120 commits

Author	SHA1	Message	Date
ehhuang	e9926564bd	fix: authorized sql store with postgres (#2641) ... # What does this PR do? postgres has different json extract syntax from sqlite ## Test Plan added integration test	2025-07-07 19:36:34 -07:00
Sébastien Han	5561f1c36d	ci: error when a pipefails (#2635) ... # What does this PR do? The CI was failing but the error was eaten by the pipe. Now we run the task with pipefail. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-07-07 16:47:30 +02:00
Sébastien Han	c4349f532b	feat: consolidate most distros into "starter" (#2516) ... # What does this PR do? * Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: https://github.com/meta-llama/llama-stack/issues/2502. ~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama to work properly in the CI.~ TODO: - [ ] We can only update `install.sh` when we get a new release. - [x] Update providers documentation - [ ] Update notebooks to reference starter instead of ollama Signed-off-by: Sébastien Han <seb@redhat.com>	2025-07-04 15:58:03 +02:00
Matthew Farrellee	ef26259209	feat: add llama guard 4 model (#2579) ... add support for Llama Guard 4 model to the llama_guard safety provider test with - 0. NVIDIA_API_KEY=... llama stack build --image-type conda --image-name env-nvidia --providers inference=remote::nvidia,safety=inline::llama-guard --run 1. llama-stack-client models register meta-llama/Llama-Guard-4-12B --provider-model-id meta/llama-guard-4-12b 2. pytest tests/integration/safety/test_llama_guard.py Co-authored-by: raghotham <rsm@meta.com>	2025-07-03 22:29:04 -07:00
Francisco Arceo	4afd619c56	chore: Add support for vector-stores files api for Milvus (#2582) ... # What does this PR do? ### Summary This pull request implements support for the OpenAI Vector Store Files API for the Milvus vector store provider in `llama_stack`. It enables storing, loading, updating, and deleting file metadata and file contents in Milvus collections, allowing OpenAI vector store files to be managed directly within Milvus. ### Main Changes - **Milvus Vector Store Files API Implementation** - Implements all required methods for storing, loading, updating, and deleting vector store file metadata and contents (`_save_openai_vector_store_file`, `_load_openai_vector_store_file`, `_load_openai_vector_store_file_contents`, `_update_openai_vector_store_file`, `_delete_openai_vector_store_file_from_storage`). - Uses two Milvus collections: `openai_vector_store_files` (for metadata) and `openai_vector_store_files_contents` (for chunked file contents). - Collections are created dynamically if they do not exist, with appropriate schema definitions. - **Collection Name Sanitization** - Adds a `sanitize_collection_name` utility to ensure Milvus collection names only contain valid characters (letters, numbers, underscores). - **Testing** - Updates test skip logic to include `"inline::milvus"` for cases where the OpenAI Vector Store Files API is not supported, improving integration test accuracy. - **Other Improvements** - Passes `kvstore` to `MilvusIndex` for consistency. - Removes obsolete NotImplementedErrors and legacy code for file storage. ## Test Plan CI and tested via a test script ## Notes - `VectorDB` currently uses the `name` as the `identifier` in `openai_create_vector_store`. We need to add `name` as a field to `VectorDB` and generate the `identifier` upon creation. OpenAI is not idempotent with respect to the `name` field that they pass (i.e., you can pass the same name multiple times and OpenAI will generate a new identifier). I'll add a follow up PR for this. - The `Files` api needs to use `files-` as a prefix in the identifier. I have updated the Vector Store to use the OpenAI prefix `vs_*`. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-07-03 12:15:33 -07:00
Sébastien Han	dae1fcd3c2	ci: let pytest run the distro server (#2586) ... # What does this PR do? * Use #2580 functionality to auto-start the server with the tests * Reduce timeout to 30sec * Print server logs on errors * Pytest logs are collected to a file pytest.log Signed-off-by: Sébastien Han <seb@redhat.com>	2025-07-03 10:51:46 -07:00
