SQL query, run it on the database, and retrieve the results.\npython\n\n```\n# Definining Our SQL Dabatabe Chain\n\ndb_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n```\n\nFinally, we use the `run()` method to pass our input/question to the chain and get the final response back.\npython\n\n```\n# Define a Function To Run the Chain with Our Query\n\ndef query(input: str) -> str:\n response = db_chain.run(input)\n return response\n```\n\nNow it is time to test our code. We start with a simple query that requires querying a single table.\npython\n\n```\n# Example 1:\n\nquery(\"What is the average length of films released in 2006\")\n```\n\nThe chain gets our human-style query and converts it into an SQL query first. Then using the SQL DB connection, it runs the SQL query on the database. The returned response provides context for the LLM and along with the human original query, triggers a response. In this case, you can see the final response:\ntext\n\n```\n> Entering new SQLDatabaseChain chain...\nWhat is the average length of films released in 2006\nSQLQuery:SELECT AVG(length) FROM film WHERE release_year = 2006\nSQLResult: [(Decimal('115.2720000000000000'),)]\nAnswer:The average length of films released in 2006 is 115.272 minutes.\n> Finished chain.\n'The average length of films released in 2006 is 115.272 minutes.'\n```\n\nFirst, since the `verbose=True` (where we defined the db_chain) we get more information about the constructed SQL query and the returned SQL results. If you turn off the verbose, you only see the final results (highlighted with the boldface). The final answer shows correctly that the average length of films released in 2006 is 115.272 minutes (you can verify it with your own SQL query on Postgres).\nThe second question is a little bit more complicated and requires joining three tables.\npython\n\n```\n# Example 2:\n\nquery(\"Which actor played in movies with total longer duration? And how much was the duration?\")\n```\n\nThe question asks about the actor who played in movies that their total length is more than any other actors. This question requires joining three tables: actor, film_actor, and film. Here is the chain response:\ntext\n\n```\n> Entering new SQLDatabaseChain chain...\nWhich actor played in movies with total longer duration? And how much was the duration?\nSQLQuery:SELECT a.first_name, a.last_name, SUM(f.length) AS total_duration\nFROM actor a\nJOIN film_actor fa ON a.actor_id = fa.actor_id\nJOIN film f ON fa.film_id = f.film_id\nGROUP BY a.actor_id\nORDER BY total_duration DESC\nLIMIT 1;\nSQLResult: [('Mary', 'Keitel', 4962)]\nAnswer:Mary Keitel played in movies with a total duration of 4962 minutes.\n> Finished chain.\n'Mary Keitel played in movies with a total duration of 4962 minutes.'\n```\n\nAs you see, our super-simple LangChain application did a good job of understanding the relationships between these tables and constructing the SQL query.\n## Summary\nIn this article, we introduced a powerful open-source tool called LangChain that enables us to build LLM-based applications.\nThen we used SQLDatabaseChain to build an application that queries a SQL database based on user questions and returns the results.\nThis simple Q&A application can be expanded into a more complex business analytics assistant that anyone inside a business can use daily to get the latest insights from the proprietary data.\n## Register Now to Continue Reading\n### Unlock Towards Data Science with a Free Account\nAll articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more.\nRegister for freeSign in to your account\n* * *\n![](https://assets.insightmediagroup.io/media/1787657191379_0jh99m.jpeg)\nWritten By\n## [Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\n[See all from Naser Tamimi](https://towardsdatascience.com/author/tamimi-naser/)\n[Artificial Intelligence](https://towardsdatascience.com/tag/artificial-intelligence/)[ChatGPT](https://towardsdatascience.com/tag/chatgpt/)[Data Science](https://towardsdatascience.com/tag/data-science/)[Machine Learning](https://towardsdatascience.com/tag/machine-learning/)[Technology](https://towardsdatascience.com/tag/technology/)\nShare This Article\n * [](https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&title=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n * [](https://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&title=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n * [](https://x.com/share?url=https%3A%2F%2Ftowardsdatascience.com%2Fbusiness-analytics-with-langchain-and-llms-c8e902446073%2F&text=Business%20Analytics%20with%20LangChain%20and%20LLMs)\n\n\nTowards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program.