# What does this PR do?
1. Creates a new `VectorStoreNotFoundError` class
2. Implements the new class where appropriate
Relates to #2379
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
# What does this PR do?
1. Adds a broad schema for custom exception classes in the Llama Stack
project
2. Creates a new `DatasetNotFoundError` class
3. Implements the new class where appropriate
Relates to #2379
Signed-off-by: Nathan Weinberg <nweinber@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 the following error in unit test that was running on up to
date main branch:
```
FAILED tests/unit/distribution/test_inference_recordings.py::TestInferenceRecording::test_recording_mode - ModuleNotFoundError: No module named 'ollama'
FAILED tests/unit/distribution/test_inference_recordings.py::TestInferenceRecording::test_replay_mode - ModuleNotFoundError: No module named 'ollama'
FAILED tests/unit/distribution/test_inference_recordings.py::TestInferenceRecording::test_replay_missing_recording - ModuleNotFoundError: No module named 'ollama'
FAILED tests/unit/distribution/test_inference_recordings.py::TestInferenceRecording::test_embeddings_recording - ModuleNotFoundError: No module named 'ollama'
=============================== 4 failed, 499 passed, 198 warnings in 34.50s ================================
```
<!-- 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.* -->
Run `./scripts/unit-tests.sh`
# What does this PR do?
1. Creates a new `ModelNotFoundError` class
2. Implements the new class where appropriate
Relates to #2379
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
We want to avoid re-triggering the workflow when random other labels are
added (e.g., `meta-cla`, etc.) Also no point restarting the workflow
when someone _unlabels_.
**Description**
This PR removes some of the warnings when uv builds the docs
- Errors appear when generating docs about .md files not appearing in
toctree. ~~Adding content to the `providers-gen.py ` file that adds `---
orphan: true ---` to to each file.~~. Added a toctree generator to the
`providers-gen.py` file, this gets rid of the errors in the builds.
- Deletes the `_openai_compat` files, extension of PR #2849
- Adds the `files` APIs section to the `providers` toctree on the index
page
- Manually adds the `--- orphan: true ---` to the advanced apis. Ill try
to find a way to modify the providers code gen so it automatically adds
it, but this fixes the errors.
- Adds the `testing.md` to the `contributing` toctree
- Adds `starting_llama_stack_server.md` to `distributions` toctree
There are some other warnings im still looking at but this PR gets rid
of most of the toctree errors
Theres also an issue with the actual distribution-codegen that I can
investigate in another PR. Opened a bug for it here #2873
We tried to always keep Ollama enabled. However doing so makes the
provider implementation half-assed -- should it error when it cannot
connect to Ollama or not? What happens during periodic model refresh?
Etc. Instead do the same thing we do for vLLM -- use the `OLLAMA_URL` to
conditionally enable the provider.
## Test Plan
Run `uv run llama stack build --template starter --image-type venv
--run` with and without `OLLAMA_URL` set. Verify using
`llama-stack-client provider list` that ollama is correctly enabled.
# What does this PR do?
- Initialize route_impls to None in constructor to prevent
AttributeError
- Consolidate initialization checks to single point in request() method
- Improve error message to be more helpful ("Please call initialize()
first")
- Add comprehensive test suite to prevent regressions
The library client now has better error handling when users forget to
call initialize(), showing a clear ValueError instead of confusing
AttributeError. All initialization validation is now centralized in the
request() method, with internal methods (_call_non_streaming,
_call_streaming, _convert_body) relying on this single check for
cleaner, more maintainable code.
closes#2943
## Test Plan
`./scripts/unit-tests.sh`
A couple of important updates:
- When recording tests, we cannot be generating a matrix because all the
independent recordings will conflict.
- In fact, we just don't need a matrix on test types any more because
things are very fast and the overhead of `llama stack build` and setting
up `uv` etc. is much more.
- Refactored the running of tests into an independent action
This PR makes setting up Ollama optional for CI. By default, we use
`replay` mode for inference requests and use the stored results from the
`tests/integration/recordings/` directory.
Every so often, users will update tests which will need us to re-record.
To do this, we check for the existence of a label `re-record-tests` on
the PR. If detected,
- ollama is spun up
- inference mode is set to record
- after the tests are done, if any new changes are detected, they are
pushed back to the PR
## Test Plan
This is GitHub CI. Gotta test it live.
