Commit graph

15 commits

Author SHA1 Message Date
Ashwin Bharambe
a385e0d95e more better 2025-10-05 21:55:44 -07:00
Ashwin Bharambe
ea233c2134 feat!: providers use unified 'persistence' field
BREAKING CHANGE: Provider config field names changed for semantic clarity

- Rename kvstore → persistence for all providers
- Simple providers: flat persistence with backend reference
- Complex providers (agents): nested persistence.agent_state + persistence.responses
- Files provider: metadata_store → persistence
- Provider configs now clearly express 'how do I persist?' not 'what type of store?'

Example:
  # Before
  config:
    kvstore:
      backend: kvstore
      namespace: faiss

  # After
  config:
    persistence:
      backend: kvstore
      namespace: faiss

  # Agents (nested)
  config:
    persistence:
      agent_state:
        backend: kvstore
        namespace: agents
      responses:
        backend: sqlstore
        namespace: responses
2025-10-05 20:33:03 -07:00
Ashwin Bharambe
490110eba2 Simplify to single 'default' backend name
- Replace kvstore/sqlstore backend names with unified 'default'
- Context-aware parsing handles KVStore vs SqlStore based on usage
- Provider configs use 'backend: default' everywhere
- Much cleaner: kvstore { backend: default } instead of { backend: kvstore }
2025-10-05 19:06:47 -07:00
Ashwin Bharambe
5672e70832 Fix discriminator ambiguity with context-aware backend parsing
- Both SqliteKVStoreConfig and SqliteSqlStoreConfig use type='sqlite'
- Pydantic cannot distinguish them in a union
- Solution: Custom validator parses backends based on which stores reference them
- Metadata store requires KVStore, inference/conversations require SqlStore
- Separate kvstore/sqlstore backends in configs for clarity
2025-10-05 14:16:54 -07:00
Ashwin Bharambe
b1659369e8 Refactor persistence config to use stores key with unified backends
- Add StoresConfig to group all store references under persistence.stores
- Use single 'default' backend instead of separate metadata_backend/inference_backend
- Update resolver to access persistence.stores.{metadata,inference,conversations}
- All SQLite distributions now use single store.db file with shared backend
2025-10-05 13:20:44 -07:00
Ashwin Bharambe
ac9b4b4350 Migrate starter to use unified persistence config 2025-10-05 13:14:44 -07:00
Ashwin Bharambe
42414a1a1b
fix(logging): disable console telemetry sink by default (#3623)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 21s
Test Llama Stack Build / build-single-provider (push) Failing after 25s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 27s
Unit Tests / unit-tests (3.12) (push) Failing after 22s
API Conformance Tests / check-schema-compatibility (push) Successful in 33s
UI Tests / ui-tests (22) (push) Successful in 39s
Pre-commit / pre-commit (push) Successful in 1m12s
The current span processing dumps so much junk on the console that it
makes actual understanding of what is going on in the server impossible.
I am killing the console sink as a default. If you want, you are always
free to change your run.yaml to add it.

Before: 
<img width="1877" height="1107" alt="image"
src="https://github.com/user-attachments/assets/3a7ad261-e2ba-4d40-9820-fcc282c8df37"
/>

After:
<img width="1919" height="470" alt="image"
src="https://github.com/user-attachments/assets/bc7cf763-fba9-4e95-a4b5-f65f6d1c5332"
/>
2025-09-30 14:58:05 -07:00
Sébastien Han
f31bcc11bc
feat: add Azure OpenAI inference provider support (#3396)
# What does this PR do?

Llama-stack now supports a new OpenAI compatible endpoint with Azure
OpenAI. The starter distro has been updated to add the new remote
inference provider.

A few tests have been modified and improved.