\n[Write for TDS](https://towardsdatascience.com/submissions/)\n## Related Articles\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2022/05/1YopPFjE-d1iKyuFH6TY0-Q.jpeg)](https://towardsdatascience.com/the-future-of-data-catalogs-868ffbe7354d/)\n## [The Future of Data Catalogs](https://towardsdatascience.com/the-future-of-data-catalogs-868ffbe7354d/)\n[Data Science](https://towardsdatascience.com/category/data-science/)\nLet's visit a website just to \"browse the metadata,\" said no one ever\n[Prukalpa Sankar](https://towardsdatascience.com/author/prukalpa/)\nMay 10, 20226 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2020/12/0GElqbCnogKBiErVx-scaled.jpg)](https://towardsdatascience.com/4-resources-to-get-you-started-with-quantum-computing-eb7afe3e9747/)\n## [4 Resources to Get You Started With Quantum Computing](https://towardsdatascience.com/4-resources-to-get-you-started-with-quantum-computing-eb7afe3e9747/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nThere's no better time to start than now.\n[Sara A. Metwalli](https://towardsdatascience.com/author/saraametwalli/)\nDecember 7, 20204 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2020/03/0Jy9u7aeqkZ0SP0_m.png)](https://towardsdatascience.com/understand-the-machine-learning-blackbox-with-ml-interpreter-7b0f9a2d8e9f/)\n## [Understand the machine learning Blackbox with ML interpreter](https://towardsdatascience.com/understand-the-machine-learning-blackbox-with-ml-interpreter-7b0f9a2d8e9f/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nThere are dangers in having models running the world and making decisions from hiring to criminal justice\n[Hannah Yan Han](https://towardsdatascience.com/author/yanhann10/)\nMarch 23, 20207 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2025/05/binn.png)](https://towardsdatascience.com/why-regularization-isnt-enough-a-better-way-to-train-neural-networks-with-two-objectives/)\n## [Why Regularization Isn’t Enough: A Better Way to Train Neural Networks with Two Objectives](https://towardsdatascience.com/why-regularization-isnt-enough-a-better-way-to-train-neural-networks-with-two-objectives/)\n[Deep Learning](https://towardsdatascience.com/category/artificial-intelligence/deep-learning/)\nWhy splitting your objectives and your model might be the key to better performance and clearer trade-offs in deep learning.\n[Mehdi Yazdani](https://towardsdatascience.com/author/myjahromi/)\nMay 27, 202525 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2021/07/0Zh_seOV8Mp-5J_DL-scaled.jpg)](https://towardsdatascience.com/how-to-select-an-initial-model-for-your-data-science-problem-77f7b811bd0/)\n## [How to Select an Initial Model for your Data Science Problem](https://towardsdatascience.com/how-to-select-an-initial-model-for-your-data-science-problem-77f7b811bd0/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nSave yourself some time and headaches and start simple.\n[Zachary Warnes](https://towardsdatascience.com/author/zjwarnes/)\nJuly 22, 20214 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2019/12/1O6sW5VsjhFuxiiEKA59I7g.png)](https://towardsdatascience.com/retrieving-openstreetmap-data-in-python-1777a4be45bb/)\n## [Retrieving OpenStreetMap data in Python](https://towardsdatascience.com/retrieving-openstreetmap-data-in-python-1777a4be45bb/)\n[Programming](https://towardsdatascience.com/category/programming/)\nA guide on how to access the OpenStreetMap database with Python using Google Colab.\n[Abdishakur](https://towardsdatascience.com/author/shakasom/)\nDecember 9, 20194 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2022/08/1G3bdIoj3ZxpFvVeVsOtg0Q.png)](https://towardsdatascience.com/pca-whitening-vs-zca-whitening-a-numpy-2d-visual-518b32033edf/)\n## [PCA-whitening vs ZCA-whitening : a numpy 2d visual](https://towardsdatascience.com/pca-whitening-vs-zca-whitening-a-numpy-2d-visual-518b32033edf/)\n[Data Science](https://towardsdatascience.com/category/data-science/)\nThe process of whitening data consists in a transformation such that the transformed data has identity matrix as covariance matrix. This...