Wrapped LLM as a garak generator by Nakul-Rajpal · Pull Request #1382 · NVIDIA/garak

Nakul-Rajpal · 2025-09-25T22:54:54Z

Wrapped the Python Library LLM (for OpenAI, Anthropic’s Claude, Google’s Gemini etc) as a garak generator.

Fixes Issue #463

Wrapped the Python Library LLM (for OpenAI, Anthropic’s Claude, Google’s Gemini etc) as a garak generator.

Nakul-Rajpal · 2025-09-25T22:55:04Z

@leondz Please check

leondz · 2025-09-26T07:12:18Z

thanks, will take a look!

leondz · 2025-09-26T08:17:50Z

@Nakul-Rajpal This isn't passing tests - can you amend?

Nakul-Rajpal · 2025-09-26T18:24:56Z

@leondz It should be good now? The tests were failing due to me not adding the llm library to the requirements so it ran without the module.

Nakul-Rajpal · 2025-09-29T16:09:36Z

@leondz Should be ready to go now; really sorry about the errors before I request to do another issue I should familiarize myself with the repo further.

leondz · 2025-09-29T16:10:51Z

Yeah, it's in the review queue, thank you

jmartin-tech

This looks like a great start. I noted a few edge case and a mismatch in how a system_prompt is handled.

Please take a look, happy to offer further detail or answer question about how things flow.

jmartin-tech · 2025-09-29T13:54:52Z

garak/generators/llm.py

+        if self.system:
+            prompt_kwargs["system"] = self.system


Current system prompt support in garak is tied to the conversation passed as part of prompt. The DEFAULT_PARAMS entry here should likely be removed in favor of extracting the system_prompt from the prompt via prompt.last_message("system"). That is if passing a conversation that includes the system message would not apply it.

jmartin-tech · 2025-09-30T13:57:56Z

garak/generators/llm.py

+        "max_tokens": None,
+        "top_p": None,
+        "stop": [],
+        "system": None,


Remove, the system prompt is set via the run configuration and pass to generators as part of the prompt conversation.

Suggested change

"system": None,

jmartin-tech · 2025-09-30T14:03:13Z

garak/generators/llm.py

+        if self.max_tokens is not None:
+            prompt_kwargs["max_tokens"] = self.max_tokens
+        if self.temperature is not None:
+            prompt_kwargs["temperature"] = self.temperature
+        if self.top_p is not None:
+            prompt_kwargs["top_p"] = self.top_p
+        if self.stop:
+            prompt_kwargs["stop"] = self.stop


None == False and all keys defined in DEFAULT_PARAMS will exist on self.

Suggested change

if self.max_tokens is not None:

prompt_kwargs["max_tokens"] = self.max_tokens

if self.temperature is not None:

prompt_kwargs["temperature"] = self.temperature

if self.top_p is not None:

prompt_kwargs["top_p"] = self.top_p

if self.stop:

prompt_kwargs["stop"] = self.stop

if self.max_tokens:

prompt_kwargs["max_tokens"] = self.max_tokens

if self.temperature:

prompt_kwargs["temperature"] = self.temperature

if self.top_p:

prompt_kwargs["top_p"] = self.top_p

if self.stop:

prompt_kwargs["stop"] = self.stop

jmartin-tech · 2025-09-30T14:16:30Z

garak/generators/llm.py

+
+        This calls model.prompt() once per generation and materializes the text().
+        """
+        text_prompt = prompt.last_message().text


This does not grab out the full conversation. There is an existing helper function in the base class Generator._conversation_to_list() that will format the garak Conversation object as a list of dictionaries meeting the HuggingFace and OpenAI conversation list. Looking at how the llm library handles what it considers to be conversation I don't know if there is a way to load a prefilled history in a similar pattern to how chat completions APIs for other generators are working.

For best adoption, this generator should at least validate the conversation has at most one user and one system message to know if the prompt passed will be fully processed during inference.

jmartin-tech · 2025-09-30T14:18:46Z

garak/generators/llm.py

+        "temperature": None,
+        "max_tokens": None,


temperature and max_tokens are already in Generator.DEFAULT_PARAMS is there a reason to include here?

