1061 commits

Author	SHA1	Message	Date
Francisco Arceo	48581bf651	chore: Updating how default embedding model is set in stack (#3818) ... # What does this PR do? Refactor setting default vector store provider and embedding model to use an optional `vector_stores` config in the `StackRunConfig` and clean up code to do so (had to add back in some pieces of VectorDB). Also added remote Qdrant and Weaviate to starter distro (based on other PR where inference providers were added for UX). New config is simply (default for Starter distro): ```yaml vector_stores: default_provider_id: faiss default_embedding_model: provider_id: sentence-transformers model_id: nomic-ai/nomic-embed-text-v1.5 ``` ## Test Plan CI and Unit tests. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-20 14:22:45 -07:00
Ashwin Bharambe	2c43285e22	feat(stores)!: use backend storage references instead of configs (#3697) ... **This PR changes configurations in a backward incompatible way.** Run configs today repeat full SQLite/Postgres snippets everywhere a store is needed, which means duplicated credentials, extra connection pools, and lots of drift between files. This PR introduces named storage backends so the stack and providers can share a single catalog and reference those backends by name. ## Key Changes - Add `storage.backends` to `StackRunConfig`, register each KV/SQL backend once at startup, and validate that references point to the right family. - Move server stores under `storage.stores` with lightweight references (backend + namespace/table) instead of full configs. - Update every provider/config/doc to use the new reference style; docs/codegen now surface the simplified YAML. ## Migration Before: ```yaml metadata_store: type: sqlite db_path: ~/.llama/distributions/foo/registry.db inference_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} conversations_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} ``` After: ```yaml storage: backends: kv_default: type: kv_sqlite db_path: ~/.llama/distributions/foo/kvstore.db sql_default: type: sql_postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} stores: metadata: backend: kv_default namespace: registry inference: backend: sql_default table_name: inference_store max_write_queue_size: 10000 num_writers: 4 conversations: backend: sql_default table_name: openai_conversations ``` Provider configs follow the same pattern—for example, a Chroma vector adapter switches from: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} kvstore: type: sqlite db_path: ~/.llama/distributions/foo/chroma.db ``` to: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} persistence: backend: kv_default namespace: vector_io::chroma_remote ``` Once the backends are declared, everything else just points at them, so rotating credentials or swapping to Postgres happens in one place and the stack reuses a single connection pool.	2025-10-20 13:20:09 -07:00
Shabana Baig	add64e8e2a	feat: Add instructions parameter in response object (#3741) ... # Problem The current inline provider appends the user provided instructions to messages as a system prompt, but the returned response object does not contain the instructions field (as specified in the OpenAI responses spec). # What does this PR do? This pull request adds the instruction field to the response object definition and updates the inline provider. It also ensures that instructions from previous response is not carried over to the next response (as specified in the openAI spec). Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566) ## Test Plan - Tested manually for change in model response w.r.t supplied instructions field. - Added unit test to check that the instructions from previous response is not carried over to the next response. - Added integration tests to check instructions parameter in the returned response object. - Added new recordings for the integration tests. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-20 13:10:37 -07:00
ehhuang	9936f33f7e	chore: disable telemetry if otel endpoint isn't set (#3859) ... # What does this PR do? removes error: ConnectionError: HTTPConnectionPool(host='localhost', port=4318): Max retries exceeded with url: /v1/traces (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x10fd98e60>: Failed to establish a new connection: [Errno 61] Connection refused')) ## Test Plan uv run llama stack run starter curl http://localhost:8321/v1/models observe no error in server logs	2025-10-20 11:42:57 -07:00
Jiayi Ni	165b8b07f4	docs: Documentation update for NVIDIA Inference Provider (#3840) ... # 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] --> - Fix examples in the NVIDIA inference documentation to align with current API requirements. ## 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.* --> N/A	2025-10-20 09:51:43 -07:00
Emilio Garcia	943558af36	test(telemetry): Telemetry Tests (#3805) ... # What does this PR do? Adds a test and a standardized way to build future tests out for telemetry in llama stack. Contributes to https://github.com/llamastack/llama-stack/issues/3806 ## Test Plan This is the test plan 😎	2025-10-17 10:43:33 -07:00
ehhuang	b3099d40e2	fix(telemetry): remove dependency on old telemetry config (#3830) ... # What does this PR do? old telemetry config was removed in #3815 ## Test Plan ❯ OTEL_SERVICE_NAME=aloha OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 uv run llama stack run starter <img width="1888" height="605" alt="image" src="https://github.com/user-attachments/assets/dd5cc9f0-213a-4dc6-9385-f61a3a13b4c3" />	2025-10-16 12:05:10 -07:00
Charlie Doern	f22aaef42f	chore!: remove telemetry API usage (#3815) ... # What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-16 10:39:32 -07:00
Ashwin Bharambe	185de61d8e	fix(openai_mixin): no yelling for model listing if API keys are not provided (#3826) ... As indicated in the title. Our `starter` distribution enables all remote providers _very intentionally_ because we believe it creates an easier, more welcoming experience to new folks using the software. If we do that, and then slam the logs with errors making them question their life choices, it is not so good :) Note that this fix is limited in scope. If you ever try to actually instantiate the OpenAI client from a code path without an API key being present, you deserve to fail hard. ## Test Plan Run `llama stack run starter` with `OPENAI_API_KEY` set. No more wall of text, just one message saying "listed 96 models".	2025-10-16 10:12:13 -07:00
Ashwin Bharambe	07fc8013eb	fix(tests): reduce some test noise (#3825) ... a bunch of logger.info()s are good for server code to help debug in production, but we don't want them killing our unit test output :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-16 09:52:16 -07:00
Ashwin Bharambe	f70aa99c97	fix(models)!: always prefix models with provider_id when registering (#3822) ... **!!BREAKING CHANGE!!** The lookup is also straightforward -- we always look for this identifier and don't try to find a match for something without the provider_id prefix. Note that, this ideally means we need to update the `register_model()` API also (we should kill "identifier" from there) but I am not doing that as part of this PR. ## Test Plan Existing unit tests	2025-10-16 06:47:39 -07:00
Ashwin Bharambe	f205ab6f6c	fix(responses): fixes, re-record tests (#3820) ... Wanted to re-enable Responses CI but it seems to hang for some reason due to some interactions with conversations_store or responses_store. ## Test Plan ``` # library client ./scripts/integration-tests.sh --stack-config ci-tests --suite responses # server ./scripts/integration-tests.sh --stack-config server:ci-tests --suite responses ```	2025-10-15 16:37:42 -07:00
slekkala1	99141c29b1	feat: Add responses and safety impl extra_body (#3781) ... # What does this PR do? Have closed the previous PR due to merge conflicts with multiple PRs Addressed all comments from https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying over to this one) ## Test Plan Added UTs and integration tests	2025-10-15 15:01:37 -07:00
Ashwin Bharambe	8e7e0ddfec	fix(responses): use conversation items when no stored messages exist (#3819) ... Handle a base case when no stored messages exist because no Response call has been made. ## Test Plan ``` ./scripts/integration-tests.sh --stack-config server:ci-tests \ --suite responses --inference-mode record-if-missing --pattern test_conversation_responses ```	2025-10-15 14:43:44 -07:00
ehhuang	6ba9db3929	chore!: BREAKING CHANGE: remove sqlite from telemetry config (#3808) ... # What does this PR do? - Removed sqlite sink from telemetry config. - Removed related code - Updated doc related to telemetry ## Test Plan CI	2025-10-15 14:24:45 -07:00
Ashwin Bharambe	0a96a7faa5	fix(responses): fix subtle bugs in non-function tool calling (#3817) ... We were generating "FunctionToolCall" items even for MCP (and file-search, etc.) server-side calls. ID mismatches, etc. galore.	2025-10-15 13:57:37 -07:00
