# What does this PR do?
- recent merge https://github.com/meta-llama/llama-stack/pull/1410
introduce error
```
ValueError: Provider meta-reference (Api.agents) does not implement the following methods:
[('list_agent_sessions', 'not_actually_implemented'), ('list_agents', 'not_actually_implemented')]
```
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
llama stack run
```
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/agents/test_agents.py --text-model meta-llama/Llama-3.3-70B-Instruct
```
1379530386
[//]: # (## Documentation)
# What does this PR do?
It's a dict that may contain different types, as per
resolver:instantiate_provider implementation. (AFAIU it also never
contains ProviderSpecs, but *instances* of provider implementations.)
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
mypy passing if enabled checks for these modules. (See #1543)
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Added missing shutdown handler. (Currently empty.)
Without it, when server shuts down, it posts the following warning:
```
__main__:129 server: No shutdown method for TorchtunePostTrainingImpl
```
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
(The test plan assumes shutdown logic is fixed, see #1495)
Without the patch:
```
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO 2025-03-10 20:56:43,961 __main__:140 server: Shutting down
INFO 2025-03-10 20:56:43,962 __main__:124 server: Shutting down DatasetsRoutingTable
INFO 2025-03-10 20:56:43,964 __main__:124 server: Shutting down DatasetIORouter
INFO 2025-03-10 20:56:43,965 __main__:124 server: Shutting down ScoringFunctionsRoutingTable
INFO 2025-03-10 20:56:43,966 __main__:124 server: Shutting down ScoringRouter
INFO 2025-03-10 20:56:43,967 __main__:124 server: Shutting down ModelsRoutingTable
INFO 2025-03-10 20:56:43,968 __main__:124 server: Shutting down InferenceRouter
INFO 2025-03-10 20:56:43,969 __main__:124 server: Shutting down ShieldsRoutingTable
INFO 2025-03-10 20:56:43,971 __main__:124 server: Shutting down SafetyRouter
INFO 2025-03-10 20:56:43,972 __main__:124 server: Shutting down VectorDBsRoutingTable
INFO 2025-03-10 20:56:43,973 __main__:124 server: Shutting down VectorIORouter
INFO 2025-03-10 20:56:43,974 __main__:124 server: Shutting down ToolGroupsRoutingTable
INFO 2025-03-10 20:56:43,975 __main__:124 server: Shutting down ToolRuntimeRouter
INFO 2025-03-10 20:56:43,976 __main__:124 server: Shutting down MetaReferenceAgentsImpl
INFO 2025-03-10 20:56:43,977 __main__:124 server: Shutting down TelemetryAdapter
INFO 2025-03-10 20:56:43,978 __main__:124 server: Shutting down TorchtunePostTrainingImpl
WARNING 2025-03-10 20:56:43,979 __main__:129 server: No shutdown method for TorchtunePostTrainingImpl
INFO 2025-03-10 20:56:43,979 __main__:124 server: Shutting down BenchmarksRoutingTable
INFO 2025-03-10 20:56:43,980 __main__:124 server: Shutting down EvalRouter
INFO 2025-03-10 20:56:43,981 __main__:124 server: Shutting down DistributionInspectImpl
INFO: Application shutdown complete.
