465 commits

Author	SHA1	Message	Date
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
Akram Ben Aissi	f4950f4ef0	fix: AccessDeniedError leads to HTTP 500 instead of error 403 (#2595) ... Resolves access control error visibility issues where 500 errors were returned instead of proper 403 responses with actionable error messages. • Enhance AccessDeniedError with detailed context and improve exception handling • Enhanced AccessDeniedError class to include user, action, and resource context - Added constructor parameters for action, resource, and user - Generate detailed error messages showing user principal, attributes, and attempted resource - Backward compatible with existing usage (falls back to generic message) • Updated exception handling in server.py - Import AccessDeniedError from access_control module - Return proper 403 status codes with detailed error messages - Separate handling for PermissionError (generic) vs AccessDeniedError (detailed) • Enhanced error context at raise sites - Updated routing_tables/common.py to pass action, resource, and user context - Updated agents persistence to include context in access denied errors - Provides better debugging information for access control issues • Added comprehensive unit tests - Created tests/unit/server/test_server.py with 13 test cases - Covers AccessDeniedError with and without context - Tests all exception types (ValidationError, BadRequestError, AuthenticationRequiredError, etc.) - Validates proper HTTP status codes and error message formats # 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 ``` server: port: 8321 access_policy: - permit: principal: admin actions: [create, read, delete] when: user with admin in groups - permit: actions: [read] when: user with system:authenticated in roles ``` then: ``` curl --request POST --url http://localhost:8321/v1/vector-dbs \ --header "Authorization: Bearer your-bearer" \ --data '{ "vector_db_id": "my_demo_vector_db", "embedding_model": "ibm-granite/granite-embedding-125m-english", "embedding_dimension": 768, "provider_id": "milvus" }' ``` depending if user is in group admin or not, you should get the `AccessDeniedError`. Before this PR, this was leading to an error 500 and `Traceback` displayed in the logs. After the PR, logs display a simpler error (unless DEBUG logging is set) and a 403 Forbidden error is returned on the HTTP side. --------- Signed-off-by: Akram Ben Aissi <<akram.benaissi@gmail.com>>	2025-07-03 10:50:49 -07:00
ehhuang	3c43a2f529	fix: store configs (#2593) ... # What does this PR do? https://github.com/meta-llama/llama-stack/pull/2490 broke postgres_demo, as the config expected a str but the value was converted to int. This PR: 1. Updates the type of port in sqlstore to be int 2. template generation uses `dict` instead of `StackRunConfig` so as to avoid failing pydantic typechecks. 3. Adds `replace_env_vars` to StackRunConfig instantiation in `configure.py` (not sure why this wasn't needed before). ## Test Plan `llama stack build --template postgres_demo --image-type conda --run`	2025-07-03 10:07:23 -07:00
Sébastien Han	25268854bc	fix: allow default empty vars for conditionals (#2570) ... # What does this PR do? We were not using conditionals correctly, conditionals can only be used when the env variable is set, so `${env.ENVIRONMENT:+}` would return None is ENVIRONMENT is not set. If you want to create a conditional value, you need to do `${env.ENVIRONMENT:=}`, this will pick the value of ENVIRONMENT if set, otherwise will return None. Closes: https://github.com/meta-llama/llama-stack/issues/2564 Signed-off-by: Sébastien Han <seb@redhat.com>	2025-07-01 14:42:05 +02:00
Juanma	e7eb9f9adc	fix: dataset metadata without provider_id (#2527) ... # What does this PR do? Fixes an error when inferring dataset provider_id with metadata Closes #[2506](https://github.com/meta-llama/llama-stack/issues/2506) Signed-off-by: Juanma Barea <juanmabareamartinez@gmail.com>	2025-06-27 08:51:29 -04:00
