forked from phoenix-oss/llama-stack-mirror
114 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Aidan Do
|
39c34dd25f
|
[#432] Groq Provider tool call tweaks (#811)
# What does this PR do? Follow up for @ashwinb's comments in https://github.com/meta-llama/llama-stack/pull/630 - [x] Contributes to issue (#432) ## Test Plan <details> <summary>Environment</summary> ```shell export GROQ_API_KEY=<api-key> # Create environment if not already conda create --name llamastack-groq python=3.10 conda activate llamastack-groq wget https://raw.githubusercontent.com/aidando73/llama-stack/9165502582cd7cb178bc1dcf89955b45768ab6c1/build.yaml wget https://raw.githubusercontent.com/meta-llama/llama-stack/918172c7fa92522c9ebc586bdb4f386b1d9ea224/run.yaml # Build pip install -e . && llama stack build --config ./build.yaml --image-type conda # Activate built environment conda activate llamastack-groq # Test deps pip install pytest pytest_html pytest_asyncio ``` </details> <details> <summary>Unit tests</summary> ```shell # Setup conda activate llamastack-groq pytest llama_stack/providers/tests/inference/groq/test_groq_utils.py -vv -k groq -s # Result llama_stack/providers/tests/inference/groq/test_groq_utils.py ....................... ========================================= 23 passed, 11 warnings in 0.06s ========================================= ``` </details> <details> <summary>Integration tests</summary> ```shell # Tests pytest llama_stack/providers/tests/inference/test_text_inference.py -k groq -s # Results ___________________________ TestInference.test_chat_completion_with_tool_calling[-groq] ___________________________ llama_stack/providers/tests/inference/test_text_inference.py:403: in test_chat_completion_with_tool_calling assert len(message.tool_calls) > 0 E assert 0 > 0 E + where 0 = len([]) E + where [] = CompletionMessage(role='assistant', content='<function=get_weather>{"location": "San Francisco, CA"}', stop_reason=<StopReason.end_of_turn: 'end_of_turn'>, tool_calls=[]).tool_calls ============================================= short test summary info ============================================= FAILED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-groq] - assert 0 > 0 ======================== 1 failed, 3 passed, 5 skipped, 99 deselected, 7 warnings in 2.13s ======================== ``` (One failure as expected from 3.2 3B - re: https://github.com/meta-llama/llama-stack/pull/630#discussion_r1914056503) </details> ## 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). - [x] 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. - [x] Wrote necessary unit or integration tests. Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
Ashwin Bharambe
|
d78027f3b5 |
Move runpod provider to the correct directory
Also cleanup the test code to avoid skipping tests. Let failures be known and public. |
||
snova-edwardm
|
22dc684da6
|
Sambanova inference provider (#555)
# What does this PR do? This PR adds SambaNova as one of the Provider - Add SambaNova as a provider ## Test Plan Test the functional command ``` pytest -s -v --providers inference=sambanova llama_stack/providers/tests/inference/test_embeddings.py llama_stack/providers/tests/inference/test_prompt_adapter.py llama_stack/providers/tests/inference/test_text_inference.py llama_stack/providers/tests/inference/test_vision_inference.py --env SAMBANOVA_API_KEY=<sambanova-api-key> ``` Test the distribution template: ``` # Docker LLAMA_STACK_PORT=5001 docker run -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \ llamastack/distribution-sambanova \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY # Conda llama stack build --template sambanova --image-type conda llama stack run ./run.yaml \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY ``` ## Source [SambaNova API Documentation](https://cloud.sambanova.ai/apis) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [Y] Ran pre-commit to handle lint / formatting issues. - [Y] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [Y] Updated relevant documentation. - [Y ] Wrote necessary unit or integration tests. --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
Sixian Yi
|
bfbd773b54 | remove test report | ||
|
Aidan Do
|
910717c1fd
|
Add vLLM raw completions API (#823)
# What does this PR do? Adds raw completions API to vLLM ## Test Plan <details> <summary>Setup</summary> ```bash # Run vllm server conda create -n vllm python=3.12 -y conda activate vllm pip install vllm # Run llamastack conda create --name llamastack-vllm python=3.10 conda activate llamastack-vllm export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct && \ pip install -e . && \ pip install --no-cache --index-url https://pypi.org/simple/ --extra-index-url https://test.pypi.org/simple/ llama-stack==0.1.0rc7 && \ llama stack build --template remote-vllm --image-type conda && \ llama stack run ./distributions/remote-vllm/run.yaml \ --port 5000 \ --env INFERENCE_MODEL=$INFERENCE_MODEL \ --env VLLM_URL=http://localhost:8000/v1 | tee -a llama-stack.log ``` </details> <details> <summary>Integration</summary> ```bash # Run conda activate llamastack-vllm export VLLM_URL=http://localhost:8000/v1 pip install pytest pytest_html pytest_asyncio aiosqlite pytest llama_stack/providers/tests/inference/test_text_inference.py -v -k vllm # Results llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[-vllm_remote] PASSED [ 11%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-vllm_remote] PASSED [ 22%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_logprobs[-vllm_remote] SKIPPED [ 33%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-vllm_remote] SKIPPED [ 44%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[-vllm_remote] PASSED [ 55%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[-vllm_remote] PASSED [ 66%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-vllm_remote] PASSED [ 77%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-vllm_remote] PASSED [ 88%] llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[-vllm_remote] PASSED [100%] ====================================== 7 passed, 2 skipped, 99 deselected, 1 warning in 9.80s ====================================== ``` </details> <details> <summary>Manual</summary> ```bash # Install pip install --no-cache --index-url https://pypi.org/simple/ --extra-index-url https://test.pypi.org/simple/ llama-stack==0.1.0rc7 ``` Apply this diff ```diff diff --git a/llama_stack/distribution/server/server.py b/llama_stack/distribution/server/server.py index 8dbb193..95173e2 100644 --- a/llama_stack/distribution/server/server.py +++ b/llama_stack/distribution/server/server.py @@ -250,7 +250,7 @@ class ClientVersionMiddleware: server_version_parts = tuple( map(int, self.server_version.split(".")