Continuing with https://github.com/meta-llama/llama-stack/pull/2952
This also includes a "fix" to inference store related tests so that we
pull a large number of inference responses from the DB so as to always
find the one we just wrote.
Post training tests need _much_ better thinking before we can re-enable
them to be run on every single PR. Running periodically should be
approached only when it is shown that the tests are reliable and as
light-weight as can be; otherwise, it is just kicking the can down the
road.
Continue to build on top of
https://github.com/meta-llama/llama-stack/pull/2941
## Test Plan
Run server with `LLAMA_STACK_TEST_INFERENCE_MODE=record` and then run
the integration tests with `--stack-config=server:starter`. Then restart
the server with `LLAMA_STACK_TEST_INFERENCE_MODE=replay` and re-run the
tests. Verify that no request hit Ollama at any point.
# What does this PR do?
when --image-name is not provided the build script default to the
image_name in the config, this makes sure the same is done for the run
script
## Test Plan
llama stack build w/o --image-name
At the moment, the code coverage action has just been failing. It's
misleading when interpreting the status badge on the main branch.
https://github.com/meta-llama/llama-stack/actions/workflows/coverage-badge.yml
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
<!-- 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.* -->
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Implements a comprehensive recording and replay system for inference API
calls that eliminates dependency on online inference providers during
testing. The system treats inference as deterministic by recording real
API responses and replaying them in subsequent test runs. Applies to
OpenAI clients (which should cover many inference requests) as well as
Ollama AsyncClient.
For storing, we use a hybrid system: Sqlite for fast lookups and JSON
files for easy greppability / debuggability.
As expected, tests become much much faster (more than 3x in just
inference testing.)
```bash
LLAMA_STACK_TEST_INFERENCE_MODE=record LLAMA_STACK_TEST_RECORDING_DIR=<...> \
uv run pytest -s -v tests/integration/inference \
--stack-config=starter \
-k "not( builtin_tool or safety_with_image or code_interpreter or test_rag )" \
--text-model="ollama/llama3.2:3b-instruct-fp16" \
--embedding-model=sentence-transformers/all-MiniLM-L6-v2
```
```bash
LLAMA_STACK_TEST_INFERENCE_MODE=replay LLAMA_STACK_TEST_RECORDING_DIR=<...> \
uv run pytest -s -v tests/integration/inference \
--stack-config=starter \
-k "not( builtin_tool or safety_with_image or code_interpreter or test_rag )" \
--text-model="ollama/llama3.2:3b-instruct-fp16" \
--embedding-model=sentence-transformers/all-MiniLM-L6-v2
```
- `LLAMA_STACK_TEST_INFERENCE_MODE`: `live` (default), `record`, or
`replay`
- `LLAMA_STACK_TEST_RECORDING_DIR`: Storage location (must be specified
for record or replay modes)
# What does this PR do?
- Change max_seq_length to max_length in SFTConfig constructor
- TRL deprecated max_seq_length in Feb 2024 and removed it in v0.20.0
- Reference: https://github.com/huggingface/trl/pull/2895
This resolves the SFT training failure in CI tests
# What does this PR do?
OpenAI Chat Completions supports passing a base64 encoded PDF file to a
model, but Llama Stack currently does not allow for this behavior. This
PR extends our implementation of the OpenAI API spec to change that.
Closes#2129
## Test Plan
A new functional test has been added to test the validity of such a
request
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
Updates provider template from outdated `ollama` to `starter`
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes: #2839
## 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.* -->
We don't need this. We have kept it since existing wisdom is that "it
helps with back-compat". Well, the entire ecosystem is moving to `uv` at
an unprecedented rate and keeping this creates unnecessary work and
confusion. The specific reason I am killing this is that it confuses
`dependabot` which ends up not bumping `uv.lock` which is the more
important file to change.
