# What does this PR do?
Adds the API to query metrics from telemetry.
## Test Plan
llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
---------
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
Mainly tried to cover the entire llama_stack/apis directory, we only
have one left. Some excludes were just noop.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
The goal of this PR is code base modernization.
Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)
Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Add support for the temperature to the responses API
## Test Plan
Manually tested simple case
unit tests added for simple case and tool calls
Signed-off-by: Derek Higgins <derekh@redhat.com>
# What does this PR do?
This provides an initial [OpenAI Responses
API](https://platform.openai.com/docs/api-reference/responses)
implementation. The API is not yet complete, and this is more a
proof-of-concept to show how we can store responses in our key-value
stores and use them to support the Responses API concepts like
`previous_response_id`.
## Test Plan
I've added a new
`tests/integration/openai_responses/test_openai_responses.py` as part of
a test-driven development for this new API. I'm only testing this
locally with the remote-vllm provider for now, but it should work with
any of our inference providers since the only API it requires out of the
inference provider is the `openai_chat_completion` endpoint.
```
VLLM_URL="http://localhost:8000/v1" \
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack build --template remote-vllm --image-type venv --run
```
```
LLAMA_STACK_CONFIG="http://localhost:8321" \
python -m pytest -v \
tests/integration/openai_responses/test_openai_responses.py \
--text-model "meta-llama/Llama-3.2-3B-Instruct"
```
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
Allow users to name an agent and use the name in telemetry instead of
relying on randomly generated agent_ids. This improves the developer
experience by making it easier to find specific agents in telemetry
logs.
Closes#1832
## Test Plan
- Added tests to verify the agent name is properly stored and retrieved
- Ran `uv run -- pytest -v
tests/integration/telemetry/test_telemetry.py::test_agent_name_filtering`
from the root of the project and made sure the tests pass
- Ran `uv run -- pytest -v
tests/integration/telemetry/test_telemetry.py::test_agent_query_spans`
to verify existing code without agent names still works correctly
## Use Example
```
agent = Agent(
llama_stack_client,
model=text_model_id,
name="CustomerSupportAgent", # New parameter
instructions="You are a helpful customer support assistant"
)
session_id = agent.create_session(f"test-session-{uuid4()}")
```
## Implementation Notes
- Agent names are optional string parameters with no additional
validation
- Names are not required to be unique - multiple agents can have the
same name
- The agent_id remains the unique identifier for an agent
---------
Co-authored-by: raghotham <raghotham@gmail.com>
# What does this PR do?
Some of our multi-turn verification tests were failing because I had
accidentally marked content as a required field in the OpenAI chat
completion request assistant messages, but it's actually optional. It is
required for messages from other roles, but assistant is explicitly
allowed to be optional.
Similarly, the assistant message tool_calls field should default to None
instead of an empty list.
These two changes get the openai-llama-stack verification test back to
100% passing, just like it passes 100% when not behind Llama Stack. They
also increase the pass rate of some of the other providers in the
verification test, but don't get them to 100%.
## Test Plan
I started a Llama Stack server setup to run all the verification tests
(requires OPENAI_API_KEY env variable)
```
llama stack run --image-type venv tests/verifications/openai-api-verification-run.yaml
```
Then, I manually ran the verification tests to see which were failing,
fix them, and ran them again after these changes to ensure they were all
passing.
```
python -m pytest -s -v tests/verifications/openai_api/test_chat_completion.py --provider=openai-llama-stack
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
TLDR: Changes needed to get 100% passing tests for OpenAI API
verification tests when run against Llama Stack with the `together`,
`fireworks`, and `openai` providers. And `groq` is better than before,
at 88% passing.
This cleans up the OpenAI API support for image message types
(specifically `image_url` types) and handling of the `response_format`
chat completion parameter. Both of these required a few more Pydantic
model definitions in our Inference API, just to move from the
not-quite-right stubs I had in place to something fleshed out to match
the actual OpenAI API specs.
As part of testing this, I also found and fixed a bug in the litellm
implementation of openai_completion and openai_chat_completion, so the
providers based on those should actually be working now.
The method `prepare_openai_completion_params` in
`llama_stack/providers/utils/inference/openai_compat.py` was improved to
actually recursively clean up input parameters, including handling of
lists, dicts, and dumping of Pydantic models to dicts. These changes
were required to get to 100% passing tests on the OpenAI API
verification against the `openai` provider.