INFO: Finished server process [33862]
```
Run with the patch and observe no warning:
```
$ kill -INT $(ps ax | grep llama_stack.distribution.server.server | grep -v nvim | awk -e '{print $1}' | sort | head -n 1)
```
```
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO 2025-03-11 00:32:56,863 __main__:140 server: Shutting down
INFO 2025-03-11 00:32:56,864 __main__:124 server: Shutting down DatasetsRoutingTable
INFO 2025-03-11 00:32:56,866 __main__:124 server: Shutting down DatasetIORouter
INFO 2025-03-11 00:32:56,867 __main__:124 server: Shutting down ScoringFunctionsRoutingTable
INFO 2025-03-11 00:32:56,868 __main__:124 server: Shutting down ScoringRouter
INFO 2025-03-11 00:32:56,869 __main__:124 server: Shutting down ModelsRoutingTable
INFO 2025-03-11 00:32:56,870 __main__:124 server: Shutting down InferenceRouter
INFO 2025-03-11 00:32:56,871 __main__:124 server: Shutting down ShieldsRoutingTable
INFO 2025-03-11 00:32:56,872 __main__:124 server: Shutting down SafetyRouter
INFO 2025-03-11 00:32:56,873 __main__:124 server: Shutting down VectorDBsRoutingTable
INFO 2025-03-11 00:32:56,874 __main__:124 server: Shutting down VectorIORouter
INFO 2025-03-11 00:32:56,875 __main__:124 server: Shutting down ToolGroupsRoutingTable
INFO 2025-03-11 00:32:56,876 __main__:124 server: Shutting down ToolRuntimeRouter
INFO 2025-03-11 00:32:56,877 __main__:124 server: Shutting down MetaReferenceAgentsImpl
INFO 2025-03-11 00:32:56,878 __main__:124 server: Shutting down TelemetryAdapter
INFO 2025-03-11 00:32:56,879 __main__:124 server: Shutting down TorchtunePostTrainingImpl
INFO 2025-03-11 00:32:56,880 __main__:124 server: Shutting down BenchmarksRoutingTable
INFO 2025-03-11 00:32:56,881 __main__:124 server: Shutting down EvalRouter
INFO 2025-03-11 00:32:56,882 __main__:124 server: Shutting down DistributionInspectImpl
```
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
This PR has two fixes needed for correct trace context propagation
across asycnio boundary
Fix 1: Start using context vars to store the global trace context.
This is needed since we cannot use the same trace context across
coroutines since the state is shared. each coroutine
should have its own trace context so that each of it can start storing
its state correctly.
Fix 2: Start a new span for each new coroutines started for running
shields to keep the span tree clean
## Test Plan
### Integration tests with server
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/together/together-run.yaml
LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
server logs:
https://gist.github.com/dineshyv/51ac5d9864ed031d0d89ce77352821fe
test logs:
https://gist.github.com/dineshyv/e66acc1c4648a42f1854600609c467f3
### Integration tests with library client
LLAMA_STACK_CONFIG=fireworks pytest -s --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
logs: https://gist.github.com/dineshyv/ca160696a0b167223378673fb1dcefb8
### Apps test with server:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/together/together-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
server logs:
https://gist.github.com/dineshyv/1717a572d8f7c14279c36123b79c5797
app logs:
https://gist.github.com/dineshyv/44167e9f57806a0ba3b710c32aec02f8
## What does this PR do?
Created a new math_500 open-benchmark based on OpenAI's [Let's Verify
Step by Step](https://arxiv.org/abs/2305.20050) paper and hugging face's
[HuggingFaceH4/MATH-500](https://huggingface.co/datasets/HuggingFaceH4/MATH-500)
dataset.
The challenge part of this benchmark is to parse the generated and
expected answer and verify if they are same. For the parsing part, we
refer to [Minerva: Solving Quantitative Reasoning Problems with Language
Models](https://research.google/blog/minerva-solving-quantitative-reasoning-problems-with-language-models/).
To simply the parse logic, as the next step, we plan to also refer to
what [simple-eval](https://github.com/openai/simple-evals) is doing,
using llm as judge to check if the generated answer matches the expected
answer or not
## Test Plan
on sever side, spin up a server with open-benchmark template `llama
stack run llama_stack/templates/open-benchamrk/run.yaml`
on client side, issue an open benchmark eval request `llama-stack-client
--endpoint xxx eval run-benchmark "meta-reference-math-500" --model-id
"meta-llama/Llama-3.3-70B-Instruct" --output-dir "/home/markchen1015/"
--num-examples 20` and get ther aggregated eval results
<img width="238" alt="Screenshot 2025-03-10 at 7 57 04 PM"
src="https://github.com/user-attachments/assets/2c9da042-3b70-470e-a7c4-69f4cc24d1fb"