Sumanth Kamenani	bc8b377a7c	fix(vector-io): handle missing document_id in insert_chunks (#3521) ... Fixed KeyError when chunks don't have document_id in metadata or chunk_metadata. Updated logging to safely extract document_id using getattr and RAG memory to handle different document_id locations. Added test for missing document_id scenarios. Fixes issue #3494 where /v1/vector-io/insert would crash with KeyError. Fixed KeyError when chunks don't have document_id in metadata or chunk_metadata. Updated logging to safely extract document_id using getattr and RAG memory to handle different document_id locations. Added test for missing document_id scenarios. # What does this PR do? Fixes a KeyError crash in `/v1/vector-io/insert` when chunks are missing `document_id` fields. The API was failing even though `document_id` is optional according to the schema. Closes #3494 ## Test Plan **Before fix:** - POST to `/v1/vector-io/insert` with chunks → 500 KeyError - Happened regardless of where `document_id` was placed **After fix:** - Same request works fine → 200 OK - Tested with Postman using FAISS backend - Added unit test covering missing `document_id` scenarios	2025-10-15 11:02:48 -07:00
Ashwin Bharambe	e9b4278a51	feat(responses)!: improve responses + conversations implementations (#3810) ... This PR updates the Conversation item related types and improves a couple critical parts of the implemenation: - it creates a streaming output item for the final assistant message output by the model. until now we only added content parts and included that message in the final response. - rewrites the conversation update code completely to account for items other than messages (tool calls, outputs, etc.) ## Test Plan Used the test script from https://github.com/llamastack/llama-stack-client-python/pull/281 for this ``` TEST_API_BASE_URL=http://localhost:8321/v1 \ pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs ```	2025-10-15 09:36:11 -07:00
Juan Pérez de Algaba	add8cd801b	feat(gemini): Support gemini-embedding-001 and fix models/ prefix in metadata keys (#3813) ... # Add support for Google Gemini `gemini-embedding-001` embedding model and correctly registers model type MR message created with the assistance of Claude-4.5-sonnet This resolves https://github.com/llamastack/llama-stack/issues/3755 ## What does this PR do? This PR adds support for the `gemini-embedding-001` Google embedding model to the llama-stack Gemini provider. This model provides high-dimensional embeddings (3072 dimensions) compared to the existing `text-embedding-004` model (768 dimensions). Old embeddings models (such as text-embedding-004) will be deprecated soon according to Google ([Link](https://developers.googleblog.com/en/gemini-embedding-available-gemini-api/)) ## Problem The Gemini provider only supported the `text-embedding-004` embedding model. The newer `gemini-embedding-001` model, which provides higher-dimensional embeddings for improved semantic representation, was not available through llama-stack. ## Solution This PR consists of three commits that implement, fix the model registration, and enable embedding generation: ### Commit 1: Initial addition of gemini-embedding-001 Added metadata for `gemini-embedding-001` to the `embedding_model_metadata` dictionary: ```python embedding_model_metadata: dict[str, dict[str, int]] = { "text-embedding-004": {"embedding_dimension": 768, "context_length": 2048}, "gemini-embedding-001": {"embedding_dimension": 3072, "context_length": 2048}, # NEW } ``` **Issue discovered:** The model was not being registered correctly because the dictionary keys didn't match the model IDs returned by Gemini's API. ### Commit 2: Fix model ID matching with `models/` prefix Updated both dictionary keys to include the `models/` prefix to match Gemini's OpenAI-compatible API response format: ```python embedding_model_metadata: dict[str, dict[str, int]] = { "models/text-embedding-004": {"embedding_dimension": 768, "context_length": 2048}, # UPDATED "models/gemini-embedding-001": {"embedding_dimension": 3072, "context_length": 2048}, # UPDATED } ``` **Root cause:** Gemini's OpenAI-compatible API returns model IDs with the `models/` prefix (e.g., `models/text-embedding-004`). The `OpenAIMixin.list_models()` method directly matches these IDs against the `embedding_model_metadata` dictionary keys. Without the prefix, the models were being registered as LLMs instead of embedding models. ### Commit 3: Fix embedding generation for providers without usage stats Fixed a bug in `OpenAIMixin.openai_embeddings()` that prevented embedding generation for providers (like Gemini) that don't return usage statistics: ```python # Before (Line 351-354): usage = OpenAIEmbeddingUsage( prompt_tokens=response.usage.prompt_tokens, # ← Crashed with AttributeError total_tokens=response.usage.total_tokens, ) # After (Lines 351-362): if response.usage: usage = OpenAIEmbeddingUsage( prompt_tokens=response.usage.prompt_tokens, total_tokens=response.usage.total_tokens, ) else: usage = OpenAIEmbeddingUsage( prompt_tokens=0, # Default when not provided total_tokens=0, # Default when not provided ) ``` **Impact:** This fix enables embedding generation for **all** Gemini embedding models, not just the newly added one. ## Changes ### Modified Files **`llama_stack/providers/remote/inference/gemini/gemini.py`** - Line 17: Updated `text-embedding-004` key to `models/text-embedding-004` - Line 18: Added `models/gemini-embedding-001` with correct metadata **`llama_stack/providers/utils/inference/openai_mixin.py`** - Lines 351-362: Added null check for `response.usage` to handle providers without usage statistics ## Key Technical Details ### Model ID Matching Flow 1. `list_provider_model_ids()` calls Gemini's `/v1/models` endpoint 2. API returns model IDs like: `models/text-embedding-004`, `models/gemini-embedding-001` 3. `OpenAIMixin.list_models()` (line 410) checks: `if metadata := self.embedding_model_metadata.get(provider_model_id)` 4. If matched, registers as `model_type: "embedding"` with metadata; otherwise registers as `model_type: "llm"` ### Why Both Keys Needed the Prefix The `text-embedding-004` model was already working because there was likely separate configuration or manual registration handling it. For auto-discovery to work correctly for **both** models, both keys must match the API's model ID format exactly. ## How to test this PR Verified the changes by: 1. **Model Auto-Discovery**: Started llama-stack server and confirmed models are auto-discovered from Gemini API 2. **Model Registration**: Confirmed both embedding models are correctly registered and visible ```bash curl http://localhost:8325/v1/models | jq '.data[] | select(.provider_id == "gemini" and .model_type == "embedding")' ``` **Results:** - ✅ `gemini/models/text-embedding-004` - 768 dimensions - `model_type: "embedding"` - ✅ `gemini/models/gemini-embedding-001` - 3072 dimensions - `model_type: "embedding"` 3. **Before Fix (Commit 1)**: Models appeared as `model_type: "llm"` without embedding metadata 4. **After Fix (Commit 2)**: Models correctly identified as `model_type: "embedding"` with proper metadata 5. **Generate Embeddings**: Verified embedding generation works ```bash curl -X POST http://localhost:8325/v1/embeddings \ -H "Content-Type: application/json" \ -d '{"model": "gemini/models/gemini-embedding-001", "input": "test"}' | \ jq '.data[0].embedding | length' ```	2025-10-15 12:22:10 -04:00
slekkala1	ce8ea2f505	chore: Support embedding params from metadata for Vector Store (#3811) ... # What does this PR do? Support reading embedding model and dimensions from metadata for vector store ## Test Plan Unit Tests	2025-10-15 15:53:36 +02:00
Francisco Arceo	ef4bc70bbe	feat: Enable setting a default embedding model in the stack (#3803) ... # What does this PR do? Enables automatic embedding model detection for vector stores and by using a `default_configured` boolean that can be defined in the `run.yaml`. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan - Unit tests - Integration tests - Simple example below: Spin up the stack: ```bash uv run llama stack build --distro starter --image-type venv --run ``` Then test with OpenAI's client: ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") vs = client.vector_stores.create() ``` Previously you needed: ```python vs = client.vector_stores.create( extra_body={ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2", "embedding_dimension": 384, } ) ``` The `extra_body` is now unnecessary. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-14 18:25:13 -07:00
Jiayi Ni	d875e427bf	refactor: use extra_body to pass in input_type params for asymmetric embedding models for NVIDIA Inference Provider (#3804) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Previously, the NVIDIA inference provider implemented a custom `openai_embeddings` method with a hardcoded `input_type="query"` parameter, which is required by NVIDIA asymmetric embedding models([https://github.com/llamastack/llama-stack/pull/3205](https://github.com/llamastack/llama-stack/pull/3205)). Recently `extra_body` parameter is added to the embeddings API ([https://github.com/llamastack/llama-stack/pull/3794](https://github.com/llamastack/llama-stack/pull/3794)). So, this PR updates the NVIDIA inference provider to use the base `OpenAIMixin.openai_embeddings` method instead and pass the `input_type` through the `extra_body` parameter for asymmetric embedding models. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Run the following command for the ```embedding_model```: ```nvidia/llama-3.2-nv-embedqa-1b-v2```, ```nvidia/nv-embedqa-e5-v5```, ```nvidia/nv-embedqa-mistral-7b-v2```, and ```snowflake/arctic-embed-l```. ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model={embedding_model} --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" --inference-mode=record ```	2025-10-14 13:52:55 -07:00
