LangChain for EDA: Construct a CSV Sanity-Verify Agent in Python

, brokers carry out actions.

That’s precisely what we’re going to check out in right now’s article.

On this article, we’ll use LangChain and Python to construct our personal CSV sanity examine agent. With this agent, we’ll automate typical exploratory knowledge evaluation (EDA) duties as displaying columns, detecting lacking values (NaNs) and retrieving descriptive statistics.

Brokers determine step-by-step which software to name and when to reply a query about our knowledge. This can be a massive distinction from an utility within the conventional sense, the place the developer defines how the method works (e.g., by way of if-else loops). It additionally goes far past easy prompting as a result of we’re constructing a system that acts (albeit in a easy manner) and doesn’t simply discuss.

This text is for you if you happen to:

• …work with Pandas and wish to automate EDA.
• …discover LLMs thrilling, however have little expertise with LangChain to this point.
• …wish to perceive how brokers actually work (from setup to mini-evaluation) utilizing a easy instance.

Desk of Contents
What we construct & why
Arms-On-Instance: CSV-Sanity-Verify Agent with LangChain
Mini-Analysis
Last Ideas – Pitfalls, Ideas and Subsequent Steps
The place Can You Proceed Studying?

What we construct & why

An agent is a system to which we assign duties. The system then decides for itself which instruments to make use of to resolve these duties.

This requires three parts:

Agent = LLM + Instruments + Management logic

Let’s take a better take a look at the three parts:

• The LLM supplies the intelligence: It understands the query, plans steps, and decides what to do.
• The instruments are small Python capabilities that the agent is allowed to name (e.g., get_schema() or get_nulls()): They supply particular info from the info, akin to column names or statistics.
• The management logic (coverage) ensures that the LLM doesn’t reply instantly, however first decides whether or not it ought to use a software. It thinks step-by-step: First, the query is analyzed, then the suitable software is chosen, then the result’s interpreted and, if obligatory, a subsequent step is chosen, and at last a response is returned.

As a substitute of manually describing all knowledge as in basic prompting, we switch the accountability to the agent: The system ought to act by itself, however solely with the instruments offered.

Let’s take a look at a easy instance:

A person asks: “What’s the common age within the CSV?”

At this level, the agent calls up the software we’ve got outlined, df.describe(). The output is a clearly structured worth (e.g., “imply”: 29.7). Right here we will additionally see that this may scale back or decrease hallucinations, because the system is aware of what to use and can’t return a solution akin to “In all probability between 20 and 40.”

LangChain as a framework

We use the LangChain framework for the agent. This enables us to attach LLMs with instruments and construct techniques with outlined conduct. The system can carry out actions as a substitute of simply offering solutions or producing textual content. An in depth rationalization would make this text too lengthy. However in a earlier article, you will discover a proof of LangChain and a comparability with Langflow: LangChain vs Langflow: Construct a Easy LLM App with Code or Drag & Drop.

What the agent does for us

Once we obtain a brand new CSV, we normally ask ourselves the next questions first (begin of exploratory knowledge evaluation):

• What columns are there?
• The place is knowledge lacking?
• What do the descriptive statistics seem like?

That is precisely what we wish the agent to do mechanically.

Instruments we outline for the agent

For the agent to work, it wants clearly outlined instruments. It’s best to outline them as small, particular, and managed as potential. This fashion, we keep away from errors, hallucinations or unclear outputs as a result of they make the output deterministic. In addition they make the agent reproducible and testable as a result of the identical enter ought to produce a constant end result.

In our instance, we outline three instruments:

• schema: Returns column names and knowledge varieties.
• nulls: Reveals columns with lacking values (together with quantity).
• describe: Offers descriptive statistics for numeric columns.

Later, we are going to add a small mini-evaluation to make sure that our agent is working appropriately.

Why is that this an agent and never an app?

We’re not constructing a basic program with a hard and fast sequence (e.g., utilizing if-else), however moderately the mannequin plans itself primarily based on the query, selects the suitable software, and combines steps as essential to arrive at a solution:

Arms-On-Instance: CSV-Sanity-Verify Agent with LangChain

1) Setup

Prerequisite: Python 3.10 or increased should be put in. Many packages within the AI tooling world require ≥ 3.10. You’ll find the code and the hyperlink to the repo under.

Tip for newbies:
You’ll be able to examine this by getting into “python –model” in cmd.exe.

With the code under, we first create a brand new undertaking, create an remoted Python atmosphere and activate it. We do that in order that packages and variations are reproducible and don’t consolidate with different initiatives.

