mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
41 commits
Author | SHA1 | Message | Date | |
---|---|---|---|---|
|
873a400544 |
chore: OpenAIMixin implements ModelsProtocolPrivate (#3662)
# What does this PR do? add ModelsProtocolPrivate methods to OpenAIMixin this will allow providers using OpenAIMixin to use a common interface ## Test Plan ci w/ new tests |
||
|
2e544ecd8a |
feat(tools)!: substantial clean up of "Tool" related datatypes (#3627)
This is a sweeping change to clean up some gunk around our "Tool" definitions. First, we had two types `Tool` and `ToolDef`. The first of these was a "Resource" type for the registry but we had stopped registering tools inside the Registry long back (and only registered ToolGroups.) The latter was for specifying tools for the Agents API. This PR removes the former and adds an optional `toolgroup_id` field to the latter. Secondly, as pointed out by @bbrowning in https://github.com/llamastack/llama-stack/pull/3003#issuecomment-3245270132, we were doing a lossy conversion from a full JSON schema from the MCP tool specification into our ToolDefinition to send it to the model. There is no necessity to do this -- we ourselves aren't doing any execution at all but merely passing it to the chat completions API which supports this. By doing this (and by doing it poorly), we encountered limitations like not supporting array items, or not resolving $refs, etc. To fix this, we replaced the `parameters` field by `{ input_schema, output_schema }` which can be full blown JSON schemas. Finally, there were some types in our llama-related chat format conversion which needed some cleanup. We are taking this opportunity to clean those up. This PR is a substantial breaking change to the API. However, given our window for introducing breaking changes, this suits us just fine. I will be landing a concurrent `llama-stack-client` change as well since API shapes are changing. |
||
|
36543a1100 |
chore: fix agents tests for non-ollama providers, provide max_tokens (#3657)
# What does this PR do? closes #3656 ## Test Plan openai is not enabled in ci, so manual testing with: ``` $ ./scripts/integration-tests.sh --stack-config ci-tests --suite base --setup gpt --subdirs agents --inference-mode live === Llama Stack Integration Test Runner === Stack Config: ci-tests Setup: gpt Inference Mode: live Test Suite: base Test Subdirs: agents Test Pattern: Checking llama packages llama-stack 0.2.23 .../llama-stack llama-stack-client 0.3.0a3 ollama 0.5.1 === System Resources Before Tests === ... === Applying Setup Environment Variables === Setting up environment variables: === Running Integration Tests === Test subdirs to run: agents Added test files from agents: 3 files === Running all collected tests in a single pytest command === Total test files: 3 + pytest -s -v tests/integration/agents/test_persistence.py tests/integration/agents/test_openai_responses.py tests/integration/agents/test_agents.py --stack-config=ci-tests --inference-mode=live -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag )' --setup=gpt --color=yes --capture=tee-sys WARNING 2025-10-02 13:14:32,653 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,043 root:258 uncategorized: Unknown logging category: tests. Falling back to default 'root' level: 20 INFO 2025-10-02 13:14:33,063 tests.integration.conftest:86 tests: Applying setup 'gpt' ========================================= test session starts ========================================== platform linux -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- .../.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'Linux-6.16.7-200.fc42.x86_64-x86_64-with-glibc2.41', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'html': '4.1.1', 'anyio': '4.9.0', 'timeout': '2.4.0', 'cov': '6.2.1', 'asyncio': '1.1.0', 'nbval': '0.11.0', 'socket': '0.7.0', 'json-report': '1.5.0', 'metadata': '3.1.1'}} rootdir: ... configfile: pyproject.toml plugins: html-4.1.1, anyio-4.9.0, timeout-2.4.0, cov-6.2.1, asyncio-1.1.0, nbval-0.11.0, socket-0.7.0, json-report-1.5.0, metadata-3.1.1 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 32 items / 6 deselected / 26 selected tests/integration/agents/test_persistence.py::test_delete_agents_and_sessions SKIPPED (This ...) [ 3%] tests/integration/agents/test_persistence.py::test_get_agent_turns_and_steps SKIPPED (This t...) [ 7%] tests/integration/agents/test_openai_responses.py::test_responses_store[openai_client-txt=openai/gpt-4o-tools0-True] instantiating llama_stack_client WARNING 2025-10-02 13:14:33,472 root:258 uncategorized: Unknown logging category: testing. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,477 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,960 root:258 uncategorized: Unknown logging category: tokenizer_utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,962 root:258 uncategorized: Unknown logging category: models::llama. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,963 root:258 uncategorized: Unknown logging category: models::llama. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,968 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,974 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:33,978 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,350 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,366 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,489 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,490 root:258 uncategorized: Unknown logging category: inference_store. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,697 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:35,918 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 INFO 2025-10-02 13:14:35,945 llama_stack.providers.utils.inference.inference_store:74 inference_store: Write queue disabled for SQLite to avoid concurrency issues WARNING 2025-10-02 13:14:36,172 root:258 uncategorized: Unknown logging category: files. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,218 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,219 root:258 uncategorized: Unknown logging category: vector_io. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,231 root:258 uncategorized: Unknown logging category: vector_io. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,255 root:258 uncategorized: Unknown logging category: tool_runtime. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,486 root:258 uncategorized: Unknown logging category: responses_store. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,503 root:258 uncategorized: Unknown logging category: openai::responses. Falling back to default 'root' level: 20 INFO 2025-10-02 13:14:36,524 llama_stack.providers.utils.responses.responses_store:80 responses_store: Write queue disabled for SQLite to avoid concurrency issues WARNING 2025-10-02 13:14:36,528 root:258 uncategorized: Unknown logging category: providers::utils. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,703 root:258 uncategorized: Unknown logging category: uncategorized. Falling back to default 'root' level: 20 WARNING 2025-10-02 13:14:36,726 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider fireworks: Pass Fireworks API Key in the header X-LlamaStack-Provider-Data as { "fireworks_api_key": <your api key>} WARNING 2025-10-02 13:14:36,727 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>} WARNING 2025-10-02 13:14:38,404 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider anthropic: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"anthropic_api_key": "<API_KEY>"}, or in the provider config. WARNING 2025-10-02 13:14:38,406 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. WARNING 2025-10-02 13:14:38,408 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. WARNING 2025-10-02 13:14:38,411 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. llama_stack_client instantiated in 5.237s SKIPPED [ 11%] tests/integration/agents/test_openai_responses.py::test_list_response_input_items[openai_client-txt=openai/gpt-4o] SKIPPED [ 15%] tests/integration/agents/test_openai_responses.py::test_list_response_input_items_with_limit_and_order[txt=openai/gpt-4o] SKIPPED [ 19%] tests/integration/agents/test_openai_responses.py::test_function_call_output_response[txt=openai/gpt-4o] SKIPPED [ 23%] tests/integration/agents/test_openai_responses.py::test_function_call_output_response_with_none_arguments[txt=openai/gpt-4o] SKIPPED [ 26%] tests/integration/agents/test_agents.py::test_agent_simple[openai/gpt-4o] PASSED [ 30%] tests/integration/agents/test_agents.py::test_agent_name[txt=openai/gpt-4o] SKIPPED (this te...) [ 34%] tests/integration/agents/test_agents.py::test_tool_config[openai/gpt-4o] PASSED [ 38%] tests/integration/agents/test_agents.py::test_custom_tool[openai/gpt-4o] FAILED [ 42%] tests/integration/agents/test_agents.py::test_custom_tool_infinite_loop[openai/gpt-4o] PASSED [ 46%] tests/integration/agents/test_agents.py::test_tool_choice_required[openai/gpt-4o] INFO 2025-10-02 13:14:51,559 llama_stack.providers.inline.agents.meta_reference.agent_instance:691 agents::meta_reference: done with MAX iterations (2), exiting. PASSED [ 50%] tests/integration/agents/test_agents.py::test_tool_choice_none[openai/gpt-4o] PASSED [ 53%] tests/integration/agents/test_agents.py::test_tool_choice_get_boiling_point[openai/gpt-4o] XFAIL [ 57%] tests/integration/agents/test_agents.py::test_create_turn_response[openai/gpt-4o-client_tools0] PASSED [ 61%] tests/integration/agents/test_agents.py::test_multi_tool_calls[openai/gpt-4o] PASSED [ 65%] tests/integration/agents/test_openai_responses.py::test_responses_store[openai_client-txt=openai/gpt-4o-tools0-False] SKIPPED [ 69%] tests/integration/agents/test_openai_responses.py::test_list_response_input_items[client_with_models-txt=openai/gpt-4o] PASSED [ 73%] tests/integration/agents/test_agents.py::test_create_turn_response[openai/gpt-4o-client_tools1] PASSED [ 76%] tests/integration/agents/test_openai_responses.py::test_responses_store[openai_client-txt=openai/gpt-4o-tools1-True] SKIPPED [ 80%] tests/integration/agents/test_openai_responses.py::test_responses_store[openai_client-txt=openai/gpt-4o-tools1-False] SKIPPED [ 84%] tests/integration/agents/test_openai_responses.py::test_responses_store[client_with_models-txt=openai/gpt-4o-tools0-True] SKIPPED [ 88%] tests/integration/agents/test_openai_responses.py::test_responses_store[client_with_models-txt=openai/gpt-4o-tools0-False] SKIPPED [ 92%] tests/integration/agents/test_openai_responses.py::test_responses_store[client_with_models-txt=openai/gpt-4o-tools1-True] SKIPPED [ 96%] tests/integration/agents/test_openai_responses.py::test_responses_store[client_with_models-txt=openai/gpt-4o-tools1-False] SKIPPED [100%] =============================================== FAILURES =============================================== ___________________________________ test_custom_tool[openai/gpt-4o] ____________________________________ tests/integration/agents/test_agents.py:370: in test_custom_tool assert "-100" in logs_str E assert '-100' in "inference> Polyjuice Potion is a fictional substance from the Harry Potter series, and it doesn't have a scientifically defined boiling point. If you have any other real liquid in mind, feel free to ask!" ========================================= slowest 10 durations ========================================= 5.47s setup tests/integration/agents/test_openai_responses.py::test_responses_store[openai_client-txt=openai/gpt-4o-tools0-True] 4.78s call tests/integration/agents/test_agents.py::test_custom_tool[openai/gpt-4o] 3.01s call tests/integration/agents/test_agents.py::test_tool_choice_required[openai/gpt-4o] 2.97s call tests/integration/agents/test_agents.py::test_agent_simple[openai/gpt-4o] 2.85s call tests/integration/agents/test_agents.py::test_tool_choice_none[openai/gpt-4o] 2.06s call tests/integration/agents/test_agents.py::test_multi_tool_calls[openai/gpt-4o] 1.83s call tests/integration/agents/test_agents.py::test_create_turn_response[openai/gpt-4o-client_tools0] 1.83s call tests/integration/agents/test_agents.py::test_custom_tool_infinite_loop[openai/gpt-4o] 1.29s call tests/integration/agents/test_agents.py::test_create_turn_response[openai/gpt-4o-client_tools1] 0.57s call tests/integration/agents/test_openai_responses.py::test_list_response_input_items[client_with_models-txt=openai/gpt-4o] ======================================= short test summary info ======================================== FAILED tests/integration/agents/test_agents.py::test_custom_tool[openai/gpt-4o] - assert '-100' in "inference> Polyjuice Potion is a fictional substance from the Harry Potter series... =========== 1 failed, 9 passed, 15 skipped, 6 deselected, 1 xfailed, 139 warnings in 27.18s ============ ``` note: the failure is separate from the issue being fixed |
||
|
7e48cc48bc
|
refactor(agents): migrate to OpenAI chat completions API (#3323)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 1s
Test Llama Stack Build / build-single-provider (push) Failing after 2s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 8s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 17s
Python Package Build Test / build (3.13) (push) Failing after 14s
Test Llama Stack Build / generate-matrix (push) Successful in 18s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build (push) Failing after 4s
UI Tests / ui-tests (22) (push) Successful in 44s
Pre-commit / pre-commit (push) Successful in 1m16s
|
||
|
f7c5ef4ec0
|
chore: remove /v1/inference/completion and implementations (#3622)
# What does this PR do? the /inference/completion route is gone. this removes the implementations. ## Test Plan ci |
||
|
ca47d90926
|
fix: Ensure that tool calls with no arguments get handled correctly (#3560)
# What does this PR do? When a model decides to use an MCP tool call that requires no arguments, it sets the `arguments` field to `None`. This causes the user to see a `400 bad requst error` due to validation errors down the stack because this field gets removed when being parsed by an openai compatible inference provider like vLLM This PR ensures that, as soon as the tool call args are accumulated while streaming, we check to ensure no tool call function arguments are set to None - if they are we replace them with "{}" <!-- If resolving an issue, uncomment and update the line below --> Closes #3456 ## Test Plan Added new unit test to verify that any tool calls with function arguments set to `None` get handled correctly --------- Signed-off-by: Jaideep Rao <jrao@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
ac7c35fbe6
|
fix: don't pass default response format in Responses (#3614)