With the above, the together.ai provider was passing as well as it is
without Llama Stack. But, since we have Llama Stack in the middle, I
took the opportunity to clean up the together.ai provider so that it now
also passes the OpenAI API spec tests we have at 100%. That means
together.ai is now passing our verification test better when using an
OpenAI client talking to Llama Stack than it is when hitting together.ai
directly, without Llama Stack in the middle.
And, another round of work for Fireworks to improve translation of
incoming OpenAI chat completion requests to Llama Stack chat completion
requests gets the fireworks provider passing at 100%. The server-side
fireworks.ai tool calling support with OpenAI chat completions and Llama
4 models isn't great yet, but by pointing the OpenAI clients at Llama
Stack's API we can clean things up and get everything working as
expected for Llama 4 models.
## Test Plan
### OpenAI API Verification Tests
I ran the OpenAI API verification tests as below and 100% of the tests
passed.
First, start a Llama Stack server that runs the `openai` provider with
the `gpt-4o` and `gpt-4o-mini` models deployed. There's not a template
setup to do this out of the box, so I added a
`tests/verifications/openai-api-verification-run.yaml` to do this.
First, ensure you have the necessary API key environment variables set:
```
export TOGETHER_API_KEY="..."
export FIREWORKS_API_KEY="..."
export OPENAI_API_KEY="..."
```
Then, run a Llama Stack server that serves up all these providers:
```
llama stack run \
--image-type venv \
tests/verifications/openai-api-verification-run.yaml
```
Finally, generate a new verification report against all these providers,
both with and without the Llama Stack server in the middle.
```
python tests/verifications/generate_report.py \
--run-tests \
--provider \
together \
fireworks \
groq \
openai \
together-llama-stack \
fireworks-llama-stack \
groq-llama-stack \
openai-llama-stack
```
You'll see that most of the configurations with Llama Stack in the
middle now pass at 100%, even though some of them do not pass at 100%
when hitting the backend provider's API directly with an OpenAI client.
### OpenAI Completion Integration Tests with vLLM:
I also ran the smaller `test_openai_completion.py` test suite (that's
not yet merged with the verification tests) on multiple of the
providers, since I had to adjust the method signature of
openai_chat_completion a bit and thus had to touch lots of these
providers to match. Here's the tests I ran there, all passing:
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```
### OpenAI Completion Integration Tests with ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```
### OpenAI Completion Integration Tests with together.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" llama stack build --template together --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct-Turbo"
```
### OpenAI Completion Integration Tests with fireworks.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" llama stack build --template fireworks --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.1-8B-Instruct"
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
This PR adds two methods to the Inference API:
- `batch_completion`
- `batch_chat_completion`
The motivation is for evaluations targeting a local inference engine
(like meta-reference or vllm) where batch APIs provide for a substantial
amount of acceleration.
Why did I not add this to `Api.batch_inference` though? That just
resulted in a _lot_ more book-keeping given the structure of Llama
Stack. Had I done that, I would have needed to create a notion of a
"batch model" resource, setup routing based on that, etc. This does not
sound ideal.
So what's the future of the batch inference API? I am not sure. Maybe we
can keep it for true _asynchronous_ execution. So you can submit
requests, and it can return a Job instance, etc.
## Test Plan
Run meta-reference-gpu using:
```bash
export INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct
export INFERENCE_CHECKPOINT_DIR=../checkpoints/Llama-4-Scout-17B-16E-Instruct-20250331210000
export MODEL_PARALLEL_SIZE=4
export MAX_BATCH_SIZE=32
export MAX_SEQ_LEN=6144
LLAMA_MODELS_DEBUG=1 llama stack run meta-reference-gpu
```
Then run the batch inference test case.
# What does this PR do?
Today, supervised_fine_tune itself and the `TrainingConfig` class have a
bunch of required fields that a provider implementation might not need.
for example, if a provider wants to handle hyperparameters in its
configuration as well as any type of dataset retrieval, optimizer or
LoRA config, a user will still need to pass in a virtually empty
`DataConfig`, `OptimizerConfig` and `AlgorithmConfig` in some cases.
