llama-stack-mirror/llama_stack/providers/tests
Henry Tu 64c6df8392
Cerebras Inference Integration (#265)
Adding Cerebras Inference as an API provider.

## Testing

### Conda
```
$ llama stack build --template cerebras --image-type conda
$ llama stack run ~/.llama/distributions/llamastack-cerebras/cerebras-run.yaml
...
Listening on ['::', '0.0.0.0']:5000
INFO:     Started server process [12443]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://['::', '0.0.0.0']:5000 (Press CTRL+C to quit)
```

### Chat Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/chat-completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": "What is the temperature in Seattle right now?"
        }
    ],
    "stream": false,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 100
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}' 
```

#### Non-Streaming Response
```
{
  "completion_message": {
    "role": "assistant",
    "content": "",
    "stop_reason": "end_of_message",
    "tool_calls": [
      {
        "call_id": "6f42fdcc-6cbb-46ad-a17b-5d20ac64b678",
        "tool_name": "getTemperature",
        "arguments": {
          "location": "Seattle"
        }
      }
    ]
  },
  "logprobs": null
}
```

#### Streaming Response
```
data: {"event":{"event_type":"start","delta":"","logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"","parse_status":"started"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"{\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"type","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"function","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"name","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"get","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Temperature","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"parameters","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" {\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"location","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Seattle","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\"}}","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":{"call_id":"e742df1f-0ae9-40ad-a49e-18e5c905484f","tool_name":"getTemperature","arguments":{"location":"Seattle"}},"parse_status":"success"},"logprobs":null,"stop_reason":"end_of_message"}}
data: {"event":{"event_type":"complete","delta":"","logprobs":null,"stop_reason":"end_of_message"}}
```

### Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "content": "1,2,3,",
    "stream": true,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 10
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}'
```

#### Non-Streaming Response
```
{
  "content": "4,5,6,7,8,",
  "stop_reason": "out_of_tokens",
  "logprobs": null
}
```

#### Streaming Response
```
data: {"delta":"4","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"5","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"6","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"7","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"8","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":"out_of_tokens","logprobs":null}
```

### Pre-Commit Checks
```
trim trailing whitespace.................................................Passed
check python ast.........................................................Passed
check for merge conflicts................................................Passed
check for added large files..............................................Passed
fix end of files.........................................................Passed
Insert license in comments...............................................Passed
flake8...................................................................Passed
Format files with µfmt...................................................Passed
```

### Testing with `test_inference.py`
```
$ export CEREBRAS_API_KEY=<insert API key here>
$ pytest -v -s llama_stack/providers/tests/inference/test_text_inference.py -m "cerebras and llama_8b" 
/net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/lib/python3.12/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"

  warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
=================================================== test session starts ===================================================
platform linux -- Python 3.12.3, pytest-8.3.3, pluggy-1.5.0 -- /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/bin/python3.12
cachedir: .pytest_cache
rootdir: /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack
configfile: pyproject.toml
plugins: anyio-4.6.2.post1, asyncio-0.24.0
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 128 items / 120 deselected / 8 selected                                                                         

llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_8b-cerebras] Resolved 4 providers
 inner-inference => cerebras
 models => __routing_table__
 inference => __autorouted__
 inspect => __builtin__

Models: meta-llama/Llama-3.1-8B-Instruct served by cerebras

PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_8b-cerebras] PASSED

================================ 6 passed, 2 skipped, 120 deselected, 6 warnings in 3.95s =================================
```