[:2]) ) - if client_version_parts != server_version_parts: + if False and client_version_parts != server_version_parts: async def send_version_error(send): await send( diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml index 4eac4da..32eb50e 100644 --- a/llama_stack/templates/remote-vllm/run.yaml +++ b/llama_stack/templates/remote-vllm/run.yaml @@ -94,7 +94,8 @@ metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db models: -- metadata: {} +- metadata: + llama_model: meta-llama/Llama-3.2-3B-Instruct model_id: ${env.INFERENCE_MODEL} provider_id: vllm-inference model_type: llm ``` Test 1: ```python from llama_stack_client import LlamaStackClient client = LlamaStackClient( base_url="http://localhost:5000", ) response = client.inference.completion( model_id="meta-llama/Llama-3.2-3B-Instruct", content="Hello, world client!", ) print(response) ``` Test 2 ``` from llama_stack_client import LlamaStackClient client = LlamaStackClient( base_url="http://localhost:5000", ) response = client.inference.completion( model_id="meta-llama/Llama-3.2-3B-Instruct", content="Hello, world client!", stream=True, ) for chunk in response: print(chunk.delta, end="", flush=True) ``` ``` I'm excited to introduce you to our latest project, a comprehensive guide to the best coffee shops in [City]. As a coffee connoisseur, you're in luck because we've scoured the city to bring you the top picks for the perfect cup of joe. In this guide, we'll take you on a journey through the city's most iconic coffee shops, highlighting their unique features, must-try drinks, and insider tips from the baristas themselves. From cozy cafes to trendy cafes, we've got you covered. **Top 5 Coffee Shops in [City]** 1. **The Daily Grind**: This beloved institution has been serving up expertly crafted pour-overs and lattes for over 10 years. Their expert baristas are always happy to guide you through their menu, which features a rotating selection of single-origin beans from around the world... ``` </details> ## 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. |
||
|
Ashwin Bharambe
|
6c205e1d5a | Fix tool tests | ||
|
Ashwin Bharambe
|
f3d8864c36 | Rename builtin::memory -> builtin::rag | ||
|
Ashwin Bharambe
|
07b87365ab
|
[inference api] modify content types so they follow a more standard structure (#841)
Some small updates to the inference types to make them more standard Specifically: - image data is now located in a "image" subkey - similarly tool call data is located in a "tool_call" subkey The pattern followed is `dict(type="foo", foo=<...>)` |
||
|
Ashwin Bharambe
|
a63a43c646
|
[memory refactor][6/n] Update naming and routes (#839)
Making a few small naming changes as per feedback: - RAGToolRuntime methods are called `insert` and `query` to keep them more general - The tool names are changed to non-namespaced forms `insert_into_memory` and `query_from_memory` - The REST endpoints are more REST-ful |
||
|
Ashwin Bharambe
|
c9e5578151
|
[memory refactor][5/n] Migrate all vector_io providers (#835)
See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. This PR finishes off all the stragglers and migrates everything to the new naming. |
||
|
Ashwin Bharambe
|
1a7490470a
|
[memory refactor][3/n] Introduce RAGToolRuntime as a specialized sub-protocol (#832)
See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. Third part: - we need to make `tool_runtime.rag_tool.query_context()` and `tool_runtime.rag_tool.insert_documents()` methods work smoothly with complete type safety. To that end, we introduce a sub-resource path `tool-runtime/rag-tool/` and make changes to the resolver to make things work. - the PR updates the agents implementation to directly call these typed APIs for memory accesses rather than going through the complex, untyped "invoke_tool" API. the code looks much nicer and simpler (expectedly.) - there are a number of hacks in the server resolver implementation still, we will live with some and fix some Note that we must make sure the client SDKs are able to handle this subresource complexity also. Stainless has support for subresources, so this should be possible but beware. ## Test Plan Our RAG test is sad (doesn't actually test for actual RAG output) but I verified that the implementation works. I will work on fixing the RAG test afterwards. ```bash pytest -s -v tests/agents/test_agents.py -k "rag and together" --safety-shield=meta-llama/Llama-Guard-3-8B ``` |
||
|
Ashwin Bharambe
|
78a481bb22
|
[memory refactor][2/n] Update faiss and make it pass tests (#830)
See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. Second part: - updates routing table / router code - updates the faiss implementation ## Test Plan ``` pytest -s -v -k sentence test_vector_io.py --env EMBEDDING_DIMENSION=384 ``` |
||
|
Sixian Yi
|
e41873f268
|
[ez] structured output for /completion ollama & enable tests (#822)
# What does this PR do?
1) enabled structured output for ollama /completion API. It seems we
missed this one.
2) fixed ollama structured output test in client sdk - ollama does not
support list format for structured output
3) enable structured output unit test as the result was stable on
Llama-3.1-8B-Instruct and ollama, fireworks, together.
## Test Plan
1) Run `test_completion_structured_output` on /completion API with 3
providers: ollama, fireworks, together.
pytest -v -s -k "together"
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output
```
(base) sxyi@sxyi-mbp llama-stack % pytest -s -v llama_stack/providers/tests/inference --config=ci_test_config.yaml
/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/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 darwin -- Python 3.13.0, pytest-8.3.4, pluggy-1.5.0 -- /Library/Frameworks/Python.framework/Versions/3.13/bin/python3.13
cachedir: .pytest_cache
metadata: {'Python': '3.13.0', 'Platform': 'macOS-15.1.1-arm64-arm-64bit-Mach-O', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.24.0', 'html': '4.1.1', 'metadata': '3.1.1', 'md': '0.2.0', 'dependency': '0.6.0', 'md-report': '0.6.3', 'anyio': '4.6.2.post1'}}
rootdir: /Users/sxyi/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.24.0, html-4.1.1, metadata-3.1.1, md-0.2.0, dependency-0.6.0, md-report-0.6.3, anyio-4.6.2.post1
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 85 items / 82 deselected / 3 selected
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct-ollama] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct-fireworks]
PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[meta-llama/Llama-3.1-8B-Instruct-together] PASSED
==================================================================================== 3 passed, 82 deselected, 8 warnings in 5.67s ====================================================================================
```
2)
` LLAMA_STACK_CONFIG="./llama_stack/templates/ollama/run.yaml"
/opt/miniconda3/envs/stack/bin/pytest -s -v tests/client-sdk/inference`
Before:
```
________________________________________________________________________________________ test_completion_structured_output __________________________________________________________________________________________
tests/client-sdk/inference/test_inference.py:174: in test_completion_structured_output
answer = AnswerFormat.model_validate_json(response.content)
E pydantic_core._pydantic_core.ValidationError: 1 validation error for AnswerFormat
E Invalid JSON: expected value at line 1 column 2 [type=json_invalid, input_value=' The year he retired, he...5\n\nThe best answer is', input_type=str]
E For further information visit https://errors.pydantic.dev/2.10/v/json_invalid
```
After:
test consistently passes
## 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.
|
||
|
Sixian Yi
|
55067fa81d
|
test report for v0.1 (#814)
# What does this PR do? MD file for the test results of provider <> inference tests ## Test Plan 1) install `pip install pytest-md-report` 2) Run inference tests with the additions to the commands `--md-report --md-report-verbose=1 --md-report-output=tgi.md` Test text model: meta-llama/Llama-3.1-8B-Instruct Test vision model: meta-llama/Llama-3.2-11B-Vision-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. --------- Co-authored-by: Xi Yan <xiyan@meta.com> |
||
Hardik Shah
|
b2ac29b9da
|
fix provider model list test (#800)
Fixes provider tests ``` pytest -v -s -k "together or fireworks or ollama" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py ``` ``` ... .... llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-together] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-together] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[-together] PASSED ================ 21 passed, 6 skipped, 81 deselected, 5 warnings in 32.11s ================= ``` Co-authored-by: Hardik Shah <hjshah@fb.com> |
||
|
Sixian Yi
|
48b12b9777
|
[Test automation] generate custom test report (#739)
# What does this PR do? Generate a test report in MD that contains two main infos: 1) custom report on inference provider -> API / functionalities 2) [TO BE ADDED] test log for easy debugging ## Test Plan For local testing, run test script in command line. See a test report being generated at tests/report.html `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/. --config=ci_test_config.yaml` See [gist](https://gist.github.com/sixianyi0721/a421fd3bc450b74354a1c2c7da483fa5) for output MD file ## 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). - [x] Ran pre-commit to handle lint / formatting issues. - [x] 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. |
||
|
Sixian Yi
|
c79b087552
|
[test automation] support run tests on config file (#730)
# Context For test automation, the end goal is to run a single pytest command from root test directory (llama_stack/providers/tests/.) such that we execute push-blocking tests The work plan: 1) trigger pytest from llama_stack/providers/tests/. 2) use config file to determine what tests and parametrization we want to run # What does this PR do? 1) consolidates the "inference-models" / "embedding-model" / "judge-model" ... options in root conftest.py. Without this change, we will hit into error when trying to run `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/.` because of duplicated `addoptions` definitions across child conftest files. 2) Add a `config` option to specify test config in YAML. (see [`ci_test_config.yaml`](https://gist.github.com/sixianyi0721/5b37fbce4069139445c2f06f6e42f87e) for example config file) For provider_fixtures, we allow users to use either a default fixture combination or define their own {api:provider} combinations. ``` memory: .... fixtures: provider_fixtures: - default_fixture_param_id: ollama // use default fixture combination with param_id="ollama" in [providers/tests/memory/conftest.py](https://fburl.com/mtjzwsmk) - inference: sentence_transformers memory: faiss - default_fixture_param_id: chroma ``` 3) generate tests according to the config. Logic lives in two places: a) in `{api}/conftest.py::pytest_generate_tests`, we read from config to do parametrization. b) after test collection, in `pytest_collection_modifyitems`, we filter the tests to include only functions listed in config. ## Test Plan 1) `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/. --collect-only --config=ci_test_config.yaml` Using `--collect-only` tag to print the pytests listed in the config file (`ci_test_config.yaml`). output: [gist](https://gist.github.com/sixianyi0721/05145e60d4d085c17cfb304beeb1e60e) 2) sanity check on `--inference-model` option ``` pytest -v -s -k "ollama" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py ``` ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] 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. |
||
|
Sixian Yi
|
67450e4024
|
bug fixes on inference tests (#774)
# What does this PR do?
Fixes two issues on providers/test/inference
- [ ] Addresses issue (#issue)
## Test Plan
### Before
```
===================================================================================== FAILURES =====================================================================================
__________________________________ TestVisionModelInference.test_vision_chat_completion_streaming[llama_vision-fireworks][llama_vision] ___________________________________
providers/tests/inference/test_vision_inference.py:145: in test_vision_chat_completion_streaming
content = "".join(
E TypeError: sequence item 0: expected str instance, TextDelta found
------------------------------------------------------------------------------ Captured log teardown -------------------------------------------------------------------------------
ERROR asyncio:base_events.py:1858 Task was destroyed but it is pending!
task: <Task pending name='Task-5' coro=<<async_generator_athrow without __name__>()>>
============================================================================= short test summary info ==============================================================================
FAILED providers/tests/inference/test_vision_inference.py::TestVisionModelInference::test_vision_chat_completion_streaming[llama_vision-fireworks] - TypeError: sequence item 0: expected str instance, TextDelta found
============================================================== 1 failed, 2 passed, 33 deselected, 7 warnings in 3.59s ==============================================================
(base) sxyi@sxyi-mbp llama_stack %
```
### After
```
(base) sxyi@sxyi-mbp llama_stack % pytest -k "fireworks" /Users/sxyi/llama-stack/llama_stack/providers/tests/inference/test_vision_inference.py
/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/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 darwin -- Python 3.13.0, pytest-8.3.3, pluggy-1.5.0
rootdir: /Users/sxyi/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.24.0, html-4.1.1, metadata-3.1.1, dependency-0.6.0, anyio-4.6.2.post1
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 36 items / 33 deselected / 3 selected
providers/tests/inference/test_vision_inference.py ... [100%]
=================================================================== 3 passed, 33 deselected, 7 warnings in 3.75s ===================================================================
(base) sxyi@sxyi-mbp llama_stack %
```
## 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.
|
||
Xi Yan
|
6deef1ece0
|
rebase eval test w/ tool_runtime fixtures (#773)
# What does this PR do? - fix eval tests to include tool_runtime fixtures - rebase eval for extracting memory retrieval context ## Test Plan ``` pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py ``` - With notebook: https://gist.github.com/yanxi0830/1260a6cb7ec42498a195b88422462a34 ## 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. |
||
|
Hardik Shah
|
a51c8b4efc
|
Convert SamplingParams.strategy to a union (#767)
# What does this PR do?
Cleans up how we provide sampling params. Earlier, strategy was an enum
and all params (top_p, temperature, top_k) across all strategies were
grouped. We now have a strategy union object with each strategy (greedy,
top_p, top_k) having its corresponding params.
Earlier,
```
class SamplingParams:
strategy: enum ()
top_p, temperature, top_k and other params
```
However, the `strategy` field was not being used in any providers making
it confusing to know the exact sampling behavior purely based on the
params since you could pass temperature, top_p, top_k and how the
provider would interpret those would not be clear.
Hence we introduced -- a union where the strategy and relevant params
are all clubbed together to avoid this confusion.
Have updated all providers, tests, notebooks, readme and otehr places
where sampling params was being used to use the new format.
## Test Plan
`pytest llama_stack/providers/tests/inference/groq/test_groq_utils.py`
// inference on ollama, fireworks and together
`with-proxy pytest -v -s -k "ollama"
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/inference/test_text_inference.py `
// agents on fireworks
`pytest -v -s -k 'fireworks and create_agent'
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/agents/test_agents.py
--safety-shield="meta-llama/Llama-Guard-3-8B"`
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [X] Ran pre-commit to handle lint / formatting issues.
- [X] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [X] Updated relevant documentation.
- [X] Wrote necessary unit or integration tests.