Many of these fields are intended to work specifically with llama models
and knobs intended for customizing inline.
Adding remote post_training providers will require loosening these
arguments, or forcing users to pass in empty objects to satisfy the
pydantic models.
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
This stubs in some OpenAI server-side compatibility with three new
endpoints:
/v1/openai/v1/models
/v1/openai/v1/completions
/v1/openai/v1/chat/completions
This gives common inference apps using OpenAI clients the ability to
talk to Llama Stack using an endpoint like
http://localhost:8321/v1/openai/v1 .
The two "v1" instances in there isn't awesome, but the thinking is that
Llama Stack's API is v1 and then our OpenAI compatibility layer is
compatible with OpenAI V1. And, some OpenAI clients implicitly assume
the URL ends with "v1", so this gives maximum compatibility.
The openai models endpoint is implemented in the routing layer, and just
returns all the models Llama Stack knows about.
The following providers should be working with the new OpenAI
completions and chat/completions API:
* remote::anthropic (untested)
* remote::cerebras-openai-compat (untested)
* remote::fireworks (tested)
* remote::fireworks-openai-compat (untested)
* remote::gemini (untested)
* remote::groq-openai-compat (untested)
* remote::nvidia (tested)
* remote::ollama (tested)
* remote::openai (untested)
* remote::passthrough (untested)
* remote::sambanova-openai-compat (untested)
* remote::together (tested)
* remote::together-openai-compat (untested)
* remote::vllm (tested)
The goal to support this for every inference provider - proxying
directly to the provider's OpenAI endpoint for OpenAI-compatible
providers. For providers that don't have an OpenAI-compatible API, we'll
add a mixin to translate incoming OpenAI requests to Llama Stack
inference requests and translate the Llama Stack inference responses to
OpenAI responses.
This is related to #1817 but is a bit larger in scope than just chat
completions, as I have real use-cases that need the older completions
API as well.
## Test Plan
### vLLM
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```
### ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```
## Documentation
Run a Llama Stack distribution that uses one of the providers mentioned
in the list above. Then, use your favorite OpenAI client to send
completion or chat completion requests with the base_url set to
http://localhost:8321/v1/openai/v1 . Replace "localhost:8321" with the
host and port of your Llama Stack server, if different.
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
Move around bits. This makes the copies from llama-models _much_ easier
to maintain and ensures we don't entangle meta-reference specific
tidbits into llama-models code even by accident.
Also, kills the meta-reference-quantized-gpu distro and rolls
quantization deps into meta-reference-gpu.
## Test Plan
```
LLAMA_MODELS_DEBUG=1 \
with-proxy llama stack run meta-reference-gpu \
--env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct \
--env INFERENCE_CHECKPOINT_DIR=<DIR> \
--env MODEL_PARALLEL_SIZE=4 \
--env QUANTIZATION_TYPE=fp8_mixed
```
Start a server with and without quantization. Point integration tests to
it using:
```
pytest -s -v tests/integration/inference/test_text_inference.py \
--stack-config http://localhost:8321 --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
# What does this PR do?
- **chore: mypy for strong_typing**
- **chore: mypy for remote::vllm**
- **chore: mypy for remote::ollama**
- **chore: mypy for providers.datatype**
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Don't return list for runtime tools. Instead return Response object for
pagination and consistency with other APIs.
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Move pagination logic from LocalFS and HuggingFace implementations into
a common helper function to ensure consistent pagination behavior across
providers. This reduces code duplication and centralizes pagination
logic in one place.
## Test Plan
Run this script:
```
from llama_stack_client import LlamaStackClient
# Initialize the client
client = LlamaStackClient(base_url="http://localhost:8321")
# Register a dataset
response = client.datasets.register(
purpose="eval/messages-answer", # or "eval/question-answer" or "post-training/messages"
source={"type": "uri", "uri": "huggingface://datasets/llamastack/simpleqa?split=train"},
dataset_id="my_dataset", # optional, will be auto-generated if not provided
metadata={"description": "My evaluation dataset"}, # optional
)
# Verify the dataset was registered by listing all datasets
datasets = client.datasets.list()
print(f"Registered datasets: {[d.identifier for d in datasets]}")
# You can then access the data using the datasetio API
# rows = client.datasets.iterrows(dataset_id="my_dataset", start_index=1, limit=2)
rows = client.datasets.iterrows(dataset_id="my_dataset")
print(f"Data: {rows.data}")
```
And play with `start_index` and `limit`.