# What does this PR do? Fireworks doesn't allow repsonse_format with tool use. The default response format is 'text' anyway, so we can safely omit. ## Test Plan Below script failed without the change, runs after. ``` #!/usr/bin/env python3 """ Script to test Responses API with kubernetes-mcp-server. This script: 1. Connects to the llama stack server 2. Uses the Responses API with MCP tools 3. Asks for the list of Kubernetes namespaces using the kubernetes-mcp-server """ import json from openai import OpenAI # Connect to the llama stack server base_url = "http://localhost:8321/v1" client = OpenAI(base_url=base_url, api_key="fake") # Define the MCP tool pointing to the kubernetes-mcp-server # The kubernetes-mcp-server is running on port 3000 with SSE endpoint at /sse mcp_server_url = "http://localhost:3000/sse" tools = [ { "type": "mcp", "server_label": "k8s", "server_url": mcp_server_url, } ] # Create a response request asking for k8s namespaces print("Sending request to list Kubernetes namespaces...") print(f"Using MCP server at: {mcp_server_url}") print("Available tools will be listed automatically by the MCP server.") print() response = client.responses.create( # model="meta-llama/Llama-3.2-3B-Instruct", # Using the vllm model model="fireworks/accounts/fireworks/models/llama4-scout-instruct-basic", # model="openai/gpt-4o", input="what are all the Kubernetes namespaces? Use tool call to `namespaces_list`. make sure to adhere to the tool calling format UNDER ALL CIRCUMSTANCES.", tools=tools, stream=False, ) print("\n" + "=" * 80) print("RESPONSE OUTPUT:") print("=" * 80) # Print the output for i, output in enumerate(response.output): print(f"\n[Output {i + 1}] Type: {output.type}") if output.type == "mcp_list_tools": print(f" Server: {output.server_label}") print(f" Tools available: {[t.name for t in output.tools]}") elif output.type == "mcp_call": print(f" Tool called: {output.name}") print(f" Arguments: {output.arguments}") print(f" Result: {output.output}") if output.error: print(f" Error: {output.error}") elif output.type == "message": print(f" Role: {output.role}") print(f" Content: {output.content}") print("\n" + "=" * 80) print("FINAL RESPONSE TEXT:") print("=" * 80) print(response.output_text) ``` |
||
|
2de4e6c900
|
feat: use /v1/chat/completions for safety model inference (#3591)
# What does this PR do? migrate safety api implementation from /inference/chat-completion to /v1/chat/completions ## Test Plan ci w/ recordings --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
7c888fc0da
|
feat: update eval runner to use openai endpoints (#3588)
# What does this PR do? move the eval=inline::meta-reference implementation to use openai_completion/openai_chat_completion note: this breaks backward compatibility if eval setup used sampling params' repetition_penalty or strategy ## Test Plan ci w/ new recordings Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
65f7b81e98
|
feat: Add items and title to ToolParameter/ToolParamDefinition (#3003)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 17s
Python Package Build Test / build (3.12) (push) Failing after 17s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 19s
Unit Tests / unit-tests (3.13) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (push) Failing after 20s
Test External API and Providers / test-external (venv) (push) Failing after 3s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 19s
Python Package Build Test / build (3.13) (push) Failing after 16s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
API Conformance Tests / check-schema-compatibility (push) Successful in 25s
UI Tests / ui-tests (22) (push) Successful in 50s
Pre-commit / pre-commit (push) Successful in 1m16s
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Add items and title to ToolParameter/ToolParamDefinition. Adding items will resolve the issue that occurs with Gemini LLM when an MCP tool has array-type properties. <!-- 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.* --> Unite test cases will be added. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Kai Wu <kaiwu@meta.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
0d94f3e2c0
|
chore: recordings for fireworks (inference + openai) (#3573)
# What does this PR do? recorded for: ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup fireworks --subdirs inference --pattern openai ## Test Plan ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup fireworks --subdirs inference --pattern openai |
||
|
53b15725b6
|
chore(apis): unpublish deprecated /v1/inference apis (#3297)
# What does this PR do? unpublish (make unavailable to users) the following apis - - `/v1/inference/completion`, replaced by `/v1/openai/v1/completions` - `/v1/inference/chat-completion`, replaced by `/v1/openai/v1/chat/completions` - `/v1/inference/embeddings`, replaced by `/v1/openai/v1/embeddings` - `/v1/inference/batch-completion`, replaced by `/v1/openai/v1/batches` - `/v1/inference/batch-chat-completion`, replaced by `/v1/openai/v1/batches` note: the implementations are still available for internal use, e.g. agents uses chat-completion. |
||
|
b48d5cfed7
|
feat(internal): add image_url download feature to OpenAIMixin (#3516)
# What does this PR do? simplify Ollama inference adapter by - - moving image_url download code to OpenAIMixin - being a ModelRegistryHelper instead of having one (mypy blocks check_model_availability method assignment) ## Test Plan - add unit tests for new download feature - add integration tests for openai_chat_completion w/ image_url (close test gap) |
||
|
65e01b5684 |
feat: together now supports base64 embedding encoding (#3559)
# What does this PR do? use together's new base64 support ## Test Plan recordings for: ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup together --subdirs inference --pattern openai |
||
|
b67aef2fc4
|
feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)
# What does this PR do? - remove auto-download of ollama embedding models - add embedding model metadata to dynamic listing w/ unit test - add support and tests for allowed_models - removed inference provider models.py files where dynamic listing is enabled - store embedding metadata in embedding_model_metadata field on inference providers - make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin - make OpenAIMixin a ModelRegistryHelper - skip base64 embedding test for remote::ollama, always returns floats - only use OpenAI client for ollama model listing - remove unused build_model_entry function - remove unused get_huggingface_repo function ## Test Plan ci w/ new tests |
||
|
a50b63906c
|
chore: use ollama/all-minilm:l6-v2 for ollama tests (#3537)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 2s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 9s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 2s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 5s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 5s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 6s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Test Llama Stack Build / build (push) Failing after 4s
UI Tests / ui-tests (22) (push) Successful in 33s
Pre-commit / pre-commit (push) Successful in 1m25s
# What does this PR do? use ollama embedding models for ollama test, previously using sentence-transformer recordings: - ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup ollama --inference-mode record - ./scripts/integration-tests.sh --stack-config server:ci-tests --suite vision --setup ollama-vision --inference-mode record ## Test Plan ci w/ added skip base64 embedding test |
||
|
ce7a3b4dff
|
feat: update Cerebras inference provider to support dynamic model listing (#3481)
