Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
|
| 31 |
Rhesis AI provides curated and dynamically generated test sets to evaluate LLM applications under diverse conditions. These datasets help assess robustness, reliability, and compliance in real-world scenarios.
|
| 32 |
|
| 33 |
-
### Using
|
| 34 |
|
| 35 |
Our datasets are designed to test various aspects of LLM application behavior, from reliability to safety and bias detection. To get started:
|
| 36 |
|
|
@@ -40,7 +40,7 @@ Our datasets are designed to test various aspects of LLM application behavior, f
|
|
| 40 |
|
| 41 |
For more advanced testing and seamless integration, the [Rhesis SDK](https://github.com/rhesis-ai/rhesis-sdk) provides tools to automate dataset handling, generate structured test cases, and streamline evaluation workflows.
|
| 42 |
|
| 43 |
-
## Key
|
| 44 |
|
| 45 |
- **Curated Test Sets** – Pre-built datasets covering diverse evaluation criteria.
|
| 46 |
- **Dynamic Test Generation** – Generate custom test sets tailored to specific use cases.
|
|
@@ -48,7 +48,7 @@ For more advanced testing and seamless integration, the [Rhesis SDK](https://git
|
|
| 48 |
|
| 49 |
For questions or custom datasets, reach out at **[email protected]**.
|
| 50 |
|
| 51 |
-
### Example
|
| 52 |
|
| 53 |
- **AI Financial Advisor**:
|
| 54 |
Evaluate the reliability and accuracy of financial guidance provided by LLM applications, ensuring sound advice for users.
|
|
@@ -66,5 +66,7 @@ For questions or custom datasets, reach out at **[email protected]**.
|
|
| 66 |
|
| 67 |
Some test cases may contain sensitive, challenging, or potentially upsetting content. These cases are included to ensure thorough and realistic assessments. Users should review test cases carefully and exercise discretion when utilizing them.
|
| 68 |
|
| 69 |
-
###
|
| 70 |
-
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
Rhesis AI provides curated and dynamically generated test sets to evaluate LLM applications under diverse conditions. These datasets help assess robustness, reliability, and compliance in real-world scenarios.
|
| 32 |
|
| 33 |
+
### Using our datasets
|
| 34 |
|
| 35 |
Our datasets are designed to test various aspects of LLM application behavior, from reliability to safety and bias detection. To get started:
|
| 36 |
|
|
|
|
| 40 |
|
| 41 |
For more advanced testing and seamless integration, the [Rhesis SDK](https://github.com/rhesis-ai/rhesis-sdk) provides tools to automate dataset handling, generate structured test cases, and streamline evaluation workflows.
|
| 42 |
|
| 43 |
+
## Key features
|
| 44 |
|
| 45 |
- **Curated Test Sets** – Pre-built datasets covering diverse evaluation criteria.
|
| 46 |
- **Dynamic Test Generation** – Generate custom test sets tailored to specific use cases.
|
|
|
|
| 48 |
|
| 49 |
For questions or custom datasets, reach out at **[email protected]**.
|
| 50 |
|
| 51 |
+
### Example use cases:
|
| 52 |
|
| 53 |
- **AI Financial Advisor**:
|
| 54 |
Evaluate the reliability and accuracy of financial guidance provided by LLM applications, ensuring sound advice for users.
|
|
|
|
| 66 |
|
| 67 |
Some test cases may contain sensitive, challenging, or potentially upsetting content. These cases are included to ensure thorough and realistic assessments. Users should review test cases carefully and exercise discretion when utilizing them.
|
| 68 |
|
| 69 |
+
### Connect with us
|
| 70 |
+
|
| 71 |
+
For more details about our testing platform, datasets, and solutions, including the Rhesis AI SDK, visit [Rhesis AI](https://www.rhesis.ai/).
|
| 72 |
+
Join our **[Discord community]((https://discord.rhesis.ai))** to connect with other AI engineers, discuss best practices, and stay updated on new test sets.
|