Skip to content
Merged
Changes from all commits
Commits
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
28 changes: 28 additions & 0 deletions content/en/security/ai_guard/setup/automatic_integrations.md
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,12 @@ AI Guard can automatically evaluate LLM calls made through supported AI ecosyste
| [AI SDK](#nodejs) | v6 | >= 5.95.0 |
| [OpenAI](#nodejs) | >= 4.87.0 | >= 5.105.0 |

{{% /tab %}}
{{% tab "Ruby" %}}
| Package | Supported Versions | SDK Version |
|----------------------------------|--------------------|-------------|
| [RubyLLM](#ruby) | >= 1.0.0 | >= 2.28.0 |

{{% /tab %}}
{{< /tabs >}}

Expand Down Expand Up @@ -142,6 +148,28 @@ AI Guard automatically evaluates the following OpenAI operations:
{{% /tab %}}
{{< /tabs >}}

### Ruby

{{< tabs >}}
{{% tab "RubyLLM" %}}
The [RubyLLM][1] integration automatically applies AI Guard evaluations to chat messages and tool calls.

#### Traced operations

AI Guard automatically evaluates the following RubyLLM operations:

- [Chat][2]:
- `RubyLLM::Chat#ask`
- `RubyLLM::Chat#complete`
Comment thread
y9v marked this conversation as resolved.
- [Tool calling][3]:
- `RubyLLM::Chat#handle_tool_calls`

[1]: https://rubyllm.com/
[2]: https://rubyllm.com/chat/
[3]: https://rubyllm.com/tools/
{{% /tab %}}
{{< /tabs >}}

## Further reading

{{< partial name="whats-next/whats-next.html" >}}
Loading