https://github.com/meta-llama/llama-stack-client-python/pull/238 updated
llama-stack-client to also support Open AI endpoints for embeddings,
files, vector-stores. This updates the test to test all configs --
openai sdk, llama stack sdk and library-as-client.
Updated the `search` functionality return response to match openai.
## Test Plan
```
pytest -sv --stack-config=http://localhost:8321 tests/integration/vector_io/test_openai_vector_stores.py --embedding-model all-MiniLM-L6-v2
```
# What does this PR do?
Fixes provider weaviate `query_vector` function for when the distance
between the query embedding and an embedding within the vector db is 0
(identical vectors). Catches `ZeroDivisionError` and then sets `score`
to infinity, which represent maximum similarity.
<!-- If resolving an issue, uncomment and update the line below -->
Closes [#2381]
## Test Plan
Checkout this PR
Execute this code and there will no longer be a `ZeroDivisionError`
exception
```
from llama_stack_client import LlamaStackClient
base_url = "http://localhost:8321"
client = LlamaStackClient(base_url=base_url)
models = client.models.list()
embedding_model = (
em := next(m for m in models if m.model_type == "embedding")
).identifier
embedding_dimension = 384
_ = client.vector_dbs.register(
vector_db_id="foo_db",
embedding_model=embedding_model,
embedding_dimension=embedding_dimension,
provider_id="weaviate",
)
chunk = {
"content": "foo",
"mime_type": "text/plain",
"metadata": {
"document_id": "foo-id"
}
}
client.vector_io.insert(vector_db_id="foo_db", chunks=[chunk])
client.vector_io.query(vector_db_id="foo_db", query="foo")
```
# What does this PR do?
The test wasn't using the correct virtual environment. Also augment the
console width for logs.
Signed-off-by: Sébastien Han <seb@redhat.com>
Extracts common OpenAI vector-store code into its own mixin so that all
providers can share the same core logic.
This also makes it easy for Llama Stack to support both vector-stores
and Llama Stack APIs in the interim so that both share the same
underlying vector-dbs.
Each provider contains storage specific logic to `create / edit / delete
/ list` vector dbs while the plumbing logic is standardized in the
common code.
Ensured that this works well with both faiss and sqllite-vec.
### Test Plan
```
llama stack run starter
pytest -sv --stack-config http://localhost:8321 tests/integration/vector_io/test_openai_vector_stores.py --embedding-model all-MiniLM-L6-v2
```
Adding OpenAI compat `/v1/vector-store` apis.
This PR implements the `faiss` provider with followup PRs coming up for
other providers.
Added routes to create, update, delete, list vector stores.
Also added route to search a vector store
Inserting into vector stores is missing and will be a follow up diff.
### Test Plan
- Added new integration test for testing the faiss provider
```
pytest -sv --stack-config http://localhost:8321 tests/integration/vector_io/test_openai_vector_stores.py --embedding-model all-MiniLM-L6-v2
```
# What does this PR do?
This loosens up the tool call function name and arguments checks in
`tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls`
because the small models we use in CI cannot reliably get the tool call
function name or arguments exactly right.
Closes#2345
## Test Plan
I ran this flaking test in a loop, let it run many dozens of times, and
didn't observe any flakes after the changes. Previously it flaked quite
regularly.
```
while uv run pytest -s -v \
'tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[llama_stack_client-txt=3B-False]' \
--stack-config=http://localhost:8321 \
--text-model="meta-llama/Llama-3.2-3B-Instruct" \
--embedding-model=all-MiniLM-L6-v2; do; sleep 0.1; done
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
Fixes provider pgvector `query_vector` function for when the distance
between the query embedding and an embedding within the vector db is 0
(identical vectors). Catches `ZeroDivisionError` and then sets `score`
to infinity, which represent maximum similarity.
