# What does this PR do?
DocVQA asks model to look a a picture, then answer a question given in
text, with a text answer by text information in the picture. these
questions often require understanding of relative positions of texts
within the picture.
original dataset is defined in the "Task1" of
https://www.docvqa.org/datasets
## Test Plan
setup llama server with
```
llama stack run ./llama_stack/templates/open-benchmark/run.yaml
```
then send traffic:
```
llama-stack-client eval run-benchmark "meta-reference-docvqa" --model-id meta-llama/Llama-3.3-70B-Instruct --output-dir /tmp/gpqa --num-examples 200
```
# What does this PR do?
FAILED
tests/integration/tools/test_tools.py::test_toolsgroups_unregister[None]
- AttributeError: 'coroutine' object has no attribute 'data'
## Test Plan
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/tools/test_tools.py
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1704).
* #1705
* __->__ #1704
## 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?
- To make it easier, delete existing `eval/scoring/scoring_function`
apis. There will be a bunch of broken impls here. The sequence is:
1. migrate benchmark graders
2. clean up existing scoring functions
- Add a skeleton evaluation impl to make tests pass.
## Test Plan
tested in following PRs
[//]: # (## Documentation)
These block on io reads which in turn block the
server. Move them to their own thread.
Closes: #1697
# What does this PR do?
To avoid blocking the main eventloop, updates datasetio/localfs to load
data in a seperate thread
Signed-off-by: Derek Higgins <derekh@redhat.com>
### What does this PR do?
Currently, `ToolCall.arguments` is a `Dict[str, RecursiveType]`.
However, on the client SDK side -- the `RecursiveType` gets deserialized
into a number ( both int and float get collapsed ) and hence when params
are `int` they get converted to float which might break client side
tools that might be doing type checking.
Closes: https://github.com/meta-llama/llama-stack/issues/1683
### Test Plan
Stainless changes --
https://github.com/meta-llama/llama-stack-client-python/pull/204
```
pytest -s -v --stack-config=fireworks tests/integration/agents/test_agents.py --text-model meta-llama/Llama-3.1-8B-Instruct
```
# What does this PR do?
This is a follow-up of
https://github.com/meta-llama/llama-stack/issues/965 to avoid mentioning
exclusive support on Llama models.
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
- fixes routing table so that `llama stack run` works
- fixes pre-commit
- one of many fixes to address implementation fix
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
llama stack run
```
[//]: # (## Documentation)
This PR adds support (or is a proposal for) for supporting API KEY
authentication on the Llama Stack server end. `llama-stack-client`
already supports accepting an api_key parameter and passes it down
through every request as an `Authentication: ` header.
Currently, Llama Stack does not propose APIs for handling authentication
or authorization for resources of any kind. Given that, and the fact
that any deployment will typically have _some_ authentication system
present, we simply adopt a delegation mechanism: delegate to an HTTPS
endpoint performing key management / authentication.
It is configured via:
```yaml
server:
auth:
endpoint: <...>
```
in the run.yaml configuration.
## How It Works
When authentication is enabled:
1. Every API request must include an `Authorization: Bearer <token>`
header
2. The server will send a _POST_ validation request to the configured
endpoint with the following payload:
```json
{
"api_key": "<token>",
"request": {
"path": "/api/path",
"headers": { "header1": "value1", ... },
"params": { "param1": "value1", ... }
}
}
```
3. If the authentication endpoint returns a 200 status code, the request
is allowed to proceed
4. If the authentication endpoint returns any other status code, a 401
Unauthorized response is returned
## Test Plan
Unit tests
# 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?
The previous installation instructions were mostly duplicating
information already covered in the documentation, either in the “Start a
Server” or “Contributing Guide” sections. Removed these redundant
details to avoid confusion and streamline the setup process.
Signed-off-by: Sébastien Han <seb@redhat.com>
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This is a follow up from
https://github.com/meta-llama/llama-stack/pull/1463. cc @yanxi0830
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
Made code interpreter tool call to be async such that its non blocking
## Test Plan
pytest -s -v tests/integration/agents/test_agents.py
--stack-config=together --text-model=meta-llama/Llama-3.3-70B-Instruct
<img width="1693" alt="image"
src="https://github.com/user-attachments/assets/42520bb6-7acf-42d5-b71f-b35ca149d722"
/>
[//]: # (## Documentation)
Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>
# What does this PR do?
This makes it easier to know the statuses of both and identifying failed
builds.
Signed-off-by: Yuan Tang <terrytangyuan@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?
Removed local execution option from the remote Qdrant provider and
introduced an explicit inline provider for the embedded execution.
Updated the ollama template to include this option: this part can be
reverted in case we don't want to have two default `vector_io`
providers.
(Closes#1082)
## Test Plan
Build and run an ollama distro:
```bash
llama stack build --template ollama --image-type conda
llama stack run --image-type conda ollama
```
Run one of the sample ingestionapplicatinos like
[rag_with_vector_db.py](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/rag_with_vector_db.py),
but replace this line:
```py
selected_vector_provider = vector_providers[0]
```
with the following, to use the `qdrant` provider:
```py
selected_vector_provider = vector_providers[1]
```
After running the test code, verify the timestamp of the Qdrant store:
```bash
% ls -ltr ~/.llama/distributions/ollama/qdrant.db/collection/test_vector_db_*
total 784
-rw-r--r--@ 1 dmartino staff 401408 Feb 26 10:07 storage.sqlite
```
[//]: # (## Documentation)
---------
Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
Co-authored-by: Francisco Arceo <farceo@redhat.com>
# What does this PR do?
Enable ruff for scripts.
[//]: # (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?
support nvidia hosted 3.2 11b/90b vision models. they are not hosted on
the common https://integrate.api.nvidia.com/v1. they are hosted on their
own individual urls.
## Test Plan
`LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -s -v
tests/client-sdk/inference/test_vision_inference.py
--inference-model=meta/llama-3.2-11b-vision-instruct -k image`
# What does this PR do?
Adds a container file that can be used to build the playground UI.
This file will be built by this PR in the stack-ops repo:
https://github.com/meta-llama/llama-stack-ops/pull/9
Docker command in the docs will need to change once I know the address
of the official repository.
## Test Plan
Tested image on my local Openshift Instance using this helm chart:
https://github.com/Jaland/llama-stack-helm/tree/main/llama-stack
[//]: # (## Documentation)
---------
Co-authored-by: Jamie Land <hokie10@gmail.com>
# What does this PR do?
Run additional tests in a matrix to accelerate the process and clearly
identify failing providers.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
Add the option to not verify SSL certificates for the remote-vllm
provider. This allows llama stack server to talk to remote LLMs which
have self-signed certificates
Partially addresses #1545
# Summary:
Includes fixes to get test_agents working with openAI model, e.g. tool
parsing and message conversion
# Test Plan:
```
LLAMA_STACK_CONFIG=dev pytest -s -v tests/integration/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model openai/gpt-4o-mini
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1550).
* #1556
* __->__ #1550
# What does this PR do?
This avoids flaky timeout issue observed in CI builds, e.g.
3891286596
## Test Plan
Ran multiple times and pass consistently.
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
This PR adds dependabot updates for Python dependencies. In addition:
* Consistent weekly schedule on a specific day
* Specific commit messages
* `open-pull-requests-limit` is intentional to avoid upgrading
dependencies that will likely cause regressions. We want to keep the
focus here on security updates only
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
