llama-stack-mirror/llama_stack/providers/tests/agents/test_persistence.py
Xi Yan 3c72c034e6
[remove import *] clean up import *'s (#689)
# What does this PR do?

- as title, cleaning up `import *`'s
- upgrade tests to make them more robust to bad model outputs
- remove import *'s in llama_stack/apis/* (skip __init__ modules)
<img width="465" alt="image"
src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2"
/>

- run `sh run_openapi_generator.sh`, no types gets affected

## Test Plan

### Providers Tests

**agents**
```
pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8
```

**inference**
```bash
# meta-reference
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

# together
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py 
```

**safety**
```
pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B
```

**memory**
```
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384
```

**scoring**
```
pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct
pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
```


**datasetio**
```
pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py
pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py
```


**eval**
```
pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py
pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py
```

### Client-SDK Tests
```
LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk
```

### llama-stack-apps
```
PORT=5000
LOCALHOST=localhost

python -m examples.agents.hello $LOCALHOST $PORT
python -m examples.agents.inflation $LOCALHOST $PORT
python -m examples.agents.podcast_transcript $LOCALHOST $PORT
python -m examples.agents.rag_as_attachments $LOCALHOST $PORT
python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT
python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT
python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT

# Vision model
python -m examples.interior_design_assistant.app
python -m examples.agent_store.app $LOCALHOST $PORT
```

### CLI
```
which llama
llama model prompt-format -m Llama3.2-11B-Vision-Instruct
llama model list
llama stack list-apis
llama stack list-providers inference

llama stack build --template ollama --image-type conda
```

### Distributions Tests
**ollama**
```
llama stack build --template ollama --image-type conda
ollama run llama3.2:1b-instruct-fp16
llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct
```

**fireworks**
```
llama stack build --template fireworks --image-type conda
llama stack run ./llama_stack/templates/fireworks/run.yaml
```

**together**
```
llama stack build --template together --image-type conda
llama stack run ./llama_stack/templates/together/run.yaml
```

**tgi**
```
llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
```

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
2024-12-27 15:45:44 -08:00

122 lines
3.8 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import pytest
from llama_stack.apis.agents import AgentConfig, Turn
from llama_stack.apis.inference import SamplingParams, UserMessage
from llama_stack.providers.datatypes import Api
from llama_stack.providers.utils.kvstore import kvstore_impl, SqliteKVStoreConfig
from .fixtures import pick_inference_model
from .utils import create_agent_session
@pytest.fixture
def sample_messages():
return [
UserMessage(content="What's the weather like today?"),
]
@pytest.fixture
def common_params(inference_model):
inference_model = pick_inference_model(inference_model)
return dict(
model=inference_model,
instructions="You are a helpful assistant.",
enable_session_persistence=True,
sampling_params=SamplingParams(temperature=0.7, top_p=0.95),
input_shields=[],
output_shields=[],
tools=[],
max_infer_iters=5,
)
class TestAgentPersistence:
@pytest.mark.asyncio
async def test_delete_agents_and_sessions(self, agents_stack, common_params):
agents_impl = agents_stack.impls[Api.agents]
agent_id, session_id = await create_agent_session(
agents_impl,
AgentConfig(
**{
**common_params,
"input_shields": [],
"output_shields": [],
}
),
)
run_config = agents_stack.run_config
provider_config = run_config.providers["agents"][0].config
persistence_store = await kvstore_impl(
SqliteKVStoreConfig(**provider_config["persistence_store"])
)
await agents_impl.delete_agents_session(agent_id, session_id)
session_response = await persistence_store.get(
f"session:{agent_id}:{session_id}"
)
await agents_impl.delete_agents(agent_id)
agent_response = await persistence_store.get(f"agent:{agent_id}")
assert session_response is None
assert agent_response is None
@pytest.mark.asyncio
async def test_get_agent_turns_and_steps(
self, agents_stack, sample_messages, common_params
):
agents_impl = agents_stack.impls[Api.agents]
agent_id, session_id = await create_agent_session(
agents_impl,
AgentConfig(
**{
**common_params,
"input_shields": [],
"output_shields": [],
}
),
)
# Create and execute a turn
turn_request = dict(
agent_id=agent_id,
session_id=session_id,
messages=sample_messages,
stream=True,
)
turn_response = [
chunk async for chunk in await agents_impl.create_agent_turn(**turn_request)
]
final_event = turn_response[-1].event.payload
turn_id = final_event.turn.turn_id
provider_config = agents_stack.run_config.providers["agents"][0].config
persistence_store = await kvstore_impl(
SqliteKVStoreConfig(**provider_config["persistence_store"])
)
turn = await persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
response = await agents_impl.get_agents_turn(agent_id, session_id, turn_id)
assert isinstance(response, Turn)
assert response == final_event.turn
assert turn == final_event.turn.model_dump_json()
steps = final_event.turn.steps
step_id = steps[0].step_id
step_response = await agents_impl.get_agents_step(
agent_id, session_id, turn_id, step_id
)
assert step_response.step == steps[0]