Reverts meta-llama/llama-stack#1252
The above PR breaks the following invocation:
```bash
llama stack run ~/.llama/distributions/together/together-run.yaml
```
# 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
This is unfortunate because `sqlite-vec` seems promising. But its PIP
package is not quite complete. It does not have binary for arm64 (I
think, or maybe it even lacks 64 bit builds?) which results in the arm64
container resulting in
```
File "/usr/local/lib/python3.10/site-packages/sqlite_vec/init.py", line 17, in load
conn.load_extension(loadable_path())
sqlite3.OperationalError: /usr/local/lib/python3.10/site-packages/sqlite_vec/vec0.so: wrong ELF class: ELFCLASS32
```
To get around I tried to install from source via `uv pip install
sqlite-vec --no-binary=sqlite-vec` however it even lacks a source
distribution which makes that impossible.
## Test Plan
Build the container locally using:
```bash
LLAMA_STACK_DIR=. llama stack build --template ollama --image-type container
```
Run the container as:
```
podman run --privileged -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env OLLAMA_URL=http://host.containers.internal:11434 \
-v ~/local/llama-stack:/app/llama-stack-source
localhost/distribution-ollama:dev --port $LLAMA_STACK_PORT
```
Verify the container starts up correctly. Without this patch, it would
encounter the ELFCLASS32 error.
# What does this PR do?
Users prefer to rely on the main CLI rather than invoking the server
through a Python module. Users interact with a high-level CLI rather
than needing to know internal module structures.
Now, when running llama stack run <path-to-config>, the server will
attempt to use the system package or a virtual environment if one is
active.
This also eliminates the current process dependency chain when running
from a virtual environment:
-> llama stack run
-> start_env.sh
-> python -m server...
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Run:
```
ollama run llama3.2:3b-instruct-fp16 --keepalive=2m &
llama stack run ./llama_stack/templates/ollama/run.yaml --disable-ipv6
```
Notice that the server starts and shutdowns normally.
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
currently the `"Environment variable LLAMA_STACK_LOGGING found"` message
is printed with no color switch to cprint and highlight in yellow for
visibility
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
Uses together async client instead of sync client
[//]: # (If resolving an issue, uncomment and update the line below)
## Test Plan
Command to run the test is in the image below(2 tests fail, and they
were failing for the old stable version as well with the same errors.)
<img width="1689" alt="image"
src="https://github.com/user-attachments/assets/503db720-5379-425d-9844-0225010e41a1"
/>
[//]: # (## Documentation)
---------
Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>
This disambiguates "Image" term from "container image" alternative usage
and allows for:
```python
if image_type == LlamaStackImagetype.venv:
...
```
accesses rather than `ImageType.venv.value`
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
Changes enum use to comply with semantic python styling and naming
conventions.
## 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.*]
Refactor was automated and small so simple run-through of creating
images was done.
Signed-off-by: James Kunstle <jkunstle@redhat.com>
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
It should changed in this pr
https://github.com/meta-llama/llama-stack/pull/1190/files#diff-53e3f35ced54ee5e57dc8b0d3b04770ed84f2f6434c6f492f42569b3c2810ecd
[//]: # (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.*]
[//]: # (## Documentation)
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
# 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>
Concurrent requests should not trample (or reuse) each others' provider
data. Provider data should be scoped to each request.
## Test Plan
Set the uvicorn server to have a single worker process + thread by
updating the config:
```python
uvicorn_config = {
...
"workers": 1,
"loop": "asyncio",
}
```
Then perform the following steps on `origin/main` (without this change).
(1) Run the server using `llama stack run dev` without having
`FIREWORKS_API_KEY` in the environment.
(2) Run a test by specifying the FIREWORKS_API_KEY env var so it gets
stored in the thread local
```
pytest -s -v tests/integration/inference/test_text_inference.py \
--stack-config http://localhost:8321 \
--text-model accounts/fireworks/models/llama-v3p1-8b-instruct \
-k test_text_chat_completion_with_tool_calling_and_streaming \
--env FIREWORKS_API_KEY=<...>
```
Ensure you don't have any other API keys in the environment (otherwise
the bug will not reproduce due to other specifics in our testing code.)