ehhuang	fc735a414e	test: Add one-step integration testing with server auto-start (#2580) ... ## Summary Add support for `server:<config>` format in `--stack-config` option to enable seamless one-step integration testing. This eliminates the need to manually start servers in separate terminals before running tests. ## Key Features - **Auto-start server**: Automatically launches `llama stack run <config>` if target port is available - **Smart reuse**: Reuses existing server if port is already occupied - **Health check polling**: Waits up to 2 minutes for server readiness via `/v1/health` endpoint - **Custom port support**: Use `server:<config>:<port>` for non-default ports - **Clean output**: Server runs quietly in background without cluttering test output - **Backward compatibility**: All existing `--stack-config` formats continue to work ## Usage Examples ```bash # Auto-start server with default port 8321 pytest tests/integration/inference/ --stack-config=server:fireworks # Use custom port pytest tests/integration/safety/ --stack-config=server:together:8322 # Run multiple test suites seamlessly pytest tests/integration/inference/ tests/integration/agents/ --stack-config=server:starter ``` ## Implementation Details - Enhanced `llama_stack_client` fixture with server management - Updated documentation with cleaner organization and comprehensive examples - Added utility functions for port checking, server startup, and health verification ## Test Plan - Verified server auto-start when port 8321 is available - Verified server reuse when port 8321 is occupied - Tested health check polling via `/v1/health` endpoint - Confirmed custom port configuration works correctly - Verified backward compatibility with existing config formats ## Before/After Comparison **Before (2 steps):** ```bash # Terminal 1: Start server manually llama stack run fireworks --port 8321 # Terminal 2: Wait for startup, then run tests pytest tests/integration/inference/ --stack-config=http://localhost:8321 ``` **After (1 step):** ```bash # Single command handles everything pytest tests/integration/inference/ --stack-config=server:fireworks ```	2025-07-01 14:48:46 -07:00
Francisco Arceo	0066135944	chore: Enabling VectorIO Integration tests for Milvus (#2546)	2025-06-30 19:49:59 -07:00
Krzysztof Malczuk	be9bf68246	feat: Add webmethod for deleting openai responses (#2160) ... # What does this PR do? This PR creates a webmethod for deleting open AI responses, adds and implementation for it and makes an integration test for the OpenAI delete response method. [//]: # (If resolving an issue, uncomment and update the line below) # (Closes #2077) ## Test Plan Ran the standard tests and the pre-commit hooks and the unit tests. # (## Documentation) For this pr I made the routes and implementation based on the current get and create methods. The unit tests were not able to handle this test due to the mock interface in use, which did not allow for effective CRUD to be tested. I instead created an integration test to match the existing ones in the test_openai_responses.	2025-06-30 11:28:02 +02:00
Francisco Arceo	cc19b56c87	chore: OpenAI compatibility for Milvus (#2470) ... # What does this PR do? Closes https://github.com/meta-llama/llama-stack/issues/2461 ## Test Plan Tested with the `ollama` distriubtion template and updated the vector_io provider to: ```yaml vector_io: - provider_id: milvus provider_type: inline::milvus config: db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/milvus_store.db kvstore: type: sqlite db_name: milvus_registry.db ``` Ran the stack ```bash llama stack run ./llama_stack/templates/ollama/run.yaml --image-type venv --env OLLAMA_URL="http://0.0.0.0:11434" ``` Ran the tests: ``` pytest -sv --stack-config=http://localhost:8321 tests/integration/vector_io/test_openai_vector_stores.py --embedding-model all-MiniLM-L6-v2 ``` Output passed. Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-06-27 16:00:36 -07:00
ehhuang	1d3f27fe5b	fix: resume responses with tool call output (#2524) ... # What does this PR do? closes #2522 ## Test Plan added integration test LLAMA_STACK_CONFIG=http://localhost:8321 pytest -v tests/integration/agents/test_openai_responses.py --text-model "accounts/fireworks/models/llama-v3p3-70b-instruct" -vv -k 'function_call'	2025-06-25 14:43:37 -07:00