/>
check the generated answer and the related scoring and they make sense
# What does this PR do?
This PR converts blocking calls for in built tools like wolfram, brave,
tavily and bing into non blocking async calls
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]
pytest -s -v tool_runtime/test_builtin_tools.py --stack-config=together
--text-model=meta-llama/Llama-3.1-8B-Instruct
Used the command above to get the below results
<img width="1710" alt="image"
src="https://github.com/user-attachments/assets/76b0ca06-f6e4-45fa-a114-0449bef2325b"
/>
<img width="1389" alt="image"
src="https://github.com/user-attachments/assets/5220ccbb-7882-4240-b17e-f362ad46d25b"
/>
<img width="1432" alt="image"
src="https://github.com/user-attachments/assets/bb93a41e-e82a-4c98-a22d-6b0e320aa974"
/>
[//]: # (## Documentation)
---------
Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>
Summary:
| File
"/Users/erichuang/projects/llama-stack/llama_stack/distribution/server/server.py",
line 213, in sse_generator
| logger.exception(f"Error in sse_generator: {e}")
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1864, in exception
| self.log(ERROR, msg, *args, exc_info=exc_info, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1879, in log
| self.logger.log(level, msg, *args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1547, in log
| self._log(level, msg, args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1624, in _log
| self.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1634, in handle
| self.callHandlers(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1696, in callHandlers
| hdlr.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 968, in handle
| self.emit(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 167, in emit
| message_renderable = self.render_message(record, message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 193, in render_message
| message_text = Text.from_markup(message) if use_markup else
Text(message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/text.py",
line 287, in from_markup
| rendered_text = render(text, style, emoji=emoji,
emoji_variant=emoji_variant)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/markup.py",
line 167, in render
| raise MarkupError(
| rich.errors.MarkupError: closing tag '[/INST]' at position 105 doesn't
match any open tag
Test Plan:
reran failing rag_with_vector_db example
# What does this PR do?
This PR updates the inline vLLM inference provider in several
significant ways:
* Models are now attached at run time to instances of the provider via
the `.../models` API instead of hard-coding the model's full name into
the provider's YAML configuration.
* The provider supports models that are not Meta Llama models. Any model
that vLLM supports can be loaded by passing Huggingface coordinates in
the "provider_model_id" field. Custom fine-tuned versions of Meta Llama
models can be loaded by specifying a path on local disk in the
"provider_model_id".
* To implement full chat completions support, including tool calling and
constrained decoding, the provider now routes the `chat_completions` API
to a captive (i.e. called directly in-process, not via HTTPS) instance
of vLLM's OpenAI-compatible server .
* The `logprobs` parameter and completions API are also working.
## Test Plan
Existing tests in
`llama_stack/providers/tests/inference/test_text_inference.py` have good
coverage of the new functionality. These tests can be invoked as
follows:
```
cd llama-stack && pytest \
-vvv \
llama_stack/providers/tests/inference/test_text_inference.py \
--providers inference=vllm \
--inference-model meta-llama/Llama-3.2-3B-Instruct
====================================== test session starts ======================================
platform linux -- Python 3.12.8, pytest-8.3.4, pluggy-1.5.0 -- /mnt/datadisk1/freiss/llama/env/bin/python3.12
cachedir: .pytest_cache
metadata: {'Python': '3.12.8', 'Platform': 'Linux-6.8.0-1016-ibm-x86_64-with-glibc2.39', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'anyio': '4.8.0', 'html': '4.1.1', 'metadata': '3.1.1', 'asyncio': '0.25.2'}, 'JAVA_HOME': '/usr/lib/jvm/java-8-openjdk-amd64'}
rootdir: /mnt/datadisk1/freiss/llama/llama-stack
configfile: pyproject.toml
plugins: anyio-4.8.0, html-4.1.1, metadata-3.1.1, asyncio-0.25.2
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] PASSED [ 22%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_logprobs[-vllm] PASSED [ 33%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-vllm] PASSED [ 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] PASSED [ 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%]
=========================== 9 passed, 13 warnings in 97.18s (0:01:37) ===========================
```
## Sources
## 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?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---------
Co-authored-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Summary:
error:
llama_stack/providers/inline/agents/meta_reference/agent_instance.py:1032:
in execute_tool_call_maybe
logger.info(f"tool call {name} completed with result: {result}")
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1841:
in info
self.log(INFO, msg, *args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1879:
in log
self.logger.log(level, msg, *args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1547:
in log
self._log(level, msg, args, **kwargs)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1624:
in _log
self.handle(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1634:
in handle
self.callHandlers(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:1696:
in callHandlers
hdlr.handle(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py:968:
in handle
self.emit(record)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py:167:
in emit
message_renderable = self.render_message(record, message)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py:193:
in render_message
message_text = Text.from_markup(message) if use_markup else
Text(message)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/text.py:287:
in from_markup
rendered_text = render(text, style, emoji=emoji,
emoji_variant=emoji_variant)
/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/markup.py:167:
in render
raise MarkupError(
E rich.errors.MarkupError: closing tag '[/INST]' at position 3274
doesn't match any open tag
Test Plan:
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
See https://github.com/meta-llama/llama-stack/pull/1171 which is the
original PR. Author: @zc277584121
feat: add [Milvus](https://milvus.io/) vectorDB
note: I use the MilvusClient to implement it instead of
AsyncMilvusClient, because when I tested AsyncMilvusClient, it would
raise issues about evenloop, which I think AsyncMilvusClient SDK is not
robust enough to be compatible with llama_stack framework.