Verify this works.
(3) Run the same command again without specifying FIREWORKS_API_KEY. See
that the request actually succeeds when it *should have failed*.
----
Now do the same tests on this branch, verify step (3) results in
failure.
Finally, run the full `test_text_inference.py` test suite with this
change, verify it succeeds.
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 switches from an OpenAI client to the AsyncOpenAI client in the
remote vllm provider. The main benefit of this is that instead of each
client call being a blocking operation that was blocking our server
event loop, the client calls are now async operations that do not block
the event loop.
The actual fix is quite simple and straightforward. Creating a reliable
reproducer of this with a unit test that verifies we were blocking the
event loop before and are not blocking it any longer was a bit harder.
Some other inference providers have this same issue, so we may want to
make that simple delayed http server a bit more generic and pull it into
a common place as other inference providers get fixed.
(Closes#1457)
## Test Plan
I verified the unit tests and test_text_inference tests pass with this
change like below:
```
python -m pytest -v tests/unit
```
```
VLLM_URL="http://localhost:8000/v1" \
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
LLAMA_STACK_CONFIG=remote-vllm \
python -m pytest -v -s \
tests/integration/inference/test_text_inference.py \
--text-model "meta-llama/Llama-3.2-3B-Instruct"
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Summary:
+ llama model prompt-format -m Llama3.2-11B-Vision-Instruct
Traceback (most recent call last):
File "/tmp/tmp.gCwyyCcjoA/.venv/bin/llama", line 10, in <module>
sys.exit(main())
File
"/tmp/tmp.gCwyyCcjoA/.venv/lib/python3.10/site-packages/llama_stack/cli/llama.py",
line 50, in main
parser.run(args)
File
"/tmp/tmp.gCwyyCcjoA/.venv/lib/python3.10/site-packages/llama_stack/cli/llama.py",
line 44, in run
args.func(args)
File
"/tmp/tmp.gCwyyCcjoA/.venv/lib/python3.10/site-packages/llama_stack/cli/model/prompt_format.py",
line 59, in _run_model_template_cmd
if args.list:
AttributeError: 'Namespace' object has no attribute 'list'
Test Plan:
llama model prompt-format -m Llama3.2-11B-Vision-Instruct
# 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?
using `formatter_class=argparse.ArgumentDefaultsHelpFormatter` displays
(default: DEFAULT_VALUE) for each flag. add this formatter class to
build and run to show users some default values like `conda`, `8321`,
etc
## Test Plan
ran locally with following output:
before:
```
llama stack run --help
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE] [--tls-certfile TLS_CERTFILE]
[--image-type {conda,container,venv}]
config
Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
positional arguments:
config Path to config file to use for the run
options:
-h, --help show this help message and exit
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. Defaults to 8321
--image-name IMAGE_NAME
Name of the image to run. Defaults to the current conda environment
--disable-ipv6 Disable IPv6 support
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times.
--tls-keyfile TLS_KEYFILE
Path to TLS key file for HTTPS
--tls-certfile TLS_CERTFILE
Path to TLS certificate file for HTTPS
--image-type {conda,container,venv}
Image Type used during the build. This can be either conda or container or venv.
```
after:
```
llama stack run --help
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE] [--tls-certfile TLS_CERTFILE]
[--image-type {conda,container,venv}]
config
Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
positional arguments:
config Path to config file to use for the run
options:
-h, --help show this help message and exit
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
--image-name IMAGE_NAME
Name of the image to run. Defaults to the current conda environment (default: None)
--disable-ipv6 Disable IPv6 support (default: False)
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times. (default: [])
--tls-keyfile TLS_KEYFILE
Path to TLS key file for HTTPS (default: None)
--tls-certfile TLS_CERTFILE
Path to TLS certificate file for HTTPS (default: None)
--image-type {conda,container,venv}
Image Type used during the build. This can be either conda or container or venv. (default: conda)
```
[//]: # (## Documentation)
Signed-off-by: Charlie Doern <cdoern@redhat.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?
Fix import errors due to `chardet` and `pypdf` not being installed while
imported from `url_utils.py`.