IAN MILLER	007efa6eb5	refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The purpose of this PR is to replace the Llama Stack's default embedding model by nomic-embed-text-v1.5. These are the key reasons why Llama Stack community decided to switch from all-MiniLM-L6-v2 to nomic-embed-text-v1.5: 1. The training data for [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data) includes a lot of data sets with various licensing terms, so it is tricky to know when/whether it is appropriate to use this model for commercial applications. 2. The model is not particularly competitive on major benchmarks. For example, if you look at the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click on Miscellaneous/BEIR to see English information retrieval accuracy, you see that the top of the leaderboard is dominated by enormous models but also that there are many, many models of relatively modest size whith much higher Retrieval scores. If you want to look closely at the data, I recommend clicking "Download Table" because it is easier to browse that way. More discussion info can be founded [here](https://github.com/llamastack/llama-stack/issues/2418) <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2418 ## 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.* --> 1. Run `./scripts/unit-tests.sh` 2. Integration tests via CI wokrflow --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> Co-authored-by: Sébastien Han <seb@redhat.com>	2025-10-14 10:44:20 -04:00
Cesare Pompeiano	0dbf79c328	fix: Fixed WatsonX remote inference provider (#3801) ... # What does this PR do? This PR fixes issues with the WatsonX provider so it works correctly with LiteLLM. The main problem was that WatsonX requests failed because the provider data validator didn’t properly handle the API key and project ID. This was fixed by updating the WatsonXProviderDataValidator and ensuring the provider data is loaded correctly. The openai_chat_completion method was also updated to match the behavior of other providers while adding WatsonX-specific fields like project_id. It still calls await super().openai_chat_completion.__func__(self, params) to keep the existing setup and tracing logic. After these changes, WatsonX requests now run correctly. ## Test Plan The changes were tested by running chat completion requests and confirming that credentials and project parameters are passed correctly. I have tested with my WatsonX credentials, by using the cli with `uv run llama-stack-client inference chat-completion --session` --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: Sébastien Han <seb@redhat.com>	2025-10-14 14:52:32 +02:00
Francisco Arceo	968c364a3e	chore: Auto-detect Provider ID when only 1 Vector Store Provider avai… (#3802) ... # What does this PR do? 2 main changes: 1. Remove `provider_id` requirement in call to vector stores and 2. Removes "register first embedding model" logic - Now forces embedding model id as required on Vector Store creation Simplifies the UX for OpenAI to: ```python vs = client.vector_stores.create( name="my_citations_db", extra_body={ "embedding_model": "ollama/nomic-embed-text:latest", } ) ``` <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-13 10:25:36 -07:00
raghotham	b95f095a54	feat: Allow :memory: for kvstore (#3696) ... ## Test Plan added unit tests	2025-10-13 11:19:27 +02:00
Ashwin Bharambe	ecc8a554d2	feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794) ... Applies the same pattern from https://github.com/llamastack/llama-stack/pull/3777 to embeddings and vector_stores.create() endpoints. This should _not_ be a breaking change since (a) our tests were already using the `extra_body` parameter when passing in to the backend (b) but the backend probably wasn't extracting the parameters correctly. This PR will fix that. Updated APIs: `openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()`	2025-10-12 19:01:52 -07:00
slekkala1	3bb6ef351b	chore!: Safety api refactoring to use OpenAIMessageParam (#3796) ... # What does this PR do? Remove usage of deprecated `Message` from Safety apis ## Test Plan CI	2025-10-12 08:01:00 -07:00
Ashwin Bharambe	7c63aebd64	feat(responses)!: add reasoning and annotation added events (#3793) ... Implements missing streaming events from OpenAI Responses API spec: - reasoning text/summary events for o1/o3 models, - refusal events for safety moderation - annotation events for citations, - and file search streaming events. Added optional reasoning_content field to chat completion chunks to support non-standard provider extensions. **NOTE:** OpenAI does _not_ fill reasoning_content when users use the chat_completion APIs. This means there is no way for us to implement Responses (with reasoning) by using OpenAI chat completions! We'd need to transparently punt to OpenAI's responses endpoints if we wish to do that. For others though (vLLM, etc.) we can use it. ## Test Plan File search streaming test passes: ``` ./scripts/integration-tests.sh --stack-config server:ci-tests \ --suite responses --setup gpt --inference-mode replay --pattern test_response_file_search_streaming_events ``` Need more complex setup and validation for reasoning tests (need a vLLM powered OSS model maybe gpt-oss which can return reasoning_content). I will do that in a followup PR.	2025-10-11 16:47:14 -07:00
Francisco Arceo	a165b8b5bb	chore!: BREAKING CHANGE removing VectorDB APIs (#3774) ... # What does this PR do? Removes VectorDBs from API surface and our tests. Moves tests to Vector Stores. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-11 14:07:08 -07:00
ehhuang	06e4cd8e02	feat(api)!: BREAKING CHANGE: support passing extra_body through to providers (#3777) ... # What does this PR do? Allows passing through extra_body parameters to inference providers. With this, we removed the 2 vllm-specific parameters from completions API into `extra_body`. Before/After <img width="1883" height="324" alt="image" src="https://github.com/user-attachments/assets/acb27c08-c748-46c9-b1da-0de64e9908a1" /> closes #2720 ## Test Plan CI and added new test ``` ❯ uv run pytest -s -v tests/integration/ --stack-config=server:starter --inference-mode=record -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag ) and test_openai_completion_guided_choice' --setup=vllm --suite=base --color=yes Uninstalled 3 packages in 125ms Installed 3 packages in 19ms INFO 2025-10-10 14:29:54,317 tests.integration.conftest:118 tests: Applying setup 'vllm' for suite base INFO 2025-10-10 14:29:54,331 tests.integration.conftest:47 tests: Test stack config type: server (stack_config=server:starter) ============================================================================================================== test session starts ============================================================================================================== platform darwin -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- /Users/erichuang/projects/llama-stack-1/.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', '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'}} rootdir: /Users/erichuang/projects/llama-stack-1 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 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 285 items / 284 deselected / 1 selected tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] instantiating llama_stack_client Starting llama stack server with config 'starter' on port 8321... Waiting for server at http://localhost:8321... (0.0s elapsed) Waiting for server at http://localhost:8321... (0.5s elapsed) Waiting for server at http://localhost:8321... (5.1s elapsed) Waiting for server at http://localhost:8321... (5.6s elapsed) Waiting for server at http://localhost:8321... (10.1s elapsed) Waiting for server at http://localhost:8321... (10.6s elapsed) Server is ready at http://localhost:8321 llama_stack_client instantiated in 11.773s PASSEDTerminating llama stack server process... Terminating process 98444 and its group... Server process and children terminated gracefully ============================================================================================================= slowest 10 durations ============================================================================================================== 11.88s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 3.02s call tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 0.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] ================================================================================================ 1 passed, 284 deselected, 3 warnings in 16.21s ================================================================================================= ```	2025-10-10 16:21:44 -07:00
ehhuang	80d58ab519	chore: refactor (chat)completions endpoints to use shared params struct (#3761) ... # What does this PR do? Converts openai(_chat)_completions params to pydantic BaseModel to reduce code duplication across all providers. ## Test Plan CI --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761). * #3777 * __->__ #3761	2025-10-10 15:46:34 -07:00