[//]: # (## Documentation)
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This is to stay consistent with other APIs.
This change registers files in API, even though there are still no
providers. Removing tests that require a provider existing for a merged
API to enable it in API layer.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
[//]: # (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: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
This PR adds support for NVIDIA's NeMo Customizer API to the Llama Stack
post-training module. The integration enables users to fine-tune models
using NVIDIA's cloud-based customization service through a consistent
Llama Stack interface.
[//]: # (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.*]
Yet to be done
Things pending under this PR:
- [x] Integration of fine-tuned model(new checkpoint) for inference with
nvidia llm distribution
- [x] distribution integration of API
- [x] Add test cases for customizer(In Progress)
- [x] Documentation
```
LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/post_training/test_supervised_fine_tuning.py
============================================================================================================================================================================ test session starts =============================================================================================================================================================================
platform linux -- Python 3.10.0, pytest-8.3.4, pluggy-1.5.0 -- /home/ubuntu/llama-stack/.venv/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.10.0', 'Platform': 'Linux-6.8.0-1021-gcp-x86_64-with-glibc2.35', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'nbval': '0.11.0', 'metadata': '3.1.1', 'anyio': '4.8.0', 'html': '4.1.1', 'asyncio': '0.25.3'}}
rootdir: /home/ubuntu/llama-stack
configfile: pyproject.toml
plugins: nbval-0.11.0, metadata-3.1.1, anyio-4.8.0, html-4.1.1, asyncio-0.25.3
asyncio: mode=strict, asyncio_default_fixture_loop_scope=None
collected 2 items
tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_post_training_provider_registration[txt=8B] PASSED [ 50%]
tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_list_training_jobs[txt=8B] PASSED [100%]
======================================================================================================================================================================== 2 passed, 1 warning in 0.10s ========================================================================================================================================================================
```
cc: @mattf @dglogo @sumitb
---------
Co-authored-by: Ubuntu <ubuntu@llama-stack-customizer-dev-inst-2tx95fyisatvlic4we8hidx5tfj.us-central1-a.c.brevdevprod.internal>
# What does this PR do?
- We cannot directly return a literal type
> Note: this is not final jobs API change
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
<img width="837" alt="image"
src="https://github.com/user-attachments/assets/18a17561-35f9-443d-987d-54afdd6ff40c"
/>
[//]: # (## Documentation)
# What does this PR do?
Clean up mypy violations for inline::{telemetry,tool_runtime,vector_io}.
This also makes API accept a tool call result without any content (like
RAG tool already may produce).
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Don't set type variables from register_schema().
`mypy` is not happy about it since type variables are calculated at
runtime and hence the typing hints are not available during static
analysis.
Good news is there is no good reason to set the variables from the
return type.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
with the new /v1/providers API, /v1/inspect/providers is duplicative,
deprecate it by removing the route, and add a test for the full
/v1/providers API
resolves#1623
## Test Plan
`uv run pytest -v tests/integration/providers --stack-config=ollama
--text-model="meta-llama/Llama-3.2-3B-Instruct"
--embedding-model=all-MiniLM-L6-v2`
<img width="1512" alt="Screenshot 2025-03-18 at 9 18 38 AM"
src="https://github.com/user-attachments/assets/2db30f25-3ff6-4374-b39d-0047f093fe36"
/>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
In this PR, we added a new eval open benchmark IfEval based on paper
https://arxiv.org/abs/2311.07911 to measure the model capability of
instruction following.
## Test Plan
spin up a llama stack server with open-benchmark template
run `llama-stack-client --endpoint xxx eval run-benchmark
"meta-reference-ifeval" --model-id "meta-llama/Llama-3.3-70B-Instruct"
--output-dir "/home/markchen1015/" --num-examples 20` on client side and
get the eval aggregate results
## What does this PR do?
open-benchmark templated is broken after the datasets api refactor due
to 2 reasons
- provider_id and provider_resource_id are no longer needed
- the type in run.yaml will be resolved as dict
this PR is to fix the above 2 issues
## Test
spin up a llama stack server successfully with llama stack run
`llama_stack/templates/open-benchmark/run.yaml`
# What does this PR do?
Fixes a bunch of violations.
