Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
68 commits
Select commit Hold shift + click to select a range
1b3f67a
support agent use case
AnilSorathiya Jun 24, 2025
723fcab
wrapper function for agent
AnilSorathiya Jun 24, 2025
28d9fbb
ragas metrics
AnilSorathiya Jun 30, 2025
ecf8e09
update ragas metrics
AnilSorathiya Jun 30, 2025
53e8879
fix lint error
AnilSorathiya Jun 30, 2025
1662368
create helper functions
AnilSorathiya Jul 1, 2025
cc84cbc
Merge branch 'main' into anilsorathiya/sc-10863/add-support-for-llm-a…
AnilSorathiya Jul 2, 2025
6f09780
delete old notebook
AnilSorathiya Jul 2, 2025
0bb731e
update description for each section
AnilSorathiya Jul 2, 2025
e758979
simplify agent
AnilSorathiya Jul 9, 2025
7c35cfe
simple demo notebook using langchain agent
AnilSorathiya Jul 10, 2025
9bb70e9
Update description of the simplified langgraph agent demo notebook
AnilSorathiya Jul 10, 2025
894d52a
add brief description to tests
AnilSorathiya Jul 14, 2025
d86a9af
add brief description to tests
AnilSorathiya Jul 14, 2025
884000f
Allow dict return type predict_fn
AnilSorathiya Jul 17, 2025
fbd5aa9
update notebook and refactor utils
AnilSorathiya Jul 18, 2025
daceabf
lint fix
AnilSorathiya Jul 18, 2025
5f8823a
Merge branch 'main' into anilsorathiya/sc-11324/extend-the-predict-fn…
AnilSorathiya Jul 18, 2025
70a5636
fix the test failure
AnilSorathiya Jul 18, 2025
33b06fb
new unit tests for multiple columns return in assign_predictions
AnilSorathiya Jul 18, 2025
8e12bd2
update notebooks to return multiple values in predict_fn
AnilSorathiya Jul 18, 2025
e38929d
general plotting and stats tests
AnilSorathiya Jul 23, 2025
e900a65
clear output
AnilSorathiya Jul 23, 2025
a08e881
Merge branch 'main' into anilsorathiya/sc-11380/add-generlize-plots-a…
AnilSorathiya Jul 24, 2025
16f4700
remove duplicate tests
AnilSorathiya Jul 24, 2025
bb9f9af
update notebook
AnilSorathiya Jul 24, 2025
5078a7a
Integration between deepeval and validmind
AnilSorathiya Jul 25, 2025
2eb6abb
Merge branch 'main' into anilsorathiya/sc-11452/support-for-the-deepe…
AnilSorathiya Aug 12, 2025
ad0b719
add MetricValues class for metric return type
AnilSorathiya Aug 15, 2025
94ca006
Return MetricValues in the unit tests
AnilSorathiya Aug 15, 2025
c4c885a
update all the unit metric tests
AnilSorathiya Aug 15, 2025
a1f3220
add unit tests for MetricValues class
AnilSorathiya Aug 15, 2025
1a7d0b6
update result to support MetricValues for unit metric tests