Tip for newbies:
I work with Home windows. We open a terminal with Home windows + R > cmd and paste the next code.

mkdir csv-agent

cd csv-agent
python -m venv .venv
.venvScriptsactivate

Then we set up the mandatory packages:

pip set up "langchain>=0.2,<0.3" "langchain-openai>=0.1.7" "langchain-community>=0.2" pandas seaborn

With this command, we pin LangChain to the 0.2 line and set up the OpenAI connection and the group package deal. We additionally set up pandas for the EDA capabilities and seaborn for loading the Titanic pattern dataset.

Tip for newbies:
In the event you don’t wish to use OpenAI, you possibly can work domestically with Ollama (e.g., with Llama or Mistral). This feature is out there later within the code.

2) Put together the info set in prepare_data.py

Subsequent, we create a Python file referred to as prepare_data.py. I exploit Visible Studio Code for this, however you can too use one other IDE. On this file, we load the Titanic dataset, as it’s publicly out there.

# prepare_data.py
import seaborn as sns
df = sns.load_dataset("titanic")
df.to_csv("titanic.csv", index=False)
print("Saved titanic.csv")

With seaborn.load_dataset(“titanic”), we load the general public dataset (891 rows + first row with column names) immediately into reminiscence and put it aside as titanic.csv. The dataset incorporates solely numeric, Boolean and categorical columns, making it very best for an EDA agent.

Ideas for newbies:

• sns.load_dataset() requires web entry (the info comes from the seaborn repo).
• Save the file within the undertaking folder (csv-agent) so htat important.py can discover it.

Within the terminal, we execute the Python file with the next command, in order that the titanic.csv file is situated within the undertaking:

python prepare_data.py

We then see within the terminal that the csv has been saved and see the titanic.csv file within the folder:

Aspect Notice – Titanic dataset

The evaluation is predicated on the Titanic dataset (OpenML ID 40945), which is marked as public on OpenML.

Once we open the file, we see the next 14 columns and 891 rows of knowledge. The Titanic dataset is a basic instance of exploratory knowledge evaluation (EDA). It incorporates info on 891 passengers of the Titanic and is commonly used to research the connection between traits (e.g., gender, age, ticket class) and survival.

Listed below are the 14 columns with a short rationalization:

• survived: Survived (1) or didn’t survive (0).
• pclass: Ticket class (1 = 1st class, 2 = 2nd class, 3 = third class).
• intercourse: Gender of the passenger.
• age: Age of the passenger (in years, could also be lacking).
• sibsp: Variety of siblings/spouses on board.
• parch: Variety of dad and mom/kids on board.
• fare: Fare paid by the passenger.
• embarked: Port of embarkation (C = Cherbourg, Q = Queenstown, S = Southampton).
• class: Ticket class as textual content (First, Second, Third). Corresponds to pclass.
• who: Categorization “man,” “girl,” “little one.”
• adult_male: Boolean subject: Was the passenger an grownup male (True/False)?
• deck: Cabin deck (typically lacking).
• embark_town: Metropolis of port of embarkation (Cherbourg, Queenstown, Southampton).
• alone: Boolean subject: Did the passenger journey alone (True/False)?

Optionally available for superior readers
If you wish to observe and consider your agent runs later, you should use LangSmith.

2) Outline instruments in important.py

Subsequent, we outline the varied instruments. To do that, we create a brand new Python file referred to as important.py and put it aside within the csv-agent folder as nicely. We add the next code to it:

# important.py
import os, json
import pandas as pd

# --- 0) Loading CSV ---
DF_PATH = "titanic.csv"
df = pd.read_csv(DF_PATH)

# --- 1) Defining instruments as small, concise instructions ---
# IMPORTANT: Instruments return strings (on this case, JSON strings) in order that the LLM sees clearly structured responses.

from langchain_core.instruments import software

@software
def tool_schema(dummy: str) -> str:
    """Returns column names and knowledge varieties as JSON."""
    schema = {col: str(dtype) for col, dtype in df.dtypes.gadgets()}
    return json.dumps(schema)

@software
def tool_nulls(dummy: str) -> str:
    """Returns columns with the variety of lacking values as JSON (solely columns with >0 lacking values)."""
    nulls = df.isna().sum()
    end result = {col: int(n) for col, n in nulls.gadgets() if n > 0}
    return json.dumps(end result)