Suggested change

"temperature": None,

"max_tokens": None,

This question is still pending, is there a reason that max_tokens is still overridden here? This deviates from other generators fragmenting expectations as the default inference generation limits will not be consistent with other generators. This is not a blocking issue simply one that needs to be explained to be sure this is the best approach for users of this generator.

leondz

Looks pretty good. Requests to add a pattern supporting parallelisation, some renaming, and vars ensuring test consistency

garak/generators/llm.py

leondz · 2025-10-09T04:42:06Z

tests/generators/test_llm.py

+# SPDX-FileCopyrightText: Portions Copyright (c) 2025 NVIDIA CORPORATION &
+#                         AFFILIATES. All rights reserved.


Suggested change

# SPDX-FileCopyrightText: Portions Copyright (c) 2025 NVIDIA CORPORATION &

# AFFILIATES. All rights reserved.

# SPDX-FileCopyrightText: Portions Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.

pyproject.toml

leondz · 2025-10-09T04:52:50Z

tests/generators/test_llm.py

+def test_generate_returns_message(cfg, fake_llm):
+    gen = LLMGenerator(name="alias", config_root=cfg)
+
+    conv = Conversation([Turn("user", Message(text="ping"))])


Suggested change

conv = Conversation([Turn("user", Message(text="ping"))])

test_txt = "ping"

conv = Conversation([Turn("user", Message(text=test_txt))])

leondz · 2025-10-09T04:53:00Z

tests/generators/test_llm.py

+    assert out[0].text == "OK_FAKE"
+
+    prompt_text, kwargs = fake_llm.calls[0]
+    assert prompt_text == "ping"


Suggested change

assert prompt_text == "ping"

assert prompt_text == test_txt

leondz · 2025-10-09T04:53:47Z

tests/generators/test_llm.py

+    gen.temperature = 0.2
+    gen.max_tokens = 64
+    gen.top_p = 0.9
+    gen.stop = ["\n\n"]
+    gen.system = "you are testy"


use vars for these values (and the checks later)

leondz · 2025-10-09T04:54:40Z

tests/generators/test_llm.py

+    assert kwargs["temperature"] == 0.2
+    assert kwargs["max_tokens"] == 64
+    assert kwargs["top_p"] == 0.9
+    assert kwargs["stop"] == ["\n\n"]
+    assert kwargs["system"] == "you are testy"


vars here. could do a list assignment / check likex,y = 1,2 for brevity

leondz · 2025-10-09T04:59:13Z

tests/generators/test_llm.py

+    class BoomModel:
+        def prompt(self, *a, **k):
+            raise RuntimeError("boom")
+    monkeypatch.setattr(llm, "get_model", lambda *a, **k: BoomModel())


jmartin-tech

Some tweaks to ensure consistent behaviour.

Code suggestions are untested.

garak/generators/llm.py

jmartin-tech · 2025-10-17T13:40:20Z

garak/generators/llm.py

+        prompt_kwargs = {
+            key: getattr(self, key)
+            for key in ("max_tokens", "temperature", "top_p")
+            if getattr(self, key) is not None
+        }
+        if self.stop:
+            prompt_kwargs["stop"] = self.stop


Could this inspect the accepted arguments to self.target.prompt() vs a hard coded list here? Something similar exists in the OpenAICompatible class, where we collect all options set on the generator that the target API accepts.

Adjusted LLMGenerator, Updated generator tests accordingly.

garak/generators/llm.py

tests/generators/test_llm.py

- Remove duplicate documentation in llm.py - Remove duplicate license header in test_llm.py - Add InjectLeet to CLEAR_TRIGGER_PROBES to fix CI failure (Leetspeak doesn't encode special characters like <>/. so triggers appear in prompts)

Signed-off-by: Nakul Rajpal <66713174+Nakul-Rajpal@users.noreply.github.com>

Nakul-Rajpal · 2025-12-17T23:28:24Z

@jmartin-tech @leondz Hi. I removed the duplicated documentation and license header in the test file. I also fixed the CI test failure. Everything should work now.

Nakul-Rajpal · 2025-12-31T07:56:59Z

@leondz @jmartin-tech Just wanted to check whether this can be merged.

Signed-off-by: Jeffrey Martin <jemartin@nvidia.com>

garak/generators/llm.py

leondz

Almost there. Some doubts around multiple generation & parallelisation setup

leondz · 2026-01-12T10:30:28Z

garak/generators/llm.py

+        "top_p": None,
+        "stop": [],
+    }
+


Looks like this generator is set with two defaults True - supports_multiple_generations and parallel_capable. I'm not sure either of these are sensible in this case.

Defaults are currently:

supports_multiple_generations = False parallel_capable = True

If these are left in place the implementation here handles multiprocessing support, though maybe it should not if using an ollama or some other locally executed model stack is specified.