AnilSorathiya Aug 15, 2025
1d785ba
add copyright statement
AnilSorathiya Aug 15, 2025
271e85b
add deepeval lib as an extra dependency
AnilSorathiya Aug 15, 2025
f806fc6
fix the error
AnilSorathiya Aug 15, 2025
61c7ef6
demo draft change
AnilSorathiya Aug 18, 2025
b646d0b
demo draft change
AnilSorathiya Aug 18, 2025
dda4ced
fix api issue
AnilSorathiya Aug 18, 2025
dd8e0df
Merge branch 'main' into anilsorathiya/sc-11452/support-for-the-deepe…
AnilSorathiya Aug 21, 2025
81249c2
separate unit metrics and row metrics
AnilSorathiya Aug 22, 2025
794a322
draft notebook
AnilSorathiya Aug 22, 2025
a27bc48
Merge branch 'main' into anilsorathiya/sc-11452/support-for-the-deepe…
AnilSorathiya Aug 22, 2025
84dfa2f
update assign_score notebook
AnilSorathiya Aug 22, 2025
7aa2acc
update assign score notebook
AnilSorathiya Sep 1, 2025
247eacc
rename notebook
AnilSorathiya Sep 1, 2025
394c57c
update deepeval and VM integration notebook
AnilSorathiya Sep 1, 2025
66cef34
Demo Notebook for Agent Testing/Documentation
AnilSorathiya Sep 4, 2025
2177b0d
Demo Notebook for Agent Testing/Documentation
AnilSorathiya Sep 4, 2025
385b8a5
Merge branch 'main' into anilsorathiya/sc-11945/demo-notebook-for-age…
AnilSorathiya Sep 23, 2025
c4aebcd
fix lint error
AnilSorathiya Sep 23, 2025
c22106f
remove duplicate tests
AnilSorathiya Sep 23, 2025
e371c26
remove metricValues class
AnilSorathiya Sep 23, 2025
5c1f604
add copyright statement
AnilSorathiya Sep 23, 2025
6766adb
update pyproject for numpy dependency
AnilSorathiya Sep 23, 2025
61d1b20
update banking tools
AnilSorathiya Sep 24, 2025
4f44143
add more cases to dataset
AnilSorathiya Sep 24, 2025
8053fa3
more tests in demo notebook
AnilSorathiya Sep 24, 2025
f7ee917
fix tests
AnilSorathiya Sep 24, 2025
ef1bd83
remove old notebooks
AnilSorathiya Sep 24, 2025
c9bd908
update notebook
AnilSorathiya Sep 25, 2025
48d5504
move import top of the file
AnilSorathiya Sep 25, 2025
4bb7f96
update notebook
AnilSorathiya Sep 25, 2025
47cf614
uncommit the package dependency change
AnilSorathiya Sep 26, 2025
80d258a
update introduction and move notebook
AnilSorathiya Sep 26, 2025
6d59490
log dataset
AnilSorathiya Sep 26, 2025
a82c7c2
uncommit poetry.lock
AnilSorathiya Sep 26, 2025
15d57f1
remove output
AnilSorathiya Sep 26, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1,074 changes: 0 additions & 1,074 deletions notebooks/agents/langchain_agent_simple_demo.ipynb