Note: this patch touches all files but post_training.py that will be
significantly changed by #1437, hence leaving it out of the picture for
now.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Testing with https://github.com/meta-llama/llama-stack/pull/1543
Also checked that GPU training works with the change:
```
INFO: ::1:53316 - "POST /v1/post-training/supervised-fine-tune HTTP/1.1" 200 OK
INFO: ::1:53316 - "GET /v1/post-training/job/status?job_uuid=test-jobb5ca2d84-d541-42f8-883b-762828b4c0e7 HTTP/1.1" 200 OK
INFO: ::1:53316 - "GET /v1/post-training/job/artifacts?job_uuid=test-jobb5ca2d84-d541-42f8-883b-762828b4c0e7 HTTP/1.1" 200 OK
21:24:01.161 [END] /v1/post-training/supervised-fine-tune [StatusCode.OK] (32526.75ms)
21:23:28.769 [DEBUG] Setting manual seed to local seed 3918872849. Local seed is seed + rank = 3918872849 + 0
21:23:28.996 [INFO] Identified model_type = Llama3_2. Ignoring output.weight in checkpoint in favor of the tok_embedding.weight tied weights.
21:23:29.933 [INFO] Memory stats after model init:
GPU peak memory allocation: 6.05 GiB
GPU peak memory reserved: 6.10 GiB
GPU peak memory active: 6.05 GiB
21:23:29.934 [INFO] Model is initialized with precision torch.bfloat16.
21:23:30.115 [INFO] Tokenizer is initialized.
21:23:30.118 [INFO] Optimizer is initialized.
21:23:30.119 [INFO] Loss is initialized.
21:23:30.896 [INFO] Dataset and Sampler are initialized.
21:23:30.898 [INFO] Learning rate scheduler is initialized.
21:23:31.618 [INFO] Memory stats after model init:
GPU peak memory allocation: 6.24 GiB
GPU peak memory reserved: 6.30 GiB
GPU peak memory active: 6.24 GiB
21:23:31.620 [INFO] Starting checkpoint save...
21:23:59.428 [INFO] 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
21:23:59.445 [INFO] 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
```
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
- Removed Optional return types for GET methods
- Raised ValueError when requested resource is not found
- Ensures proper 4xx response for missing resources
- Updated the API generator to check for wrong signatures
```
$ uv run --with ".[dev]" ./docs/openapi_generator/run_openapi_generator.sh
Validating API method return types...
API Method Return Type Validation Errors:
Method ScoringFunctions.get_scoring_function returns Optional type
```
Closes: https://github.com/meta-llama/llama-stack/issues/1630
## Test Plan
Run the server then:
```
curl http://127.0.0.1:8321/v1/models/foo
{"detail":"Invalid value: Model 'foo' not found"}%
```
Server log:
```
INFO: 127.0.0.1:52307 - "GET /v1/models/foo HTTP/1.1" 400 Bad Request
09:51:42.654 [END] /v1/models/foo [StatusCode.OK] (134.65ms)
09:51:42.651 [ERROR] Error executing endpoint route='/v1/models/{model_id:path}' method='get'
Traceback (most recent call last):
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 193, in endpoint
return await maybe_await(value)
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 156, in maybe_await
return await value
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/providers/utils/telemetry/trace_protocol.py", line 102, in async_wrapper
result = await method(self, *args, **kwargs)
File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 217, in get_model
raise ValueError(f"Model '{model_id}' not found")
ValueError: Model 'foo' not found
```
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
currently the `inspect` API for providers is really a `list` API. Create
a new `providers` API which has a GET `providers/{provider_id}` inspect
API
which returns "user friendly" configuration to the end user. Also add a
GET `/providers` endpoint which returns the list of providers as
`inspect/providers` does today.
This API follows CRUD and is more intuitive/RESTful.