## Test Plan
have passed the unit test and ene2end test
Here is my end2end test logs, including the client code, client log,
server logs from inline and remote settings
[test_end2end_logs.zip](https://github.com/user-attachments/files/18964391/test_end2end_logs.zip)
---------
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Cheney Zhang <chen.zhang@zilliz.com>
# What does this PR do?
The commit addresses the Ruff warning B008 by refactoring the code to
avoid calling SamplingParams() directly in function argument defaults.
Instead, it either uses Field(default_factory=SamplingParams) for
Pydantic models or sets the default to None and instantiates
SamplingParams inside the function body when the argument is None.
Signed-off-by: Sébastien Han <seb@redhat.com>
You now run the integration tests with these options:
```bash
Custom options:
--stack-config=STACK_CONFIG
a 'pointer' to the stack. this can be either be:
(a) a template name like `fireworks`, or
(b) a path to a run.yaml file, or
(c) an adhoc config spec, e.g.
`inference=fireworks,safety=llama-guard,agents=meta-
reference`
--env=ENV Set environment variables, e.g. --env KEY=value
--text-model=TEXT_MODEL
comma-separated list of text models. Fixture name:
text_model_id
--vision-model=VISION_MODEL
comma-separated list of vision models. Fixture name:
vision_model_id
--embedding-model=EMBEDDING_MODEL
comma-separated list of embedding models. Fixture name:
embedding_model_id
--safety-shield=SAFETY_SHIELD
comma-separated list of safety shields. Fixture name:
shield_id
--judge-model=JUDGE_MODEL
comma-separated list of judge models. Fixture name:
judge_model_id
--embedding-dimension=EMBEDDING_DIMENSION
Output dimensionality of the embedding model to use for
testing. Default: 384
--record-responses Record new API responses instead of using cached ones.
--report=REPORT Path where the test report should be written, e.g.
--report=/path/to/report.md
```
Importantly, if you don't specify any of the models (text-model,
vision-model, etc.) the relevant tests will get **skipped!**
This will make running tests somewhat more annoying since all options
will need to be specified. We will make this easier by adding some easy
wrapper yaml configs.
## Test Plan
Example:
```bash
ashwin@ashwin-mbp ~/local/llama-stack/tests/integration (unify_tests) $
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/test_text_inference.py \
--text-model meta-llama/Llama-3.2-3B-Instruct
```
# Summary:
Client side change in
https://github.com/meta-llama/llama-stack-client-python/pull/180
Changes the resume_turn API to accept `ToolResponse` instead of
`ToolResponseMessage`:
1. `ToolResponse` contains `metadata`
2. `ToolResponseMessage` is a concept for model inputs. Here we are just
submitting the outputs of tool execution.
# Test Plan:
Ran integration tests with newly added test using client tool with
metadata
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --record-responses
# What does this PR do?
Inference router computes the token usage related metrics for all
providers and returns the metrics as part of response and also logs to
telemetry.