## Test Plan

Deploy a model in the Aure portal then:

```
$ AZURE_API_KEY=... AZURE_API_BASE=... uv run llama stack build --image-type venv --providers inference=remote::azure --run
...
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model azure/gpt-4.1 tests/integration/inference/test_openai_completion.py
...

Results:

```
============================================= test session starts
============================================== platform darwin -- Python
3.12.8, pytest-8.4.1, pluggy-1.6.0 --
/Users/leseb/Documents/AI/llama-stack/.venv/bin/python3 cachedir:
.pytest_cache
metadata: {'Python': '3.12.8', 'Platform':
'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1',
'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1',
'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0',
'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval':
'0.11.0', 'hydra-core': '1.3.2'}} rootdir:
/Users/leseb/Documents/AI/llama-stack
configfile: pyproject.toml
plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0,
json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1,
nbval-0.11.0, hydra-core-1.3.2 asyncio: mode=Mode.AUTO,
asyncio_default_fixture_loop_scope=None,
asyncio_default_test_loop_scope=function collected 27 items


tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=azure/gpt-5-mini-inference:completion:sanity]
SKIPPED [ 3%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=azure/gpt-5-mini-inference:completion:suffix]
SKIPPED [ 7%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=azure/gpt-5-mini-inference:completion:sanity]
SKIPPED [ 11%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-1]
SKIPPED [ 14%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=azure/gpt-5-mini]
SKIPPED [ 18%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01]
PASSED [ 22%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 25%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 29%]
tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-True]
PASSED [ 33%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-True]
PASSED [ 37%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=azure/gpt-5-mini]
SKIPPEDed files.) [ 40%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-0]
SKIPPED [ 44%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02]
PASSED [ 48%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 51%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 55%]
tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-False]
PASSED [ 59%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-False]
PASSED [ 62%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01]
PASSED [ 66%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 70%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 74%]
tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-True]
PASSED [ 77%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-True]
PASSED [ 81%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02]
PASSED [ 85%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 88%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 92%]
tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-False]
PASSED [ 96%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-False]
PASSED [100%]

=========================================== short test summary info
============================================ SKIPPED [3]
tests/integration/inference/test_openai_completion.py:63: Model
azure/gpt-5-mini hosted by remote::azure doesn't support OpenAI
completions. SKIPPED [3]
tests/integration/inference/test_openai_completion.py:118: Model
azure/gpt-5-mini hosted by remote::azure doesn't support vllm extra_body
parameters. SKIPPED [1]
tests/integration/inference/test_openai_completion.py:124: Model
azure/gpt-5-mini hosted by remote::azure doesn't support chat completion
calls with base64 encoded files. ================================== 20
passed, 7 skipped, 2 warnings in 51.77s
==================================
```

Signed-off-by: Sébastien Han <seb@redhat.com>
2025-09-11 13:48:38 +02:00
Ashwin Bharambe
9fa69b0337
feat(distro): no huggingface provider for starter (#3258)
The `trl` dependency brings in `accelerate` which brings in nvidia
dependencies for torch. We cannot have that in the starter distro. As
such, no CPU-only post-training for the huggingface provider.
2025-08-26 14:06:36 -07:00
Ashwin Bharambe
7519b73fcc
feat(distro): fork off a starter-gpu distribution (#3240)
The starter distribution added post-training which added torch
dependencies which pulls in all the nvidia CUDA libraries. This made our
starter container very big. We have worked hard to keep the starter
container small so it serves its purpose as a starter. This PR tries to
get it back to its size by forking off duplicate "-gpu" providers for
post-training. These forked providers are then used for a new
`starter-gpu` distribution which can pull in all dependencies.
2025-08-22 15:47:15 -07:00
slekkala1
7519ab4024
feat: Code scanner Provider impl for moderations api (#3100)
# What does this PR do?
Add CodeScanner implementations

## Test Plan
`SAFETY_MODEL=CodeScanner LLAMA_STACK_CONFIG=starter uv run pytest -v
tests/integration/safety/test_safety.py
--text-model=llama3.2:3b-instruct-fp16
--embedding-model=all-MiniLM-L6-v2 --safety-shield=ollama`

This PR need to land after this
https://github.com/meta-llama/llama-stack/pull/3098
2025-08-18 14:15:40 -07:00
Matthew Farrellee
914c7be288
feat: add batches API with OpenAI compatibility (with inference replay) (#3162)
Add complete batches API implementation with protocol, providers, and
tests:

Core Infrastructure:
- Add batches API protocol using OpenAI Batch types directly
- Add Api.batches enum value and protocol mapping in resolver
- Add OpenAI "batch" file purpose support
- Include proper error handling (ConflictError, ResourceNotFoundError)

Reference Provider:
- Add ReferenceBatchesImpl with full CRUD operations (create, retrieve,
cancel, list)
- Implement background batch processing with configurable concurrency
- Add SQLite KVStore backend for persistence
- Support /v1/chat/completions endpoint with request validation

Comprehensive Test Suite:
- Add unit tests for provider implementation with validation
- Add integration tests for end-to-end batch processing workflows
- Add error handling tests for validation, malformed inputs, and edge
cases

Configuration:
- Add max_concurrent_batches and max_concurrent_requests_per_batch
options
- Add provider documentation with sample configurations

Test with -