# What does this PR do? - update Cerebras to use OpenAIMixin - enable openai completions tests - enable openai chat completions tests - disable with n > 1 tests - add recording for --setup cerebras --subdirs inference --pattern openai ## Test Plan `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai` ``` tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.053s PASSED [ 2%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=cerebras/llama-3.3-70b-inference:completion:suffix] SKIPPED (Suffix is not supported for the model: cerebras/llama-3.3-70b.) [ 4%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] PASSED [ 6%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=cerebras/llama-3.3-70b-1] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 8%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=cerebras/llama-3.3-70b] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 10%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] PASSED [ 12%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] PASSED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cere...) [ 17%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-True] PASSED [ 19%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-True] PASSED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=cerebras/llama-3.3-70b] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support chat completion calls wit...) [ 23%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 25%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 27%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 29%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 31%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 34%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 36%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 38%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 40%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 42%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=cerebras/llama-3.3-70b-0] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 46%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cere...) [ 53%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-False] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-False] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 65%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 68%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 70%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 72%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 74%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 76%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote:...) [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote:...) [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-False] PASSED [100%] =================================================================================================================== slowest 10 durations ==================================================================================================================== 0.37s call tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] 0.34s call tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-False] 0.18s call tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-True] 0.17s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] 0.15s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-True] 0.13s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-True] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-False] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-True] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-False] 0.08s call tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] ================================================================================================================== short test summary info ================================================================================================================== SKIPPED [1] tests/integration/inference/test_openai_completion.py:75: Suffix is not supported for the model: cerebras/llama-3.3-70b. SKIPPED [3] tests/integration/inference/test_openai_completion.py:123: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters. SKIPPED [4] tests/integration/inference/test_openai_completion.py:103: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support n param. SKIPPED [1] tests/integration/inference/test_openai_completion.py:129: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support chat completion calls with base64 encoded files. SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:90: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:112: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:136: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:154: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:175: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:195: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:206: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:217: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:244: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:278: embedding_model_id empty - skipping test ================================================================================================= 18 passed, 29 skipped, 50 deselected, 4 warnings in 3.02s ================================================================================================= ``` |
||
|
d07ebce4d9
|
feat: (re-)enable Databricks inference adapter (#3500)
# What does this PR do? add/enable the Databricks inference adapter Databricks inference adapter was broken, closes #3486 - remove deprecated completion / chat_completion endpoints - enable dynamic model listing w/o refresh, listing is not async - use SecretStr instead of str for token - backward incompatible change: for consistency with databricks docs, env DATABRICKS_URL -> DATABRICKS_HOST and DATABRICKS_API_TOKEN -> DATABRICKS_TOKEN - databricks urls are custom per user/org, add special recorder handling for databricks urls - add integration test --setup databricks - enable chat completions tests - enable embeddings tests - disable n > 1 tests - disable embeddings base64 tests - disable embeddings dimensions tests note: reasoning models, e.g. gpt oss, fail because databricks has a custom, incompatible response format ## Test Plan ci and ``` ./scripts/integration-tests.sh --stack-config server:ci-tests --setup databricks --subdirs inference --pattern openai ``` note: databricks needs to be manually added to the ci-tests distro for replay testing |
||
|
ea396a54cd
|
chore: update the ollama inference impl to use OpenAIMixin for openai-compat functions (#3395)
# What does this PR do? update Ollama inference provider to use OpenAIMixin for openai-compat endpoints ## Test Plan ci |
||
|
49d4a5cc84
|
feat: add embedding and dynamic model support to Together inference adapter (#3458)
# What does this PR do? adds embedding and dynamic model support to Together inference adapter - updated to use OpenAIMixin - workarounds for Together api quirks - recordings for together suite when subdirs=inference,pattern=openai ## Test Plan ``` $ TOGETHER_API_KEY=_NONE_ ./scripts/integration-tests.sh --stack-config server:ci-tests --setup together --subdirs inference --pattern openai ... tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.121s PASSED [ 2%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:suffix] SKIPPED [ 4%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] PASSED [ 6%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-1] SKIPPED [ 8%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 10%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 12%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 17%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 19%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 23%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 25%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 27%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 29%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 31%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 34%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 36%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 38%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 40%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 42%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-0] SKIPPED [ 46%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 53%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 65%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 68%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 70%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 72%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 74%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 76%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [100%] ============================================ 30 passed, 17 skipped, 50 deselected, 4 warnings in 21.96s ============================================= ``` |
||