## Test Plan
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/fireworks/fireworks-run.yaml
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770903Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770916Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 411,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770919Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 421,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world, inhabiting almost every continent, country, and region. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica (research stations only)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Regions:** Humans live in diverse regions, including:\n\t* Deserts (e.g., Sahara, Mojave)\n\t* Forests (e.g., Amazon, Congo)\n\t* Grasslands (e.g., Prairies, Steppes)\n\t* Mountains (e.g., Himalayas, Andes)\n\t* Oceans (e.g., coastal areas, islands)\n\t* Tundras (e.g., Arctic, sub-Arctic)\n4. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near:\n\t* Coastlines\n\t* Rivers\n\t* Lakes\n\t* Mountains\n5. **Rural areas:** Some humans live in rural areas, such as:\n\t* Villages\n\t* Farms\n\t* Countryside\n6. **Islands:** Humans inhabit many islands, including:\n\t* Tropical islands (e.g., Hawaii, Maldives)\n\t* Arctic islands (e.g., Greenland, Iceland)\n\t* Continental islands (e.g., Great Britain, Ireland)\n7. **Extreme environments:** Humans also live in extreme environments, such as:\n\t* High-altitude areas (e.g., Tibet, Andes)\n\t* Low-altitude areas (e.g., Death Valley, Dead Sea)\n\t* Areas with extreme temperatures (e.g., Arctic, Sahara)\n\nOverall, humans have adapted to live in a wide range of environments and ecosystems around the world.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/inference
======================================================================== short test summary info =========================================================================
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-True] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-False] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_non_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
========================================================= 4 failed, 16 passed, 23 xfailed, 17 warnings in 44.36s =========================================================
```
# What does this PR do?
- add ability to register a llm-as-judge scoring function with custom
judge prompts / params.
- Closes https://github.com/meta-llama/llama-stack/issues/1395
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
**Via CLI**
```
llama-stack-client scoring_functions register \
--scoring-fn-id "llm-as-judge::my-prompt" \
--description "my custom judge" \
--return-type '{"type": "string"}' \
--provider-id "llm-as-judge" \
--provider-scoring-fn-id "my-prompt" \
--params '{"type": "llm_as_judge", "judge_model": "meta-llama/Llama-3.2-3B-Instruct", "prompt_template": "always output 1.0"}'
```
<img width="1373" alt="image"
src="https://github.com/user-attachments/assets/7c6fc0ae-64fe-4581-8927-a9d8d746bd72"
/>
- Unit test will be addressed with
https://github.com/meta-llama/llama-stack/issues/1396
[//]: # (## Documentation)
# What does this PR do?
The agent API allows to query multiple DBs using the `vector_db_ids`
argument of the `rag` tool:
```py
toolgroups=[
{
"name": "builtin::rag",
"args": {"vector_db_ids": [vector_db_id]},
}
],
```
This means that multiple DBs can be used to compose an aggregated
context by executing the query on each of them.
When documents are passed to the next agent turn, there is no explicit
way to configure the vector DB where the embeddings will be ingested. In
such cases, we can assume that:
- if any `vector_db_ids` is given, we use the first one (it probably
makes sense to assume that it's the only one in the list, otherwise we
should loop on all the given DBs to have a consistent ingestion)
- if no `vector_db_ids` is given, we can use the current logic to
generate a default DB using the default provider. If multiple providers
are defined, the API will fail as expected: the user has to provide
details on where to ingest the documents.
(Closes#1270)
## Test Plan
The issue description details how to replicate the problem.
[//]: # (## Documentation)
---------
Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
Summary:
Test Plan:
added new test
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/api/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B
# What does this PR do?
- This was missed from previous deprecation:
https://github.com/meta-llama/llama-stack/pull/1186
- Part of https://github.com/meta-llama/llama-stack/issues/1396
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
pytest -v -s --nbval-lax ./llama-stack/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
[//]: # (## Documentation)
# What does this PR do?
- Deprecate allow_turn_resume flag as this is used for staying backward
compat.
- Closes https://github.com/meta-llama/llama-stack/issues/1363
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/api/agents/test_agents.py --inference-model "meta-llama/Llama-3.3-70B-Instruct" --record-responses
```
<img width="1054" alt="image"
src="https://github.com/user-attachments/assets/d31de2d4-0953-41e1-a71a-7e1579fa351a"
/>
[//]: # (## Documentation)
Summary:
1. The `tools` parameter we construct to pass the inference API is
non-deterministic. As a result, our recordable mocks is flaky as the
ordering change sometimes. This PR makes it so that `tools` ordering is
deterministic and aligned with the order user specified.
2. In recordable mock key generation, client tool's parameter type was
'str' and now is 'string' for some reason. I didn't dig into exactly
why, but just regenerated the fixtures.