```
$ uv run llama stack build --image-type venv --providers inference=YOU_PICK,files=inline::localfs,batches=inline::reference --run &
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/unit/providers/batches tests/integration/batches --text-model YOU_PICK
```

addresses #3066

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
2025-08-15 15:34:15 -07:00
Eran Cohen
a4bad6c0b4
feat: Add Google Vertex AI inference provider support (#2841)
Some checks failed
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 10s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 12s
Python Package Build Test / build (3.13) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 10s
Test Llama Stack Build / generate-matrix (push) Successful in 8s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 13s
Test External API and Providers / test-external (venv) (push) Failing after 11s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 17s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 10s
Test Llama Stack Build / build-single-provider (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 8s
Unit Tests / unit-tests (3.12) (push) Failing after 10s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 15s
Update ReadTheDocs / update-readthedocs (push) Failing after 9s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 23s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 47s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 49s
Unit Tests / unit-tests (3.13) (push) Failing after 39s
Pre-commit / pre-commit (push) Successful in 1m37s
# What does this PR do?
- Add new Vertex AI remote inference provider with litellm integration
- Support for Gemini models through Google Cloud Vertex AI platform
- Uses Google Cloud Application Default Credentials (ADC) for
authentication
- Added VertexAI models: gemini-2.5-flash, gemini-2.5-pro,
gemini-2.0-flash.
- Updated provider registry to include vertexai provider
- Updated starter template to support Vertex AI configuration
- Added comprehensive documentation and sample configuration

<!-- If resolving an issue, uncomment and update the line below -->
relates to https://github.com/meta-llama/llama-stack/issues/2747

## 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: Eran Cohen <eranco@redhat.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
2025-08-11 08:22:04 -04:00
Ashwin Bharambe
7f834339ba
chore(misc): make tests and starter faster (#3042)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 9s
Python Package Build Test / build (3.12) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 12s
Test Llama Stack Build / generate-matrix (push) Successful in 11s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 14s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 22s
Test External API and Providers / test-external (venv) (push) Failing after 14s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 15s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 22s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build-single-provider (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 18s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 20s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 16s
Python Package Build Test / build (3.13) (push) Failing after 53s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 59s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 1m1s
Update ReadTheDocs / update-readthedocs (push) Failing after 1m6s
Pre-commit / pre-commit (push) Successful in 1m53s
A bunch of miscellaneous cleanup focusing on tests, but ended up
speeding up starter distro substantially.

- Pulled llama stack client init for tests into `pytest_sessionstart` so
it does not clobber output
- Profiling of that told me where we were doing lots of heavy imports
for starter, so lazied them
- starter now starts 20seconds+ faster on my Mac
- A few other smallish refactors for `compat_client`
2025-08-05 14:55:05 -07:00
Ashwin Bharambe
cc87995e2b
chore: rename templates to distributions (#3035)
As the title says. Distributions is in, Templates is out.

`llama stack build --template` --> `llama stack build --distro`. For
backward compatibility, the previous option is kept but results in a
warning.

Updated `server.py` to remove the "config_or_template" backward
compatibility since it has been a couple releases since that change.
2025-08-04 11:34:17 -07:00
Renamed from llama_stack/templates/starter/run.yaml (Browse further)