|
f4ab154ade
|
feat: add dynamic model registration support to TGI inference (#3417)
Some checks failed
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
UI Tests / ui-tests (22) (push) Successful in 43s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 3s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Pre-commit / pre-commit (push) Successful in 1m21s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
Python Package Build Test / build (3.13) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 5s
# What does this PR do? adds dynamic model support to TGI add new overwrite_completion_id feature to OpenAIMixin to deal with TGI always returning id="" ## Test Plan tgi: `docker run --gpus all --shm-size 1g -p 8080:80 -v /data:/data ghcr.io/huggingface/text-generation-inference --model-id Qwen/Qwen3-0.6B` stack: `TGI_URL=http://localhost:8080 uv run llama stack build --image-type venv --distro ci-tests --run` test: `./scripts/integration-tests.sh --stack-config http://localhost:8321 --setup tgi --subdirs inference --pattern openai` |
||
|
f31bcc11bc
|
feat: add Azure OpenAI inference provider support (#3396)
# What does this PR do? Llama-stack now supports a new OpenAI compatible endpoint with Azure OpenAI. The starter distro has been updated to add the new remote inference provider. A few tests have been modified and improved. ## Test Plan Deploy a model in the Aure portal then: ``` $ AZURE_API_KEY=... AZURE_API_BASE=... uv run llama stack build --image-type venv --providers inference=remote::azure --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model azure/gpt-4.1 tests/integration/inference/test_openai_completion.py ... Results: ``` ============================================= test session starts ============================================== platform darwin -- Python 3.12.8, pytest-8.4.1, pluggy-1.6.0 -- /Users/leseb/Documents/AI/llama-stack/.venv/bin/python3 cachedir: .pytest_cache metadata: {'Python': '3.12.8', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0', 'hydra-core': '1.3.2'}} rootdir: /Users/leseb/Documents/AI/llama-stack configfile: pyproject.toml plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0, hydra-core-1.3.2 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 27 items tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=azure/gpt-5-mini-inference:completion:sanity] SKIPPED [ 3%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=azure/gpt-5-mini-inference:completion:suffix] SKIPPED [ 7%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=azure/gpt-5-mini-inference:completion:sanity] SKIPPED [ 11%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-1] SKIPPED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=azure/gpt-5-mini] SKIPPED [ 18%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01] PASSED [ 22%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 25%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 29%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-True] PASSED [ 33%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-True] PASSED [ 37%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=azure/gpt-5-mini] SKIPPEDed files.) [ 40%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-0] SKIPPED [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-False] PASSED [ 59%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-False] PASSED [ 62%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01] PASSED [ 66%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 70%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 74%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-True] PASSED [ 77%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-True] PASSED [ 81%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02] PASSED [ 85%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 88%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 92%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-False] PASSED [ 96%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-False] PASSED [100%] =========================================== short test summary info ============================================ SKIPPED [3] tests/integration/inference/test_openai_completion.py:63: Model azure/gpt-5-mini hosted by remote::azure doesn't support OpenAI completions. SKIPPED [3] tests/integration/inference/test_openai_completion.py:118: Model azure/gpt-5-mini hosted by remote::azure doesn't support vllm extra_body parameters. SKIPPED [1] tests/integration/inference/test_openai_completion.py:124: Model azure/gpt-5-mini hosted by remote::azure doesn't support chat completion calls with base64 encoded files. ================================== 20 passed, 7 skipped, 2 warnings in 51.77s ================================== ``` Signed-off-by: Sébastien Han <seb@redhat.com> |
||
|
df1526991f
|
feat(batches, completions): add /v1/completions support to /v1/batches (#3309)
# What does this PR do? add support for /v1/completions to the /v1/batches api ## Test Plan ci |
||
|
c3d3a0b833
|
feat(tests): auto-merge all model list responses and unify recordings (#3320)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Python Package Build Test / build (3.13) (push) Failing after 8s
Python Package Build Test / build (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 14s
UI Tests / ui-tests (22) (push) Successful in 1m7s
Pre-commit / pre-commit (push) Successful in 2m34s
One needed to specify record-replay related environment variables for running integration tests. We could not use defaults because integration tests could be run against Ollama instances which could be running different models. For example, text vs vision tests needed separate instances of Ollama because a single instance typically cannot serve both of these models if you assume the standard CI worker configuration on Github. As a result, `client.list()` as returned by the Ollama client would be different between these runs and we'd end up overwriting responses. This PR "solves" it by adding a small amount of complexity -- we store model list responses specially, keyed by the hashes of the models they return. At replay time, we merge all of them and pretend that we have the union of all models available. ## Test Plan Re-recorded all the tests using `scripts/integration-tests.sh --inference-mode record`, including the vision tests. |
||
|
478b4ff1e6
|
chore(migrate apis): move VectorDBWithIndex from embeddings to openai_embeddings (#3294)
# What does this PR do? migrates VectorDBWithIndex to use openai_embeddings part of #2365 ## Test Plan existing unit tests |
||
|
7ca8233889
|
feat(testing): remove SQLite dependency from inference recorder (#3254)