Wen Zhou	8c3f2762fb	build: update temp. created Containerfile (#2492) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> - conditionally created folder /.llama/providers.d if external_providers_dir is set - do not create /.cache folder, not in use anywhere - combine chmod and copy to one command <!-- 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.* --> updated test: ``` export CONTAINER_BINARY=podman LLAMA_STACK_DIR=. uv run llama stack build --template remote-vllm --image-type container --image-name <name> ``` log: ``` Containerfile created successfully in /tmp/tmp.rPMunE39Aw/Containerfile FROM python:3.11-slim WORKDIR /app RUN apt-get update && apt-get install -y iputils-ping net-tools iproute2 dnsutils telnet curl wget telnet git procps psmisc lsof traceroute bubblewrap gcc && rm -rf /var/lib/apt/lists/* ENV UV_SYSTEM_PYTHON=1 RUN pip install uv RUN uv pip install --no-cache sentencepiece pillow pypdf transformers pythainlp faiss-cpu opentelemetry-sdk requests datasets chardet scipy nltk numpy matplotlib psycopg2-binary aiosqlite langdetect autoevals tree_sitter tqdm pandas chromadb-client opentelemetry-exporter-otlp-proto-http redis scikit-learn openai pymongo emoji sqlalchemy[asyncio] mcp aiosqlite fastapi fire httpx uvicorn opentelemetry-sdk opentelemetry-exporter-otlp-proto-http RUN uv pip install --no-cache sentence-transformers --no-deps RUN uv pip install --no-cache torch torchvision --index-url https://download.pytorch.org/whl/cpu # Allows running as non-root user RUN mkdir -p /.llama/providers.d /.cache RUN uv pip install --no-cache llama-stack RUN pip uninstall -y uv ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "remote-vllm"] RUN chmod -R g+rw /app /.llama /.cache PWD: /tmp/llama-stack Containerfile: /tmp/tmp.rPMunE39Aw/Containerfile + podman build --progress=plain --security-opt label=disable --platform linux/amd64 -t distribution-remote-vllm:0.2.12 -f /tmp/tmp.rPMunE39Aw/Containerfile /tmp/llama-stack .... Success! Build Successful! You can find the newly-built template here: /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml You can run the new Llama Stack distro via: llama stack run /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml --image-type container ``` ``` podman tag localhost/distribution-remote-vllm:dev quay.io/wenzhou/distribution-remote-vllm:2492_2 podman push quay.io/wenzhou/distribution-remote-vllm:2492_2 docker run --rm -p 8321:8321 -e INFERENCE_MODEL="meta-llama/Llama-2-7b-chat-hf" -e VLLM_URL="http://localhost:8000/v1" quay.io/wenzhou/distribution-remote-vllm:2492_2 --port 8321 INFO 2025-06-26 13:47:31,813 __main__:436 server: Using template remote-vllm config file: /app/llama-stack-source/llama_stack/templates/remote-vllm/run.yaml INFO 2025-06-26 13:47:31,818 __main__:438 server: Run configuration: INFO 2025-06-26 13:47:31,826 __main__:440 server: apis: - agents - datasetio - eval - inference - safety - scoring - telemetry - tool_runtime - vector_io benchmarks: [] container_image: null .... ``` ----- previous test: local run` >llama stack build --template remote-vllm --image-type container` image stored in `quay.io/wenzhou/distribution-remote-vllm:2492` --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com>	2025-06-27 10:23:12 +02:00
Ben Browning	0883944bc3	fix: Some missed env variable changes from PR 2490 (#2538) ... # What does this PR do? Some templates were still using the old environment variable substition syntax instead of the new one and were not getting substituted properly. Also, some places didn't handle the new None vs old empty string ("") values that come from the conditional environment variable substitution. This gets the starter and remote-vllm distributions starting again, and I tested various permutations of the starter as chroma and pgvector needed some adjustments to their config classes to handle the new possible `None` values. And, I had to tweak our `Provider` class to also handle `None` values, for cases where we disable providers in the starter config via environment variables. This may not have caught everything that was missed, but I did grep around quite a bit to try and find anything lingering. ## Test Plan The following permutations now all run (or attempt to run to the point of complaining that they can't connect to chroma, vllm, etc) when before they failed immediately on startup because of bad environment variable substitions: ``` uv run llama stack run llama_stack/templates/starter/run.yaml ENABLE_SQLITE_VEC=true uv run llama stack run llama_stack/templates/starter/run.yaml ENABLE_PGVECTOR=true uv run llama stack run llama_stack/templates/starter/run.yaml ENABLE_CHROMADB=true uv run llama stack run llama_stack/templates/starter/run.yaml uv run llama stack run llama_stack/templates/remote-vllm/run.yaml ``` <!-- 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: Ben Browning <bbrownin@redhat.com> Co-authored-by: raghotham <rsm@meta.com>	2025-06-26 17:59:15 -07:00
