forked from phoenix-oss/llama-stack-mirror
2 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Xi Yan
|
3c72c034e6
|
[remove import *] clean up import *'s (#689)
# What does this PR do? - as title, cleaning up `import *`'s - upgrade tests to make them more robust to bad model outputs - remove import *'s in llama_stack/apis/* (skip __init__ modules) <img width="465" alt="image" src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2" /> - run `sh run_openapi_generator.sh`, no types gets affected ## Test Plan ### Providers Tests **agents** ``` pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8 ``` **inference** ```bash # meta-reference torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py # together pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py ``` **safety** ``` pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B ``` **memory** ``` pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384 ``` **scoring** ``` pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py ``` **datasetio** ``` pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py ``` **eval** ``` pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py ``` ### Client-SDK Tests ``` LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk ``` ### llama-stack-apps ``` PORT=5000 LOCALHOST=localhost python -m examples.agents.hello $LOCALHOST $PORT python -m examples.agents.inflation $LOCALHOST $PORT python -m examples.agents.podcast_transcript $LOCALHOST $PORT python -m examples.agents.rag_as_attachments $LOCALHOST $PORT python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT # Vision model python -m examples.interior_design_assistant.app python -m examples.agent_store.app $LOCALHOST $PORT ``` ### CLI ``` which llama llama model prompt-format -m Llama3.2-11B-Vision-Instruct llama model list llama stack list-apis llama stack list-providers inference llama stack build --template ollama --image-type conda ``` ### Distributions Tests **ollama** ``` llama stack build --template ollama --image-type conda ollama run llama3.2:1b-instruct-fp16 llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct ``` **fireworks** ``` llama stack build --template fireworks --image-type conda llama stack run ./llama_stack/templates/fireworks/run.yaml ``` **together** ``` llama stack build --template together --image-type conda llama stack run ./llama_stack/templates/together/run.yaml ``` **tgi** ``` llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests. |
||
Dinesh Yeduguru
|
c8be0bf1c9
|
Tools API with brave and MCP providers (#639)
This PR adds a new Tools api and adds two tool runtime providers: brave and MCP. Test plan: ``` curl -X POST 'http://localhost:5000/alpha/toolgroups/register' \ -H 'Content-Type: application/json' \ -d '{ "tool_group_id": "simple_tool", "tool_group": { "type": "model_context_protocol", "endpoint": {"uri": "http://localhost:56000/sse"} }, "provider_id": "model-context-protocol" }' curl -X POST 'http://localhost:5000/alpha/toolgroups/register' \ -H 'Content-Type: application/json' \ -d '{ "tool_group_id": "search", "provider_id": "brave-search", "tool_group": { "type": "user_defined", "tools": [ { "name": "brave_search", "description": "A web search tool", "parameters": [ { "name": "query", "parameter_type": "string", "description": "The query to search" } ], "metadata": {}, "tool_prompt_format": "json" } ] } }' curl -X GET http://localhost:5000/alpha/tools/list | jq . % Total % Received % Xferd Average Speed Time Time Time Current Dload Upload Total Spent Left Speed 100 662 100 662 0 0 333k 0 --:--:-- --:--:-- --:--:-- 646k [ { "identifier": "brave_search", "provider_resource_id": "brave_search", "provider_id": "brave-search", "type": "tool", "tool_group": "search", "description": "A web search tool", "parameters": [ { "name": "query", "parameter_type": "string", "description": "The query to search" } ], "metadata": {}, "tool_prompt_format": "json" }, { "identifier": "fetch", "provider_resource_id": "fetch", "provider_id": "model-context-protocol", "type": "tool", "tool_group": "simple_tool", "description": "Fetches a website and returns its content", "parameters": [ { "name": "url", "parameter_type": "string", "description": "URL to fetch" } ], "metadata": { "endpoint": "http://localhost:56000/sse" }, "tool_prompt_format": "json" } ] curl -X POST 'http://localhost:5000/alpha/tool-runtime/invoke' \ -H 'Content-Type: application/json' \ -d '{ "tool_name": "fetch", "args": { "url": "http://google.com/" } }' curl -X POST 'http://localhost:5000/alpha/tool-runtime/invoke' \ -H 'Content-Type: application/json' -H 'X-LlamaStack-ProviderData: {"api_key": "<KEY>"}' \ -d '{ "tool_name": "brave_search", "args": { "query": "who is meta ceo" } }' ``` |