Varsha	32fde8d9a8	feat: Add /v1/embeddings endpoint to batches API (#3384) ... # What does this PR do? This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes: https://github.com/llamastack/llama-stack/issues/3145 ## 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.* --> ``` (stack-client) ➜ llama-stack git:(support/embeddings-api) conda activate stack-client && python -m pytest tests/unit/providers/batches/test_reference.py -v ============================================================================================================================================ test session starts ============================================================================================================================================= platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'xdist': '3.8.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, xdist-3.8.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 46 items tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_and_retrieve_batch_success PASSED [ 2%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_without_metadata PASSED [ 4%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_completion_window PASSED [ 6%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[/v1/invalid/endpoint] PASSED [ 8%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[] PASSED [ 10%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_metadata PASSED [ 13%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_retrieve_batch_not_found PASSED [ 15%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_success PASSED [ 17%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[failed] PASSED [ 19%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[expired] PASSED [ 21%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[completed] PASSED [ 23%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_not_found PASSED [ 26%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_empty PASSED [ 28%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_single_batch PASSED [ 30%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_multiple_batches PASSED [ 32%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_limit PASSED [ 34%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_pagination PASSED [ 36%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_invalid_after PASSED [ 39%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_kvstore_persistence PASSED [ 41%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_not_found PASSED [ 43%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_exists_empty_content PASSED [ 45%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_mixed_valid_invalid_json PASSED [ 47%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_model PASSED [ 50%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 52%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 54%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 56%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 58%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 60%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[messages-body.messages-invalid_request-Messages parameter is required] PASSED [ 63%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 65%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 67%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 69%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 71%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 73%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[prompt-body.prompt-invalid_request-Prompt parameter is required] PASSED [ 76%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_url_mismatch PASSED [ 78%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_multiple_errors_per_request PASSED [ 80%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_request_format PASSED [ 82%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[custom_id-custom_id-12345-Custom_id must be a string] PASSED [ 84%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[url-url-123-URL must be a string] PASSED [ 86%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[method-method-invalid_value2-Method must be a string] PASSED [ 89%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[body-body-invalid_value3-Body must be a JSON dictionary object] PASSED [ 91%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[model-body.model-123-Model must be a string] PASSED [ 93%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[messages-body.messages-invalid messages format-Messages must be an array] PASSED [ 95%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_max_concurrent_batches PASSED [ 97%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_embeddings_endpoint PASSED [100%] ``` --------- Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 13:25:58 -07:00
Ashwin Bharambe	1394403360	feat(responses): implement usage tracking in streaming responses (#3771) ... Implementats usage accumulation to StreamingResponseOrchestrator. The most important part was to pass `stream_options = { "include_usage": true }` to the chat_completion call. This means I will have to record all responses tests again because request hash will change :) Test changes: - Add usage assertions to streaming and non-streaming tests - Update test recordings with actual usage data from OpenAI	2025-10-10 12:27:03 -07:00
Francisco Arceo	e7d21e1ee3	feat: Add support for Conversations in Responses API (#3743) ... # What does this PR do? This PR adds support for Conversations in Responses. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan Unit tests Integration tests <Details> <Summary>Manual testing with this script: (click to expand)</Summary> ```python from openai import OpenAI client = OpenAI() client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") def test_conversation_create(): print("Testing conversation create...") conversation = client.conversations.create( metadata={"topic": "demo"}, items=[ {"type": "message", "role": "user", "content": "Hello!"} ] ) print(f"Created: {conversation}") return conversation def test_conversation_retrieve(conv_id): print(f"Testing conversation retrieve for {conv_id}...") retrieved = client.conversations.retrieve(conv_id) print(f"Retrieved: {retrieved}") return retrieved def test_conversation_update(conv_id): print(f"Testing conversation update for {conv_id}...") updated = client.conversations.update( conv_id, metadata={"topic": "project-x"} ) print(f"Updated: {updated}") return updated def test_conversation_delete(conv_id): print(f"Testing conversation delete for {conv_id}...") deleted = client.conversations.delete(conv_id) print(f"Deleted: {deleted}") return deleted def test_conversation_items_create(conv_id): print(f"Testing conversation items create for {conv_id}...") items = client.conversations.items.create( conv_id, items=[ { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "Hello!"}] }, { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "How are you?"}] } ] ) print(f"Items created: {items}") return items def test_conversation_items_list(conv_id): print(f"Testing conversation items list for {conv_id}...") items = client.conversations.items.list(conv_id, limit=10) print(f"Items list: {items}") return items def test_conversation_item_retrieve(conv_id, item_id): print(f"Testing conversation item retrieve for {conv_id}/{item_id}...") item = client.conversations.items.retrieve(conversation_id=conv_id, item_id=item_id) print(f"Item retrieved: {item}") return item def test_conversation_item_delete(conv_id, item_id): print(f"Testing conversation item delete for {conv_id}/{item_id}...") deleted = client.conversations.items.delete(conversation_id=conv_id, item_id=item_id) print(f"Item deleted: {deleted}") return deleted def test_conversation_responses_create(): print("\nTesting conversation create for a responses example...") conversation = client.conversations.create() print(f"Created: {conversation}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "What are the 5 Ds of dodgeball?"}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") return response, conversation def test_conversations_responses_create_followup( conversation, content="Repeat what you just said but add 'this is my second time saying this'", ): print(f"Using: {conversation.id}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": content}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") conv_items = client.conversations.items.list(conversation.id) print(f"\nRetrieving list of items for conversation {conversation.id}:") print(conv_items.model_dump_json(indent=2)) def test_response_with_fake_conv_id(): fake_conv_id = "conv_zzzzzzzzz5dc81908289d62779d2ac510a2b0b602ef00a44" print(f"Using {fake_conv_id}") try: response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "say hello"}], conversation=fake_conv_id, ) print(f"Created response: {response} for conversation {fake_conv_id}") except Exception as e: print(f"failed to create response for conversation {fake_conv_id} with error {e}") def main(): print("Testing OpenAI Conversations API...") # Create conversation conversation = test_conversation_create() conv_id = conversation.id # Retrieve conversation test_conversation_retrieve(conv_id) # Update conversation test_conversation_update(conv_id) # Create items items = test_conversation_items_create(conv_id) # List items items_list = test_conversation_items_list(conv_id) # Retrieve specific item if items_list.data: item_id = items_list.data[0].id test_conversation_item_retrieve(conv_id, item_id) # Delete item test_conversation_item_delete(conv_id, item_id) # Delete conversation test_conversation_delete(conv_id) response, conversation2 = test_conversation_responses_create() print('\ntesting reseponse retrieval') test_conversation_retrieve(conversation2.id) print('\ntesting responses follow up') test_conversations_responses_create_followup(conversation2) print('\ntesting responses follow up x2!') test_conversations_responses_create_followup( conversation2, content="Repeat what you just said but add 'this is my third time saying this'", ) test_response_with_fake_conv_id() print("All tests completed!") if __name__ == "__main__": main() ``` </Details> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 11:57:40 -07:00