Sébastien Han	43c1f39bd6	refactor(env)!: enhanced environment variable substitution (#2490) ... # What does this PR do? This commit significantly improves the environment variable substitution functionality in Llama Stack configuration files: * The version field in configuration files has been changed from string to integer type for better type consistency across build and run configurations. * The environment variable substitution system for ${env.FOO:} was fixed and properly returns an error * The environment variable substitution system for ${env.FOO+} returns None instead of an empty strings, it better matches type annotations in config fields * The system includes automatic type conversion for boolean, integer, and float values. * The error messages have been enhanced to provide clearer guidance when environment variables are missing, including suggestions for using default values or conditional syntax. * Comprehensive documentation has been added to the configuration guide explaining all supported syntax patterns, best practices, and runtime override capabilities. * Multiple provider configurations have been updated to use the new conditional syntax for optional API keys, making the system more flexible for different deployment scenarios. The telemetry configuration has been improved to properly handle optional endpoints with appropriate validation, ensuring that required endpoints are specified when their corresponding sinks are enabled. * There were many instances of ${env.NVIDIA_API_KEY:} that should have caused the code to fail. However, due to a bug, the distro server was still being started, and early validation wasn’t triggered. As a result, failures were likely being handled downstream by the providers. I’ve maintained similar behavior by using ${env.NVIDIA_API_KEY:+}, though I believe this is incorrect for many configurations. I’ll leave it to each provider to correct it as needed. * Environment variable substitution now uses the same syntax as Bash parameter expansion. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-26 08:20:08 +05:30
Sébastien Han	36d70637b9	fix: finish conversion to StrEnum (#2514) ... # What does this PR do? We still had a few enum declared to behave like string as well as enum. Let's use StrEnum for those. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-26 08:01:26 +05:30
Sébastien Han	ac5fd57387	chore: remove nested imports (#2515) ... # What does this PR do? * Given that our API packages use "import *" in `__init.py__` we don't need to do `from llama_stack.apis.models.models` but simply from llama_stack.apis.models. The decision to use `import *` is debatable and should probably be revisited at one point. * Remove unneeded Ruff F401 rule * Consolidate Ruff F403 rule in the pyprojectfrom llama_stack.apis.models.models Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-26 08:01:05 +05:30
Ben Browning	fa0b0c13d4	fix: Ollama should be optional in starter distro (#2482) ... # What does this PR do? Our starter distro required Ollama to be running (and a large list of models available in that Ollama) to successfully start. This adjusts things so that Ollama does not have to be running to use the starter template / distro. To accomplish this, a few changes were needed: * The Ollama provider is now configurable whether it raises an Exception or just logs a warning when it cannot reach the Ollama server on startup. The default is to raise an exception (same as previous behavior), but in the starter template we adjust this to just log a warning so that we can bring the stack up without needing a running Ollama server. * The starter template no longer specifies a default list of models for Ollama, as any models specified there need to actually be pulled and available in Ollama. Instead, it adds a new `OLLAMA_INFERENCE_MODEL` environment variable where users can provide an optional model to register with the Ollama provider on startup. Additional models can also be registered via the typical `models.register(...)