Varsha	cfee63bd0d	feat: Add search_mode support to OpenAI vector store API (#2500) ... # What does this PR do? Add search_mode parameter (vector/keyword/hybrid) to openai_search_vector_store method. Fixes OpenAPI code generation by using str instead of Literal type. Closes: #2459 ## 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: Varsha Prasad Narsing <varshaprasad96@gmail.com>	2025-06-24 20:38:47 -04:00
Ben Browning	f394c7f2d9	feat: Add missing Vector Store Files API surface (#2468) ... # What does this PR do? This adds the ability to list, retrieve, update, and delete Vector Store Files. It implements these new APIs for the faiss and sqlite-vec providers, since those are the two that also have the rest of the vector store files implementation. Closes #2445 ## Test Plan ### test_openai_vector_stores Integration Tests There are a number of new integration tests added, which I ran for each provider as outlined below. faiss (from ollama distro): ``` INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run llama_stack/templates/ollama/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \ --embedding-model=all-MiniLM-L6-v2 ``` sqlite-vec (from starter distro): ``` llama stack run llama_stack/templates/starter/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \ --embedding-model=all-MiniLM-L6-v2 ``` ### file_search verification tests I also ensured the file_search verification tests continue to work, both for faiss and sqlite-vec. faiss (ollama distro): ``` INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run llama_stack/templates/ollama/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=meta-llama/Llama-3.2-3B-Instruct ``` sqlite-vec (starter distro): ``` llama stack run llama_stack/templates/starter/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=together/meta-llama/Llama-3.2-3B-Instruct-Turbo ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>	2025-06-19 11:08:24 -04:00
Sébastien Han	6039d922c0	fix: allow running vector tests with embedding dimension (#2467) ... # What does this PR do? Do not force 384 for the embedding dimension, use the one provided by the test run. ## Test Plan ``` pytest -s -vvv tests/integration/vector_io/test_vector_io.py --stack-config=http://localhost:8321 \ -k "not(builtin_tool or safety_with_image or code_interpreter or test_rag)" \ --text-model="meta-llama/Llama-3.2-3B-Instruct" \ --embedding-model=granite-embedding-125m --embedding-dimension=768 Uninstalled 1 package in 16ms Installed 1 package in 11ms INFO 2025-06-18 10:52:03,314 tests.integration.conftest:59 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS /Users/leseb/Documents/AI/llama-stack/.venv/lib/python3.10/site-packages/pytest_asyncio/plugin.py:207: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset. The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session" warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET)) ================================================= test session starts ================================================= platform darwin -- Python 3.10.16, pytest-8.3.4, pluggy-1.5.0 -- /Users/leseb/Documents/AI/llama-stack/.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.10.16', 'Platform': 'macOS-15.5-arm64-arm-64bit', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'cov': '6.0.0', 'html': '4.1.1', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'asyncio': '0.25.3', 'anyio': '4.8.0', 'nbval': '0.11.0'}} rootdir: /Users/leseb/Documents/AI/llama-stack configfile: pyproject.toml plugins: cov-6.0.0, html-4.1.1, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, asyncio-0.25.3, anyio-4.8.0, nbval-0.11.0 asyncio: mode=strict, asyncio_default_fixture_loop_scope=None collected 8 items tests/integration/vector_io/test_vector_io.py::test_vector_db_retrieve[emb=granite-embedding-125m:dim=768] PASSED tests/integration/vector_io/test_vector_io.py::test_vector_db_register[emb=granite-embedding-125m:dim=768] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=granite-embedding-125m:dim=768-test_case0] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=granite-embedding-125m:dim=768-test_case1] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=granite-embedding-125m:dim=768-test_case2] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=granite-embedding-125m:dim=768-test_case3] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=granite-embedding-125m:dim=768-test_case4] PASSED tests/integration/vector_io/test_vector_io.py::test_insert_chunks_with_precomputed_embeddings[emb=granite-embedding-125m:dim=768] PASSED ================================================== 8 passed in 5.50s ================================================== ``` Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-19 13:29:04 +05:30