Ashwin Bharambe	548ccff368	fix(mypy): fix wrong attribute access (#3770)	2025-10-10 09:30:43 -07:00
grs	8bf07f91cb	feat: reuse previous mcp tool listings where possible (#3710) ... # What does this PR do? This PR checks whether, if a previous response is linked, there are mcp_list_tools objects that can be reused instead of listing the tools explicitly every time. Closes #3106 ## Test Plan Tested manually. Added unit tests to cover new behaviour. --------- Signed-off-by: Gordon Sim <gsim@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 09:28:25 -07:00
Matthew Farrellee	0066d986c5	feat: use SecretStr for inference provider auth credentials (#3724) ... # What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests	2025-10-10 07:32:50 -07:00
Ashwin Bharambe	e039b61d26	feat(responses)!: add in_progress, failed, content part events (#3765) ... ## Summary - add schema + runtime support for response.in_progress / response.failed / response.incomplete - stream content parts with proper indexes and reasoning slots - align tests + docs with the richer event payloads ## Testing - uv run pytest tests/unit/providers/agents/meta_reference/test_openai_responses.py::test_create_openai_response_with_string_input - uv run pytest tests/unit/providers/agents/meta_reference/test_response_conversion_utils.py	2025-10-10 07:27:34 -07:00
Akram Ben Aissi	a548169b99	fix: allow skipping model availability check for vLLM (#3739) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Allows model check to fail gracefully instead of crashing on startup. <!-- 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.* --> set VLLM_URL to your VLLM server ``` (base) akram@Mac llama-stack % LAMA_STACK_LOGGING="all=debug" VLLM_ENABLE_MODEL_DISCOVERY=false MILVUS_DB_PATH=./milvus.db INFERENCE_MODEL=vllm uv run --with llama-stack llama stack build --distro starter --image-type venv --run ``` ``` INFO 2025-10-08 20:11:24,637 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues INFO 2025-10-08 20:11:24,866 llama_stack.providers.utils.responses.responses_store:96 openai_responses: Write queue disabled for SQLite to avoid concurrency issues ERROR 2025-10-08 20:11:26,160 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: <a href="https://oauth.akram.a1ey.p3.openshiftapps.com:443/oauth/authorize?approval_prompt=force&amp;client_id=system%3Aserviceaccount%3Arhoai-30-genai%3Adefault&amp;redirect_uri=ht tps%3A%2F%2Fvllm-rhoai-30-genai.apps.rosa.akram.a1ey.p3.openshiftapps.com%2Foauth%2Fcallback&amp;response_type=code&amp;scope=user%3Ainfo+user%3Acheck-access&amp;state=9fba207425 5851c718aca717a5887d76%3A%2Fmodels">Found</a>. [...] INFO 2025-10-08 20:11:26,295 uvicorn.error:84 uncategorized: Started server process [83144] INFO 2025-10-08 20:11:26,296 uvicorn.error:48 uncategorized: Waiting for application startup. INFO 2025-10-08 20:11:26,297 llama_stack.core.server.server:170 core::server: Starting up INFO 2025-10-08 20:11:26,297 llama_stack.core.stack:399 core: starting registry refresh task INFO 2025-10-08 20:11:26,311 uvicorn.error:62 uncategorized: Application startup complete. INFO 2025-10-08 20:11:26,312 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) ERROR 2025-10-08 20:11:26,791 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: <a href="https://oauth.akram.a1ey.p3.openshiftapps.com:443/oauth/authorize?approval_prompt=force&amp;client_id=system%3Aserviceaccount%3Arhoai-30-genai%3Adefault&amp;redirect_uri=ht tps%3A%2F%2Fvllm-rhoai-30-genai.apps.rosa.akram.a1ey.p3.openshiftapps.com%2Foauth%2Fcallback&amp;response_type=code&amp;scope=user%3Ainfo+user%3Acheck-access&amp;state=8ef0cba3e1 71a4f8b04cb445cfb91a4c%3A%2Fmodels">Found</a>. ```	2025-10-10 07:23:13 -07:00
Ashwin Bharambe	ebae0385bb	fix: update dangling references to llama download command (#3763) ... ## Summary After removing model management CLI in #3700, this PR updates remaining references to the old `llama download` command to use `huggingface-cli download` instead. ## Changes - Updated error messages in `meta_reference/common.py` to recommend `huggingface-cli download` - Updated error messages in `torchtune/recipes/lora_finetuning_single_device.py` to use `huggingface-cli download` - Updated post-training notebook to use `huggingface-cli download` instead of `llama download` - Fixed typo: "you model" -> "your model" ## Test Plan - Verified error messages provide correct guidance for users - Checked that notebook instructions are up-to-date with current tooling	2025-10-09 18:35:02 -07:00
Ashwin Bharambe	f50ce11a3b	feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403) ... Renames `inference_recorder.py` to `api_recorder.py` and extends it to support recording/replaying tool invocations in addition to inference calls. This allows us to record web-search, etc. tool calls and thereafter apply recordings for `tests/integration/responses` ## Test Plan ``` export OPENAI_API_KEY=... export TAVILY_SEARCH_API_KEY=... ./scripts/integration-tests.sh --stack-config ci-tests \ --suite responses --inference-mode record-if-missing ```	2025-10-09 14:27:51 -07:00
grs	26fd5dbd34	fix: add traces for tool calls and mcp tool listing (#3722) ... # What does this PR do? Adds traces around tool execution and mcp tool listing for better observability. Closes #3108 ## Test Plan Manually examined traces in jaeger to verify the added information was available. Signed-off-by: Gordon Sim <gsim@redhat.com>	2025-10-09 09:59:09 -07:00
grs	96886afaca	fix(responses): fix regression in support for mcp tool require_approval argument (#3731) ... # What does this PR do? It prevents a tool call message being added to the chat completions message without a corresponding tool call result, which is needed in the case that an approval is required first or if the approval request is denied. In both these cases the tool call messages is popped of the next turn messages. Closes #3728 ## Test Plan Ran the integration tests Manual check of both approval and denial against gpt-4o Signed-off-by: Gordon Sim <gsim@redhat.com>	2025-10-08 10:47:17 -04:00
Bill Murdock	5d711d4bcb	fix: Update watsonx.ai provider to use LiteLLM mixin and list all models (#3674) ... # What does this PR do? - The watsonx.ai provider now uses the LiteLLM mixin instead of using IBM's library, which does not seem to be working (see #3165 for context). - The watsonx.ai provider now lists all the models available by calling the watsonx.ai server instead of having a hard coded list of known models. (That list gets out of date quickly) - An edge case in [llama_stack/core/routers/inference.py](https://github.com/llamastack/llama-stack/pull/3674/files#diff-a34bc966ed9befd9f13d4883c23705dff49be0ad6211c850438cdda6113f3455) is addressed that was causing my manual tests to fail. - Fixes `b64_encode_openai_embeddings_response` which was trying to enumerate over a dictionary and then reference elements of the dictionary using .field instead of ["field"]. That method is called by the LiteLLM mixin for embedding models, so it is needed to get the watsonx.ai embedding models to work. - A unit test along the lines of the one in #3348 is added. A more comprehensive plan for automatically testing the end-to-end functionality for inference providers would be a good idea, but is out of scope for this PR. - Updates to the watsonx distribution. Some were in response to the switch to LiteLLM (e.g., updating the Python packages needed). Others seem to be things that were already broken that I found along the way (e.g., a reference to a watsonx specific doc template that doesn't seem to exist). Closes #3165 Also it is related to a line-item in #3387 but doesn't really address that goal (because it uses the LiteLLM mixin, not the OpenAI one). I tried the OpenAI one and it doesn't work with watsonx.ai, presumably because the watsonx.ai service is not OpenAI compatible. It works with LiteLLM because LiteLLM has a provider implementation for watsonx.ai. ## Test Plan The test script below goes back and forth between the OpenAI and watsonx providers. The idea is that the OpenAI provider shows how it should work and then the watsonx provider output shows that it is also working with watsonx. Note that the result from the MCP test is not as good (the Llama 3.3 70b model does not choose tools as wisely as gpt-4o), but it is still working and providing a valid response. For more details on setup and the MCP server being used for testing, see [the AI Alliance sample notebook](https://github.com/The-AI-Alliance/llama-stack-examples/blob/main/notebooks/01-responses/) that these examples are drawn from. ```python #!