` at runtime. * The vLLM template was adjusted to also allow an optional `VLLM_INFERENCE_MODEL` specified on startup, so that the behavior between vLLM and Ollama was consistent here to make it easy to get up and running quickly. * The default vector store was changed from sqlite-vec to faiss. sqlite-vec can enabled via setting the `ENABLE_SQLITE_VEC` environment variable, like we do for chromadb and pgvector. This is due to sqlite-vec not shipping proper arm64 binaries, like we previously fixed in #1530 for the ollama distribution. ## Test Plan With this change, the following scenarios now work with the starter template that did not before: * no Ollama running * Ollama running but not all of the Llama models pulled locally * Ollama running with a custom model registered on startup * vLLM running with a custom model registered on startup * running the starter template on linux/arm64, like when running containers on Mac without rosetta emulation --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>	2025-06-25 15:54:00 +02:00
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
ehhuang	114946ae88	chore: fix build script bug (#2507) ... # What does this PR do? Fixes ``` Installing pip dependencies error: Failed to parse: `scikit-learn pymongo pythainlp datasets torch sentencepiece requests aiohttp psycopg2-binary trl pillow pandas chardet nltk scipy ollama faiss-cpu pypdf tree_sitter langdetect openai matplotlib asyncpg peft redis autoevals mcp opentelemetry-exporter-otlp-proto-http sqlalchemy[asyncio] tqdm opentelemetry-sdk aiosqlite numpy chromadb-client emoji transformers aiosqlite fastapi fire httpx uvicorn opentelemetry-sdk opentelemetry-exporter-otlp-proto-http` Caused by: Expected one of `@`, `(`, `<`, `=`, `>`, `~`, `!`, `;`, found `p` scikit-learn pymongo pythainlp datasets torch sentencepiece requests aiohttp psycopg2-binary trl pillow pandas chardet nltk scipy ollama faiss-cpu pypdf tree_sitter langdetect openai matplotlib asyncpg peft redis autoevals mcp opentelemetry-exporter-otlp-proto-http sqlalchemy[asyncio] tqdm opentelemetry-sdk aiosqlite numpy chromadb-client emoji transformers aiosqlite fastapi fire httpx uvicorn opentelemetry-sdk opentelemetry-exporter-otlp-proto-http ^ ERROR 2025-06-24 11:33:33,362 llama_stack.distribution.build:145 uncategorized: Failed to build target myenv with return code 2 Error building stack: Failed to build image myenv ``` ## Test Plan	2025-06-24 12:05:22 -07:00
Sébastien Han	9c8be89fb6	chore: bump python supported version to 3.12 (#2475) ... # What does this PR do? The project now supports Python >= 3.12 Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-24 09:22:04 +05:30
Rohan Awhad	d797f9aec1	fix: #2495 FileNotFound Err in container image (#2498) ... # What does this PR do? Closes #2495 Changes: - Delay the `COPY run.yaml` into docker image step until after external provider handling - Split the check for `external_providers_dir` into “non-empty” and “directory exists" ## Test Plan 0. Create and Activate venv 1. Create a `simple_build.yaml` ```yaml version: '2' distribution_spec: providers: inference: - remote::openai image_type: container image_name: openai-stack ``` 2. Run llama stack build: ```bash llama stack build --config simple_build.yaml ``` 3. Run the docker container: ```bash docker run \ -p 8321:8321 \ -e OPENAI_API_KEY=$OPENAI_API_KEY \ openai_stack:0.2.12 ``` This should show server is running. ``` INFO 2025-06-23 19:07:57,832 llama_stack.distribution.distribution:151 core: Loading external providers from /.llama/providers.d INFO 2025-06-23 19:07:59,324 __main__:572 server: Listening on ['::', '0.0.0.0']:8321 INFO: Started server process [1] INFO: Waiting for application startup. INFO 2025-06-23 19:07:59,336 __main__:156 server: Starting up INFO: Application startup complete. INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) ``` Notice the first line: ``` Loading external providers from /.llama/providers.d ``` This is expected behaviour. Co-authored-by: Rohan Awhad <rawhad@redhat.com>	2025-06-24 09:08:08 +05:30
ehhuang	d3b60507d7	feat: support auth attributes in inference/responses stores (#2389) ... # What does this PR do? Inference/Response stores now store user attributes when inserting, and respects them when fetching. ## Test Plan pytest tests/unit/utils/test_sqlstore.py	2025-06-20 10:24:45 -07:00
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	c20388c424	ci: add python package build test (#2457) ... # What does this PR do? We now test a package build on every PRs. Closes: https://github.com/meta-llama/llama-stack/issues/2406 Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-19 18:57:32 +05:30