<!-- If resolving an issue, uncomment and update the line below -->
Closes [#2381]
## Test Plan
Checkout this PR
Execute this code and there will no longer be a `ZeroDivisionError`
exception
```
from llama_stack_client import LlamaStackClient
base_url = "http://localhost:8321"
client = LlamaStackClient(base_url=base_url)
models = client.models.list()
embedding_model = (
em := next(m for m in models if m.model_type == "embedding")
).identifier
embedding_dimension = 384
_ = client.vector_dbs.register(
vector_db_id="foo_db",
embedding_model=embedding_model,
embedding_dimension=embedding_dimension,
provider_id="pgvector",
)
chunk = {
"content": "foo",
"mime_type": "text/plain",
"metadata": {
"document_id": "foo-id"
}
}
client.vector_io.insert(vector_db_id="foo_db", chunks=[chunk])
client.vector_io.query(vector_db_id="foo_db", query="foo")
```
# What does this PR do?
Adds try-catch to faiss `query_vector` function for when the distance
between the query embedding and an embedding within the vector db is 0
(identical vectors). Catches `ZeroDivisionError` and then appends `(1.0
/ sys.float_info.min)` to `scores` to represent maximum similarity.
<!-- If resolving an issue, uncomment and update the line below -->
Closes [#2381]
## Test Plan
Checkout this PR
Execute this code and there will no longer be a `ZeroDivisionError`
exception
```
from llama_stack_client import LlamaStackClient
base_url = "http://localhost:8321"
client = LlamaStackClient(base_url=base_url)
models = client.models.list()
embedding_model = (
em := next(m for m in models if m.model_type == "embedding")
).identifier
embedding_dimension = 384
_ = client.vector_dbs.register(
vector_db_id="foo_db",
embedding_model=embedding_model,
embedding_dimension=embedding_dimension,
provider_id="faiss",
)
chunk = {
"content": "foo",
"mime_type": "text/plain",
"metadata": {
"document_id": "foo-id"
}
}
client.vector_io.insert(vector_db_id="foo_db", chunks=[chunk])
client.vector_io.query(vector_db_id="foo_db", query="foo")
```
### Running unit tests
`uv run pytest tests/unit/rag/test_rag_query.py -v`
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
To add health status check for remote VLLM
<!-- 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.* -->
PR includes the unit test to test the added health check implementation
feature.
# What does this PR do?
Instead of downloading the models each time we now have a single Ollama
container that is baked with the models pulled and ready to use.
This will remove the CI flakiness on model pulling.
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
## Test Plan
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/files/test_files.py::test_openai_client_basic_operations
trying to run `llama` cli after installing wheel fails with this error
```
Traceback (most recent call last):
File "/tmp/tmp.wdZath9U6j/.venv/bin/llama", line 4, in <module>
from llama_stack.cli.llama import main
File "/tmp/tmp.wdZath9U6j/.venv/lib/python3.10/site-packages/llama_stack/__init__.py", line 7, in <module>
from llama_stack.distribution.library_client import ( # noqa: F401
ModuleNotFoundError: No module named 'llama_stack.distribution.library_client'
```
This PR fixes it by ensurring that all sub-directories of `llama_stack`
are also included.
Also, fixes the missing `fastapi` dependency issue.
# What does this PR do?
Expand the test matrix to include Python 3.10, 3.11, and 3.12 to ensure
the project runs correctly on these versions. This will give us
confidence to begin considering an increase to the project's minimum
supported Python version.
Signed-off-by: Sébastien Han <seb@redhat.com>
The non-streaming version is just a small layer on top of the streaming
version - just pluck off the final `response.completed` event and return
that as the response!
This PR also includes a couple other changes which I ended up making
while working on it on a flight:
- changes to `ollama` so it does not pull embedding models
unconditionally
- a small fix to library client to make the stream and non-stream cases
a bit more symmetric
This PR fixes a runtime import error caused by missing OpenTelemetry
dependencies during `llama stack run`.