Recording files use a predictable naming format, making the SQLite index redundant. The binary SQLite file was causing frequent git conflicts. Simplify by calculating file paths directly from request hashes. Signed-off-by: Derek Higgins <derekh@redhat.com> |
||
|
3b9278f254
|
feat: implement query_metrics (#3074)
# What does this PR do? query_metrics currently has no implementation, meaning once a metric is emitted there is no way in llama stack to query it from the store. implement query_metrics for the meta_reference provider which follows a similar style to `query_traces`, using the trace_store to format an SQL query and execute it in this case the parameters for the query are `metric.METRIC_NAME, start_time, and end_time` and any other matchers if they are provided. this required client side changes since the client had no `query_metrics` or any associated resources, so any tests here will fail but I will provide manual execution logs for the new tests I am adding order the metrics by timestamp. Additionally add `unit` to the `MetricDataPoint` class since this adds much more context to the metric being queried. depends on https://github.com/llamastack/llama-stack-client-python/pull/260 ## Test Plan ``` import time import uuid def create_http_client(): from llama_stack_client import LlamaStackClient return LlamaStackClient(base_url="http://localhost:8321") client = create_http_client() response = client.telemetry.query_metrics(metric_name="total_tokens", start_time=0) print(response) ``` ``` ╰─ python3.12 ~/telemetry.py INFO:httpx:HTTP Request: POST http://localhost:8322/v1/telemetry/metrics/total_tokens "HTTP/1.1 200 OK" [TelemetryQueryMetricsResponse(data=None, metric='total_tokens', labels=[], values=[{'timestamp': 1753999514, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999816, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999881, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999956, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754000200, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754000419, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000714, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000876, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000908, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754001309, 'value': 584.0, 'unit': 'tokens'}, {'timestamp': 1754001311, 'value': 138.0, 'unit': 'tokens'}, {'timestamp': 1754001316, 'value': 349.0, 'unit': 'tokens'}, {'timestamp': 1754001318, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001320, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001341, 'value': 923.0, 'unit': 'tokens'}, {'timestamp': 1754001350, 'value': 354.0, 'unit': 'tokens'}, {'timestamp': 1754001462, 'value': 417.0, 'unit': 'tokens'}, {'timestamp': 1754001464, 'value': 158.0, 'unit': 'tokens'}, {'timestamp': 1754001475, 'value': 697.0, 'unit': 'tokens'}, {'timestamp': 1754001477, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001479, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001489, 'value': 298.0, 'unit': 'tokens'}, {'timestamp': 1754001541, 'value': 615.0, 'unit': 'tokens'}, {'timestamp': 1754001543, 'value': 119.0, 'unit': 'tokens'}, {'timestamp': 1754001548, 'value': 310.0, 'unit': 'tokens'}, {'timestamp': 1754001549, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001551, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001568, 'value': 714.0, 'unit': 'tokens'}, {'timestamp': 1754001800, 'value': 437.0, 'unit': 'tokens'}, {'timestamp': 1754001802, 'value': 200.0, 'unit': 'tokens'}, {'timestamp': 1754001806, 'value': 262.0, 'unit': 'tokens'}, {'timestamp': 1754001808, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001810, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001816, 'value': 82.0, 'unit': 'tokens'}, {'timestamp': 1754001923, 'value': 61.0, 'unit': 'tokens'}, {'timestamp': 1754001929, 'value': 391.0, 'unit': 'tokens'}, {'timestamp': 1754001939, 'value': 598.0, 'unit': 'tokens'}, {'timestamp': 1754001941, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001942, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001952, 'value': 252.0, 'unit': 'tokens'}, {'timestamp': 1754002053, 'value': 251.0, 'unit': 'tokens'}, {'timestamp': 1754002059, 'value': 375.0, 'unit': 'tokens'}, {'timestamp': 1754002062, 'value': 244.0, 'unit': 'tokens'}, {'timestamp': 1754002064, 'value': 111.0, 'unit': 'tokens'}, {'timestamp': 1754002065, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754002083, 'value': 719.0, 'unit': 'tokens'}, {'timestamp': 1754002302, 'value': 279.0, 'unit': 'tokens'}, {'timestamp': 1754002306, 'value': 218.0, 'unit': 'tokens'}, {'timestamp': 1754002308, 'value': 198.0, 'unit': 'tokens'}, {'timestamp': 1754002309, 'value': 69.0, 'unit': 'tokens'}, {'timestamp': 1754002311, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754002324, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754003161, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003161, 'value': 69.0, 'unit': 'tokens'}, {'timestamp': 1754003169, 'value': 499.0, 'unit': 'tokens'}, {'timestamp': 1754003171, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003173, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003185, 'value': 422.0, 'unit': 'tokens'}, {'timestamp': 1754003448, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003453, 'value': 422.0, 'unit': 'tokens'}, {'timestamp': 1754003589, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003609, 'value': 279.0, 'unit': 'tokens'}, {'timestamp': 1754003614, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754003706, 'value': 303.0, 'unit': 'tokens'}, {'timestamp': 1754003706, 'value': 51.0, 'unit': 'tokens'}, {'timestamp': 1754003713, 'value': 426.0, 'unit': 'tokens'}, {'timestamp': 1754003714, 'value': 70.0, 'unit': 'tokens'}, {'timestamp': 1754003715, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003724, 'value': 225.0, 'unit': 'tokens'}, {'timestamp': 1754004226, 'value': 516.0, 'unit': 'tokens'}, {'timestamp': 1754004228, 'value': 127.0, 'unit': 'tokens'}, {'timestamp': 1754004232, 'value': 281.0, 'unit': 'tokens'}, {'timestamp': 1754004234, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004236, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004244, 'value': 206.0, 'unit': 'tokens'}, {'timestamp': 1754004683, 'value': 338.0, 'unit': 'tokens'}, {'timestamp': 1754004690, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754004692, 'value': 124.0, 'unit': 'tokens'}, {'timestamp': 1754004692, 'value': 65.0, 'unit': 'tokens'}, {'timestamp': 1754004694, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004703, 'value': 211.0, 'unit': 'tokens'}, {'timestamp': 1754004743, 'value': 338.0, 'unit': 'tokens'}, {'timestamp': 1754004749, 'value': 211.0, 'unit': 'tokens'}, {'timestamp': 1754005566, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754006101, 'value': 159.0, 'unit': 'tokens'}, {'timestamp': 1754006105, 'value': 272.0, 'unit': 'tokens'}, {'timestamp': 1754006109, 'value': 308.0, 'unit': 'tokens'}, {'timestamp': 1754006110, 'value': 61.0, 'unit': 'tokens'}, {'timestamp': 1754006112, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754006130, 'value': 705.0, 'unit': 'tokens'}, {'timestamp': 1754051825, 'value': 454.0, 'unit': 'tokens'}, {'timestamp': 1754051827, 'value': 152.0, 'unit': 'tokens'}, {'timestamp': 1754051834, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754051835, 'value': 55.0, 'unit': 'tokens'}, {'timestamp': 1754051837, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754051845, 'value': 102.0, 'unit': 'tokens'}, {'timestamp': 1754099929, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754510050, 'value': 598.0, 'unit': 'tokens'}, {'timestamp': 1754510052, 'value': 160.0, 'unit': 'tokens'}, {'timestamp': 1754510064, 'value': 725.0, 'unit': 'tokens'}, {'timestamp': 1754510065, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754510067, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754510083, 'value': 535.0, 'unit': 'tokens'}, {'timestamp': 1754596582, 'value': 36.0, 'unit': 'tokens'}])] ``` adding tests for each currently documented metric in llama stack using this new function. attached is also some manual testing integrations tests passing locally with replay mode and the linked client changes: <img width="1907" height="529" alt="Screenshot 2025-08-08 at 2 49 14 PM" src="https://github.com/user-attachments/assets/d482ab06-dcff-4f0c-a1f1-f870670ee9bc" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> |
||