Hardik Shah	985d0b156c	feat: Add suffix to openai_completions (#2449) ... For code completion apps need "fill in the middle" capabilities. Added option of `suffix` to `openai_completion` to enable this. Updated ollama provider to showcase the same. ### Test Plan ``` pytest -sv --stack-config="inference=ollama" tests/integration/inference/test_openai_completion.py --text-model qwen2.5-coder:1.5b -k test_openai_completion_non_streaming_suffix ``` ### OpenAI Sample script ``` from openai import OpenAI client = OpenAI(base_url="http://localhost:8321/v1/openai/v1") response = client.completions.create( model="qwen2.5-coder:1.5b", prompt="The capital of ", suffix="is Paris.", max_tokens=10, ) print(response.choices[0].text) ``` ### Output ``` France is ____. To answer this question, we ```	2025-06-13 16:06:06 -07:00
Francisco Arceo	554ada57b0	chore: Add OpenAI compatibility for Ollama embeddings (#2440) ... # What does this PR do? This PR adds OpenAI compatibility for Ollama embeddings. Closes https://github.com/meta-llama/llama-stack/issues/2428 Summary of changes: - `llama_stack/providers/remote/inference/ollama/ollama.py` - Implements the OpenAI embeddings endpoint for Ollama, replacing the NotImplementedError with a full function that validates the model, prepares parameters, calls the client, encodes embedding data (optionally in base64), and returns a correctly structured response. - Updates import statements to include the new embedding response utilities. - `llama_stack/providers/utils/inference/litellm_openai_mixin.py` - Refactors the embedding data encoding logic to use a new shared utility (`b64_encode_openai_embeddings_response`) instead of inline base64 encoding and packing logic. - Cleans up imports accordingly. - `llama_stack/providers/utils/inference/openai_compat.py` - Adds `b64_encode_openai_embeddings_response` to handle encoding OpenAI embedding outputs (including base64 support) in a reusable way. - Adds `prepare_openai_embeddings_params` utility for standardizing embedding parameter preparation. - Updates imports to include the new embedding data class. - `tests/integration/inference/test_openai_embeddings.py` - Removes `"remote::ollama"` from the list of providers that skip OpenAI embeddings tests, since support is now implemented. ## Note There was one minor issue, which required me to override the `OpenAIEmbeddingsResponse.model` name with `self._get_model(model).identifier` name, which is very unsatisfying. ## Test Plan Unit Tests and integration tests --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-06-13 14:28:51 -04:00
Hardik Shah	fef670b024	feat: update openai tests to work with both clients (#2442) ... 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.	2025-06-12 16:30:23 -07:00
Hardik Shah	0bc1747ed8	feat: update search for vector_stores (#2441) ... 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 ```	2025-06-12 15:34:22 -07:00
Ibrahim Haroon	35c2817d0a	fix(weaviate): handle case where distance is 0 by setting score to infinity (#2415) ... # 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") ```	2025-06-12 11:23:59 -04:00
Hardik Shah	5ac43268e8	feat: Add OpenAI compat /v1/vector_store APIs (#2423) ... 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 ```	2025-06-10 13:07:39 -07:00
Ben Browning	ee57e58f29	fix: loosen tool call checks in inference store (#2420) ... # 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>	2025-06-10 14:45:55 +02:00
ehhuang	92b59a3377	test: skip files integrations tests for library client (#2407) ... # 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	2025-06-05 13:42:10 -07:00
ehhuang	3c9a10d2fe	feat: reference implementation for files API (#2330) ... # 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/	2025-06-02 21:54:24 -07:00