Specifically, the following imports fail if `opentelemetry-sdk` and
`opentelemetry-exporter-otlp-proto-http` are not present in the
environment:
```python
from opentelemetry import metrics, trace
from opentelemetry.exporter.otlp.proto.http.metric_exporter import OTLPMetricExporter
```
See
[llama\_stack/providers/inline/telemetry/meta\_reference/telemetry.py#L10-L19](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/inline/telemetry/meta_reference/telemetry.py#L10-L19)
This PR resolves the issue by adding both packages to the
`SERVER_DEPENDENCIES` list:
```python
"opentelemetry-sdk",
"opentelemetry-exporter-otlp-proto-http",
```
### Reproduction Steps
```bash
llama stack build --config llama.yaml --image-type venv --image-name fun-with-lamas
llama stack run ~/.llama/distributions/fun-with-lamas/fun-with-lamas-run.yaml
```
Results in:
```
ModuleNotFoundError: No module named 'opentelemetry'
```
or
```
ModuleNotFoundError: No module named 'opentelemetry.exporter'
```
Signed-off-by: Jose Angel Morena <jmorenas@redhat.com>
Co-authored-by: raghotham <rsm@meta.com>
# What does this PR do?
This adds some initial content documenting our OpenAI compatible APIs
- Responses, Chat Completions, Completions, and Models - along with
instructions on how to use them via OpenAI or Llama Stack clients and
some simple examples for each.
It's not a lot of content, but it's a start so that users have some idea
how to get going as we continue to work on these APIs.
## Test Plan
I generated the docs site locally and verified things render properly. I
also ran each code example to ensure it works as expected. And, I asked
my AI code assistant to do a quick spell-check and review of the docs
and it didn't flag any obvious errors.
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Francisco Arceo <farceo@redhat.com>
This allows a set of rules to be defined for determining access to
resources. The rules are (loosely) based on the cedar policy format.
A rule defines a list of action either to permit or to forbid. It may
specify a principal or a resource that must match for the rule to take
effect. It may also specify a condition, either a 'when' or an 'unless',
with additional constraints as to where the rule applies.
A list of rules is held for each type to be protected and tried in order
to find a match. If a match is found, the request is permitted or
forbidden depening on the type of rule. If no match is found, the
request is denied. If no rules are specified for a given type, a rule
that allows any action as long as the resource attributes match the user
attributes is added (i.e. the previous behaviour is the default.
Some examples in yaml:
```
model:
- permit:
principal: user-1
actions: [create, read, delete]
comment: user-1 has full access to all models
- permit:
principal: user-2
actions: [read]
resource: model-1
comment: user-2 has read access to model-1 only
- permit:
actions: [read]
when:
user_in: resource.namespaces
comment: any user has read access to models with matching attributes
vector_db:
- forbid:
actions: [create, read, delete]
unless:
user_in: role::admin
comment: only user with admin role can use vector_db resources
```
---------
Signed-off-by: Gordon Sim <gsim@redhat.com>
# What does this PR do?
This adds the missing `text` parameter to the Responses API that is how
users control structured outputs. All we do with that parameter is map
it to the corresponding chat completion response_format.
## Test Plan
The new unit tests exercise the various permutations allowed for this
property, while a couple of new verification tests actually use it for
real to verify the model outputs are following the format as expected.
Unit tests:
`python -m pytest -s -v
tests/unit/providers/agents/meta_reference/test_openai_responses.py`
Verification tests:
```
llama stack run llama_stack/templates/together/run.yaml
pytest -s -vv 'tests/verifications/openai_api/test_responses.py' \
--base-url=http://localhost:8321/v1/openai/v1 \
--model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
Note that the verification tests can only be run with a real Llama Stack
server (as opposed to using the library client via
`--provider=stack:together`) because the Llama Stack python client is
not yet updated to accept this text field.
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
This PR fixes a bug where running a known template by name using:
`llama stack run ollama`
would fail with the following error:
`ValueError: Config file ollama does not exist`
<!-- If resolving an issue, uncomment and update the line below -->
Closes#2291
## 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.* -->
`llama stack run ollama` should work
# What does this PR do?
TSIA
Added Files provider to the fireworks template. Might want to add to all
templates as a follow-up.