@software
def tool_describe(input_str: str) -> str:
    """
    Returns describe() statistics.
    Optionally available: input_str can include a comma-separated listing of columns, e.g. "age, fare".
    """
    cols = None
    if input_str and input_str.strip():
        cols = [c.strip() for c in input_str.split(",") if c.strip() in df.columns]
    stats = df[cols].describe() if cols else df.describe()
    # describe() has a MultiIndex. Flatten it for the LLM to maintain it readable:
    return stats.to_csv(index=True)

After importing the mandatory packages, we load titanic.csv into df as soon as and outline three small, narrowly outlined instruments. Let’s take a better take a look at every of those instruments:

• tool_schema returns the column names and knowledge varieties as JSON. This provides us an outline of what we’re coping with and is normally step one in any knowledge evaluation. Even when a software doesn’t want enter (like schema), it should nonetheless settle for one argument, as a result of the agent at all times passes a string. We merely ignore it.
• tool_nulls counts lacking values per column and returns solely columns with lacking values.
• tool_describe calls df.describe(). You will need to word that this software solely works for numeric columns. Strings or Booleans, however, are ignored. This is a vital step within the sanity examine or EDA. This enables us to shortly see the imply, min, max, and so on. of the completely different columns. For giant CSVs, describe() can take a very long time. On this case, you possibly can combine df.pattern(n=10000) as sampling logic, for instance.

These instruments are the managed interfaces by way of which the LLM is allowed to entry the info. They’re deterministic and subsequently reproducible. Instruments ought to ideally be clear and restricted: In different phrases, they need to have just one operate or activity.

Why do we’d like instruments in any respect?

An LLM can generate textual content, but it surely can’t immediately “see” knowledge. To ensure that the LLM to work meaningfully with a CSV, we have to present interfaces. That’s precisely what instruments are for:

Instruments are small Python capabilities that the agent is allowed to name. As a substitute of constructing every thing free, we solely permit very particular, reproducible actions.

What precisely does the code do?

With the @software decorator, LangChain mechanically infers the software’s title, description and argument schema from the operate signature and docstring. This implies we solely want to write down the operate itself. LangChain takes care of the remainder.

• The mannequin passes arguments that match the software’s schema (typically JSON). On this tutorial we hold issues easy and settle for a single string argument (e.g., input_str: str or a dummy string we ignore).
• Instruments at all times return a string (textual content). JSON is right for structured knowledge, which we outline with return json.dumps(…).

This can be a multi-step thought course of. The LLM plans iteratively. As a substitute of responding immediately, it thinks step-by-step: it decides which software to name, interprets the end result, and will proceed till it has sufficient info to reply.

4) Registering instruments for LangChain in important.py

We add the code under to the identical important.py file to register the beforehand outlined instruments for the agent:

# --- 2) Registering instruments for LangChain ---

instruments = [tool_schema, tool_nulls, tool_describe]

With this code, we merely accumulate the embellished capabilities into an inventory. Every operate has already been transformed right into a LangChain software by the @software decorator.

5) Configuring LLM in important.py

Subsequent, we configure the LLM that the agent makes use of. Right here, you possibly can both use the variant for OpenAI or for an open-source software with Ollama.

I used OpenAI, which is why we first must set the API key:

At OpenAI, we create a brand new API key:

We then copy it immediately (it won’t be displayed later) and set it as an atmosphere variable within the terminal with the next command.

setx OPENAI_API_KEY "your_key”

You will need to restart cmd and reactivate .venv afterwards. We are able to use echo to examine whether or not an API key has been saved.

Now we add the next code to the top of important.py:

# --- 3) Configure LLM ---
# Possibility A: OpenAI (easy)
#   export OPENAI_API_KEY=...    # Home windows: setx OPENAI_API_KEY "YOUR_KEY"
#   Use a decrease temperature for extra secure software utilization
USE_OPENAI = bool(os.getenv("OPENAI_API_KEY"))

if USE_OPENAI:
    from langchain_openai import ChatOpenAI
    llm = ChatOpenAI(mannequin="gpt-4o-mini", temperature=0.1)
else:
    # Possibility B: Native with Ollama (be sure that to drag the mannequin first, e.g. 'ollama run llama3')
    from langchain_community.chat_models import ChatOllama
    llm = ChatOllama(mannequin="llama3.1:8b", temperature=0.1)

The code makes use of OpenAI if an OpenAI_API_KEY is out there, in any other case Ollama domestically.

We set the temperature to 0.1. This ensures that the responses are extra deterministic, which is vital for the following check.