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
|
||
|
Ashwin Bharambe
|
d9d34433fc | Update spec | ||
|
Ashwin Bharambe
|
9a5803a429 | move all implementations to use updated type | ||
|
Aidan Do
|
fdcc74fda2
|
[#432] Add Groq Provider - tool calls (#630)
# What does this PR do?
Contributes to issue #432
- Adds tool calls to Groq provider
- Enables tool call integration tests
### PR Train
- https://github.com/meta-llama/llama-stack/pull/609
- https://github.com/meta-llama/llama-stack/pull/630 👈
## Test Plan
Environment:
```shell
export GROQ_API_KEY=<api-key>
# build.yaml and run.yaml files
wget https://raw.githubusercontent.com/aidando73/llama-stack/9165502582cd7cb178bc1dcf89955b45768ab6c1/build.yaml
wget https://raw.githubusercontent.com/aidando73/llama-stack/9165502582cd7cb178bc1dcf89955b45768ab6c1/run.yaml
# Create environment if not already
conda create --prefix ./envs python=3.10
conda activate ./envs
# Build
pip install -e . && llama stack build --config ./build.yaml --image-type conda
# Activate built environment
conda activate llamastack-groq
```
<details>
<summary>Unit tests</summary>
```shell
# Setup
conda activate llamastack-groq
pytest llama_stack/providers/tests/inference/groq/test_groq_utils.py -vv -k groq -s
# Result
llama_stack/providers/tests/inference/groq/test_groq_utils.py .....................
======================================== 21 passed, 1 warning in 0.05s ========================================
```
</details>
<details>
<summary>Integration tests</summary>
```shell
# Run
conda activate llamastack-groq
pytest llama_stack/providers/tests/inference/test_text_inference.py -k groq -s
# Result
llama_stack/providers/tests/inference/test_text_inference.py .sss.s.ss.sss.s...
========================== 8 passed, 10 skipped, 180 deselected, 7 warnings in 2.73s ==========================
```
</details>
<details>
<summary>Manual</summary>
```bash
llama stack run ./run.yaml --port 5001
```
Via this Jupyter notebook:
|
||
Fred Reiss
|
8b2376bfb3
|
Add inline vLLM inference provider to regression tests and fix regressions (#662)
# What does this PR do?
This PR adds the inline vLLM inference provider to the regression tests
for inference providers. The PR also fixes some regressions in that
inference provider in order to make the tests pass.
## Test Plan
Command to run the new tests (from root of project):
```
pytest \
-vvv \
llama_stack/providers/tests/inference/test_text_inference.py \
--providers inference=vllm \
--inference-model meta-llama/Llama-3.2-3B-Instruct \
```
Output of the above command after these changes:
```
/mnt/datadisk1/freiss/llama/env/lib/python3.12/site-packages/pytest_asyncio/plugin.py:207: 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 3.12.7, pytest-8.3.4, pluggy-1.5.0 -- /mnt/datadisk1/freiss/llama/env/bin/python3.12
cachedir: .pytest_cache
rootdir: /mnt/datadisk1/freiss/llama/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.25.0, anyio-4.6.2.post1
asyncio: mode=Mode.STRICT, asyncio_default_fixture_loop_scope=None
collected 9 items
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[-vllm] PASSED [ 11%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-vllm] SKIPPED (Other inference providers don't
support completion() yet) [ 22%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_logprobs[-vllm] SKIPPED (Other inference providers
don't support completion() yet) [ 33%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-vllm] SKIPPED (This test is not
quite robust) [ 44%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[-vllm] PASSED [ 55%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[-vllm] SKIPPED (Other inference providers don't
support structured output yet) [ 66%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-vllm] PASSED [ 77%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-vllm] PASSED [ 88%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[-vllm] PASSED [100%]
======================================================== 5 passed, 4 skipped, 2 warnings in 25.56s ========================================================
Task was destroyed but it is pending!
task: <Task pending name='Task-6' coro=<AsyncLLMEngine.run_engine_loop() running at /mnt/datadisk1/freiss/llama/env/lib/python3.12/site-packages/vllm/engine/async_llm_engine.py:848> cb=[_log_task_completion(error_callback=<bound method...7cfc479440b0>>)() at /mnt/datadisk1/freiss/llama/env/lib/python3.12/site-packages/vllm/engine/async_llm_engine.py:45, shield.<locals>._inner_done_callback() at /mnt/datadisk1/freiss/llama/env/lib/python3.12/asyncio/tasks.py:905]>
[rank0]:[W1219 11:38:34.689424319 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
```
The warning about "asyncio_default_fixture_loop_scope" appears to be due
to my environment having a newer version of pytest-asyncio.
The warning about a pending task appears to be due to a bug in
`vllm.AsyncLLMEngine.shutdown_background_loop()`. It looks like that
method returns without stopping a pending task. I will look into that
issue separately.
## Sources
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [X] Ran pre-commit to handle lint / formatting issues.
- [X] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [X] Wrote necessary unit or integration tests.
|
||
|
Ashwin Bharambe
|
ffc6bd4805
|
Add X-LlamaStack-Client-Version, rename ProviderData -> Provider-Data (#735)
Add another header so client SDKs can identify their versions which can be used for immediate detection of possible compatibility issues. A semver mismatch against the wrong server should be immediately flagged and requests should be denied. Also change `X-LlamaStack-ProviderData` to `X-LlamaStack-Provider-Data` since that hyphenation is better. |
||
Dinesh Yeduguru
|
a5c57cd381
|
agents to use tools api (#673)
# What does this PR do? PR #639 introduced the notion of Tools API and ability to invoke tools through API just as any resource. This PR changes the Agents to start using the Tools API to invoke tools. Major changes include: 1) Ability to specify tool groups with AgentConfig 2) Agent gets the corresponding tool definitions for the specified tools and pass along to the model 3) Attachements are now named as Documents and their behavior is mostly unchanged from user perspective 4) You can specify args that can be injected to a tool call through Agent config. This is especially useful in case of memory tool, where you want the tool to operate on a specific memory bank. 5) You can also register tool groups with args, which lets the agent inject these as well into the tool call. 6) All tests have been migrated to use new tools API and fixtures including client SDK tests 7) Telemetry just works with tools API because of our trace protocol decorator ## Test Plan ``` pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct pytest -s -v -k together llama_stack/providers/tests/tools/test_tools.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py ``` run.yaml: https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994 Notebook: https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing |
||
|
Aidan Do
|
e1f42eb5a5
|
[#432] Add Groq Provider - chat completions (#609)