## Test Plan
llama-stack pytest tests/unit/files/test_files.py
llama-stack llama stack build --template fireworks --image-type conda
--run
LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s -v
tests/integration/files/
# What does this PR do?
The chat completion ids generated by Ollama are not unique enough to use
with stored chat completions as they rely on only 3 numbers of
randomness to give unique values - ie `chatcmpl-373`. This causes
frequent collisions in id values of chat completions in Ollama, which
creates issues in our SQL storage of chat completions by id where it
expects ids to actually be unique.
So, this adjusts Ollama responses to use uuids as unique ids. This does
mean we're replacing the ids generated natively by Ollama. If we don't
wish to do this, we'll either need to relax the unique constraint on our
chat completions id field in the inference storage or convince Ollama
upstream to use something closer to uuid values here.
Closes#2315
## Test Plan
I tested by running the openai completion / chat completion integration
tests in a loop. Without this change, I regularly get unique id
collisions. With this change, I do not. We sometimes see flakes from
these unique id collisions in our CI tests, and this will resolve those.
```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack run llama_stack/templates/ollama/run.yaml
while true; do; \
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
pytest -s -v \
tests/integration/inference/test_openai_completion.py \
--stack-config=http://localhost:8321 \
--text-model="meta-llama/Llama-3.2-3B-Instruct"; \
done
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
I think the implementation needs more simplification. Spent way too much
time trying to get the tests pass with models not co-operating :(
Finally had to switch claude-sonnet to get things to pass reliably.
### Test Plan
```
export TAVILY_SEARCH_API_KEY=...
export OPENAI_API_KEY=...
uv run pytest -p no:warnings \
-s -v tests/verifications/openai_api/test_responses.py \
--provider=stack:starter \
--model openai/gpt-4o
```
# What does this PR do?
1. remove openai dep
2. temporarily update llama-stack-client to stainless sync'd branch as
the responses/inputitems API wasn't included in the last push. This will
automatically be updated to the next version in the release.
## Test Plan
npm run dev
go to any responses details page
fixes provider to use stream var correctly
Before
```
curl --request POST \
--url http://localhost:8321/v1/openai/v1/chat/completions \
--header 'content-type: application/json' \
--data '{
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"messages": [
{
"role": "user",
"content": "Who are you?"
}
]
}'
{"detail":"Internal server error: An unexpected error occurred."}
```
After
```
llama-stack % curl --request POST \
--url http://localhost:8321/v1/openai/v1/chat/completions \
--header 'content-type: application/json' \
--data '{
"model": "accounts/fireworks/models/llama4-scout-instruct-basic",
"messages": [
{
"role": "user",
"content": "Who are you?"
}
]
}'
{"id":"chatcmpl-97978538-271d-4c73-8d4d-c509bfb6c87e","choices":[{"message":{"role":"assistant","content":"I'm an AI assistant designed by Meta. I'm here to answer your questions, share interesting ideas and maybe even surprise you with a fresh perspective. What's on your mind?","name":null,"tool_calls":null},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","created":1748896403,"model":"accounts/fireworks/models/llama4-scout-instruct-basic"}%
```
This Kubernetes cluster has:
- vLLM for serving an inference model
- vLLM for serving a safety model
- Postgres DB (for metadata and other state for the Llama Stack distro)
- Chroma DB for Vector IO (memory)
Perhaps most importantly, this was me trying to learn Kubernetes for the
first time.
## Test Plan
Run `sh apply.sh` against an EKS cluster, then after `kubectl
port-forward service/llama-stack-service 8321:8321` and after many
attempts, we have finally:
<img width="1589" alt="image"
src="https://github.com/user-attachments/assets/c69f242d-6aaa-4def-9f7c-172113b8bfc1"
/>
<img width="1978" alt="image"
src="https://github.com/user-attachments/assets/cf678404-f551-4fa5-9077-bebe3e8e8ae8"
/>