Test Plan:
Regenerate mocks:
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --record-responses
```
Rerun tests without --record-responses:
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B
```
# What does this PR do?
We currently use `max_infer_iters` in 2 different ways
1/ Server: track number of times
2/ Client side: track number of times we send `resume_turn` request
This PR gets rid of the need of (2) and makes server track total number
of times we perform inference within a Turn
**NOTE**
The PR will assume StopReason is set to
- end_of_message: turn is not finished, we could be waiting for client
tool call responses
- end_of_turn: if the entire turn is finished and there's no more things
to be done.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/client-sdk/agents/test_agents.py::test_custom_tool_infinite_loop --inference-model "meta-llama/Llama-3.3-70B-Instruct"
```
[//]: # (## Documentation)
# What does this PR do?
We want to bundle a bunch of (typically remote) providers in a distro
template and be able to configure them "on the fly" via environment
variables. So far, we have been able to do this with simple env var
replacements. However, sometimes you want to only conditionally enable
providers (because the relevant remote services may not be alive, or
relevant.) This was not possible until now.
To aid this, we add a simple (bash-like) env var replacement
enhancement: `${env.FOO+bar}` evaluates to `bar` if the variable is SET
and evaluates to empty string if it is not. On top of that, we update
our main resolver to ignore any provider whose ID is null.
This allows using the distro like this:
```bash
llama stack run dev --env CHROMADB_URL=http://localhost:6001 --env ENABLE_CHROMADB=1
```
when only Chroma is UP. This disables the other `pgvector` provider in
the run configuration.
## Test Plan
Hard code `chromadb` as the vector io provider inside
`test_vector_io.py` and run:
```bash
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -s -v tests/client-sdk/vector_io/ --embedding-model all-MiniLM-L6-v2
```
# What does this PR do?
- using `eval` is a security risk
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- see https://github.com/meta-llama/llama-stack/pull/1327
cc @SLR722 we will need to update the corresponding dataset via
```python
def update_to_json_str():
dataset = datasets.load_dataset(...)
processed_dataset = dataset[split].map(
lambda x: {
"column": json.dumps(eval(x["column"]))
}
)
processed_dataset.push_to_hub(...)
```
[//]: # (## Documentation)
# What does this PR do?
- Using `eval` on server is a security risk
- Replace `eval` with `json.loads`
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
pytest -v -s --nbval-lax ./llama-stack/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
<img width="747" alt="image"
src="https://github.com/user-attachments/assets/7aff3d95-0b12-4394-b9d0-aeff791eee38"
/>
[//]: # (## Documentation)
Original telemetry outputs for agent turns look like this.
Note: how output was a `str(message)` making it difficult to read them
back for downstream tasks ( eg. building eval datasets )
```
{
│ │ 'input': [
│ │ │ '{"role":"system","content":"You are a helpful assistant. Use search tool to answer the questions. "}',
│ │ │ '{"role":"user","content":"Which teams played in the NBA western conference finals of 2024","context":null}'
│ │ ],
│ │ 'output': "content: tool_calls: [ToolCall(call_id='8b7294ec-a83f-4798-ad8f-6bed662f08b6', tool_name=<BuiltinTool.brave_search: 'brave_search'>, arguments={'query': 'NBA Western Conference Finals 2024 teams'})]"
│ },
```
Updated the outputs to be structured .