/usr/bin/env python3 import json from llama_stack_client import LlamaStackClient from litellm import completion import http.client def print_response(response): """Print response in a nicely formatted way""" print(f"ID: {response.id}") print(f"Status: {response.status}") print(f"Model: {response.model}") print(f"Created at: {response.created_at}") print(f"Output items: {len(response.output)}") for i, output_item in enumerate(response.output): if len(response.output) > 1: print(f"\n--- Output Item {i+1} ---") print(f"Output type: {output_item.type}") if output_item.type in ("text", "message"): print(f"Response content: {output_item.content[0].text}") elif output_item.type == "file_search_call": print(f" Tool Call ID: {output_item.id}") print(f" Tool Status: {output_item.status}") # 'queries' is a list, so we join it for clean printing print(f" Queries: {', '.join(output_item.queries)}") # Display results if they exist, otherwise note they are empty print(f" Results: {output_item.results if output_item.results else 'None'}") elif output_item.type == "mcp_list_tools": print_mcp_list_tools(output_item) elif output_item.type == "mcp_call": print_mcp_call(output_item) else: print(f"Response content: {output_item.content}") def print_mcp_call(mcp_call): """Print MCP call in a nicely formatted way""" print(f"\n🛠️ MCP Tool Call: {mcp_call.name}") print(f" Server: {mcp_call.server_label}") print(f" ID: {mcp_call.id}") print(f" Arguments: {mcp_call.arguments}") if mcp_call.error: print("Error: {mcp_call.error}") elif mcp_call.output: print("Output:") # Try to format JSON output nicely try: parsed_output = json.loads(mcp_call.output) print(json.dumps(parsed_output, indent=4)) except: # If not valid JSON, print as-is print(f" {mcp_call.output}") else: print(" ⏳ No output yet") def print_mcp_list_tools(mcp_list_tools): """Print MCP list tools in a nicely formatted way""" print(f"\n🔧 MCP Server: {mcp_list_tools.server_label}") print(f" ID: {mcp_list_tools.id}") print(f" Available Tools: {len(mcp_list_tools.tools)}") print("=" * 80) for i, tool in enumerate(mcp_list_tools.tools, 1): print(f"\n{i}. {tool.name}") print(f" Description: {tool.description}") # Parse and display input schema schema = tool.input_schema if schema and 'properties' in schema: properties = schema['properties'] required = schema.get('required', []) print(" Parameters:") for param_name, param_info in properties.items(): param_type = param_info.get('type', 'unknown') param_desc = param_info.get('description', 'No description') required_marker = " (required)" if param_name in required else " (optional)" print(f" • {param_name} ({param_type}){required_marker}") if param_desc: print(f" {param_desc}") if i < len(mcp_list_tools.tools): print("-" * 40) def main(): """Main function to run all the tests""" # Configuration LLAMA_STACK_URL = "http://localhost:8321/" LLAMA_STACK_MODEL_IDS = [ "openai/gpt-3.5-turbo", "openai/gpt-4o", "llama-openai-compat/Llama-3.3-70B-Instruct", "watsonx/meta-llama/llama-3-3-70b-instruct" ] # Using gpt-4o for this demo, but feel free to try one of the others or add more to run.yaml. OPENAI_MODEL_ID = LLAMA_STACK_MODEL_IDS[1] WATSONX_MODEL_ID = LLAMA_STACK_MODEL_IDS[-1] NPS_MCP_URL = "http://localhost:3005/sse/" print("=== Llama Stack Testing Script ===") print(f"Using OpenAI model: {OPENAI_MODEL_ID}") print(f"Using WatsonX model: {WATSONX_MODEL_ID}") print(f"MCP URL: {NPS_MCP_URL}") print() # Initialize client print("Initializing LlamaStackClient...") client = LlamaStackClient(base_url="http://localhost:8321") # Test 1: List models print("\n=== Test 1: List Models ===") try: models = client.models.list() print(f"Found {len(models)} models") except Exception as e: print(f"Error listing models: {e}") raise e # Test 2: Basic chat completion with OpenAI print("\n=== Test 2: Basic Chat Completion (OpenAI) ===") try: chat_completion_response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}] ) print("OpenAI Response:") for chunk in chat_completion_response.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with OpenAI chat completion: {e}") raise e # Test 3: Basic chat completion with WatsonX print("\n=== Test 3: Basic Chat Completion (WatsonX) ===") try: chat_completion_response_wxai = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], ) print("WatsonX Response:") for chunk in chat_completion_response_wxai.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with WatsonX chat completion: {e}") raise e # Test 4: Tool calling with OpenAI print("\n=== Test 4: Tool Calling (OpenAI) ===") tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather for a specific location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g., San Francisco, CA", }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] }, }, "required": ["location"], }, }, } ] messages = [ {"role": "user", "content": "What's the weather like in Boston, MA?"} ] try: print("--- Initial API Call ---") response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("OpenAI tool calling response received") except Exception as e: print(f"Error with OpenAI tool calling: {e}") raise e # Test 5: Tool calling with WatsonX print("\n=== Test 5: Tool Calling (WatsonX) ===") try: wxai_response = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("WatsonX tool calling response received") except Exception as e: print(f"Error with WatsonX tool calling: {e}") raise e # Test 6: Streaming with WatsonX print("\n=== Test 6: Streaming Response (WatsonX) ===") try: chat_completion_response_wxai_stream = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], stream=True ) print("Model response: ", end="") for chunk in chat_completion_response_wxai_stream: # Each 'chunk' is a ChatCompletionChunk object. # We want the content from the 'delta' attribute. if hasattr(chunk, 'choices') and chunk.choices is not None: content = chunk.choices[0].delta.content # The first few chunks might have None content, so we check for it. if content is not None: print(content, end="", flush=True) print() except Exception as e: print(f"Error with streaming: {e}") raise e # Test 7: MCP with OpenAI print("\n=== Test 7: MCP Integration (OpenAI) ===") try: mcp_llama_stack_client_response = client.responses.create( model=OPENAI_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (OpenAI): {e}") raise e # Test 8: MCP with WatsonX print("\n=== Test 8: MCP Integration (WatsonX) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="What is the capital of France?" ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (WatsonX): {e}") raise e # Test 9: MCP with Llama 3.3 print("\n=== Test 9: MCP Integration (Llama 3.3) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (Llama 3.3): {e}") raise e # Test 10: Embeddings print("\n=== Test 10: Embeddings ===") try: conn = http.client.HTTPConnection("localhost:8321") payload = json.dumps({ "model": "watsonx/ibm/granite-embedding-278m-multilingual", "input": "Hello, world!", }) headers = { 'Content-Type': 'application/json', 'Accept': 'application/json' } conn.request("POST", "/v1/openai/v1/embeddings", payload, headers) res = conn.getresponse() data = res.read() print(data.decode("utf-8")) except Exception as e: print(f"Error with Embeddings: {e}") raise e print("\n=== Testing Complete ===") if __name__ == "__main__": main() ``` --------- Signed-off-by: Bill Murdock <bmurdock@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-08 07:29:43 -04:00
slekkala1	1ac320b7e6	chore: remove dead code (#3729) ... # What does this PR do? Removing some dead code, found by vulture and checked by claude that there are no references or imports for these ## Test Plan CI	2025-10-07 20:26:02 -07:00
ehhuang	b6e9f41041	chore: Revert "fix: fix nvidia provider (#3716)" (#3730) ... This reverts commit c940fe7938. @wukaixingxp I stamped to fast. Let's wait for @mattf's review.	2025-10-07 19:16:51 -07:00