Closes#1432
## Test Plan
Now able to run the server with the config.
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.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>
# What does this PR do?
The method "dict" in class "BaseModel" is deprecated we should use
model_dump instead.
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
```
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
- From old PR, it use `BUILDS_BASE_DIR` in
`llama_stack/cli/stack/configure.py`(removed).
https://github.com/meta-llama/llama-stack/pull/371/files
- Based on the current `build` code, it should only use
`DISTRIBS_BASE_DIR` to save it.
46b0a404e8/llama_stack/cli/stack/_build.py (L298)46b0a404e8/llama_stack/cli/stack/_build.py (L301)
Pls correct me if I am understand incorrectly.
So it should no need to use in `run` now.
[//]: # (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.*]
[//]: # (## Documentation)
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
# What does this PR do?
Some imports were not switched to in-tree copy of the modules.
This is a follow-up to:
https://github.com/meta-llama/llama-stack/pull/1344Closes#1435
## Test Plan
Manually started the server...
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# 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?
This gracefully handles the case where the vLLM server responded to a
completion request with no choices, which can happen in certain vLLM
error situations. Previously, we'd error out with a stack trace about a
list index out of range. Now, we just log a warning to the user and move
past any chunks with an empty choices list.
A specific example of the type of stack trace this fixes:
```
File "/app/llama-stack-source/llama_stack/providers/remote/inference/vllm/vllm.py", line 170, in _process_vllm_chat_completion_stream_response
choice = chunk.choices[0]
~~~~~~~~~~~~~^^^
IndexError: list index out of range
```
Now, instead of erroring out with that stack trace, we log a warning
that vLLM failed to generate any completions and alert the user to check
the vLLM server logs for details.
This is related to #1277 and addresses the stack trace shown in that
issue, although does not in and of itself change the functional behavior
of vLLM tool calling.
## Test Plan
As part of this fix, I added new unit tests to trigger this same error
and verify it no longer happens. That is
`test_process_vllm_chat_completion_stream_response_no_choices` in the
new `tests/unit/providers/inference/test_remote_vllm.py`. I also added a
couple of more tests to trigger and verify the last couple of remote
vllm provider bug fixes - specifically a test for #1236 (builtin tool
calling) and #1325 (vLLM <= v0.6.3).
This required fixing the signature of
`_process_vllm_chat_completion_stream_response` to accept the actual
type of chunks it was getting passed - specifically changing from our
openai_compat `OpenAICompatCompletionResponse` to
`openai.types.chat.chat_completion_chunk.ChatCompletionChunk`. It was
not actually getting passed `OpenAICompatCompletionResponse` objects
before, and was using attributes that didn't exist on those objects. So,
the signature now matches the type of object it's actually passed.
Run these new unit tests like this:
```
pytest tests/unit/providers/inference/test_remote_vllm.py
```
Additionally, I ensured the existing `test_text_inference.py` tests
passed via:
```
VLLM_URL="http://localhost:8000/v1" \
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
LLAMA_STACK_CONFIG=remote-vllm \
python -m pytest -v tests/integration/inference/test_text_inference.py \
--inference-model "meta-llama/Llama-3.2-3B-Instruct" \
--vision-inference-model ""
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# 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?
- add some docs to OpenAPI for agents/eval/scoring/datasetio
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- read
[//]: # (## Documentation)
# What does this PR do?
When going through READMEs, I found that I had to keep editing the code
blocks since they were prefixed with `$ `. A common pattern is to triple
click (highlight all) a block and then copy paste. This minor change
will make this easier for folks to follow the READMEs.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
N/A
[//]: # (## 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>
All of the tests from `llama_stack/providers/tests/` are now moved to
`tests/integration`.
I converted the `tools`, `scoring` and `datasetio` tests to use API.
However, `eval` and `post_training` proved to be a bit challenging to
leaving those. I think `post_training` should be relatively
straightforward also.
As part of this, I noticed that `wolfram_alpha` tool wasn't added to
some of our commonly used distros so I added it. I am going to remove a
lot of code duplication from distros next so while this looks like a
one-off right now, it will go away and be there uniformly for all
distros.
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)