# What does this PR do?
Contributes towards issue (#432)
- Groq text chat completions
- Streaming
- All the sampling params that Groq supports
A lot of inspiration taken from @mattf's good work at
https://github.com/meta-llama/llama-stack/pull/355
**What this PR does not do**
- Tool calls (Future PR)
- Adding llama-guard model
- See if we can add embeddings
### PR Train
- https://github.com/meta-llama/llama-stack/pull/609 👈
- https://github.com/meta-llama/llama-stack/pull/630
## Test Plan
<details>
<summary>Environment</summary>
```bash
export GROQ_API_KEY=<api_key>
wget https://raw.githubusercontent.com/aidando73/llama-stack/240e6e2a9c20450ffdcfbabd800a6c0291f19288/build.yaml
wget https://raw.githubusercontent.com/aidando73/llama-stack/92c9b5297f9eda6a6e901e1adbd894e169dbb278/run.yaml
# Build and run environment
pip install -e . \
&& llama stack build --config ./build.yaml --image-type conda \
&& llama stack run ./run.yaml \
--port 5001
```
</details>
<details>
<summary>Manual tests</summary>
Using this jupyter notebook to test manually:
|
||
|
Xi Yan
|
3a269c4635
|
[rag evals] refactor & add ability to eval retrieval + generation in agentic eval pipeline (#664)
# What does this PR do? - See https://github.com/meta-llama/llama-stack/pull/666 & https://github.com/meta-llama/llama-stack/pull/668 - Refactor BaseScoringFn to be just a minimal interface, add new RegistrableBaseScoring - Refactor data schema check - To separately evaluate retrieval component in RAG, we will have scoring functions needing "context" column additionally. - Refactor braintrust eval (more scoring fn added & tested in following PR) ## Test Plan ``` pytest -v -s -m llm_as_judge_scoring_together_inference scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference scoring/test_scoring.py pytest -v -s -m braintrust_scoring_together_inference scoring/test_scoring.py ``` <img width="847" alt="image" src="https://github.com/user-attachments/assets/d099cb2d-6f9c-4bdf-9d0d-f388cf758c0f" /> ``` pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio eval/test_eval.py ``` <img width="850" alt="image" src="https://github.com/user-attachments/assets/dce28fc3-0493-4d34-820a-567260873cc8" /> ## 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. |
||
|
Aidan Do
|
5d7b611336
|
Add JSON structured outputs to Ollama Provider (#680)
# What does this PR do? Addresses issue #679 - Adds support for the response_format field for chat completions and completions so users can get their outputs in JSON ## Test Plan <details> <summary>Integration tests</summary> `pytest llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output -k ollama -s -v` ```python llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_8b-ollama] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_3b-ollama] PASSED ================================== 2 passed, 18 deselected, 3 warnings in 41.41s ================================== ``` </details> <details> <summary>Manual Tests</summary> ``` export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct export OLLAMA_INFERENCE_MODEL=llama3.2:3b-instruct-fp16 export LLAMA_STACK_PORT=5000 ollama run $OLLAMA_INFERENCE_MODEL --keepalive 60m llama stack build --template ollama --image-type conda llama stack run ./run.yaml \ --port $LLAMA_STACK_PORT \ --env INFERENCE_MODEL=$INFERENCE_MODEL \ --env OLLAMA_URL=http://localhost:11434 ``` ```python client = LlamaStackClient(base_url=f"http://localhost:{os.environ['LLAMA_STACK_PORT']}") MODEL_ID=meta-llama/Llama-3.2-3B-Instruct prompt =f""" Create a step by step plan to complete the task of creating a codebase that is a web server that has an API endpoint that translates text from English to French. You have 3 different operations you can perform. You can create a file, update a file, or delete a file. Limit your step by step plan to only these operations per step. Don't create more than 10 steps. Please ensure there's a README.md file in the root of the codebase that describes the codebase and how to run it. Please ensure there's a requirements.txt file in the root of the codebase that describes the dependencies of the codebase. """ response = client.inference.chat_completion( model_id=MODEL_ID, messages=[ {"role": "user", "content": prompt}, ], sampling_params={ "max_tokens": 200000, }, response_format={ "type": "json_schema", "json_schema": { "$schema": "http://json-schema.org/draft-07/schema#", "title": "Plan", "description": f"A plan to complete the task of creating a codebase that is a web server that has an API endpoint that translates text from English to French.", "type": "object", "properties": { "steps": { "type": "array", "items": { "type": "string" } } }, "required": ["steps"], "additionalProperties": False, } }, stream=True, ) content = "" for chunk in response: if chunk.event.delta: print(chunk.event.delta, end="", flush=True) content += chunk.event.delta try: plan = json.loads(content) print(plan) except Exception as e: print(f"Error parsing plan into JSON: {e}") plan = {"steps": []} ``` Outputs: ```json { "steps": [ "Update the requirements.txt file to include the updated dependencies specified in the peer's feedback, including the Google Cloud Translation API key.", "Update the app.py file to address the code smells and incorporate the suggested improvements, such as handling errors and exceptions, initializing the Translator object correctly, adding input validation, using type hints and docstrings, and removing unnecessary logging statements.", "Create a README.md file that describes the codebase and how to run it.", "Ensure the README.md file is up-to-date and accurate.", "Update the requirements.txt file to reflect any additional dependencies specified by the peer's feedback.", "Add documentation for each function in the app.py file using docstrings.", "Implement logging statements throughout the app.py file to monitor application execution.", "Test the API endpoint to ensure it correctly translates text from English to French and handles errors properly.", "Refactor the code to follow PEP 8 style guidelines and ensure consistency in naming conventions, indentation, and spacing.", "Create a new folder for logs and add a logging configuration file (e.g., logconfig.json) that specifies the logging level and output destination.", "Deploy the web server on a production environment (e.g., AWS Elastic Beanstalk or Google Cloud Platform) to make it accessible to external users." ] } ``` </details> ## Sources - Ollama api docs: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-completion - Ollama structured output docs: https://github.com/ollama/ollama/blob/main/docs/api.md#request-structured-outputs ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [x] Wrote necessary unit or integration tests. |
||
|
Xi Yan
|
7c1e3daa75
|
[bugfix] fix meta-reference agents w/ safety multiple model loading pytest (#694)
# What does this PR do? - Fix broken pytest for meta-reference's agents - Safety model needs to be registered to a different provider id from inference model in order to be recognized ## Test Plan ``` torchrun $CONDA_PREFIX/bin/pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "meta_reference" --safety-shield meta-llama/Llama-Guard-3-1B --inference-model meta-llama/Llama-3.1-8B-Instruct ``` **Before** <img width="845" alt="image" src="https://github.com/user-attachments/assets/83818fe1-2179-4e9c-a753-bf1472a2f01d" /> **After** <img width="851" alt="image" src="https://github.com/user-attachments/assets/1cf8124b-14e2-47bf-80fd-ef8b4b3f6fd9" /> **Other test not broken** ``` 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 ``` ## 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. |
||
|
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. |
||
Botao Chen
|
36b4fe02cc
|
[4/n][torchtune integration] support lazy load model during inference (#620)
## What does this PR do?
In this PR, we refactor the meta reference inference logic to support
- load the model during registering model instead of during spinning up
server
- support inference finetuned model checkpoint on top of native llama
model
## Why need these changes
To solve the existing pain points that
- user cannot lazy load the model and hot switch the inference
checkpoint after spinning up the server
- this blocks us doing inference and eval on the same sever for a
finetuned checkpoint after post training
- user cannot do inference on a finetuned checkpoint on top of native
llama models
## Expect user experience change
- The inference model won't be loaded when spinning up server. Instead,
it will be loaded during register model. If user add the model as models
resource in run.yaml, it will be registered and loaded automatically
when starting server. There is an optional flag 'skip_initialize' in
model metadata to skip model loading during registration.