This work is part of the RFC at
https://github.com/meta-llama/llama-stack/pull/1359
sensitive fields are redacted using `redact_sensetive_fields` on the
server side before returning a response:
<img width="456" alt="Screenshot 2025-03-13 at 4 40 21 PM"
src="https://github.com/user-attachments/assets/9465c221-2a26-42f8-a08a-6ac4a9fecce8"
/>
## Test Plan
using https://github.com/meta-llama/llama-stack-client-python/pull/181 a
user is able to to run the following:
`llama stack build --template ollama --image-type venv`
`llama stack run --image-type venv
~/.llama/distributions/ollama/ollama-run.yaml`
`llama-stack-client providers inspect ollama`
<img width="378" alt="Screenshot 2025-03-13 at 4 39 35 PM"
src="https://github.com/user-attachments/assets/8273d05d-8bc3-44c6-9e4b-ef95e48d5466"
/>
also, was able to run the new test_list integration test locally with
ollama:
<img width="1509" alt="Screenshot 2025-03-13 at 11 03 40 AM"
src="https://github.com/user-attachments/assets/9b9db166-f02f-45b0-86a4-306d85149bc8"
/>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
Summary:
This is not used anywhere.
closes#1421
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct --record-responses
# What does this PR do?
This change adds a compact type to include metrics in response as
opposed to the full MetricEvent which is relevant for internal logging
purposes.
## Test Plan
```
LLAMA_STACK_CONFIG=~/.llama/distributions/fireworks/fireworks-run.yaml pytest -s -v agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model meta-llama/Llama-3.1-8B-Instruct
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
}'
{
"metrics": [
{
"metric": "prompt_tokens",
"value": 10,
"unit": null
},
{
"metric": "completion_tokens",
"value": 522,
"unit": null
},
{
"metric": "total_tokens",
"value": 532,
"unit": null
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world...............",
"stop_reason": "out_of_tokens",
"tool_calls": []
},
"logprobs": null
}
```
# What does this PR do?
This PR adds back the changes in #1300 which were reverted in #1476 .
It also adds logic to preserve context variables across asyncio
boundary. this is needed with the library client since the async
generator logic yields control to code outside the event loop, and on
resuming, does not have the same context as before and this requires
preserving the context vars.
address #1477
## Test Plan
```
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": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549084Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549449Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 369,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549457Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 379,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\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. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
Orignal repro no longer showing any error:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
client logs:
https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166
server logs:
https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559
# What does this PR do?
Add support for listing agents, describing an agent, and retrieving
session IDs for a given agent. This is only the API definition, the
implementations will come separately.
Closes: https://github.com/meta-llama/llama-stack/issues/1294
Signed-off-by: Sébastien Han <seb@redhat.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>
# 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 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?
- 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)
# What does this PR do?
An API spec must talk about Error handling. This was a pretty glaring
omission so far. This PR begins to address it by adding a set of
standard error responses we can attach to all our API calls.
At a future point, we can add specific error types where necessary
(although we should not hurry to do that; it is best done very late.)
## Test Plan
Checked that Stainless SDK generation succeeds.
# What does this PR do?
- Enable mypy to run in the CI on a subset of the repository
- Fix a few mypy errors
- Run mypy from pre-commit
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (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: Sébastien Han <seb@redhat.com>
Summary:
Allows tools to output metadata. This is useful for evaluating tool
outputs, e.g. RAG tool will output document IDs, which can be used to
score recall.
Will need to make a similar change on the client side to support
ClientTool outputting metadata.
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/client-sdk/agents/test_agents.py
# Problem
Our current Agent framework has discrepancies in definition on how we
handle server side and client side tools.
1. Server Tools: a single Turn is returned including `ToolExecutionStep`
in agenst
2. Client Tools: `create_agent_turn` is called in loop with client agent
lib yielding the agent chunk
ad6ffc63df/src/llama_stack_client/lib/agents/agent.py (L186-L211)
This makes it inconsistent to work with server & client tools. It also
complicates the logs to telemetry to get information about agents turn /
history for observability.
#### Principle
The same `turn_id` should be used to represent the steps required to
complete a user message including client tools.
## Solution
1. `AgentTurnResponseEventType.turn_awaiting_input` status to indicate
that the current turn is not completed, and awaiting tool input
2. `continue_agent_turn` endpoint to update agent turn with client's
tool response.
# What does this PR do?
- Skeleton API as example
## 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.*]
- Just API update, no functionality change
```
llama stack run + client-sdk test
```
<img width="842" alt="image"
src="https://github.com/user-attachments/assets/7ac56b5f-f424-4632-9476-7e0f57555bc3"
/>
[//]: # (## Documentation)