We additionally use gpt-4o-mini because the LLM. This can be a light-weight mannequin from OpenAI with a give attention to software utilization.

Tip for Newbies:
The temperature determines how creatively an LLM responds. If we enter 0.0, it responds deterministically. Which means that the mannequin virtually at all times returns the identical reply when the enter is similar. That is good for structured duties akin to software utilization, code or info, for instance. If we specify 1.0, the mannequin responds creatively and with all kinds of choices. Which means that the mannequin varies extra and may counsel completely different formulations or options, which is sweet for brainstorming or textual content concepts, for instance.

6) Defining the agent’s conduct in important.py utilizing the coverage

On this step, we outline how the agent ought to behave. The system immediate units the coverage.

# --- 4) Slender Coverage/Immediate (Agent Conduct) ---
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

SYSTEM_PROMPT = (
    "You're a data-focused assistant. "
    "If a query requires info from the CSV, first use an applicable software. "
    "Use just one software name per step if potential. "
    "Reply concisely and in a structured manner. "
    "If no software matches, briefly clarify why.nn"
    "Accessible instruments:n{instruments}n"
    "Use solely these instruments: {tool_names}."
)

immediate = ChatPromptTemplate.from_messages(
    [
        ("system", SYSTEM_PROMPT),
        ("human", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)

_tool_desc = "n".be part of(f"- {t.title}: {t.description}" for t in instruments)
_tool_names = ", ".be part of(t.title for t in instruments)
immediate = immediate.partial(instruments=_tool_desc, tool_names=_tool_names)

First, we import ChatPromptTemplate to construction our agent’s immediate. An important a part of the code is the system immediate: it defines the coverage, i.e., the “guidelines of the sport” for the agent. In it, we outline that the agent could solely use one software per step, that it needs to be concise, and that it could solely use the instruments we’ve got outlined.

With the final two strains within the system immediate, we be sure that {instruments} lists all out there instruments with their descriptions and with {tool_names}, we be sure that the agent can solely use these names and can’t invent fantasy instruments.

As well as, we use MesagesPlaceholder(“agent_scratchpad”). That is the place the agent shops intermediate steps: The agent shops which instruments it has referred to as and which ends it has obtained. This enables it to proceed its personal chain of reasoning till it arrives at a last reply.

7) Create tool-calling agent in important.py

Within the final step, we outline the agent:

# --- 5) Create & Run Device-Calling Agent ---
from langchain.brokers import create_tool_calling_agent, AgentExecutor

agent = create_tool_calling_agent(llm=llm, instruments=instruments, immediate=immediate)
agent_executor = AgentExecutor(
    agent=agent,
    instruments=instruments,
    verbose=False,   # non-obligatory: True for debug logs
    max_iterations=3,
)

if __name__ == "__main__":
    user_query = "Which columns have lacking values? Checklist 'Column: Rely'."
    end result = agent_executor.invoke({"enter": user_query})
    print("n=== AGENT ANSWER ===")
    print(end result["output"])

With create_tool_calling_agent, we join our LLM, the instruments and the immediate to kind a tool-calling agent.

To make sure that the method runs easily, we use the AgentExecutor. It takes care of the so-called agent loop: The agent first plans what must be finished, then calls up a software, receives the end result and decides whether or not one other software is required or whether or not it could possibly present the ultimate reply. This cycle repeats till the result’s prepared.

With verbose=True, we will view the intermediate steps within the terminal, which is extraordinarily useful for debugging. For instance, we will see which software was referred to as when or what knowledge was returned. If every thing is working easily, we will additionally set it to =False to maintain the output clearer.

With max_iterations=3, we restrict what number of reasoning–software–response cycles the agent could carry out. This helps stop infinite loops or extreme software calls. In our instance, the agent may fairly name schema → nulls → describe earlier than answering.

With the final a part of the code, the agent is executed with the pattern enter “Which columns have lacking values?”. The result’s printed within the terminal.

Tip for newbies:
if title == “important”: is an ordinary Python sample: If we execute the file immediately within the terminal with python important.py, the code on this block will probably be began. Nonetheless, if we solely import the file (e.g., later within the mini_eval.py file), this block is skipped. This enables us to make use of the file as a standalone script or reuse it as a module in different initiatives.

8) Run the script: Run the file important.py within the terminal.

Now we enter python important.py within the terminal to start out the agent. We then see the ultimate reply within the terminal:

Mini-Analysis

Lastly, we wish to examine our agent, which we do with a small analysis. This ensures that the agent behaves appropriately and doesn’t introduce any “regressions” after we change one thing within the code afterward.