This file was deleted.

29 changes: 0 additions & 29 deletions notebooks/agents/langchain_utils.py

This file was deleted.

1,488 changes: 0 additions & 1,488 deletions notebooks/agents/langgraph_agent_demo.ipynb

This file was deleted.

1,005 changes: 0 additions & 1,005 deletions notebooks/agents/langgraph_agent_simple_demo.ipynb

This file was deleted.

161 changes: 161 additions & 0 deletions notebooks/code_samples/agents/banking_test_dataset.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,161 @@
import pandas as pd
import uuid

# Banking-specific test dataset for retail and commercial banking
# tools: credit_risk_analyzer, customer_account_manager, fraud_detection_system
banking_test_dataset = pd.DataFrame([
{
"input": "Analyze credit risk for a $50,000 personal loan application with $75,000 annual income, $1,200 monthly debt, and 720 credit score",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["LOW RISK", "MEDIUM RISK", "APPROVE", "debt-to-income ratio", "19.2%", "risk score", "720", "probability of default", "2.5%"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Evaluate credit risk for a business loan of $250,000 with monthly revenue of $85,000 and existing debt of $45,000",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["MEDIUM RISK", "HIGH RISK", "business loan", "debt service coverage ratio", "1.8", "annual revenue", "$1,020,000", "risk score", "650"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Check account balance for checking account 12345",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["balance", "$3,247.82", "account information", "John Smith", "checking account", "available balance", "$3,047.82"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Analyze fraud risk for a $15,000 wire transfer from customer 67890 to Nigeria",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["HIGH RISK", "fraud score", "87", "geographic risk", "95%", "amount", "$15,000", "block transaction", "confidence", "92%"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Recommend banking products for customer 11111 with $150,000 in savings and 720 credit score",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["product recommendations", "premium accounts", "investment services", "line of credit", "$50,000", "savings rate", "4.25%"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Investigate suspicious transactions totaling $75,000 across multiple accounts in the last week",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["suspicious activity", "pattern analysis", "transaction monitoring", "VERY HIGH RISK", "alert", "fraud score", "94", "total amount", "$75,000"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Assess credit risk for a $1,000,000 commercial real estate loan with $500,000 annual business income",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["HIGH RISK", "VERY HIGH RISK", "business loan", "commercial", "risk assessment", "loan-to-value", "66.7%", "debt service coverage", "2.0"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Process a $2,500 deposit to savings account 67890",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["transaction processed", "deposit", "$2,500", "new balance", "$15,847.32", "transaction ID", "TXN-789456123"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Review credit card application for customer with 580 credit score, $42,000 annual income, and recent bankruptcy",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["VERY HIGH RISK", "DECLINE", "bankruptcy", "credit score", "580", "probability of default", "35%", "debt-to-income", "78%"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Update customer contact information and address for account holder 22334",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["customer updated", "address change", "contact information", "profile updated", "customer ID", "22334"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Detect potential fraud in multiple small transactions under $500 happening rapidly from different locations",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["velocity fraud", "geographic anomaly", "HIGH RISK", "transaction pattern", "card fraud", "velocity score", "89", "locations", "4"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Close dormant account 98765 and transfer remaining balance to active checking account",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["account closed", "balance transfer", "$487.63", "dormant account", "transaction completed", "account ID", "98765"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Assess credit risk for auto loan of $35,000 for customer with 650 credit score, $55,000 income, and no previous auto loans",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["MEDIUM RISK", "auto loan", "first-time borrower", "acceptable risk", "interest rate", "6.75%", "monthly payment", "$574"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Flag unusual ATM withdrawals of $500 every hour for the past 6 hours from account 44556",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["velocity pattern", "ATM fraud", "HIGH RISK", "card compromise", "unusual pattern", "total withdrawn", "$3,000", "frequency", "6", "transactions"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Open new business checking account for LLC with $25,000 initial deposit and setup online banking",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["business account", "new account", "online banking setup", "LLC registration", "account opened", "initial deposit", "$25,000", "account number", "987654321"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Evaluate creditworthiness for student loan refinancing of $85,000 with recent graduation and $65,000 starting salary",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["student loan", "refinancing", "MEDIUM RISK", "recent graduate", "debt consolidation", "new rate", "4.5%", "monthly payment", "$878"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Investigate merchant transactions showing unusual chargeback patterns and potential money laundering",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["merchant fraud", "chargeback analysis", "money laundering", "VERY HIGH RISK", "compliance alert", "chargeback rate", "15.3%", "risk score", "96"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Set up automatic bill pay for customer 77889 for utilities, mortgage, and insurance payments",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["automatic payments", "bill pay setup", "recurring transactions", "payment scheduling", "total monthly", "$2,847", "customer ID", "77889"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Analyze credit risk for line of credit increase from $10,000 to $25,000 for existing customer with payment history",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["credit limit increase", "LOW RISK", "payment history", "existing customer", "new limit", "$25,000", "utilization", "12%"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
},
{
"input": "Review suspicious cryptocurrency exchange transactions totaling $200,000 over 3 days from business account",
"expected_tools": ["fraud_detection_system"],
"possible_outputs": ["cryptocurrency", "large transactions", "business account", "HIGH RISK", "regulatory concern", "total amount", "$200,000", "risk score", "91"],
"session_id": str(uuid.uuid4()),
"category": "fraud_detection"
},
{
"input": "Process stop payment request for check #1234 and issue new checks for customer account 55667",
"expected_tools": ["customer_account_manager"],
"possible_outputs": ["stop payment", "check services", "new checks", "payment blocked", "customer service", "check amount", "$1,247.50", "account", "55667"],
"session_id": str(uuid.uuid4()),
"category": "account_management"
},
{
"input": "Evaluate mortgage pre-approval for $450,000 home purchase with 20% down payment, 780 credit score, and $125,000 household income",
"expected_tools": ["credit_risk_analyzer"],
"possible_outputs": ["mortgage pre-approval", "LOW RISK", "excellent credit", "strong income", "home purchase", "approved amount", "$450,000", "interest rate", "3.75%", "monthly payment", "$2,083"],
"session_id": str(uuid.uuid4()),
"category": "credit_risk"
}
])
Loading
Loading