Sébastien Han	fa1d986f72	fix: remove asyncio.TimeoutError since Python update (#2476) ... # What does this PR do? Since we now support Pythong starting from 3.11, this is not needed anymore. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-19 18:52:41 +05:30
Charlie Doern	d12f195f56	feat: drop python 3.10 support (#2469) ... # What does this PR do? dropped python3.10, updated pyproject and dependencies, and also removed some blocks of code with special handling for enum.StrEnum Closes #2458 Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-06-19 12:07:14 +05:30
ehhuang	db2cd9e8f3	feat: support filters in file search (#2472) ... # What does this PR do? Move to use vector_stores.search for file search tool in Responses, which supports filters. closes #2435 ## Test Plan Added e2e test with fitlers. myenv ❯ llama stack run llama_stack/templates/fireworks/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search and filters' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=meta-llama/Llama-3.3-70B-Instruct	2025-06-18 21:50:55 -07:00
Sumit Jaiswal	90d03552d4	feat: To add health check for faiss inline vector_io provider (#2319) ... # 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 check for faiss inline vector_io provider. I tried adding `async def health(self) -> HealthResponse:` like in inference provider, but it didn't worked for `inline->vector_io->faiss` provider. And via debug logs, I understood the critical issue, that the health responses are being stored with the API name as the key, not as a nested dictionary with provider IDs. This means that all providers of the same API type (e.g., "vector_io") will share the same health response, and only the last one processed will be visible in the API response. I've created a patch file that fixes this issue by: - Storing the original get_providers_health method - Creating a patched version that correctly maps health responses to providers - Applying the patch to the `ProviderImpl` class Not an expert, so please let me know, if there can be any other workaround using which I can get the health status updated directly from `faiss.py`. <!-- 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.* --> Added unit tests to test the provider patch implementation in the PR. Adding a screenshot with the FAISS inline vector_io health status as "OK" 	2025-06-18 17:56:25 +02:00
Hardik Shah	822307e6d5	fix: Do not throw when listing vector stores (#2460) ... When trying to `list` vector_stores , if we cannot retrieve one, log an error and return all the ones that are valid. ### Test Plan ``` pytest -sv --stack-config=http://localhost:8321 tests/integration/vector_io/test_openai_vector_stores.py --embedding-model all-MiniLM-L6-v2 ``` Also tested for `--stack-config fireworks`	2025-06-17 11:19:43 -07:00
Rohan Awhad	436c7aa751	feat: Add url field to PaginatedResponse and populate it using route … (#2419) ... …path # What does this PR do? Closes #1847 Changes: - llama_stack/apis/common/responses.py: adds optional `url` field to PaginatedResponse - llama_stack/distribution/server/server.py: automatically populate the URL field with route path ## Test Plan - Built and ran llama stack server using the following cmds: ```bash export INFERENCE_MODEL=llama3.1:8b llama stack build --run --template ollama --image-type container llama stack run llama_stack/templates/ollama/run.yaml ``` - Ran `curl` to test if we are seeing the `url` param in response: ```bash curl -X 'GET' \ 'http://localhost:8321/v1/agents' \ -H 'accept: application/json' ``` - Expected and Received Output: `{"data":[],"has_more":false,"url":"/v1/agents"}` --------- Co-authored-by: Rohan Awhad <rawhad@redhat.com>	2025-06-16 11:19:48 +02:00
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