## Test
```python
import uuid
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.lib.agents.event_logger import EventLogger
from llama_stack_client.types.agent_create_params import AgentConfig
model_id = "meta-llama/Llama-3.1-8B-Instruct"
agent_config = AgentConfig(
model=model_id,
instructions="You are a helpful assistant who will use the web search tools to help with answering questions.\nOnly provide final answer in short without writing full sentences. Use web search",
toolgroups=["builtin::websearch"],
enable_session_persistence=True,
)
agent = Agent(client, agent_config)
session_id = agent.create_session(uuid.uuid4().hex)
response = agent.create_turn(
messages=[
{
"role": "user",
"content": "latest news about llama stack",
}
],
session_id=session_id,
stream=False,
)
pprint(response)
```
Output:
```
Turn(
│ input_messages=[UserMessage(content='latest news about llama stack', role='user', context=None)],
│ output_message=CompletionMessage(
│ │ content="The latest news about Llama Stack is that Meta has released Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B) and lightweight, text-only models (1B and 3B) that fit onto select edge and mobile devices. Additionally, Llama Stack distributions have been released to simplify the way developers work with Llama models in different environments. However, a critical vulnerability has been discovered in Meta's Llama-Stack, which puts AI applications at risk.",
│ │ role='assistant',
│ │ stop_reason='end_of_turn',
│ │ tool_calls=[]
│ ),
│ session_id='77379546-4598-485a-b4f4-84e5da28c513',
│ started_at=datetime.datetime(2025, 2, 27, 11, 2, 43, 915243, tzinfo=TzInfo(-08:00)),
│ steps=[
│ │ InferenceStep(
│ │ │ api_model_response=CompletionMessage(
│ │ │ │ content='',
│ │ │ │ role='assistant',
│ │ │ │ stop_reason='end_of_turn',
│ │ │ │ tool_calls=[
│ │ │ │ │ ToolCall(
│ │ │ │ │ │ arguments={'query': 'latest news llama stack'},
│ │ │ │ │ │ call_id='84c0fa10-e24a-4f91-a9ff-415a9ec0bb0b',
│ │ │ │ │ │ tool_name='brave_search'
│ │ │ │ │ )
│ │ │ │ ]
│ │ │ ),
│ │ │ step_id='81c16bd3-eb00-4721-8edc-f386e07391a3',
│ │ │ step_type='inference',
│ │ │ turn_id='2c6b5273-4b16-404f-bed2-c0025fd63b45',
│ │ │ completed_at=datetime.datetime(2025, 2, 27, 11, 2, 44, 637149, tzinfo=TzInfo(-08:00)),
│ │ │ started_at=datetime.datetime(2025, 2, 27, 11, 2, 43, 915831, tzinfo=TzInfo(-08:00))
│ │ ),
│ │ ToolExecutionStep(
│ │ │ step_id='4782d609-a62e-45f5-8d2a-25a43db46288',
│ │ │ step_type='tool_execution',
│ │ │ tool_calls=[
│ │ │ │ ToolCall(
│ │ │ │ │ arguments={'query': 'latest news llama stack'},
│ │ │ │ │ call_id='84c0fa10-e24a-4f91-a9ff-415a9ec0bb0b',
│ │ │ │ │ tool_name='brave_search'
│ │ │ │ )
│ │ │ ],
│ │ │ tool_responses=[
│ │ │ │ ToolResponse(
│ │ │ │ │ call_id='84c0fa10-e24a-4f91-a9ff-415a9ec0bb0b',
│ │ │ │ │ content='{"query": "latest news llama stack", "top_k": [{"title": "Llama 3.2: Revol. ....... Hacker News.", "score": 0.6186197, "raw_content": null}]}',
│ │ │ │ │ tool_name='brave_search',
│ │ │ │ │ metadata=None
│ │ │ │ )
│ │ │ ],
│ │ │ turn_id='2c6b5273-4b16-404f-bed2-c0025fd63b45',
│ │ │ completed_at=datetime.datetime(2025, 2, 27, 11, 2, 46, 272176, tzinfo=TzInfo(-08:00)),
│ │ │ started_at=datetime.datetime(2025, 2, 27, 11, 2, 44, 640743, tzinfo=TzInfo(-08:00))
│ │ ),
│ │ InferenceStep(
│ │ │ api_model_response=CompletionMessage(
│ │ │ │ content="The latest news about Llama Stack is that Meta has released Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B) and lightweight, text-only models (1B and 3B) that fit onto select edge and mobile devices. Additionally, Llama Stack distributions have been released to simplify the way developers work with Llama models in different environments. However, a critical vulnerability has been discovered in Meta's Llama-Stack, which puts AI applications at risk.",
│ │ │ │ role='assistant',
│ │ │ │ stop_reason='end_of_turn',
│ │ │ │ tool_calls=[]
│ │ │ ),
│ │ │ step_id='37994419-5da3-4e84-a010-8d9b85366262',
│ │ │ step_type='inference',
│ │ │ turn_id='2c6b5273-4b16-404f-bed2-c0025fd63b45',
│ │ │ completed_at=datetime.datetime(2025, 2, 27, 11, 2, 48, 961275, tzinfo=TzInfo(-08:00)),
│ │ │ started_at=datetime.datetime(2025, 2, 27, 11, 2, 46, 273168, tzinfo=TzInfo(-08:00))
│ │ )
│ ],
│ turn_id='2c6b5273-4b16-404f-bed2-c0025fd63b45',
│ completed_at=datetime.datetime(2025, 2, 27, 11, 2, 48, 962318, tzinfo=TzInfo(-08:00)),
│ output_attachments=[]
)
```