On the finish of important.py, we add the code under:

def ask_agent(question: str) -> str:
    return agent_executor.invoke({"enter": question})["output"]

With ask_agent, we encapsulate the agent name in a operate that merely returns a string. This enables us to name the agent later from different recordsdata.

The decrease block ensures {that a} check run is carried out when important.py is named immediately. If, however, we import important into one other file, solely the operate is offered.

Now we create the mini_eval.py file and insert the next code:

# mini_eval.py

from important import ask_agent

checks = [
    ("Which columns have missing values?", ["age", "embarked", "deck", "embark_town"]),
    ("Present me the primary 3 columns with their knowledge varieties.", ["survived", "pclass", "sex"]),
    ("Give me a statistical abstract of the 'age' column.", ["mean", "min", "max"]),
]

def handed(q, out, must_include):
    textual content = out.decrease()
    return all(any(tok in textual content for tok in (m.decrease(), str(m).decrease())) for m in must_include)

if __name__ == "__main__":
    okay = 0
    for q, should in checks:
        out = ask_agent(q)
        end result = handed(q, out, should)
        print(f"[{'OK' if result else 'FAIL'}] {q}n{out}n")
        okay += int(end result)
    print(f"Handed {okay}/{len(checks)}")

Within the code, we outline three check instances. Every check consists of a query for the agent and an inventory of key phrases that should seem within the reply. The handed() operate checks whether or not these key phrases are included.

Anticipated check outcomes

• Check 1: “Which columns have lacking values?”
  Anticipated: Output mentions age, deck, embarked, embark_town.
• Check 2: “Present me the primary 3 columns with their knowledge varieties.” Anticipated: Output incorporates survived, pclass, intercourse with varieties akin to int64 or object.
• Check 3: “Give me a statistical abstract of the ‘age’ column.” Anticipated output: Output incorporates imply ≈ 29.7, min = 0.42, max = 80.

If every thing runs appropriately, the script reviews “Handed 3/3” on the finish.

We get this output within the terminal. So the check works:

You’ll find the code & the csv within the repo on GitHub.

On my Substack Information Science Espresso, I share sensible guides and bite-sized updates from the world of Information Science, Python, AI, Machine Studying, and Tech — made for curious minds like yours.

Take a look and subscribe on Medium or on Substack if you wish to keep within the loop.

Last Ideas – Pitfalls, ideas and subsequent steps

LangChain could be very sensible for this instance as a result of it already contains and properly illustrates your entire agent loop (planning, software calling, management). For small or clearly structured duties, nevertheless, options akin to pure operate calling (e.g., by way of the OpenAI API) or basic EDA frameworks like Nice Expectations is perhaps enough. That mentioned, LangChain does add some overhead. In the event you solely want fastened EDA checks, a plain Python script could be leaner and quicker. LangChain is very worthwhile whenever you wish to lengthen issues flexibly or orchestrate a number of instruments and brokers.

When working with brokers, there are some things you must be mindful:

One frequent pitfall is unclear software descriptions: If the descriptions are too imprecise, the mannequin can simply select the flawed software (misrouting). With exact and concrete descriptions, we will significantly scale back this.

One other vital level is testing: Even a small mini-evaluation with three easy checks is useful in detecting regressions (errors that keep unnoticed as a consequence of subsequent modifications) at an early stage.

It’s additionally price beginning small: In our instance, we solely labored with three clearly outlined instruments, however now we all know that they work reliably.

With regard to this agent, it may additionally be helpful to include sampling (for instance, df.pattern(n=10000)) for very massive CSV recordsdata to keep away from efficiency points. Remember that LLM brokers can even turn into expensive if each query triggers a number of software calls.

On this article, we constructed a single agent that checks CSV recordsdata. In apply, a number of brokers would typically work collectively: For instance, one agent might guarantee knowledge high quality whereas a second agent creates visualizations. Such multi-agent techniques are the following step in fixing extra advanced duties.

As a subsequent step, we might additionally incorporate LangGraph to increase the agent loop with states and orchestration. This is able to permit us to assemble brokers as in a flowchart, together with interruptions, reminiscence, or extra versatile management logic.

Lastly, in our instance, we manually outlined the three instruments schema, nulls, and describe. With the Mannequin Context Protocol (MCP), we might join instruments in a standardized manner. For instance, we might join databases, APIs or IDEs.

The place Can You Proceed Studying?