- There is an optional flag 'llama_model' in model metadata to identify
the base model of the Model class for validation and initialize model
arch. model identifier no longer needs to be a native llama model
- the default inference model name updates from
'meta-llama/Llama-3.2-3B-Instruct' to 'Llama3.2-3B-Instruct'
- It aligns with the checkpoint folder name after running 'llama model
download'
- It aligns with the descriptor name defined in llama-models SKU list
|
||
|
Ashwin Bharambe
|
8de8eb03c8
|
Update the "InterleavedTextMedia" type (#635)
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
|
||
|
Botao Chen
|
c294a01c4b
|
[2/n][torchtune integration] implement job management and return training artifacts (#593)
### Context In this PR, we - Implement the post training job management and get training artifacts apis - get_training_jobs - get_training_job_status - get_training_job_artifacts - get_training_job_logstream is deleted since the trace can be directly accessed by UI with Jaeger https://llama-stack.readthedocs.io/en/latest/building_applications/telemetry.html#jaeger-to-visualize-traces - Refactor the post training and training types definition to make them more intuitive. - Rewrite the checkpointer to make it compatible with llama-stack file system and can be recognized during inference ### Test Unit test `pytest llama_stack/providers/tests/post_training/test_post_training.py -m "torchtune_post_training_huggingface_datasetio" -v -s --tb=short --disable-warnings` <img width="1506" alt="Screenshot 2024-12-10 at 4 06 17 PM" src="https://github.com/user-attachments/assets/16225029-bdb7-48c4-9d13-e580cc769c0a"> e2e test with client side call <img width="888" alt="Screenshot 2024-12-10 at 4 09 44 PM" src="https://github.com/user-attachments/assets/de375e4c-ef67-4dcc-a045-4037d9489191"> |
||
|
Dinesh Yeduguru
|
516e1a3e59
|
add embedding model by default to distribution templates (#617)
# What does this PR do? Adds the sentence transformer provider and the `all-MiniLM-L6-v2` embedding model to the default models to register in the run.yaml for all providers. ## Test Plan llama stack build --template together --image-type conda llama stack run ~/.llama/distributions/llamastack-together/together-run.yaml |
||
|
Botao Chen
|
aeb76390fc
|
[1/n] torchtune <> llama-stack integration skeleton (#540)
### Context This is the 1st of series PRs that integrate torchtune with llama-stack as meta reference post-training implementation. For MVP, we will focus on single device LoRA SFT. Though this PR is still WIP, we want to get early feedback on the high level design of this skeleton while still working on several details ### Scope To limit the scope of this PR, we focus on the skeleton of the implementation. **What are included?** - refine the post-training SFT apis - skeleton of supervised_fine_tune implementation. We verified that we can call the supervised_fine_tune API successfully from llama stack client SDK (client side PR: https://github.com/meta-llama/llama-stack-client-python/pull/51) - a very basic single device LoRA training recipe based on torchtune core components - parity check with torchtune library and post training api unit test **What are not includes?** - implementation of other job management, get training artifacts apis (separate PR) - refactor the meta reference inference logic to support eval on finetuned model (separate PR) - several necessary functionality in the training recipe such as logging, validation etc (separate PR) - interop with telemetry for tracing and metrics logging, currently temporarily log to local disk (separate PR) ### Testing **e2e test** Although we haven't added detailed testing and numerical parity check with torchtune yet, we did a simple E2E test from client to server 1. setup server with` llama stack build --template experimental-post-training --image-type conda` and `llama stack run experimental-post-training ` 2. On client, run `llama-stack-client --endpoint http://devgpu018.nha2.facebook.com:5000 post_training supervised_fine_tune` 3. Training finishes successfully. On server side, get the finetune checkpoints under output dir. On client side, get the job uuid server <img width="1110" alt="Screenshot 2024-12-02 at 5 52 32 PM" src="https://github.com/user-attachments/assets/b548eb90-7a9b-4edc-a858-ee237cc4361d"> client <img width="807" alt="Screenshot 2024-12-02 at 5 52 37 PM" src="https://github.com/user-attachments/assets/1138ffa8-4698-40fa-b190-3d7b99646838"> **parity check** torchtune dataloader output and llama-stack post training dataloader output are same <img width="1116" alt="Screenshot 2024-12-04 at 8 18 46 PM" src="https://github.com/user-attachments/assets/5e295cdc-4c24-4ea6-82c0-ca96ef1bd6ee"> torchtune LoRA SFT and llama-stack post training LoRA SFT on alpaca dataset with llama3.2 3B instruct model are numerical match <img width="860" alt="Screenshot 2024-12-04 at 8 17 01 PM" src="https://github.com/user-attachments/assets/c05cf0a8-c674-4d2e-9f0a-c5d01b2dca99"> <img width="1049" alt="Screenshot 2024-12-04 at 8 17 06 PM" src="https://github.com/user-attachments/assets/b911d4e2-e7b1-41a9-b62c-d75529b6d443"> **unit test ** ![Uploading Screenshot 2024-12-09 at 1.35.10 PM.png…]() |
||
Matthew Farrellee
|
2a9b13dd52
|
add test for completion logprobs (#532)
# What does this PR do? adds a test for the completion api's logprobs parameter tbd which providers pass this test ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [x] Wrote necessary unit or integration tests. |
||
|
Dinesh Yeduguru
|
96e158eaac
|
Make embedding generation go through inference (#606)
This PR does the following: 1) adds the ability to generate embeddings in all supported inference providers. 2) Moves all the memory providers to use the inference API and improved the memory tests to setup the inference stack correctly and use the embedding models This is a merge from #589 and #598 |
||
|
Ashwin Bharambe
|
b7cb06f004
|
Allow using an "inline" version of Chroma using PersistentClient (#567)
The same code is used (inside providers/remote/memory/chroma/chroma.py) but it is driven by separate configurations and changes which Chroma client to use. Note that the dependencies are separate (`chromadb-client` vs `chromadb` -- the latter is a _much_ heavier package.) ``` pytest -s -v -m chroma memory/test_memory.py --env CHROMA_DB_PATH=/tmp/chroma_test pytest -s -v -m chroma memory/test_memory.py --env CHROMA_URL=http://localhost:6001 ``` |
||
|
Xi Yan
|
41487e6ed1
|
refactor scoring/eval pytests (#607)