\n[Yoann Mocquin](https://towardsdatascience.com/author/mocquin/)\nAugust 14, 20226 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2021/12/1URcZDMRoxI1Tm-GeKIaNAA.png)](https://towardsdatascience.com/part-3-building-a-deep-q-network-to-play-gridworld-learning-instability-and-target-networks-fb399cb42616/)\n## [Part 3- Building a deep Q-network to play Gridworld - Learning Instability and Target Networks](https://towardsdatascience.com/part-3-building-a-deep-q-network-to-play-gridworld-learning-instability-and-target-networks-fb399cb42616/)\n[Deep Learning](https://towardsdatascience.com/category/artificial-intelligence/deep-learning/)\nIn this article let's understand what is Learning instability which is a common problem with Deep Reinforcement Learning agents. We will...\n[NandaKishore Joshi](https://towardsdatascience.com/author/nandakishorej8/)\nDecember 5, 20216 min read\n * [![](https://assets.insightmediagroup.io/media/wp-content/uploads/2020/11/0hFVNih5nrHL_8hla-scaled.jpg)](https://towardsdatascience.com/sentiment-analysis-using-logistic-regression-and-naive-bayes-16b806eb4c4b/)\n## [Sentiment Analysis using Logistic Regression and Naive Bayes](https://towardsdatascience.com/sentiment-analysis-using-logistic-regression-and-naive-bayes-16b806eb4c4b/)\n[Machine Learning](https://towardsdatascience.com/category/artificial-intelligence/machine-learning/)\nLets compare which algorithm is better for classifying the tweets based on their sentiments.\n[Atharva Mashalkar](https://towardsdatascience.com/author/atharva-mashalkar/)\nNovember 28, 202013 min read\n\n\n * [YouTube](https://www.youtube.com/c/TowardsDataScience)\n * [X](https://x.com/TDataScience)\n * [LinkedIn](https://www.linkedin.com/company/towards-data-science/)\n * [Threads](https://www.threads.net/@towardsdatascience)\n * [Bluesky](https://bsky.app/profile/towardsdatascience.com)\n\n\n[](https://towardsdatascience.com/)\nYour home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.\nSubscribe to Our Newsletter[Write For TDS](https://towardsdatascience.com/submissions/)•[About](https://towardsdatascience.com/about-towards-data-science-d691af11cc2f/)•[Advertise](https://contact.towardsdatascience.com/advertise-with-towards-data-science)•[Privacy Policy](https://towardsdatascience.com/privacy-policy/)•[Terms of Use](https://towardsdatascience.com/website-terms-of-use/)\n© Insight Media Group, LLC 2026•[The New Stack](https://thenewstack.io)•[roadmap.sh](https://roadmap.sh)•[Creator Network](https://insightmediagroup.io/creator-network)\n#### Recommended Articles \nClose\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607686/image?etag=1782161464448&width=500&height=500) How Relevance Models Foreshadowed Transformers for NLP ](https://towardsdatascience.com/how-relevance-models-foreshadowed-transformers-for-nlp/ \"How Relevance Models Foreshadowed Transformers for NLP\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607639/image?etag=1781250125848&width=500&height=500) Javascript Fatigue: HTMX Is All You Need to Build ChatGPT — Part 1 ](https://towardsdatascience.com/javascript-fatigue-you-dont-need-js-to-build-chatgpt/ \"Javascript Fatigue: HTMX Is All You Need to Build ChatGPT — Part 1\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/607930/image?etag=1782124566054&width=500&height=500) The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs ](https://towardsdatascience.com/subset-sum-problem-solved-in-linear-time-for-dense-enough-inputs/ \"The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs\")\n * [ ![](https://h030.towardsdatascience.com/rest/v2/contentStores/d7d3a4ab-7caf-4383-bbd2-fbf7fb4f1787/items/3660/image?etag=1780176246070&width=500&height=500) Does Your Company Have a Data Strategy? ](https://towardsdatascience.com/does-your-company-have-a-data-strategy-e8944dbec4ae/ \"Does Your Company Have a Data Strategy?\")\n\n\n", "body_base_path": "attachments/619746617e38/pages/", "body_markdown_path": "attachments/619746617e38/pages/archived-body.md", "local_html": "attachments/619746617e38/pages/archived-body.html", "body_source": "prior_capture" }