Ben Browning	941f505eb0	feat: File search tool for Responses API (#2426) ... # What does this PR do? This is an initial working prototype of wiring up the `file_search` builtin tool for the Responses API to our existing rag knowledge search tool. This is me seeing what I could pull together on top of the bits we already have merged. This may not be the ideal way to implement this, and things like how I shuffle the vector store ids from the original response API tool request to the actual tool execution feel a bit hacky (grep for `tool_kwargs["vector_db_ids"]` in `_execute_tool_call` to see what I mean). ## Test Plan I stubbed in some new tests to exercise this using text and pdf documents. Note that this is currently under tests/verification only because it sometimes flakes with tool calling of the small Llama-3.2-3B model we run in CI (and that I use as an example below). We'd want to make the test a bit more robust in some way if we moved this over to tests/integration and ran it in CI. ### OpenAI SaaS (to verify test correctness) ``` pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search' \ --base-url=https://api.openai.com/v1 \ --model=gpt-4o ``` ### Fireworks with faiss vector store ``` llama stack run llama_stack/templates/fireworks/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-3.3-70B-Instruct ``` ### Ollama with faiss vector store This sometimes flakes on Ollama because the quantized small model doesn't always choose to call the tool to answer the user's question. But, it often works. ``` ollama run llama3.2:3b INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run ./llama_stack/templates/ollama/run.yaml \ --image-type venv \ --env OLLAMA_URL="http://0.0.0.0:11434" 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 ``` ### OpenAI provider with sqlite-vec vector store ``` llama stack run ./llama_stack/templates/starter/run.yaml --image-type venv pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=openai/gpt-4o-mini ``` ### Ensure existing vector store integration tests still pass ``` ollama run llama3.2:3b INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run ./llama_stack/templates/ollama/run.yaml \ --image-type venv \ --env OLLAMA_URL="http://0.0.0.0:11434" LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io \ --text-model "meta-llama/Llama-3.2-3B-Instruct" \ --embedding-model=all-MiniLM-L6-v2 ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>	2025-06-13 14:32:48 -04:00
grs	e2e15ebb6c	feat(auth): allow token to be provided for use against jwks endpoint (#2394) ... Though the jwks endpoint does not usually require authentication, it does in a kubernetes cluster. While the cluster can be configured to allow anonymous access to that endpoint, this avoids the need to do so.	2025-06-13 10:13:41 +02:00
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
Sébastien Han	eb04731750	ci: fix external provider test (#2438) ... # 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>	2025-06-12 16:14:32 +02:00
Hardik Shah	de37a04c3e	fix: set appropriate defaults for params (#2434) ... Setting defaults to be `| None` else they get marked as required params in open-api spec.	2025-06-11 17:30:34 -07:00
Hardik Shah	d55100d9b7	feat: OpenAIVectorIOMixin for vector_stores common logic (#2427) ... 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 ```	2025-06-11 15:40:57 -07:00
Rohan Awhad	4e37b49cdc	fix: #1867 InferenceRouter has no attribute formatter (#2422) ... # What does this PR do? Closes #1867 [Steps to reproduce the bug](https://github.com/meta-llama/llama-stack/issues/1867#issuecomment-2956819381) The change was designed to minimize code changes. Open to option of skipping `metrics` field entirely when `telemetry` is disabled. ## Test Plan 1. Build llama-stack remote-vllm container ```bash llama stack build --template remote-vllm --image-type container ``` 2. Create a small run.yaml ```yaml version: '2' image_name: remote-vllm apis: - inference providers: inference: - provider_id: vllm-inference provider_type: remote::vllm config: url: ${env.VLLM_URL:http://localhost:8000/v1} max_tokens: ${env.VLLM_MAX_TOKENS:4096} api_token: ${env.VLLM_API_TOKEN:fake} tls_verify: ${env.VLLM_TLS_VERIFY:true} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db inference_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/inference_store.db models: - metadata: {} model_id: ${env.INFERENCE_MODEL} provider_id: vllm-inference model_type: llm shields: [] vector_dbs: [] datasets: [] scoring_fns: [] benchmarks: [] server: port: 8321 ``` 3. Run the llama-stack server ```bash export VLLM_URL="http://localhost:8000/v1" export INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack run run.yaml ``` 4. Then perform a curl ```bash curl -X 'POST' \ 'http://localhost:8321/v1/inference/completion' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "model_id": "meta-llama/Llama-3.2-3B-Instruct", "content": "string", "sampling_params": { "strategy": { "type": "greedy" }, "max_tokens": 10, "repetition_penalty": 1, "stop": [ "string" ] }, "stream": false, "logprobs": { "top_k": 0 } }' ``` 5. You should receive a 200 response with metric values set to 0, similar to one below: ``` { "metrics": [ { "metric": "prompt_tokens", "value": 0, "unit": null }, { "metric": "completion_tokens", "value": 0, "unit": null }, { "metric": "total_tokens", "value": 0, "unit": null } ], [...] } ``` Co-authored-by: Rohan Awhad <rawhad@redhat.com>	2025-06-11 18:14:41 +02:00