# What does this PR do? - remove model registration & parameterize model in scoring/eval pytests ## Test Plan ``` pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio eval/test_eval.py ``` ``` pytest -v -s -m llm_as_judge_scoring_together_inference scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference scoring/test_scoring.py ``` <img width="860" alt="image" src="https://github.com/user-attachments/assets/d4b0badc-da34-4097-9b7c-9511f8261723" /> ## 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. |
||
|
Matthew Farrellee
|
b52df5fe5b
|
add completion api support to nvidia inference provider (#533)
# What does this PR do? add the completion api to the nvidia inference provider ## Test Plan while running the meta/llama-3.1-8b-instruct NIM from https://build.nvidia.com/meta/llama-3_1-8b-instruct?snippet_tab=Docker ``` ➜ pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_BASE_URL=http://localhost:8000 -k test_completion --inference-model Llama3.1-8B-Instruct =============================================== test session starts =============================================== platform linux -- Python 3.10.15, pytest-8.3.3, pluggy-1.5.0 -- /home/matt/.conda/envs/stack/bin/python cachedir: .pytest_cache rootdir: /home/matt/Documents/Repositories/meta-llama/llama-stack configfile: pyproject.toml plugins: anyio-4.6.2.post1, asyncio-0.24.0, httpx-0.34.0 asyncio: mode=strict, default_loop_scope=None collected 20 items / 18 deselected / 2 selected llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-nvidia] PASSED llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-nvidia] SKIPPED ============================= 1 passed, 1 skipped, 18 deselected, 6 warnings in 5.40s ============================= ``` the structured output functionality works but the accuracy fails ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [x] Wrote necessary unit or integration tests. |
||
|
Xi Yan
|
a4bcfb8bba
|
[/scoring] add ability to define aggregation functions for scoring functions & refactors (#597)
# What does this PR do? - Add ability to define aggregation functions for scoring functions via `ScoringFnParams` - Supported by `basic` / `regex_parser` / `llm_as_judge` scoring functions ## Test Plan ``` pytest -v -s -m basic_scoring_together_inference scoring/test_scoring.py ``` <img width="855" alt="image" src="https://github.com/user-attachments/assets/12db8e6e-2ad4-462e-b9b9-70ba6c050a6c"> ``` pytest -v -s -m llm_as_judge_scoring_together_inference scoring/test_scoring.py ``` <img width="858" alt="image" src="https://github.com/user-attachments/assets/bf806676-6f5e-456d-be9f-f81a26d1df19"> **Example Response** (`basic`) <img width="863" alt="image" src="https://github.com/user-attachments/assets/0e57a49c-8386-45cc-8fa9-3e61aaa9a3be"> **Example Response** (`llm-as-judge`) <img width="854" alt="image" src="https://github.com/user-attachments/assets/38065bc2-b724-47ed-9535-79b6099c4362"> ## 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. |
||
|
Aidan Do
|
1c03ba239e
|
[#342] RAG - fix PDF format in vector database (#551)
# What does this PR do? Addresses issue (#342) - PDFs uploaded from url are being loaded into vector db as raw bytes - Instead this PR extracts text from PDF if mime_type is "application/json" - Adds tests to cover new cases ## Test Plan Ran these unit tests: ```bash llama stack build --template meta-reference-gpu --image-type conda conda activate llamastack-meta-reference-gpu pip install pytest pytest-asyncio pypdf pytest llama_stack/providers/tests/memory/test_vector_store.py -v ``` ``` platform linux -- Python 3.10.15, pytest-8.3.3, pluggy-1.5.0 -- /home/ubuntu/1xa100-2/llama-stack/envs/bin/python cachedir: .pytest_cache rootdir: /home/ubuntu/1xa100-2/llama-stack configfile: pyproject.toml plugins: anyio-4.6.2.post1, asyncio-0.24.0, httpx-0.35.0 asyncio: mode=strict, default_loop_scope=None collected 3 items llama_stack/providers/tests/memory/test_vector_store.py::TestVectorStore::test_returns_content_from_pdf_data_uri PASSED [ 33%] llama_stack/providers/tests/memory/test_vector_store.py::TestVectorStore::test_downloads_pdf_and_returns_content PASSED [ 66%] llama_stack/providers/tests/memory/test_vector_store.py::TestVectorStore::test_downloads_pdf_and_returns_content_with_url_object PASSED [100%] ======================================================= 3 passed, 1 warning in 0.62s ======================================================= ``` Tested manually via [this script]( |
||
|
Aidan Do
|
095125e463
|
[#391] Add support for json structured output for vLLM (#528)
# What does this PR do?
Addresses issue (#391)
- Adds json structured output for vLLM
- Enables structured output tests for vLLM
> Give me a recipe for Spaghetti Bolognaise:
```json
{
"recipe_name": "Spaghetti Bolognaise",
"preamble": "Ah, spaghetti bolognaise - the quintessential Italian dish that fills my kitchen with the aromas of childhood nostalgia. As a child, I would watch my nonna cook up a big pot of spaghetti bolognaise every Sunday, filling our small Italian household with the savory scent of simmering meat and tomatoes. The way the sauce would thicken and the spaghetti would al dente - it was love at first bite. And now, as a chef, I want to share that same love with you, so you can recreate these warm, comforting memories at home.",
"ingredients": [
"500g minced beef",
"1 medium onion, finely chopped",
"2 cloves garlic, minced",
"1 carrot, finely chopped",
" celery, finely chopped",
"1 (28 oz) can whole peeled tomatoes",
"1 tbsp tomato paste",
"1 tsp dried basil",
"1 tsp dried oregano",
"1 tsp salt",
"1/2 tsp black pepper",
"1/2 tsp sugar",
"1 lb spaghetti",
"Grated Parmesan cheese, for serving",
"Extra virgin olive oil, for serving"
],
"steps": [
"Heat a large pot over medium heat and add a generous drizzle of extra virgin olive oil.",
"Add the chopped onion, garlic, carrot, and celery and cook until the vegetables are soft and translucent, about 5-7 minutes.",
"Add the minced beef and cook until browned, breaking it up with a spoon as it cooks.",
"Add the tomato paste and cook for 1-2 minutes, stirring constantly.",
"Add the canned tomatoes, dried basil, dried oregano, salt, black pepper, and sugar. Stir well to combine.",
"Bring the sauce to a simmer and let it cook for 20-30 minutes, stirring occasionally, until the sauce has thickened and the flavors have melded together.",
"While the sauce cooks, bring a large pot of salted water to a boil and cook the spaghetti according to the package instructions until al dente. Reserve 1 cup of pasta water before draining the spaghetti.",
"Add the reserved pasta water to the sauce and stir to combine.",
"Combine the cooked spaghetti and sauce, tossing to coat the pasta evenly.",
"Serve hot, topped with grated Parmesan cheese and a drizzle of extra virgin olive oil.",
"Enjoy!"