## Check for Telemetry
```python
agent_logs = []
for span in client.telemetry.query_spans(
attribute_filters=[
{"key": "session_id", "op": "eq", "value": session_id},
],
attributes_to_return=['input', 'output'],
):
agent_logs.append(span.attributes)
pprint(json.loads(agent_logs[-1]['output']))
```
```
{
│ 'content': "The latest news about Llama Stack is that Meta has released Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B) and lightweight, text-only models (1B and 3B) that fit onto select edge and mobile devices. Additionally, Llama Stack distributions have been released to simplify the way developers work with Llama models in different environments. However, a critical vulnerability has been discovered in Meta's Llama-Stack, which puts AI applications at risk.",
│ 'tool_calls': []
}
```
Now that remote-vllm include inline::sentence_transformers there is an
issue building the image:
Error building stack:
SentenceTransformersInferenceConfig.sample_run_config() got an
unexpected keyword argument '__distro_dir__'
To avoid that issue this fix extends the sample_run_config to accept
extra kwargs
# Summary:
Right now we would include toolgroup args when we encode messages with
tool_calls, which is confusing the model since they not in the function
description (see test plan for example).
# Test Plan:
Add a print statement before raw prompt is sent to providers (no good
way to test this currently)
Before:
```
cated in the same neighborhood?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[knowledge_search(query="Laleli Mosque and Esma Sultan Mansion same neighborhood", vector_db_ids=["829a68735d744dc3830409dcc782964a"])]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nknowledge_search tool found 5 chunks:\nBEGIN of
```
Note the extra `vector_db_ids`
After
```
>user<|end_header_id|>\n\nAre the Laleli Mosque and Esma Sultan Mansion located in the same neighborhood?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[knowledge_search(query="Laleli Mosque and Esma Sultan Mansion same neighborhood")]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nknowledge_search tool found
```
This is a follow up to:
https://github.com/meta-llama/llama-stack/pull/1140
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
Avoid unnecessary GPU memory clean attempt when the GPU is not used for
training.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
With CPU:
```
INFO 2025-02-26 16:43:56,267 torchtune.utils._logging:121: Model checkpoint of size 6.43 GB saved to /Users/ihrachys/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/consolidated.00.pth
INFO 2025-02-26 16:43:56,274 torchtune.utils._logging:132: Adapter checkpoint of size 0.00 GB saved to /Users/ihrachys/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/adapter/adapter.pth
model_file_path /Users/ihrachys/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0
```
With CUDA:
```
INFO 2025-02-26 21:39:24,314 torchtune.utils._logging:121: Model checkpoint of size 6.43 GB saved to /home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/consolidated.00.pth
INFO 2025-02-26 21:39:24,333 torchtune.utils._logging:132: Adapter checkpoint of size 0.00 GB saved to /home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0/adapter/adapter.pth
model_file_path /home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0
```
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# Summary:
Our tests sometimes error out with
```
========================== 11 passed, 342 warnings in 58.86s ==========================
Error exporting span to SQLite: Cannot operate on a closed database.
Fatal Python error: _enter_buffered_busy: could not acquire lock for <_io.BufferedWriter name='<stdout>'> at interpreter shutdown, possibly due to daemon threads
Python runtime state: finalizing (tstate=0x000000012af04280)
Current thread 0x00000001fa29c240 (most recent call first):
<no Python frame>
```
Usually able to repro this by running 10 times.
The proposed fix is to use threadsafe var for creating sqlite connection
to ensure connection is only used by one thread. Not 100% if this is the
fix, but am not able to repro with this.
# Test Plan:
Run 10 times and saw no more errors
```
for i in {1..10}; do
echo "=== Starting Run $i ==="
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B
if [[ $? -ne 0 ]]; then
echo "=== Run $i FAILED with exit code $? ==="
break
else
echo "=== Run $i PASSED ==="
fi
echo
done
```