Since this generator only supports one-shot single message prompts I think the setting both to False may be a valid conservative way to proceed.

leondz · 2026-01-12T10:31:00Z

garak/generators/llm.py

+        try:
+            response = self.target.prompt(text_prompt, **prompt_kwargs)
+            out = response.text()
+            return [Message(out)]


ignores generations_this_call, which should be respected

leondz · 2026-01-12T10:31:15Z

garak/generators/llm.py

+            return [Message(out)]
+        except Exception as e:
+            logging.error("`llm` generation failed: %s", repr(e))
+            return [None]


ignores generations_this_call, which should be respected

leondz · 2026-01-12T10:32:26Z

tests/generators/test_llm.py

+
+

can we get a test on multiple generation, i.e. _call_model with generations_this_call > 1 ?

supports_multiple_generations is currently False so generations_this_call would always be 1.

Wrapped LLM as a garak generator

5f0b1af

Wrapped the Python Library LLM (for OpenAI, Anthropic’s Claude, Google’s Gemini etc) as a garak generator.

Nakul-Rajpal added 2 commits September 26, 2025 10:01

Added LLM library Dependency

a7d109b

Added LLM library to requirements.

6a54502

Nakul-Rajpal added 2 commits September 26, 2025 15:30

Add LLM Docs

65645dc

Added LLM library to generators.rst

094141d

jmartin-tech requested changes Oct 1, 2025

View reviewed changes

leondz requested changes Oct 9, 2025

View reviewed changes

leondz added the generators Interfaces with LLMs label Oct 12, 2025

Added Recommended Changes

7f20877

Nakul-Rajpal requested review from jmartin-tech and leondz October 15, 2025 22:57

Merge branch 'main' into generator-wrapLLM

f2d730e

jmartin-tech requested changes Oct 23, 2025

View reviewed changes

Added Recommended Changes

f87c2f3

Adjusted LLMGenerator, Updated generator tests accordingly.

jmartin-tech reviewed Nov 12, 2025

View reviewed changes

garak/generators/llm.py Outdated Show resolved Hide resolved

jmartin-tech reviewed Nov 12, 2025

View reviewed changes

tests/generators/test_llm.py Outdated Show resolved Hide resolved

Nakul-Rajpal added 2 commits December 17, 2025 15:25

Fix review feedback and CI test failure

655dbb3

- Remove duplicate documentation in llm.py - Remove duplicate license header in test_llm.py - Add InjectLeet to CLEAR_TRIGGER_PROBES to fix CI failure (Leetspeak doesn't encode special characters like <>/. so triggers appear in prompts)

Merge branch 'main' into generator-wrapLLM

11ab4a0

Signed-off-by: Nakul Rajpal <66713174+Nakul-Rajpal@users.noreply.github.com>

Nakul-Rajpal requested a review from jmartin-tech December 18, 2025 19:03

jmartin-tech added 2 commits January 2, 2026 13:30

Merge 'main' into generator-wrapLLM

5753afa

updates to support lazy load of extra deps

690e183

Signed-off-by: Jeffrey Martin <jemartin@nvidia.com>

jmartin-tech reviewed Jan 7, 2026

View reviewed changes

garak/generators/llm.py Show resolved Hide resolved

leondz requested changes Jan 12, 2026

View reviewed changes

PR changes

b19a9ab

Nakul-Rajpal requested review from jmartin-tech and leondz February 20, 2026 03:33

		# SPDX-FileCopyrightText: Portions Copyright (c) 2025 NVIDIA CORPORATION &
		# AFFILIATES. All rights reserved.

	conv = Conversation([Turn("user", Message(text="ping"))])
	test_txt = "ping"
	conv = Conversation([Turn("user", Message(text=test_txt))])

Conversation

Nakul-Rajpal commented Sep 25, 2025

Uh oh!

Nakul-Rajpal commented Sep 25, 2025

Uh oh!

leondz commented Sep 26, 2025

Uh oh!

leondz commented Sep 26, 2025

Uh oh!

Nakul-Rajpal commented Sep 26, 2025

Uh oh!

Nakul-Rajpal commented Sep 29, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

leondz commented Sep 29, 2025

Uh oh!

jmartin-tech left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

leondz left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jmartin-tech left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Nakul-Rajpal commented Dec 17, 2025

Uh oh!

Nakul-Rajpal commented Dec 31, 2025

Uh oh!

Uh oh!

leondz left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Nakul-Rajpal commented Sep 29, 2025 •

edited

Loading