Hardik Shah	b21050935e	feat: New OpenAI compat embeddings API (#2314) ... # What does this PR do? Adds a new endpoint that is compatible with OpenAI for embeddings api. `/openai/v1/embeddings` Added providers for OpenAI, LiteLLM and SentenceTransformer. ## Test Plan ``` LLAMA_STACK_CONFIG=http://localhost:8321 pytest -sv tests/integration/inference/test_openai_embeddings.py --embedding-model all-MiniLM-L6-v2,text-embedding-3-small,gemini/text-embedding-004 ```	2025-05-31 22:11:47 -07:00
Francisco Arceo	f328436831	feat: Enable ingestion of precomputed embeddings (#2317)	2025-05-31 04:03:37 -06:00
ehhuang	2603f10f95	feat: support postgresql inference store (#2310) ... # What does this PR do? * Added support postgresql inference store * Added 'oracle' template that demos how to config postgresql stores (except for telemetry, which is not supported currently) ## Test Plan llama stack build --template oracle --image-type conda --run LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s -v tests/integration/ --text-model accounts/fireworks/models/llama-v3p3-70b-instruct -k 'inference_store'	2025-05-29 14:33:09 -07:00
ehhuang	0b695538af	fix: chat completion with more than one choice (#2288) ... # What does this PR do? Fix a bug in openai_compat where choices are not indexed correctly. ## Test Plan Added a new test. Rerun the failed inference_store tests: llama stack run fireworks --image-type conda pytest -s -v tests/integration/ --stack-config http://localhost:8321 -k 'test_inference_store' --text-model meta-llama/Llama-3.3-70B-Instruct --count 10	2025-05-27 15:39:15 -07:00
ehhuang	1d46f3102e	fix: enable test_responses_store (#2290) ... # What does this PR do? Changed the test to not require tool_call in output, but still keeping the tools params there as a smoke test. ## Test Plan Used llama3.3 from fireworks (same as CI) <img width="1433" alt="image" src="https://github.com/user-attachments/assets/1e5fca98-9b4f-402e-a0bc-d9f910f2c207" /> Run with ollama distro and 3b model.	2025-05-27 15:37:28 -07:00
Ashwin Bharambe	7504c2f430	test: disable test_inference_store test urrrggg (#2273)	2025-05-26 22:48:41 -07:00
Ashwin Bharambe	9623d5d230	fix: match mcp headers in provider data to Responses API shape (#2263)	2025-05-25 14:33:10 -07:00
Ashwin Bharambe	ce33d02443	fix(tools): do not index tools, only index toolgroups (#2261) ... When registering a MCP endpoint, we cannot list tools (like we used to) since the MCP endpoint may be behind an auth wall. Registration can happen much sooner (via run.yaml). Instead, we do listing only when the _user_ actually calls listing. Furthermore, we cache the list in-memory in the server. Currently, the cache is not invalidated -- we may want to periodically re-list for MCP servers. Note that they must call `list_tools` before calling `invoke_tool` -- we use this critically. This will enable us to list MCP servers in run.yaml ## Test Plan Existing tests, updated tests accordingly.	2025-05-25 13:27:52 -07:00
Ashwin Bharambe	3faf1e4a79	feat: enable MCP execution in Responses impl (#2240) ... ## Test Plan ``` pytest -s -v 'tests/verifications/openai_api/test_responses.py' \ --provider=stack:together --model meta-llama/Llama-4-Scout-17B-16E-Instruct ```	2025-05-24 14:20:42 -07:00
Ashwin Bharambe	66f09f24ed	fix: disable test_responses_store (#2244) ... The test depends on llama's tool calling ability. In the CI, we run with a small ollama model. The fix might be to check for either message or function_call because the model is flaky and we aren't really testing that behavior?	2025-05-24 08:18:06 -07:00
raghotham	84751f3e55	fix: skip failing tests (#2243) ... as title. trying release 0.2.8	2025-05-24 07:31:08 -07:00
ehhuang	15b0a67555	feat: add responses input items api (#2239) ... # What does this PR do? TSIA ## Test Plan added integration and unit tests	2025-05-24 07:05:53 -07:00
ehhuang	5844c2da68	feat: add list responses API (#2233) ... # What does this PR do? This is not part of the official OpenAI API, but we'll use this for the logs UI. In order to support more filtering options, I'm adopting the newly introduced sql store in in place of the kv store. ## Test Plan Added integration/unit tests.	2025-05-23 13:16:48 -07:00