**What:**
- Added OpenAIChatCompletionTextOnlyMessageContent type for text-only
content validation
- Modified OpenAISystemMessageParam, OpenAIAssistantMessageParam,
OpenAIDeveloperMessageParam, and OpenAIToolMessageParam to use text-only
content type instead of mixed content
- OpenAIUserMessageParam unchanged - still accepts both text and images
- Updated OpenAPI spec files to reflect text-only content restrictions
in schemas
closes#2894
**Why:**
- Enforces OpenAI API compatibility by restricting image content to user
messages only
- Prevents API misuse where images might be sent in message types that
don't support them
- Aligns with OpenAI's actual API behavior where only user messages can
contain multimodal content
- Improves type safety and validation at the API boundary
**Test plan:**
- Added comprehensive parametrized tests covering all 5 OpenAI message
types
- Tests verify text string acceptance for all message types
- Tests verify text list acceptance for all message types
- Tests verify image rejection for system/assistant/developer/tool
messages (ValidationError expected)
- Tests verify user messages still accept images (backward compatibility
maintained)
# What does this PR do?
- Add base_url field to OpenAIConfig with default
"https://api.openai.com/v1"
- Update sample_run_config to support OPENAI_BASE_URL environment
variable
- Modify get_base_url() to return configured base_url instead of
hardcoded value
- Add comprehensive test suite covering:
- Default base URL behavior
- Custom base URL from config
- Environment variable override
- Config precedence over environment variables
- Client initialization with configured URL
- Model availability checks using configured URL
This enables users to configure custom OpenAI-compatible API endpoints
via environment variables or configuration files.
Closes#2910
## Test Plan
run unit tests
# What does this PR do?
external provider docs mention setting provider_id in the build yaml.
Since we changed that to just be provider_type and module, remove
instances of provider_id
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
provider_id is no longer valid in a build.yaml, remove it in the
external provider test
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
This enhancement allows inference providers using LiteLLMOpenAIMixin to
validate model availability against LiteLLM's official provider model
listings, improving reliability and user experience when working with
different AI service providers.
- Add litellm_provider_name parameter to LiteLLMOpenAIMixin constructor
- Add check_model_availability method to LiteLLMOpenAIMixin using
litellm.models_by_provider
- Update Gemini, Groq, and SambaNova inference adapters to pass
litellm_provider_name
## Test Plan
standard CI.
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
- Added `set -e` to the beginning of the unit test script to ensure the
script exits on failure and correctly fails the CI when tests do not
pass.
- Fixed all unit tests that were silently failing in the CI.
- Fixed Python 3.13 unit test CI failing silently.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes#2877
## 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.* -->
- **Previously:** Unit tests passing in CI eventhough it failed 11 tests
->
[CI-run](4683681501 (step):4:2097)
- **Made the fix. Now, ensuring CI fails as expected on test failures:**
Unit tests failing in CI with 1 failed test ->
[CI-run](4684234247 (step):4:1506)
- This PR shows the CI passing and all unit tests passing.
# What does this PR do?
the server logs have a persistent `core: refreshing registry` log that
clogs up the output. Switch it to debug
this is what it looked like:
<img width="1126" height="1028" alt="Screenshot 2025-07-28 at 9 56
44 AM"
src="https://github.com/user-attachments/assets/a1880fd3-7fc7-4a97-bfb8-89a62e4c5c19"
/>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
currently the external provider tests don't upload log files as
artifacts nor do they use LLAMA_STACK_LOG_FILE. align with the other
integration tests
## Test Plan
logs should be present in the two tests on this PR
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
in #2637, I combined the run and build config provider types to both use
`Provider`
since this includes a provider_id, a user must now specify this when
writing a build yaml. This is not very clear because all a user should
care about upon build is the code to be installed (the module and the
provider_type)
introduce `BuildProvider` and fixup the parts of the code impacted by
this
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
Our CI is entirely undocumented, this commit adds a README.md file with
a table of the current CI and what is does
---------
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
Add support for deleting individual chunks from vector stores
- Add abstract remove_chunk() method to EmbeddingIndex base class
- Implement chunk deletion for Faiss provider, SQLite Vec, Milvus,
PGVector
- Placeholder implementations with NotImplementedError for
Chroma/Qdrant/Weaviate
- Integrate chunk deletion into OpenAI vector store file deletion flow
- removed xfail from
test_openai_vector_store_delete_file_removes_from_vector_store
Closes: #2477
---------
Signed-off-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
# What does this PR do?
Enable Chroma inline unit tests and fix integration tests.
<!-- 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.* -->
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Avoid the error message:
```
INFO 2025-07-24 21:51:54,530 __main__:598 server: Received interrupt signal, shutting down gracefully...
ERROR 2025-07-24 21:51:54,692 asyncio:1826 uncategorized: Task was destroyed but it is pending!
task: <Task pending name='Task-15' coro=<refresh_registry() running at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/stack.py:356> wait_for=<Future pending cb=[Task.task_wakeup()]> cb=>
```