|
eb07a0f86a
|
fix(ci, tests): ensure uv environments in CI are kosher, record tests (#3193)
Some checks failed
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 21s
Test Llama Stack Build / build-single-provider (push) Failing after 23s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 28s
Test Llama Stack Build / generate-matrix (push) Successful in 25s
Python Package Build Test / build (3.13) (push) Failing after 25s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 34s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 37s
Test External API and Providers / test-external (venv) (push) Failing after 33s
Unit Tests / unit-tests (3.13) (push) Failing after 33s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 38s
Python Package Build Test / build (3.12) (push) Failing after 1m0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1m4s
Unit Tests / unit-tests (3.12) (push) Failing after 59s
Test Llama Stack Build / build (push) Failing after 50s
Vector IO Integration Tests / test-matrix (push) Failing after 1m48s
UI Tests / ui-tests (22) (push) Successful in 2m12s
Pre-commit / pre-commit (push) Successful in 2m41s
I started this PR trying to unbreak a newly broken test `test_agent_name`. This test was broken all along but did not show up because during testing we were pulling the "non-updated" llama stack client. See this comment: https://github.com/llamastack/llama-stack/pull/3119#discussion_r2270988205 While fixing this, I encountered a large amount of badness in our CI workflow definitions. - We weren't passing `LLAMA_STACK_DIR` or `LLAMA_STACK_CLIENT_DIR` overrides to `llama stack build` at all in some cases. - Even when we did, we used `uv run` liberally. The first thing `uv run` does is "syncs" the project environment. This means, it is going to undo any mutations we might have done ourselves. But we make many mutations in our CI runners to these environments. The most important of which is why `llama stack build` where we install distro dependencies. As a result, when you tried to run the integration tests, you would see old, strange versions. ## Test Plan Re-record using: ``` sh scripts/integration-tests.sh --stack-config ci-tests \ --provider ollama --test-pattern test_agent_name --inference-mode record ``` Then re-run with `--inference-mode replay`. But: Eventually, this test turned out to be quite flaky for telemetry reasons. I haven't investigated it for now and just disabled it sadly since we have a release to push out. |
||
|
914c7be288
|
feat: add batches API with OpenAI compatibility (with inference replay) (#3162)
Add complete batches API implementation with protocol, providers, and tests: Core Infrastructure: - Add batches API protocol using OpenAI Batch types directly - Add Api.batches enum value and protocol mapping in resolver - Add OpenAI "batch" file purpose support - Include proper error handling (ConflictError, ResourceNotFoundError) Reference Provider: - Add ReferenceBatchesImpl with full CRUD operations (create, retrieve, cancel, list) - Implement background batch processing with configurable concurrency - Add SQLite KVStore backend for persistence - Support /v1/chat/completions endpoint with request validation Comprehensive Test Suite: - Add unit tests for provider implementation with validation - Add integration tests for end-to-end batch processing workflows - Add error handling tests for validation, malformed inputs, and edge cases Configuration: - Add max_concurrent_batches and max_concurrent_requests_per_batch options - Add provider documentation with sample configurations Test with - ``` $ uv run llama stack build --image-type venv --providers inference=YOU_PICK,files=inline::localfs,batches=inline::reference --run & $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/unit/providers/batches tests/integration/batches --text-model YOU_PICK ``` addresses #3066 --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
0e8bb94bf3
|
feat(ci): make recording workflow simpler, more parameterizable (#3169)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 7s
Python Package Build Test / build (3.12) (push) Failing after 12s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 14s
Update ReadTheDocs / update-readthedocs (push) Failing after 12s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 17s
Test External API and Providers / test-external (venv) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (push) Failing after 28s
Unit Tests / unit-tests (3.12) (push) Failing after 27s
Unit Tests / unit-tests (3.13) (push) Failing after 51s
Pre-commit / pre-commit (push) Successful in 2m6s
# What does this PR do? Recording tests has become a nightmare. This is the first part of making that process simpler by making it _less_ automatic. I tried to be too clever earlier. It simplifies the record-integration-tests workflow to use workflow dispatch inputs instead of PR labels. No more opaque stuff. Just go to the GitHub UI and run the workflow with inputs. I will soon add a helper script for this also. Other things to aid re-running just the small set of things you need to re-record: - Replaces the `test-types` JSON array parameter with a more intuitive `test-subdirs` comma-separated list. The whole JSON array crap was for matrix. - Adds a new `test-pattern` parameter to allow filtering tests using pytest's `-k` option ## Test Plan Note that this PR is in a fork not the source repository. - Replay tests on this PR are green - Manually [ran]( |
||
|
01b2afd4b5
|
fix(tests): record missing tests for test_responses_store (#3163)
# What does this PR do? Updates test recordings. ## Test Plan Started ollama serving the 3.2:3b model. Then ran the server: ``` LLAMA_STACK_TEST_INFERENCE_MODE=record \ LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings/ \ SQLITE_STORE_DIR=$(mktemp -d) \ OLLAMA_URL=http://localhost:11434 \ llama stack build --template starter --image-type venv --run ``` Then ran the tests which needed recording: ``` pytest -sv tests/integration/agents/test_openai_responses.py \ --stack-config=server:starter \ --text-model ollama/llama3.2:3b-instruct-fp16 -k test_responses_store ``` Then, restarted the server with `LLAMA_STACK_TEST_INFERENCE_MODE=replay`, re-ran the tests and verified they passed. |
||
|
0caef40e0d
|
fix: telemetry fixes (inference and core telemetry) (#2733)