]
}
```
Generated with Llama-3.2-3B-Instruct model - pretty good for a 3B
parameter model 👍
## Test Plan
`pytest -v -s
llama_stack/providers/tests/inference/test_text_inference.py -k
llama_3b-vllm_remote`
With the following setup:
```bash
# Environment
export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export INFERENCE_PORT=8000
export VLLM_URL=http://localhost:8000/v1
# vLLM server
sudo docker run --gpus all \
-v $STORAGE_DIR/.cache/huggingface:/root/.cache/huggingface \
--env "HUGGING_FACE_HUB_TOKEN=$(cat ~/.cache/huggingface/token)" \
-p 8000:$INFERENCE_PORT \
--ipc=host \
--net=host \
vllm/vllm-openai:v0.6.3.post1 \
--model $INFERENCE_MODEL
# llama-stack server
llama stack build --template remote-vllm --image-type conda && llama stack run distributions/remote-vllm/run.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
```
Results:
```
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_3b-vllm_remote] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_3b-vllm_remote] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_3b-vllm_remote] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_3b-vllm_remote] PASSED
================================ 6 passed, 2 skipped, 120 deselected, 2 warnings in 13.26s ================================
```
## Sources
- https://github.com/vllm-project/vllm/discussions/8300
- By default, vLLM uses https://github.com/dottxt-ai/outlines for
structured outputs
[[1](
|
||
Sixian Yi
|
caf1dac114
|
unregister API for dataset (#507)
# What does this PR do?
1) Implement `unregister_dataset(dataset_id)` API in both llama stack
routing table and providers: It removes {dataset_id -> Dataset} mapping
from routing table and removes the dataset_id references in provider as
well (ex. for huggingface, we use a KV store to store the dataset id =>
dataset. we delete it during unregistering as well)
2) expose the datasets/unregister_dataset api endpoint
## Test Plan
**Unit test:**
`
pytest llama_stack/providers/tests/datasetio/test_datasetio.py -m
"huggingface" -v -s --tb=short --disable-warnings
`
**Test on endpoint:**
tested llama stack using an ollama distribution template:
1) start an ollama server
2) Start a llama stack server with the default ollama distribution
config + dataset/datasetsio APIs + datasetio provider
```
---- .../ollama-run.yaml
...
apis:
- agents
- inference
- memory
- safety
- telemetry
- datasetio
- datasets
providers:
datasetio:
- provider_id: localfs
provider_type: inline::localfs
config: {}
...
```
saw that the new API showed up in startup script
```
Serving API datasets
GET /alpha/datasets/get
GET /alpha/datasets/list
POST /alpha/datasets/register
POST /alpha/datasets/unregister
```
3) query `/alpha/datasets/unregister` through curl (since we have not implemented unregister api in llama stack client)
```
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets register
--dataset-id sixian --url
https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/chat.rst
--schema {}
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets register
--dataset-id sixian2 --url
https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/chat.rst
--schema {}
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian │ localfs │ {} │ dataset │
│ sixian2 │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % curl
http://localhost:5001/alpha/datasets/unregister \
-H "Content-Type: application/json" \
-d '{"dataset_id": "sixian"}'
null%
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian2 │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % curl
http://localhost:5001/alpha/datasets/unregister \
-H "Content-Type: application/json" \
-d '{"dataset_id": "sixian2"}'
null%
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
```
## Sources
## 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.
|
||
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. |
||
|
Matthew Farrellee
|
435f34b05e
|
reduce the accuracy requirements to pass the chat completion structured output test (#522)
i find `test_structured_output` to be flakey. it's both a functionality
and accuracy test -
```
answer = AnswerFormat.model_validate_json(response.completion_message.content)
assert answer.first_name == "Michael"
assert answer.last_name == "Jordan"
assert answer.year_of_birth == 1963
assert answer.num_seasons_in_nba == 15
```
it's an accuracy test because it checks the value of first/last name,
birth year, and num seasons.
i find that -
- llama-3.1-8b-instruct and llama-3.2-3b-instruct pass the functionality
portion
- llama-3.2-3b-instruct consistently fails the accuracy portion
(thinking MJ was in the NBA for 14 seasons)
- llama-3.1-8b-instruct occasionally fails the accuracy portion
suggestions (not mutually exclusive) -
1. turn the test into functionality only, skip the value checks
2. split the test into a functionality version and an xfail accuracy
version
3. add context to the prompt so the llm can answer without accessing
embedded memory
# What does this PR do?
implements option (3) by adding context to the system prompt.
## Test Plan
`pytest -s -v ... llama_stack/providers/tests/inference/ ... -k
structured_output`
## Before submitting
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [x] Updated relevant documentation.
- [x] Wrote necessary unit or integration tests.
|
||
|
Xi Yan
|
50cc165077
|
fixes tests & move braintrust api_keys to request headers (#535)
# What does this PR do?
- braintrust scoring provider requires OPENAI_API_KEY env variable to be
set
- move this to be able to be set as request headers (e.g. like together
/ fireworks api keys)
- fixes pytest with agents dependency
## Test Plan
**E2E**
```
llama stack run
```
```yaml
scoring:
- provider_id: braintrust-0
provider_type: inline::braintrust
config: {}
```
**Client**
```python
self.client = LlamaStackClient(
base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:5000"),
provider_data={
"openai_api_key": os.environ.get("OPENAI_API_KEY", ""),
},
)
```
- run `llama-stack-client eval run_scoring`
**Unit Test**
```
pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py
```
```
pytest -v -s -m braintrust_scoring_together_inference scoring/test_scoring.py --env OPENAI_API_KEY=$OPENAI_API_KEY
```
<img width="745" alt="image"
src="https://github.com/user-attachments/assets/68f5cdda-f6c8-496d-8b4f-1b3dabeca9c2">
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
|
||
|
Dinesh Yeduguru
|
de7af28756
|
Tgi fixture (#519)
# What does this PR do? * Add a test fixture for tgi * Fixes the logic to correctly pass the llama model for chat completion Fixes #514 ## Test Plan pytest -k "tgi" llama_stack/providers/tests/inference/test_text_inference.py --env TGI_URL=http://localhost:$INFERENCE_PORT --env TGI_API_TOKEN=$HF_TOKEN |
||
|
Matthew Farrellee
|
4e6c984c26
|
add NVIDIA NIM inference adapter (#355)
# What does this PR do? this PR adds a basic inference adapter to NVIDIA NIMs what it does - - chat completion api - tool calls - streaming - structured output - logprobs - support hosted NIM on integrate.api.nvidia.com - support downloaded NIM containers what it does not do - - completion api - embedding api - vision models - builtin tools - have certainty that sampling strategies are correct ## Feature/Issue validation/testing/test plan `pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...` all tests should pass. there are pydantic v1 warnings. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [x] Did you write any new necessary tests? Thanks for contributing 🎉! |