Ashwin Bharambe	51945f1e57	feat: accept MCP authorization headers for MCP toolgroups (#2230) ... The most interesting MCP servers are those with an authorization wall in front of them. This PR uses the existing `provider_data` mechanism of passing provider API keys for passing MCP access tokens (in fact, arbitrary headers in the style of the OpenAI Responses API) from the client through to the MCP server. ``` class MCPProviderDataValidator(BaseModel): # mcp_endpoint => list of headers to send mcp_headers: dict[str, list[str]] | None = None ``` Note how we must stuff the headers for all MCP endpoints into a single "MCPProviderDataValidator". Unlike existing providers (e.g., Together and Fireworks for inference) where we could name the provider api keys clearly (`together_api_key`, `fireworks_api_key`), we cannot name these keys for MCP. We have a single generic MCP provider which can serve multiple "toolgroups". So we use a dict to combine all the headers for all MCP endpoints you may want to use in an agentic call. ## Test Plan See the added integration test for usage.	2025-05-23 08:52:18 -07:00
ehhuang	549812f51e	feat: implement get chat completions APIs (#2200) ... # What does this PR do? * Provide sqlite implementation of the APIs introduced in https://github.com/meta-llama/llama-stack/pull/2145. * Introduced a SqlStore API: llama_stack/providers/utils/sqlstore/api.py and the first Sqlite implementation * Pagination support will be added in a future PR. ## Test Plan Unit test on sql store: <img width="1005" alt="image" src="https://github.com/user-attachments/assets/9b8b7ec8-632b-4667-8127-5583426b2e29" /> Integration test: ``` INFERENCE_MODEL="llama3.2:3b-instruct-fp16" llama stack build --template ollama --image-type conda --run ``` ``` LLAMA_STACK_CONFIG=http://localhost:5001 INFERENCE_MODEL="llama3.2:3b-instruct-fp16" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-fp16" -k 'inference_store and openai' ```	2025-05-21 22:21:52 -07:00
Charlie Doern	f02f7b28c1	feat: add huggingface post_training impl (#2132) ... # What does this PR do? adds an inline HF SFTTrainer provider. Alongside touchtune -- this is a super popular option for running training jobs. The config allows a user to specify some key fields such as a model, chat_template, device, etc the provider comes with one recipe `finetune_single_device` which works both with and without LoRA. any model that is a valid HF identifier can be given and the model will be pulled. this has been tested so far with CPU and MPS device types, but should be compatible with CUDA out of the box The provider processes the given dataset into the proper format, establishes the various steps per epoch, steps per save, steps per eval, sets a sane SFTConfig, and runs n_epochs of training if checkpoint_dir is none, no model is saved. If there is a checkpoint dir, a model is saved every `save_steps` and at the end of training. ## Test Plan re-enabled post_training integration test suite with a singular test that loads the simpleqa dataset: https://huggingface.co/datasets/llamastack/simpleqa and a tiny granite model: https://huggingface.co/ibm-granite/granite-3.3-2b-instruct. The test now uses the llama stack client and the proper post_training API runs one step with a batch_size of 1. This test runs on CPU on the Ubuntu runner so it needs to be a small batch and a single step. [//]: # (## Documentation) --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-05-16 14:41:28 -07:00
ehhuang	953ccffca2	test: catch BadRequestError for non-library client (#2195) ... # What does this PR do? ## Test Plan LLAMA_STACK_CONFIG=http://localhost:8321 pytest tests/integration/tool_runtime/test_rag_tool.py --embedding-model text-embedding-3-small	2025-05-16 12:26:59 -07:00
Ben Browning	10b1056dea	fix: multiple tool calls in remote-vllm chat_completion (#2161) ... # What does this PR do? This fixes an issue in how we used the tool_call_buf from streaming tool calls in the remote-vllm provider where it would end up concatenating parameters from multiple different tool call results instead of aggregating the results from each tool call separately. It also fixes an issue found while digging into that where we were accidentally mixing the json string form of tool call parameters with the string representation of the python form, which mean we'd end up with single quotes in what should be double-quoted json strings. Closes #1120 ## Test Plan The following tests are now passing 100% for the remote-vllm provider, where some of the test_text_inference were failing before this change: ``` VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_text_inference.