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
Sumit Jaiswal	33ecefd284	feat: To add health status check for remote VLLM (#2303) ... # 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.	2025-06-06 15:33:12 -04:00
ehhuang	446893f791	feat: add deps dynamically based on metastore config (#2405) ... # What does this PR do? ## Test Plan changed metastore in one of the templates, rerun distro gen, observe change in build.yaml	2025-06-05 14:07:25 -07:00
Ashwin Bharambe	3251b44d8a	refactor: unify stream and non-stream impls for responses (#2388) ... 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	2025-06-05 17:48:09 +02:00
Jose Angel Morena Simon	ef885d2147	fix(server): Add missing OpenTelemetry dependencies to resolve telemetry import errors (#2391) ... 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>	2025-06-05 09:34:46 +02:00
grs	0de9536717	fix: remove debug print accidentally merged (#2393) ... I accidentally left a debug print in a PR that was merged. This removes that.	2025-06-04 15:14:14 +02:00
ehhuang	d96f6ec763	chore(ui): use proxy server for backend API calls; simplified k8s deployment (#2350) ... # What does this PR do? - no more CORS middleware needed ## Test Plan ### Local test llama stack run starter --image-type conda npm run dev verify UI works in browser ### Deploy to k8s temporarily change ui-k8s.yaml.template to load from PR commit <img width="604" alt="image" src="https://github.com/user-attachments/assets/87fa2e52-1e93-4e32-9e0f-5b283b7a37b3" /> sh ./apply.sh $ kubectl get services go to external_ip:8322 and play around with UI <img width="1690" alt="image" src="https://github.com/user-attachments/assets/5b7ec827-4302-4435-a9eb-df423676d873" />	2025-06-03 14:57:10 -07:00
grs	7c1998db25	feat: fine grained access control policy (#2264) ... 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>	2025-06-03 14:51:12 -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
Mark Campbell	c7be73fb16	refactor: remove container from list of run image types (#2178) ... # What does this PR do? [Provide a short summary of what this PR does and why. Link to relevant issues if applicable.] Removes the ability to run llama stack container images through the llama stack CLI Closes #2110 ## 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: ``` llama stack run /path/to/run.yaml --image-type container ``` Expected outcome: ``` llama stack run: error: argument --image-type: invalid choice: 'container' (choose from 'conda', 'venv') ``` [//]: # (## Documentation)	2025-06-02 09:57:55 +02:00
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
Sébastien Han	63a9f08c9e	chore: use starlette built-in Route class (#2267) ... # What does this PR do? Use a more common pattern and known terminology from the ecosystem, where Route is more approved than Endpoint. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-05-28 09:53:33 -07:00
Ashwin Bharambe	51e6f529f3	fix: index non-MCP toolgroups at registration time (#2272) ... Two somewhat annoying fixes: - we are going to index tools for non-MCP toolgroups always (like we used to do). because there are just random assumptions in our tests, etc. and I don't want to fix them right now - we need to handle the funny case of toolgroups like `builtin::rag/knowledge_search` where we added the tool name to use in the toolgroup itself.	2025-05-26 20:33:36 -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
raghotham	5a422e236c	chore: make cprint write to stderr (#2250) ... Also do sys.exit(1) in case of errors	2025-05-24 23:39:57 -07:00
Ashwin Bharambe	298721c238	chore: split routing_tables into individual files (#2259)	2025-05-24 23:15:05 -07:00
Ashwin Bharambe	eedf21f19c	chore: split routers into individual files (inference, tool, vector_io, eval_scoring) (#2258)	2025-05-24 22:59:07 -07:00
Ashwin Bharambe	ae7272d8ff	chore: split routers into individual files (datasets) (#2249)	2025-05-24 22:11:43 -07:00