# What does this PR do? I found a few issues while adding new metrics for various APIs: currently metrics are only propagated in `chat_completion` and `completion` since most providers use the `openai_..` routes as the default in `llama-stack-client inference chat-completion`, metrics are currently not working as expected. in order to get them working the following had to be done: 1. get the completion as usual 2. use new `openai_` versions of the metric gathering functions which use `.usage` from the `OpenAI..` response types to gather the metrics which are already populated. 3. define a `stream_generator` which counts the tokens and computes the metrics (only for stream=True) 5. add metrics to response NOTE: I could not add metrics to `openai_completion` where stream=True because that ONLY returns an `OpenAICompletion` not an AsyncGenerator that we can manipulate. acquire the lock, and add event to the span as the other `_log_...` methods do some new output: `llama-stack-client inference chat-completion --message hi` <img width="2416" height="425" alt="Screenshot 2025-07-16 at 8 28 20 AM" src="https://github.com/user-attachments/assets/ccdf1643-a184-4ddd-9641-d426c4d51326" /> and in the client: <img width="763" height="319" alt="Screenshot 2025-07-16 at 8 28 32 AM" src="https://github.com/user-attachments/assets/6bceb811-5201-47e9-9e16-8130f0d60007" /> these were not previously being recorded nor were they being printed to the server due to the improper console sink handling --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> |
||
|
7f834339ba
|
chore(misc): make tests and starter faster (#3042)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 9s
Python Package Build Test / build (3.12) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 12s
Test Llama Stack Build / generate-matrix (push) Successful in 11s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 14s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 22s
Test External API and Providers / test-external (venv) (push) Failing after 14s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 15s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 22s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build-single-provider (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 18s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 20s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 16s
Python Package Build Test / build (3.13) (push) Failing after 53s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 59s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 1m1s
Update ReadTheDocs / update-readthedocs (push) Failing after 1m6s
Pre-commit / pre-commit (push) Successful in 1m53s
A bunch of miscellaneous cleanup focusing on tests, but ended up speeding up starter distro substantially. - Pulled llama stack client init for tests into `pytest_sessionstart` so it does not clobber output - Profiling of that told me where we were doing lots of heavy imports for starter, so lazied them - starter now starts 20seconds+ faster on my Mac - A few other smallish refactors for `compat_client` |
||
|
bb6b6041d6
|
chore: fix: integration tests failures marked as successful (#3039) | ||
|
6ac710f3b0
|
fix(recording): endpoint resolution (#3013)
Some checks failed
Integration Tests (Replay) / discover-tests (push) Successful in 5s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 15s
Integration Tests (Replay) / run-replay-mode-tests (push) Failing after 10s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 19s
Python Package Build Test / build (3.12) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 15s
Test External API and Providers / test-external (venv) (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 18s
Python Package Build Test / build (3.13) (push) Failing after 14s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 18s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 23s
Unit Tests / unit-tests (3.12) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 19s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 56s
Unit Tests / unit-tests (3.13) (push) Failing after 52s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 55s
Pre-commit / pre-commit (push) Successful in 1m49s
# What does this PR do? ## Test Plan |
||
|
0b08d64ddb
|
feat(ci): introduce workflow for re-recording inference outputs (#3002) | ||
|
27d866795c
|
feat(ci): add support for running vision inference tests (#2972)
This PR significantly refactors the Integration Tests workflow. The main goal behind the PR was to enable recording of vision tests which were never run as part of our CI ever before. During debugging, I ended up making several other changes refactoring and hopefully increasing the robustness of the workflow. After doing the experiments, I have updated the trigger event to be `pull_request_target` so this workflow can get write permissions by default but it will run with source code from the base (main) branch in the source repository only. If you do change the workflow, you'd need to experiment using the `workflow_dispatch` triggers. This should not be news to anyone using Github Actions (except me!) It is likely to be a little rocky though while I learn more about GitHub Actions, etc. Please be patient :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> |
||
|
b237df8f18
|
feat(ci): use replay mode, setup ollama if specific label exists on PR (#2955)
This PR makes setting up Ollama optional for CI. By default, we use `replay` mode for inference requests and use the stored results from the `tests/integration/recordings/` directory. Every so often, users will update tests which will need us to re-record. To do this, we check for the existence of a label `re-record-tests` on the PR. If detected, - ollama is spun up - inference mode is set to record - after the tests are done, if any new changes are detected, they are pushed back to the PR ## Test Plan This is GitHub CI. Gotta test it live. |
||
|
0ac503ec0d
|
feat(tests): record responses for evals and telemetry tests (#2954)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests / discover-tests (push) Successful in 8s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 6s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 10s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 10s
Python Package Build Test / build (3.12) (push) Failing after 1s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 9s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 11s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 5s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 9s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 7s
Test Llama Stack Build / generate-matrix (push) Successful in 7s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 7s
Test Llama Stack Build / build-single-provider (push) Failing after 10s
Unit Tests / unit-tests (3.12) (push) Failing after 8s
Test External API and Providers / test-external (venv) (push) Failing after 10s
Test Llama Stack Build / build (push) Failing after 8s
Integration Tests / test-matrix (push) Failing after 9s
Unit Tests / unit-tests (3.13) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 29s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 39s
Python Package Build Test / build (3.13) (push) Failing after 38s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 41s
Pre-commit / pre-commit (push) Successful in 2m2s
Continuing with https://github.com/meta-llama/llama-stack/pull/2952 This also includes a "fix" to inference store related tests so that we pull a large number of inference responses from the DB so as to always find the one we just wrote. |
||
|
072d20a124
|
feat(test): record agents, safety and vector_io integration tests (#2952)
Continue to build on top of https://github.com/meta-llama/llama-stack/pull/2941 ## Test Plan Run server with `LLAMA_STACK_TEST_INFERENCE_MODE=record` and then run the integration tests with `--stack-config=server:starter`. Then restart the server with `LLAMA_STACK_TEST_INFERENCE_MODE=replay` and re-run the tests. Verify that no request hit Ollama at any point. |
||
|
2e5ca3f15c | chore: move recordings one directory upwards |