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_vision_inference.py --vision-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" ``` All but one of the agent tests are passing (including the multi-tool one). See the PR at https://github.com/vllm-project/vllm/pull/17917 and a gist at https://gist.github.com/bbrowning/4734240ce96b4264340caa9584e47c9e for changes needed there, which will have to get made upstream in vLLM. Agent tests: ``` VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/agents/test_agents.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" ```` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>	2025-05-15 11:23:29 -07:00
Francisco Arceo	8e7ab146f8	feat: Adding support for customizing chunk context in RAG insertion and querying (#2134) ... # What does this PR do? his PR allows users to customize the template used for chunks when inserted into the context. Additionally, this enables metadata injection into the context of an LLM for RAG. This makes a naive and crude assumption that each chunk should include the metadata, this is obviously redundant when multiple chunks are returned from the same document. In order to remove any sort of duplication of chunks, we'd have to make much more significant changes so this is a reasonable first step that unblocks users requesting this enhancement in https://github.com/meta-llama/llama-stack/issues/1767. In the future, this can be extended to support citations. List of Changes: - `llama_stack/apis/tools/rag_tool.py` - Added `chunk_template` field in `RAGQueryConfig`. - Added `field_validator` to validate the `chunk_template` field in `RAGQueryConfig`. - Ensured the `chunk_template` field includes placeholders `{index}` and `{chunk.content}`. - Updated the `query` method to use the `chunk_template` for formatting chunk text content. - `llama_stack/providers/inline/tool_runtime/rag/memory.py` - Modified the `insert` method to pass `doc.metadata` for chunk creation. - Enhanced the `query` method to format results using `chunk_template` and exclude unnecessary metadata fields like `token_count`. - `llama_stack/providers/utils/memory/vector_store.py` - Updated `make_overlapped_chunks` to include metadata serialization and token count for both content and metadata. - Added error handling for metadata serialization issues. - `pyproject.toml` - Added `pydantic.field_validator` as a recognized `classmethod` decorator in the linting configuration. - `tests/integration/tool_runtime/test_rag_tool.py` - Refactored test assertions to separate `assert_valid_chunk_response` and `assert_valid_text_response`. - Added integration tests to validate `chunk_template` functionality with and without metadata inclusion. - Included a test case to ensure `chunk_template` validation errors are raised appropriately. - `tests/unit/rag/test_vector_store.py` - Added unit tests for `make_overlapped_chunks`, verifying chunk creation with overlapping tokens and metadata integrity. - Added tests to handle metadata serialization errors, ensuring proper exception handling. - `docs/_static/llama-stack-spec.html` - Added a new `chunk_template` field of type `string` with a default template for formatting retrieved chunks in RAGQueryConfig. - Updated the `required` fields to include `chunk_template`. - `docs/_static/llama-stack-spec.yaml` - Introduced `chunk_template` field with a default value for RAGQueryConfig. - Updated the required configuration list to include `chunk_template`. - `docs/source/building_applications/rag.md` - Documented the `chunk_template` configuration, explaining how to customize metadata formatting in RAG queries. - Added examples demonstrating the usage of the `chunk_template` field in RAG tool queries. - Highlighted default values for `RAG` agent configurations. # Resolves https://github.com/meta-llama/llama-stack/issues/1767 ## Test Plan Updated both `test_vector_store.py` and `test_rag_tool.py` and tested end-to-end with a script. I also tested the quickstart to enable this and specified this metadata: ```python document = RAGDocument( document_id="document_1", content=source, mime_type="text/html", metadata={"author": "Paul Graham", "title": "How to do great work"}, ) ``` Which produced the output below:  This highlights the usefulness of the additional metadata. Notice how the metadata is redundant for different chunks of the same document. I think we can update that in a subsequent PR. # Documentation I've added a brief comment about this in the documentation to outline this to users and updated the API documentation. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-05-14 21:56:20 -04:00