Kai Wu	c940fe7938	fix: fix nvidia provider (#3716) ... # What does this PR do? (Used claude to solve #3715, coded with claude but tested by me) ## From claude summary: <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> **Problem**: The `NVIDIAInferenceAdapter` class was missing the `alias_to_provider_id_map` attribute, which caused the error: `ERROR 'NVIDIAInferenceAdapter' object has no attribute 'alias_to_provider_id_map'` **Root Cause**: The `NVIDIAInferenceAdapter` only inherited from `OpenAIMixin`, but some parts of the system expected it to have the `alias_to_provider_id_map` attribute, which is provided by the `ModelRegistryHelper` class. **Solution**: 1. **Added ModelRegistryHelper import**: Imported the `ModelRegistryHelper` class from `llama_stack.providers.utils.inference.model_registry` 2. **Updated inheritance**: Changed the class declaration to inherit from both `OpenAIMixin` and `ModelRegistryHelper` 3. **Added proper initialization**: Added an `__init__` method that properly initializes the `ModelRegistryHelper` with empty model entries (since NVIDIA uses dynamic model discovery) and the allowed models from the configuration **Key Changes**: * Added `from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper` * Changed class declaration from `class NVIDIAInferenceAdapter(OpenAIMixin):` to `class NVIDIAInferenceAdapter(OpenAIMixin, ModelRegistryHelper):` * Added `__init__` method that calls `ModelRegistryHelper.__init__(self, model_entries=[], allowed_models=config.allowed_models)` The inheritance order is important - `OpenAIMixin` comes first to ensure its `check_model_availability()` method takes precedence over the `ModelRegistryHelper` version, as mentioned in the class documentation. This fix ensures that the `NVIDIAInferenceAdapter` has the required `alias_to_provider_id_map` attribute while maintaining all existing functionality.<!-- 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.* --> Launching llama-stack server successfully, see logs: ``` NVIDIA_API_KEY=dummy NVIDIA_BASE_URL=http://localhost:8912 llama stack run /home/nvidia/.llama/distributions/starter/starter-run.yaml --image-type venv & [2] 3753042 (venv) nvidia@nv-meta-H100-testing-gpu01:~/kai/llama-stack$ WARNING 2025-10-07 00:29:09,848 root:266 uncategorized: Unknown logging category: openai::conversations. Falling back to default 'root' level: 20 WARNING 2025-10-07 00:29:09,932 root:266 uncategorized: Unknown logging category: cli. Falling back to default 'root' level: 20 INFO 2025-10-07 00:29:09,937 llama_stack.core.utils.config_resolution:45 core: Using file path: /home/nvidia/.llama/distributions/starter/starter-run.yaml INFO 2025-10-07 00:29:09,937 llama_stack.cli.stack.run:136 cli: Using run configuration: /home/nvidia/.llama/distributions/starter/starter-run.yaml Using virtual environment: /home/nvidia/kai/venv Virtual environment already activated + '[' -n /home/nvidia/.llama/distributions/starter/starter-run.yaml ']' + yaml_config_arg=/home/nvidia/.llama/distributions/starter/starter-run.yaml + llama stack run /home/nvidia/.llama/distributions/starter/starter-run.yaml --port 8321 WARNING 2025-10-07 00:29:11,432 root:266 uncategorized: Unknown logging category: openai::conversations. Falling back to default 'root' level: 20 WARNING 2025-10-07 00:29:11,593 root:266 uncategorized: Unknown logging category: cli. Falling back to default 'root' level: 20 INFO 2025-10-07 00:29:11,603 llama_stack.core.utils.config_resolution:45 core: Using file path: /home/nvidia/.llama/distributions/starter/starter-run.yaml INFO 2025-10-07 00:29:11,604 llama_stack.cli.stack.run:136 cli: Using run configuration: /home/nvidia/.llama/distributions/starter/starter-run.yaml INFO 2025-10-07 00:29:11,624 llama_stack.cli.stack.run:155 cli: No image type or image name provided. Assuming environment packages. INFO 2025-10-07 00:29:11,625 llama_stack.core.utils.config_resolution:45 core: Using file path: /home/nvidia/.llama/distributions/starter/starter-run.yaml INFO 2025-10-07 00:29:11,644 llama_stack.cli.stack.run:230 cli: HTTPS enabled with certificates: Key: None Cert: None INFO 2025-10-07 00:29:11,645 llama_stack.cli.stack.run:232 cli: Listening on ['::', '0.0.0.0']:8321 INFO 2025-10-07 00:29:11,816 llama_stack.core.utils.config_resolution:45 core: Using file path: /home/nvidia/.llama/distributions/starter/starter-run.yaml INFO 2025-10-07 00:29:11,836 llama_stack.core.server.server:480 core::server: Run configuration: INFO 2025-10-07 00:29:11,845 llama_stack.core.server.server:483 core::server: apis: - agents - batches - datasetio - eval - files - inference - post_training - safety - scoring - telemetry - tool_runtime - vector_io benchmarks: [] datasets: [] image_name: starter inference_store: db_path: /home/nvidia/.llama/distributions/starter/inference_store.db type: sqlite metadata_store: db_path: /home/nvidia/.llama/distributions/starter/registry.db type: sqlite models: [] providers: agents: - config: persistence_store: db_path: /home/nvidia/.llama/distributions/starter/agents_store.db type: sqlite responses_store: db_path: /home/nvidia/.llama/distributions/starter/responses_store.db type: sqlite provider_id: meta-reference provider_type: inline::meta-reference batches: - config: kvstore: db_path: /home/nvidia/.llama/distributions/starter/batches.db type: sqlite provider_id: reference provider_type: inline::reference datasetio: - config: kvstore: db_path: /home/nvidia/.llama/distributions/starter/huggingface_datasetio.db type: sqlite provider_id: huggingface provider_type: remote::huggingface - config: kvstore: db_path: /home/nvidia/.llama/distributions/starter/localfs_datasetio.db type: sqlite provider_id: localfs provider_type: inline::localfs eval: - config: kvstore: db_path: /home/nvidia/.llama/distributions/starter/meta_reference_eval.db type: sqlite provider_id: meta-reference provider_type: inline::meta-reference files: - config: metadata_store: db_path: /home/nvidia/.llama/distributions/starter/files_metadata.db type: sqlite storage_dir: /home/nvidia/.llama/distributions/starter/files provider_id: meta-reference-files provider_type: inline::localfs inference: - config: api_key: '********' url: https://api.fireworks.ai/inference/v1 provider_id: fireworks provider_type: remote::fireworks - config: api_key: '********' url: https://api.together.xyz/v1 provider_id: together provider_type: remote::together - config: {} provider_id: bedrock provider_type: remote::bedrock - config: api_key: '********' append_api_version: true url: http://localhost:8912 provider_id: nvidia provider_type: remote::nvidia - config: api_key: '********' base_url: https://api.openai.com/v1 provider_id: openai provider_type: remote::openai - config: api_key: '********' provider_id: anthropic provider_type: remote::anthropic - config: api_key: '********' provider_id: gemini provider_type: remote::gemini - config: api_key: '********' url: https://api.groq.com provider_id: groq provider_type: remote::groq - config: api_key: '********' url: https://api.sambanova.ai/v1 provider_id: sambanova provider_type: remote::sambanova - config: {} provider_id: sentence-transformers provider_type: inline::sentence-transformers post_training: - config: checkpoint_format: meta provider_id: torchtune-cpu provider_type: inline::torchtune-cpu safety: - config: excluded_categories: [] provider_id: llama-guard provider_type: inline::llama-guard - config: {} provider_id: code-scanner provider_type: inline::code-scanner scoring: - config: {} provider_id: basic provider_type: inline::basic - config: {} provider_id: llm-as-judge provider_type: inline::llm-as-judge - config: openai_api_key: '********' provider_id: braintrust provider_type: inline::braintrust telemetry: - config: service_name: "\u200B" sinks: sqlite sqlite_db_path: /home/nvidia/.llama/distributions/starter/trace_store.db provider_id: meta-reference provider_type: inline::meta-reference tool_runtime: - config: api_key: '********' max_results: 3 provider_id: brave-search provider_type: remote::brave-search - config: api_key: '********' max_results: 3 provider_id: tavily-search provider_type: remote::tavily-search - config: {} provider_id: rag-runtime provider_type: inline::rag-runtime - config: {} provider_id: model-context-protocol provider_type: remote::model-context-protocol vector_io: - config: kvstore: db_path: /home/nvidia/.llama/distributions/starter/faiss_store.db type: sqlite provider_id: faiss provider_type: inline::faiss - config: db_path: /home/nvidia/.llama/distributions/starter/sqlite_vec.db kvstore: db_path: /home/nvidia/.llama/distributions/starter/sqlite_vec_registry.db type: sqlite provider_id: sqlite-vec provider_type: inline::sqlite-vec scoring_fns: [] server: port: 8321 shields: [] tool_groups: - provider_id: tavily-search toolgroup_id: builtin::websearch - provider_id: rag-runtime toolgroup_id: builtin::rag vector_dbs: [] version: 2 INFO 2025-10-07 00:29:12,138 llama_stack.providers.remote.inference.nvidia.nvidia:49 inference::nvidia: Initializing NVIDIAInferenceAdapter(http://localhost:8912)... INFO 2025-10-07 00:29:12,921 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues INFO 2025-10-07 00:29:13,524 llama_stack.providers.utils.responses.responses_store:96 openai_responses: Write queue disabled for SQLite to avoid concurrency issues ERROR 2025-10-07 00:29:13,679 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: FireworksInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"fireworks_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:13,681 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider fireworks: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"fireworks_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:13,682 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: TogetherInferenceAdapter.list_provider_model_ids() failed with: Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>} WARNING 2025-10-07 00:29:13,684 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider together: Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>} Handling connection for 8912 INFO 2025-10-07 00:29:14,047 llama_stack.providers.utils.inference.openai_mixin:448 providers::utils: NVIDIAInferenceAdapter.list_provider_model_ids() returned 3 models ERROR 2025-10-07 00:29:14,062 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: OpenAIInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"openai_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,063 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider openai: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"openai_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,099 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: AnthropicInferenceAdapter.list_provider_model_ids() failed with: "Could not resolve authentication method. Expected either api_key or auth_token to be set. Or for one of the `X-Api-Key` or `Authorization` headers to be explicitly omitted" WARNING 2025-10-07 00:29:14,100 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider anthropic: "Could not resolve authentication method. Expected either api_key or auth_token to be set. Or for one of the `X-Api-Key` or `Authorization` headers to be explicitly omitted" ERROR 2025-10-07 00:29:14,102 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: GeminiInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"gemini_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,103 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider gemini: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"gemini_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,105 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: GroqInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"groq_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,106 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider groq: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"groq_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,107 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: SambaNovaInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"sambanova_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,109 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider sambanova: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"sambanova_api_key": "<API_KEY>"}, or in the provider config. INFO 2025-10-07 00:29:14,454 uvicorn.error:84 uncategorized: Started server process [3753046] INFO 2025-10-07 00:29:14,455 uvicorn.error:48 uncategorized: Waiting for application startup. INFO 2025-10-07 00:29:14,457 llama_stack.core.server.server:170 core::server: Starting up INFO 2025-10-07 00:29:14,458 llama_stack.core.stack:415 core: starting registry refresh task ERROR 2025-10-07 00:29:14,459 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: FireworksInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"fireworks_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,461 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider fireworks: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"fireworks_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,462 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: TogetherInferenceAdapter.list_provider_model_ids() failed with: Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>} WARNING 2025-10-07 00:29:14,463 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider together: Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>} ERROR 2025-10-07 00:29:14,465 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: OpenAIInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"openai_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,466 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider openai: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"openai_api_key": "<API_KEY>"}, or in the provider config. INFO 2025-10-07 00:29:14,500 uvicorn.error:62 uncategorized: Application startup complete. ERROR 2025-10-07 00:29:14,502 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: AnthropicInferenceAdapter.list_provider_model_ids() failed with: "Could not resolve authentication method. Expected either api_key or auth_token to be set. Or for one of the `X-Api-Key` or `Authorization` headers to be explicitly omitted" WARNING 2025-10-07 00:29:14,503 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider anthropic: "Could not resolve authentication method. Expected either api_key or auth_token to be set. Or for one of the `X-Api-Key` or `Authorization` headers to be explicitly omitted" ERROR 2025-10-07 00:29:14,504 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: GeminiInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"gemini_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,506 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider gemini: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"gemini_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,507 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: GroqInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"groq_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,508 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider groq: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"groq_api_key": "<API_KEY>"}, or in the provider config. ERROR 2025-10-07 00:29:14,510 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: SambaNovaInferenceAdapter.list_provider_model_ids() failed with: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"sambanova_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-07 00:29:14,511 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider sambanova: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"sambanova_api_key": "<API_KEY>"}, or in the provider config. INFO 2025-10-07 00:29:14,513 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) ``` tested with curl model, it also works: ``` curl http://localhost:8321/v1/models {"data":[{"identifier":"bedrock/meta.llama3-1-8b-instruct-v1:0","provider_resource_id":"meta.llama3-1-8b-instruct-v1:0","provider_id":"bedrock","type":"model","metadata":{},"model_type":"llm"},{"identifier":"bedrock/meta.llama3-1-70b-instruct-v1:0","provider_resource_id":"meta.llama3-1-70b-instruct-v1:0","provider_id":"bedrock","type":"model","metadata":{},"model_type":"llm"},{"identifier":"bedrock/meta.llama3-1-405b-instruct-v1:0","provider_resource_id":"meta.llama3-1-405b-instruct-v1:0","provider_id":"bedrock","type":"model","metadata":{},"model_type":"llm"},{"identifier":"nvidia/bigcode/starcoder2-7b","provider_resource_id":"bigcode/starcoder2-7b","provider_id":"nvidia","type":"model","metadata":{},"model_type":"llm"},{"identifier":"nvidia/meta/llama-3.3-70b-instruct","provider_resource_id":"meta/llama-3.3-70b-instruct","provider_id":"nvidia","type":"model","metadata":{},"model_type":"llm"},{"identifier":"nvidia/nvidia/llama-3.2-nv-embedqa-1b-v2","provider_resource_id":"nvidia/llama-3.2-nv-embedqa-1b-v2","provider_id":"nvidia","type":"model","metadata":{"embedding_dimension":2048,"context_length":8192},"model_type":"embedding"},{"identifier":"sentence-transformers/all-MiniLM-L6-v2","provider_resource_id":"all-MiniLM-L6-v2","provider_id":"sentence-transformers","type":"model","metadata":{"embedding_dimension":384},"model_type":"embedding"}]}% ``` --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-07 18:23:12 -07:00
slekkala1	c2d97a9db9	chore: fix flaky unit test and add proper shutdown for file batches (#3725) ... # What does this PR do? Have been running into flaky unit test failures: 5217035494 Fixing below 1. Shutting down properly by cancelling any stale file batches tasks running in background. 2. Also, use unique_kvstore_config, so the test dont use same db path and maintain test isolation ## Test Plan Ran unit test locally and CI	2025-10-07 14:23:14 -07:00
Akram Ben Aissi	1970b4aa4b	fix: improve model availability checks: Allows use of unavailable models on startup (#3717) ... - Allows use of unavailable models on startup - Add has_model method to ModelsRoutingTable for checking pre-registered models - Update check_model_availability to check model_store before provider APIs # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Start llama stack and point unavailable vLLM ``` VLLM_URL=https://my-unavailable-vllm/v1 MILVUS_DB_PATH=./milvus.db INFERENCE_MODEL=vllm uv run --with llama-stack llama stack build --distro starter --image-type venv --run ``` llama stack will start without crashing but only notifying error. ``` - provider_id: rag-runtime toolgroup_id: builtin::rag vector_dbs: [] version: 2 INFO 2025-10-07 06:40:41,804 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues INFO 2025-10-07 06:40:42,066 llama_stack.providers.utils.responses.responses_store:96 openai_responses: Write queue disabled for SQLite to avoid concurrency issues ERROR 2025-10-07 06:40:58,882 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: Request timed out. WARNING 2025-10-07 06:40:58,883 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider vllm: Request timed out. [...] INFO 2025-10-07 06:40:59,036 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) INFO 2025-10-07 06:41:04,064 openai._base_client:1618 uncategorized: Retrying request to /models in 0.398814 seconds INFO 2025-10-07 06:41:09,497 openai._base_client:1618 uncategorized: Retrying request to /models in 0.781908 seconds ERROR 2025-10-07 06:41:15,282 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: Request timed out. WARNING 2025-10-07 06:41:15,283 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider vllm: Request timed out. ```	2025-10-07 14:27:24 -04:00