I ran `python llama_stack/scripts/distro_codegen.py` to run codegen.
2024-12-03 21:15:32 -08:00
..
agents Support Tavily as built-in search tool. (#485) 2024-11-19 20:59:02 -08:00
datasetio change schema -> dataset_schema for register_dataset api (#443) 2024-11-13 11:17:46 -05:00
eval fixes tests & move braintrust api_keys to request headers (#535) 2024-11-26 13:11:21 -08:00
inference Cerebras Inference Integration (#265) 2024-12-03 21:15:32 -08:00
memory unregister for memory banks and remove update API (#458) 2024-11-14 17:12:11 -08:00
safety minor enhancement for test fixtures 2024-11-18 22:21:17 -08:00
scoring fixes tests & move braintrust api_keys to request headers (#535) 2024-11-26 13:11:21 -08:00
__init__.py Remove "routing_table" and "routing_key" concepts for the user (#201) 2024-10-10 10:24:13 -07:00
conftest.py Kill "remote" providers and fix testing with a remote stack properly (#435) 2024-11-12 21:51:29 -08:00
env.py Significantly simpler and malleable test setup (#360) 2024-11-04 17:36:43 -08:00
README.md update tests --inference-model to hf id 2024-11-18 17:36:58 -08:00
resolver.py Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00

Testing Llama Stack Providers

The Llama Stack is designed as a collection of Lego blocks -- various APIs -- which are composable and can be used to quickly and reliably build an app. We need a testing setup which is relatively flexible to enable easy combinations of these providers.

We use pytest and all of its dynamism to enable the features needed. Specifically:

  • We use pytest_addoption to add CLI options allowing you to override providers, models, etc.

  • We use pytest_generate_tests to dynamically parametrize our tests. This allows us to support a default set of (providers, models, etc.) combinations but retain the flexibility to override them via the CLI if needed.

  • We use pytest_configure to make sure we dynamically add appropriate marks based on the fixtures we make.

Common options

All tests support a --providers option which can be a string of the form api1=provider_fixture1,api2=provider_fixture2. So, when testing safety (which need inference and safety APIs) you can use --providers inference=together,safety=meta_reference to use these fixtures in concert.

Depending on the API, there are custom options enabled. For example, inference tests allow for an --inference-model override, etc.

By default, we disable warnings and enable short tracebacks. You can override them using pytest's flags as appropriate.

Some providers need special API keys or other configuration options to work. You can check out the individual fixtures (located in tests/<api>/fixtures.py) for what these keys are. These can be specified using the --env CLI option. You can also have it be present in the environment (exporting in your shell) or put it in the .env file in the directory from which you run the test. For example, to use the Together fixture you can use --env TOGETHER_API_KEY=<...>

Inference

We have the following orthogonal parametrizations (pytest "marks") for inference tests:

  • providers: (meta_reference, together, fireworks, ollama)
  • models: (llama_8b, llama_3b)

If you want to run a test with the llama_8b model with fireworks, you can use:

pytest -s -v llama_stack/providers/tests/inference/test_text_inference.py \
  -m "fireworks and llama_8b" \
  --env FIREWORKS_API_KEY=<...>

You can make it more complex to run both llama_8b and llama_3b on Fireworks, but only llama_3b with Ollama:

pytest -s -v llama_stack/providers/tests/inference/test_text_inference.py \
  -m "fireworks or (ollama and llama_3b)" \
  --env FIREWORKS_API_KEY=<...>

Finally, you can override the model completely by doing:

pytest -s -v llama_stack/providers/tests/inference/test_text_inference.py \
  -m fireworks \
  --inference-model "meta-llama/Llama3.1-70B-Instruct" \
  --env FIREWORKS_API_KEY=<...>

Agents

The Agents API composes three other APIs underneath:

  • Inference
  • Safety
  • Memory

Given that each of these has several fixtures each, the set of combinations is large. We provide a default set of combinations (see tests/agents/conftest.py) with easy to use "marks":

  • meta_reference -- uses all the meta_reference fixtures for the dependent APIs
  • together -- uses Together for inference, and meta_reference for the rest
  • ollama -- uses Ollama for inference, and meta_reference for the rest

An example test with Together:

pytest -s -m together llama_stack/providers/tests/agents/test_agents.py  \
 --env TOGETHER_API_KEY=<...>

If you want to override the inference model or safety model used, you can use the --inference-model or --safety-shield CLI options as appropriate.

If you wanted to test a remotely hosted stack, you can use -m remote as follows:

pytest -s -m remote llama_stack/providers/tests/agents/test_agents.py \
  --env REMOTE_STACK_URL=<...>