Sébastien Han	26dffff92a	chore: remove pytest reports (#2156) ... # What does this PR do? Cleanup old test code too. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-05-13 22:40:15 -07:00
Nathan Weinberg	e0d10dd0b1	docs: revamp testing documentation (#2155) ... # What does this PR do? reduces duplication and centralizes information to be easier to find for contributors Signed-off-by: Nathan Weinberg <nweinber@redhat.com>	2025-05-13 11:28:29 -07:00
Sébastien Han	62476a5373	fix: pytest reports (#2152) ... # What does this PR do? While adding other tests, I came across this and wasn’t sure how useful it is. It doesn’t seem to be exercised anywhere in CI, but I figured I’d fix it anyway. Happy to remove it if preferred. :) ## Test Plan Run: ``` uv run pytest tests/integration/inference --stack-config=ollama --report=test_report.md -v --text-model="llama3.2:3b" --embedding-model=all-MiniLM-L6-v2 ``` Look at the produced `test_report.md`. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-05-13 11:27:29 -07:00
ehhuang	664161c462	fix: llama4 tool use prompt fix (#2103) ... Tests: LLAMA_STACK_CONFIG=http://localhost:5002 pytest -s -v tests/integration/inference --safety-shield meta-llama/Llama-Guard-3-8B --vision-model meta-llama/Llama-4-Scout-17B-16E-Instruct --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct LLAMA_STACK_CONFIG=http://localhost:5002 pytest -s -v tests/integration/inference --safety-shield meta-llama/Llama-Guard-3-8B --vision-model Llama-4-Maverick-17B-128E-Instruct --text-model Llama-4-Maverick-17B-128E-Instruct Co-authored-by: Eric Huang <erichuang@fb.com>	2025-05-06 22:18:31 -07:00
Jorge Piedrahita Ortiz	b2b00a216b	feat(providers): sambanova updated to use LiteLLM openai-compat (#1596) ... # What does this PR do? switch sambanova inference adaptor to LiteLLM usage to simplify integration and solve issues with current adaptor when streaming and tool calling, models and templates updated ## Test Plan pytest -s -v tests/integration/inference/test_text_inference.py --stack-config=sambanova --text-model=sambanova/Meta-Llama-3.3-70B-Instruct pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=sambanova --vision-model=sambanova/Llama-3.2-11B-Vision-Instruct	2025-05-06 16:50:22 -07:00
Christian Zaccaria	18d2312690	fix: test_datasets HF scenario in CI (#2090) ... # What does this PR do? **Fixes** #1959 HuggingFace provides several loading paths that the datasets library can use. My theory on why the test would previously fail intermittently is because when calling `load_dataset(...)`, it may be trying several options such as local cache, Hugging Face Hub, or a dataset script, or other. There's one of these options that seem to work inconsistently in the CI. The HuggingFace datasets library relies on the `transformers` package to load certain datasets such as `llamastack/simpleqa`, and by adding the package, we can see the dataset is loaded consistently via the Hugging Face Hub. Please see PR in my fork demonstrating over 7 consecutive passes: https://github.com/ChristianZaccaria/llama-stack/pull/1 **Some References:** - https://github.com/huggingface/transformers/issues/8690 - https://huggingface.co/docs/datasets/en/loading [//]: # (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)	2025-05-06 14:09:15 +02:00
ehhuang	4597145011	chore: remove recordable mock (#2088) ... # What does this PR do? We've disabled it for a while given that this hasn't worked as well as expected given the frequent changes of llama_stack_client and how this requires both repos to be in sync. ## Test Plan Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-05-05 10:08:55 -07:00
Ashwin Bharambe	d27a0f276c	fix: pytest.mark.skip, not pytest.skip	2025-05-04 13:22:06 -07:00